Digital management method and system for water-soluble vitamin content detection process

Abstract

The embodiment of the invention provides a digital management method and system for a water-soluble vitamin content detection process, and relates to the technical field of digital management, and the method comprises the following steps: obtaining a sample expected to be processed and a physical sample; determining an identity label of a sample expected to be processed according to a preset detection task queue, and pushing the identity label of the sample expected to be processed to the current operation table; decoding the physical sample through scanning equipment; obtaining a checking result obtained by checking the identifier of the physical sample and the identity identifier of the sample expected to be processed by the user through the current operation table; when the identifier of the physical sample is worn and the scanning equipment cannot be completely decoded, intelligently matching information captured by the scanning equipment with the identity identifier of a sample expected to be processed to obtain an intelligent matching result; and controlling the physical sample to execute a subsequent processing flow according to the checking result and the intelligent matching result. According to the invention, the automation and intelligence level of the detection process can be improved.

Description

Technical Field

[0001] This application relates to the field of digital management technology, and in particular to a digital management method and system for the detection process of water-soluble vitamin content. Background Technology

[0002] In related technologies, within the quality control laboratories of biopharmaceutical manufacturing companies, the testing process for nutrient samples requires a digital management system to ensure data accuracy and traceability. Typically, each sample is assigned a unique digital identity, printed as a barcode label, and affixed to the sample tube as proof of sample-data matching in all subsequent testing steps. However, in practice, frequent transfer and contact of sample tubes between different areas often leads to localized wear on the barcode labels, making it difficult for handheld scanners to read them accurately. When a scan fails, the operator may manually enter the sample identifier to avoid interrupting the process. However, prolonged manual input is prone to human error, particularly mistaking the identifier of one sample for that of another valid sample within the same batch. Summary of the Invention

[0003] This application aims to address at least one of the technical problems existing in the prior art. To this end, this application proposes a digital management method and system for the detection process of water-soluble vitamin content, aiming to improve the automation and intelligence level of the detection process.

[0004] In a first aspect, embodiments of this application provide a digital management method for the detection process of water-soluble vitamin content, including: Obtain the sample and physical sample to be processed; The identity identifier of the sample to be processed is determined according to the preset detection task queue, and the identity identifier of the sample to be processed is pushed to the current operation table; The physical sample is decoded using a scanning device; Obtain the verification result of the user's comparison of the identifier of the physical sample with the identity identifier of the sample to be processed through the current operation console; When the identification of the physical sample is worn out, causing the scanning device to be unable to fully decode it, the information captured by the scanning device is intelligently matched with the identification of the sample to be processed to obtain an intelligent matching result; Based on the verification results and the intelligent matching results, the physical sample is controlled to perform subsequent processing procedures.

[0005] According to some embodiments of this application, after obtaining the verification result of the user comparing the identifier of the physical sample with the identity identifier of the sample to be processed through the current operating console, the method further includes: When the identifier of the physical sample matches the identifier of the sample to be processed, the physical sample is controlled to enter the subsequent detection operation; If the identifier of the physical sample is inconsistent with the identifier of the sample to be processed, an identity mismatch warning is triggered, and the physical sample is prevented from entering subsequent detection operations. The user is prompted to re-verify the identifier of the physical sample with the identifier of the sample to be processed through the current operation console until the verification result is consistent, at which point the warning stops.

[0006] According to some embodiments of this application, after determining the identity identifier of the sample to be processed according to a preset detection task queue and pushing the identity identifier of the sample to be processed to the current operating console, the method further includes: When the preset detection task queue is adjusted, the preset detection task queue is updated to obtain the updated detection task queue. Based on the updated detection task queue, the identity of the sample to be processed is re-determined; A timestamp is appended to the identity of the redefined sample to be processed; Verify the difference between the timestamp and the current system time; When the difference exceeds a preset threshold, a request is made to re-push the identity identifier of the sample to be processed.

[0007] According to some embodiments of this application, after triggering an identity mismatch warning when the identifier of the physical sample is inconsistent with the identity identifier of the sample to be processed, and preventing the physical sample from entering subsequent detection operations and prompting the user to re-verify the identifier of the physical sample with the identity identifier of the sample to be processed through the current operation console until the verification result is consistent and the warning is stopped, the method further includes: Record the current console identifier, user identifier, timestamp of inconsistency occurrence, identifier of the sample to be processed, and environmental parameters of the current console; Query the operation records of the control panel during the period before the inconsistency occurred, and the equipment operation log of the sample corresponding to the identity of the sample to be processed in the upstream preprocessing stage. Obtain the initial image of the sample tag corresponding to the identity identifier of the sample to be processed in the receiving stage; Aggregate the identifier of the current operating console, the user's identity identifier, the timestamp of the inconsistency occurrence, the identity identifier of the sample to be processed, the environmental parameters of the current operating console, the operation record, the device operation log, and the initial image to obtain aggregated information; Analyze the aggregated information to identify the root causes of the identity inconsistencies and generate a root cause report.

[0008] According to some embodiments of this application, the step of analyzing the aggregated information, identifying the root causes of identity inconsistencies, and generating a root cause report includes: A preliminary evaluation is performed on each type of data in the aggregated information, and the direct correlation strength between each type of data and the event that is inconsistent with the identity is calculated to obtain a preliminary evaluation result; Based on the preliminary evaluation results, and combined with the preset priority rules and mutual influence relationships, multi-dimensional cross-validation and weight allocation are performed to obtain the results of multi-dimensional cross-validation and weight allocation. Based on the results of the multi-dimensional cross-validation and the weight allocation, the root causes leading to identity inconsistencies are identified and a root cause report is generated, wherein the root cause report includes one or more root causes with the highest impact.

[0009] According to some embodiments of this application, the step of outputting one or more root causes with the highest influence based on the results of the multi-dimensional cross-validation and the weight allocation further includes: Based on the one or more root causes with the highest impact, a root cause list is generated, which includes a description of the root cause, an impact score of the root cause, suggested areas for improvement, and the responsible department. Based on the one or more of the most influential root causes, a visualization is generated that shows the causal chain and influence path between the root causes, and highlights the root cause with the highest influence. An interactive root cause report is generated based on one or more of the most influential root causes. This interactive root cause report is used to simulate and adjust the influence of different root causes in order to evaluate the potential effects of different improvement strategies.

[0010] According to some embodiments of this application, it also includes: Obtain the actual historical data of the current production batch of the sample to be processed; During the simulation adjustment, the mapping relationship between the simulation adjustment parameters and the actual effect is dynamically calibrated based on the actual historical data of the current production batch to obtain the calibrated mapping relationship. When adjusting the influence of one of the root causes, the deviation between the simulated adjustment parameters and the actual historical data is calculated and displayed in real time based on the calibrated mapping relationship. Based on the deviation between the simulation adjustment parameters and the actual historical data, the confidence interval of the simulation results is dynamically adjusted, and the confidence interval is displayed in the root cause report; When the simulation adjustment parameters exceed the confidence interval, the output simulation results have high uncertainty.

[0011] According to some embodiments of this application, the step of dynamically adjusting the confidence interval of the simulation results based on the deviation between the simulation adjustment parameters and the actual historical data, and displaying the confidence interval in the root cause report, includes: Identify whether outliers or abnormal fluctuations exist in the actual historical data; When outliers or abnormal fluctuations exist in the actual historical data, the outliers or abnormal fluctuations are preprocessed or their weights are reduced according to the preset outlier processing rules to obtain the processed actual historical data. Based on the processed actual historical data and the deviation between the simulation adjustment parameters and the processed actual historical data, the confidence interval of the simulation results is dynamically calculated and adjusted. Based on the degree of outlier handling, the robustness of the confidence interval is dynamically assessed and the confidence interval and robustness indicators are displayed in the root cause report.

[0012] According to some embodiments of this application, the step of dynamically evaluating the robustness of the confidence interval based on the degree of outlier processing and displaying the confidence interval and robustness indicators in the root cause report further includes: Calculate the skewness and kurtosis of the processed actual historical data; Based on the skewness and kurtosis, the parameters of the outlier processing rule are dynamically adjusted to obtain the dynamic adjustment range of the outlier processing rule parameters; The fitting residuals are obtained by comparing the distribution characteristics of the processed actual historical data with the fitting degree of multiple preset typical distribution patterns. When the fitting residual exceeds the preset fitting residual, a robustness assessment deviation warning is generated; Based on the dynamic adjustment range of the outlier handling rule parameters and the robustness assessment deviation warning, the robustness index is corrected.

[0013] Secondly, embodiments of this application provide a digital management system for the detection process of water-soluble vitamin content, comprising: The sample acquisition module is used to acquire the sample to be processed and the physical sample; The identification module is used to determine the identification of the sample to be processed according to the preset detection task queue, and push the identification of the sample to be processed to the current operation console; A decoding module is used to decode the physical sample using a scanning device; The verification result acquisition module is used to acquire the verification result of the user's verification of the identifier of the physical sample and the identity identifier of the sample to be processed through the current operation console; The intelligent matching module is used to intelligently match the information captured by the scanning device with the identity identifier of the sample to be processed when the identifier of the physical sample is worn out, causing the scanning device to be unable to fully decode it, and to obtain an intelligent matching result. The control module is used to control the physical sample to perform subsequent processing procedures based on the verification result and the intelligent matching result.

[0014] The technical solution according to the embodiments of this application has at least the following beneficial effects: The digital management method for water-soluble vitamin content detection process disclosed in this application acquires the sample to be processed and the physical sample, and determines the identity identifier of the sample to be processed according to a preset detection task queue, and pushes it to the current operating table. Subsequently, the physical sample is decoded by a scanning device, and the user's verification result of the physical sample identifier and the identity identifier of the sample to be processed is obtained. In particular, when the physical sample identifier is worn and the scanning device cannot fully decode it, this application introduces an intelligent matching mechanism to intelligently match the information captured by the scanning device with the identity identifier of the sample to be processed, and obtain an intelligent matching result. Finally, based on the verification result and the intelligent matching result, the physical sample is controlled to execute the subsequent processing flow. This application effectively solves the problem of sample identity misalignment caused by sample identifier wear or manual input errors in the prior art. In the prior art, when the barcode label is worn or there is a manual input error, the system often cannot identify this "substitution" error, resulting in the detection data being incorrectly associated, overwritten, or missing, which seriously affects the accuracy and reliability of the detection report. This application introduces a dual verification mechanism of user verification and intelligent matching. Even when physical sample identifiers are damaged, intelligent algorithms can still match ambiguous information, significantly reducing the error rate of manual intervention. When the verification results or intelligent matching results show inconsistencies, the system can promptly issue warnings and prevent erroneous samples from entering subsequent processes, avoiding data contamination at the source. This not only improves the accuracy and traceability of detection data but also significantly enhances the efficiency and reliability of quality control.

[0015] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0016] The accompanying drawings are used to provide a further understanding of the technical solutions of this application and constitute a part of the specification. They are used together with the embodiments of this application to explain the technical solutions of this application and do not constitute a limitation on the technical solutions of this application.

[0017] Figure 1 A flowchart illustrating a digital management method for detecting water-soluble vitamin content provided in one embodiment of this application; Figure 2 This is a schematic diagram of a digital management system for detecting the content of water-soluble vitamins provided in one embodiment of this application. Detailed Implementation

[0018] To make the objectives, technical methods, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0019] It should be noted that the meaning of "multiple" (or "more than") in the description of the embodiments of this application refers to two or more, and "greater than," "less than," "exceeding," etc. are understood to exclude the number itself, while "above," "below," "within," etc. are understood to include the number itself. If "first," "second," etc. are used in the description, they are only for the purpose of distinguishing technical features and should not be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated or the order of the technical features indicated.

[0020] In this application embodiment, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent the existence of A alone, the simultaneous existence of A and B, or the existence of B alone. A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one of the following" and similar expressions refer to any combination of these items, including any combination of singular or plural items. For example, at least one of a, b, and c can represent: the existence of a alone, the existence of b alone, the existence of c alone, the simultaneous existence of a and b, the simultaneous existence of a and c, the simultaneous existence of b and c, or the simultaneous existence of a, b, and c, where a, b, and c can be single or multiple.

[0021] In the description of this application, unless otherwise expressly defined, terms such as "setup," "installation," and "connection" should be interpreted broadly, and those skilled in the art can reasonably determine the specific meaning of the above terms in this application in conjunction with the specific content of the technical solution.

[0022] Based on the above, this application proposes a digital management method and system for the detection process of water-soluble vitamin content, aiming to improve the automation and intelligence level of the detection process.

[0023] The digital management method for water-soluble vitamin content detection process provided in this application can be applied to a terminal, a server, or software running on either a terminal or a server. In some embodiments, the terminal can be a smartphone, tablet, laptop, desktop computer, etc.; the server can be configured as an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms; the software can be an application that implements the digital management method for water-soluble vitamin content detection process, but is not limited to the above forms.

[0024] This application can be applied to numerous general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics devices, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via communication networks. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices. It should be noted that in various specific embodiments of this invention, when processing is required based on data related to the characteristics of an object (e.g., user attributes or sets of attribute information), permission or consent from the corresponding object is obtained first, and the collection, use, and processing of this data comply with relevant laws and standards. Furthermore, when the embodiments of the present invention need to obtain the attribute information of an object, they will obtain the separate permission or separate consent of the corresponding object through pop-up windows or redirection to a confirmation page. After obtaining the separate permission or separate consent of the corresponding object, they will then obtain the relevant data of the object necessary for the embodiments of the present invention to operate normally.

[0025] See Figure 1 , Figure 1 This is a flowchart illustrating a digital management method for water-soluble vitamin content detection workflow provided in one embodiment of this application. The digital management method for water-soluble vitamin content detection workflow provided in this embodiment includes, but is not limited to, steps S110 to S160, which will be described in detail below.

[0026] Step S110: Obtain the sample to be processed and the physical sample; Step S120: Determine the identity of the sample to be processed according to the preset detection task queue, and push the identity of the sample to be processed to the current operation table; Step S130: Decode the physical sample using a scanning device; Step S140: Obtain the verification result of the user's verification of the physical sample identifier and the identity identifier of the sample to be processed through the current operation console; Step S150: When the wear and tear of the physical sample's identifier prevents the scanning device from fully decoding it, the information captured by the scanning device is intelligently matched with the identifier of the sample to be processed to obtain the intelligent matching result. Step S160: Based on the verification results and intelligent matching results, control the physical sample to perform subsequent processing procedures.

[0027] It should be noted that "samples to be processed" refers to samples pre-registered and assigned identification tags in the digital management system. These tags are typically stored in the testing task queue, awaiting processing. "Physical samples" refer to actual, identifiable sample tubes containing the water-soluble vitamins to be tested. "Current workstation" refers to the workstation where the operator processes samples and verifies information, typically equipped with a display screen, input devices, and scanning devices. "Scanning device" refers to the hardware used to read the physical sample identification tags, such as a barcode scanner or QR code reader. "Identification tag" is a numerical or character code used to uniquely identify a sample. "Preset testing task queue" refers to the pre-arranged sample testing order and related information list within the system.

[0028] In one embodiment, the desired sample and physical sample are acquired. The desired sample can be automatically imported from the production plan or LIMS (Laboratory Information Management System) via a system interface, or it can be manually created by the operator in the system. The physical sample is the actual sample tube transferred from the production line or pre-processing stage to the testing laboratory. Next, the identification of the desired sample is determined according to a preset testing task queue, and the identification of the desired sample is pushed to the current operating station. For example, the system can automatically display the identification of the next sample to be processed on the screen of the current operating station according to the order of the task queue, prompting the operator to process it. Then, the physical sample is decoded by a scanning device. The operator can use a handheld scanning device to scan the barcode or QR code on the physical sample to obtain its identification information. Then, the verification result of the user's comparison of the identification of the physical sample with the identification of the desired sample is obtained through the current operating station. After the operator scans the physical sample, the system compares the scanned identification with the identification of the desired sample and displays the comparison result on the operating station for the operator to manually confirm and input the verification result. Furthermore, when wear and tear on the physical sample's identifier prevents the scanning device from fully decoding it, the system intelligently matches the information captured by the scanning device with the identifier of the sample to be processed, obtaining an intelligent matching result. For example, if the scanning device can only read part of the barcode information, the system will attempt to perform a fuzzy match between this partial information and the complete identifier of the sample to be processed in the task queue to infer the most likely sample identity. Finally, based on the verification result and the intelligent matching result, the system controls the physical sample to execute subsequent processing procedures. The system comprehensively considers the results of manual verification and intelligent matching to determine whether the physical sample can proceed to the next detection operation or requires anomaly handling.

[0029] It should be noted that when the verification result shows that the physical sample's identifier completely matches the identifier of the sample to be processed, the system will automatically allow the physical sample to enter the predetermined subsequent detection operation, such as pretreatment or instrument analysis. The identifier mismatch warning can be understood as the system issuing an alert to the operator through visual (e.g., screen flashing, color change), audible (e.g., buzzer, voice prompt), or other means, clearly indicating that the current sample's identifier does not match the expected one. In practical applications, preventing a physical sample from entering subsequent detection operations means that the system, through software logic or linkage with automated equipment, physically or logically prevents the sample from being further processed, such as locking the sample rack or disabling the next operation button. Furthermore, prompting the user to re-verify the physical sample's identifier against the identifier of the sample to be processed through the current operating console aims to guide the operator to perform secondary confirmation or correction operations, ensuring timely manual intervention in any inconsistency. Stopping the warning only when the verification result is consistent ensures that the system can only deactivate the alarm and allow the process to continue after the identifier verification is correct.

[0030] It should be noted that the aforementioned "adjustment of the preset testing task queue" can be understood as any change in the sample order, priority, addition of samples, or removal of samples within the testing task queue. When the system detects such an adjustment, it will trigger the operation of "updating the preset testing task queue." This update process can be completed automatically by the system, for example, through data synchronization with the Laboratory Information Management System (LIMS) or other upstream systems, or manually adjusted and submitted by an authorized user. The updated testing task queue is accurate data reflecting the latest testing schedule. Subsequently, "re-determining the identity of the samples to be processed based on the updated testing task queue" means that the system will recalculate or query the identity of the samples that should be processed at the current workstation based on the latest queue information. For example, if the priority of a sample in the queue is increased, the identity of that sample may be re-determined as the next processing target for the current workstation. To ensure the timeliness of the identity, it is necessary to "attach a timestamp to the re-determined identity of the samples to be processed." This timestamp records the specific time when the identity was determined or updated, serving as an important indicator of its validity. Furthermore, "verifying the difference between the timestamp and the current system time" aims to assess whether the sample identity used by the current console is still up-to-date and valid. For example, the system may periodically or before specific operations compare the timestamp of the identity with the server's current system time. The "preset threshold" can be configured according to the actual application scenario and the requirements for data real-time performance, such as 5 seconds, 10 seconds, or longer. When the difference exceeds the preset threshold, it indicates that the identity of the current console may have expired or is no longer accurate. In this case, the system will "request to re-push the identity of the sample to be processed" to ensure that the console always obtains and displays the latest and valid sample identity.

[0031] In one embodiment, suppose that a laboratory's testing task queue initially schedules tests for samples A, B, and C. The current workstation determines and pushes the identifier of sample A according to the preset testing task queue. However, before sample A has started testing, due to urgent needs, sample D is inserted at the head of the queue, and sample B is removed. At this time, the system detects that the preset testing task queue has been adjusted. The system automatically updates the testing task queue, resulting in an updated queue (sample D, sample A, sample C). Subsequently, based on the updated testing task queue, the system re-determines the identifier of the sample that the current workstation should process as sample D. A current timestamp is appended to the re-determined identifier of sample D. The system checks the difference between this timestamp and the current system time. If it finds that the current workstation is still displaying the identifier of sample A, and the difference between its timestamp and the current system time exceeds a preset threshold (e.g., 5 seconds), the system will immediately request to re-push the identifier of sample D to the current workstation. Therefore, operators can obtain the latest identification of sample D in a timely manner before starting the test, avoiding mistakenly treating sample A as the next target for processing, thus ensuring the accuracy of the testing process and the correct execution of task priorities.

[0032] It should be noted that when an identity mismatch warning is triggered, the system automatically records a series of key information. These include: the current workstation identifier for uniquely identifying the specific workstation where the problem occurred; the user's identity identifier for tracking the operator; the timestamp of the inconsistency occurrence precisely recording the time of the event; the identity identifier of the sample to be processed clarifying the expected identity of the sample involved; and the environmental parameters of the current workstation, including temperature, humidity, and lighting, which can sometimes affect the performance of the scanning equipment or the recognition of tags. Furthermore, to comprehensively trace the source of the problem, the system queries the workstation's operation records for a period of time prior to the inconsistency, such as the operator's login and logout times, other operations performed, and the equipment operation logs of the sample corresponding to the identity identifier of the sample to be processed in the upstream pre-processing stage, such as the operating status of equipment for sample dispensing and labeling, and abnormal alarms. In addition, it acquires the initial image of the sample tag corresponding to the identity identifier of the sample to be processed during the receiving stage. This image can serve as evidence of the original tag state for comparison with subsequent possible tag wear or damage. Therefore, the current console identifier, user identity identifier, timestamp of the inconsistency occurrence, identity identifier of the sample to be processed, environmental parameters of the current console, operation records, equipment operation logs, and initial image are aggregated to form a comprehensive aggregated information. This aggregated information includes the entire data chain from sample reception to the failed verification at the current console. Finally, the aggregated information is analyzed in depth. Through data mining, pattern recognition, and other techniques, the root cause of the identity inconsistency is identified, such as due to label printing errors, sample confusion, scanning equipment malfunction, operator error, or environmental factors, and a detailed root cause report is generated.

[0033] It should be noted that a preliminary evaluation is performed on each type of data in the aggregated information. The system calculates the direct correlation strength between each data type and events with inconsistent identities to obtain preliminary evaluation results. First, the system independently analyzes each type of data in the aggregated information, such as the current console identifier, user identity identifier, timestamp of the inconsistency occurrence, identity identifier of the sample to be processed, environmental parameters of the current console, operation records, equipment operation logs, and initial images. Statistical methods or machine learning models are used to calculate the direct correlation or influence degree between each data type and events with inconsistent identities, thereby quantifying its "direct correlation strength." For example, if a specific operator's user identity identifier is associated with high-frequency events with inconsistent identities in the historical record, then the direct correlation strength between that operator's identity identifier and events with inconsistent identities is high. Further, based on the preliminary evaluation results, combined with preset priority rules and mutual influence relationships, multi-dimensional cross-validation and weight allocation are performed to obtain the results of multi-dimensional cross-validation and weight allocation. After obtaining the preliminary evaluation results, the system introduces a more complex analysis mechanism. Preset priority rules can be set based on experience or historical data; for example, equipment malfunctions may be given higher priority than human error. The interaction relationship assessment considers the synergistic effects between different factors; for example, a particular operator is more prone to errors under specific environmental parameters (such as insufficient lighting). Multi-dimensional cross-validation ensures the robustness and accuracy of the assessment results, avoiding the biases of single-dimensional analysis. Weight allocation assigns a quantified weight to each potential cause based on the priority and interaction relationships of each factor, reflecting its comprehensive impact on the identity inconsistency event. Based on the results of multi-dimensional cross-validation and weight allocation, the root causes leading to identity inconsistencies are identified, and a root cause report is generated. This report includes one or more root causes with the highest impact. After the refined assessment and allocation described above, the system can identify the root causes with the greatest impact and highest weight on the identity inconsistency event. These root causes are included in the root cause report, which not only lists the root causes but may also include information such as their degree of impact and frequency of occurrence, highlighting those with the highest impact for management to prioritize.

[0034] It's important to note that generating a root cause list involves presenting one or more of the most impactful root causes in a structured text format. This list includes not only a clear description of each root cause, such as "blurry sample label printing," "scanning equipment calibration deviation," or "insufficient operator training," but also an impact score. This score can be a quantitative indicator reflecting the root cause's contribution to the identity inconsistency event or its potential risk. Furthermore, the list provides suggested improvement directions for each root cause, such as "optimize label printing quality," "regularly calibrate scanning equipment," or "enhance operator skills training," and clearly identifies the responsible departments for implementing these improvements, thus providing clear guidance for subsequent improvement measures. Generating visualizations can be understood as visually representing the root causes and their interrelationships. For example, fishbone diagrams, cause-and-effect loop diagrams, or flowcharts can be used to intuitively show the causal chains and impact paths between various root causes. Through this visualization, users can clearly see which root causes are at the core, which are upstream causes leading to other problems, and how they collectively lead to the identity inconsistency event. The most impactful root causes are highlighted in the chart, for example, through color, size, or special markers, to guide users to prioritize and address these key issues. In practice, generating an interactive root cause report specifically involves providing a dynamic, user-interactive reporting interface. Within this report, users can simulate and adjust the impact of different root causes. For example, users can drag a slider or enter a value to change the "strength" or "probability" of a particular root cause, and the system will calculate and display in real time the potential impact of this adjustment on the frequency or severity of overall identity inconsistencies.

[0035] In one embodiment, suppose that during a water-soluble vitamin content test, multiple instances occurred where the physical sample identification did not match the identification of the sample to be processed. The system first aggregates relevant data and analyzes it to identify the root causes of these inconsistencies, such as "low ink cartridges in the label printer cause some labels to be blurry (impact score: 8.5)," "Operator A has a higher error rate during the night shift (impact score: 7.0)," and "the reflective material of the new batch of sample labels makes scanning difficult (impact score: 6.0)." Based on these identified root causes, the system generates a root cause list. This list clearly lists the three root causes and provides their descriptions, impact scores, suggested improvement directions (e.g., for low ink cartridges, "regularly check and replace printer ink cartridges"; for Operator A, "strengthen night shift operator training and supervision"; for label material, "adjust scanning equipment parameters or change label suppliers"), and the responsible department (e.g., equipment maintenance department, quality management department, purchasing department). Simultaneously, the system generates a visual chart, such as a cause-and-effect chain diagram. In this chart, "Label printer ink cartridge low" might be identified as an upstream cause, leading to "partially blurred labels," which in turn leads to "scanning equipment unable to fully decode," ultimately resulting in "identity inconsistency." "Operator A's operational error" could directly cause "identity inconsistency." "Reflective material on new batch sample labels" could also directly cause "scanning difficulties," leading to "identity inconsistency." "Label printer ink cartridge low" and "Operator A's operational error" are likely to be highlighted as the root causes with the highest impact. Furthermore, the system provides an interactive root cause report. In this report interface, users can attempt to simulate adjustments. For example, a user can simulate reducing the impact of "Label printer ink cartridge low" by 90% (assuming this is achieved through timely cartridge replacement). The system will calculate and display in real time that, all other things being equal, the incidence of identity inconsistency events is expected to decrease by 30%. Users can also simulate reducing the "Operator A's operational error rate" by 50% (assuming this is achieved through training), and the system will display an expected reduction of 15%.

[0036] It's important to note that the first step is to obtain the actual historical data of the current production batch of the samples to be processed. This historical data can include various parameters related to the testing process, such as test results under different operating conditions, sample processing time, and equipment operating status. Its purpose is to provide a real-world reference benchmark for subsequent simulation adjustments. Furthermore, during simulation adjustments, the mapping relationship between simulation adjustment parameters and actual effects is dynamically calibrated based on the actual historical data of the current production batch, resulting in a calibrated mapping relationship. This aims to ensure that the simulation model better reflects the specific characteristics and behavioral patterns of the current production batch, making the simulation results closer to the performance in the actual production environment. Specifically, when adjusting the influence of a root cause, the deviation between the simulation adjustment parameters and the actual historical data is calculated and displayed in real time based on the calibrated mapping relationship. This real-time feedback mechanism allows users to immediately perceive the degree of agreement between the current simulation operation and historical trends, and to promptly identify and correct any potential deviations. In addition, the confidence interval of the simulation results is dynamically adjusted based on the deviation between the simulation adjustment parameters and the actual historical data, and the confidence interval is displayed in the report. The confidence interval provides a quantitative measure of the reliability of the simulation results, helping users understand the possible range of predicted effects. When simulation adjustment parameters exceed the confidence interval, the system will output a warning indicating that the simulation results have high uncertainty. This mechanism aims to warn users that when simulation operations enter areas where historical data support is weak or nonexistent, they should treat the simulation results with caution and avoid over-reliance on potentially unreliable predictions.

[0037] It's important to note that identifying outliers or anomalous fluctuations in historical data involves applying statistical methods (e.g., Z-score, IQR, DBSCAN clustering) or machine learning algorithms (e.g., Isolation Forest, Local Outlier Factor (LOF)) to conduct in-depth analysis of the historical data. This analysis detects whether data points significantly deviate from the overall trend or expected distribution pattern. Outliers are typically defined as observations in a dataset that are significantly different from other data points, while anomalous fluctuations refer to large, unexpected changes in data over a short period. When outliers or anomalous fluctuations are identified in historical data, these outliers or fluctuations are preprocessed or have their weights reduced according to predefined outlier handling rules. These predefined outlier handling rules may include, but are not limited to: directly deleting outliers, using the mean, median, or mode for filling, using interpolation for repair, or reducing the weight of outliers in subsequent calculations. For example, data points with extreme deviations can be directly removed from the dataset; for minor outliers, their influence in confidence interval calculation can be reduced to minimize their interference with the overall estimate, thus obtaining processed historical data. Specifically, the confidence interval of the simulation results is dynamically calculated and adjusted based on the processed historical data and the deviation between the simulation adjustment parameters and the processed historical data. This means that when determining confidence intervals, the original historical data is no longer relied upon alone; cleaned or weighted data is prioritized. Confidence intervals can be calculated using various statistical methods, such as parameter estimation based on t-distribution or normal distribution, or using non-parametric bootstrap resampling methods. By using processed data, confidence intervals can better reflect the true distribution characteristics of the data, effectively reducing the bias caused by outliers. Furthermore, the robustness of the confidence intervals is dynamically evaluated based on the degree of outlier handling, and the confidence intervals and robustness indicators are displayed in the report. The degree of outlier handling can be quantified by the number of data points processed, the proportion of weight reduction, or the degree of change in the data distribution before and after processing. Robustness metrics may include, but are not limited to, the width of the confidence interval, coverage, and stability under different data perturbations. For example, if outliers are handled extensively, it may indicate significant problems with the quality of the original data. In this case, the robustness metric for the confidence interval may decrease accordingly, thus alerting the user that the reliability of the simulation results may be potentially affected by data quality.

[0038] In one embodiment, assuming that the vitamin B12 content of a certain batch needs to be simulated and adjusted in the water-soluble vitamin content detection process to evaluate the potential effects of different improvement strategies, the system first acquires the actual historical data of the vitamin B12 in that batch. During the simulation adjustment, the system identifies whether there are outliers or abnormal fluctuations in these historical data. For example, if a test results in abnormally high data due to equipment failure, the system will identify it as an outlier. According to preset outlier handling rules, the outlier may be assigned a lower weight or replaced with the median of other normal data in the batch, thus obtaining the processed actual historical data. Subsequently, the system dynamically calculates and adjusts the confidence interval of the simulation results based on the deviation between the simulation adjustment parameters and the processed actual historical data. For example, if the processed data is more concentrated, the confidence interval may be narrowed accordingly, indicating higher certainty in the simulation results. At the same time, the system dynamically evaluates and displays the robustness index of the confidence interval based on the degree of outlier handling (e.g., how many data points are processed and how they are processed). If there are many outliers or the processing level is high, robustness indicators may prompt users that, although the confidence interval has been adjusted, the quality of the original data still needs to be considered, thereby providing users with more comprehensive and reliable simulation evaluation results.

[0039] What's needed is to calculate the skewness and kurtosis of the processed historical data. This involves performing statistical analysis on the processed historical data to quantify its distribution shape characteristics. Skewness measures the asymmetry of the data distribution, while kurtosis measures the sharpness or thickness of the tails. Calculating these statistics provides a deeper understanding of the data distribution pattern. Furthermore, based on skewness and kurtosis, the parameters of the outlier processing rules are dynamically adjusted to determine the dynamic adjustment range of these parameters. This means that if the data distribution exhibits significant skewness or anomalous kurtosis, the parameters of the outlier processing rules can be adjusted accordingly, such as adjusting the outlier identification threshold or processing intensity. Thus, the outlier processing process can better adapt to the actual distribution characteristics of the data, improving the accuracy and effectiveness of the processing. In addition, comparing the distribution characteristics of the processed historical data with the fit of multiple preset typical distribution patterns and calculating the fitting residuals involves comparing the processed historical data with various known statistical distribution models such as the normal distribution, Poisson distribution, and exponential distribution. By calculating the residuals between the data and these typical distribution patterns, the "standard"ness of the data distribution or its deviation from the typical pattern can be assessed. Smaller residuals indicate a high degree of fit to a typical pattern, while larger residuals suggest that the data distribution may have unique or non-standard characteristics. When the residuals exceed a preset limit, a robustness assessment bias warning is generated. This means that the system will issue a warning when the processed actual historical data distribution differs significantly from the preset typical distribution pattern. This warning aims to remind the user that the current robustness assessment may have potential biases, requiring further attention or action. Finally, the robustness index is corrected based on the dynamic adjustment of the outlier handling rule parameters and the robustness assessment bias warning. This means that the final value of the robustness index not only considers the degree of outlier handling but also integrates the dynamic adjustment of the outlier handling rule parameters and the deviation in data distribution fitting. In this way, the robustness index can more comprehensively and accurately reflect the true robustness of the confidence interval.

[0040] See Figure 2 , Figure 2 This is a schematic diagram of a digital management system for water-soluble vitamin content detection workflow provided in one embodiment of this application. The digital management system 200 for water-soluble vitamin content detection workflow includes: The sample acquisition module 210 is used to acquire the sample to be processed and the physical sample; The identification module 220 is used to determine the identification of the sample to be processed according to the preset detection task queue, and push the identification of the sample to be processed to the current operation table; Decoding module 230 is used to decode physical samples using a scanning device; The verification result acquisition module 240 is used to acquire the verification result of the user's verification of the physical sample identifier and the identity identifier of the sample to be processed through the current operation table; The intelligent matching module 250 is used to intelligently match the information captured by the scanning device with the identity identifier of the sample to be processed when the identifier of the physical sample is worn and the scanning device cannot fully decode it, so as to obtain the intelligent matching result. The control module 260 is used to control the physical sample to perform subsequent processing procedures based on the verification results and intelligent matching results.

[0041] It should be noted that the information interaction and execution process between the above modules are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, which will not be repeated here.

[0042] It will be understood by those skilled in the art that all or some of the steps and systems in the methods disclosed above can be implemented as software, firmware, hardware, and suitable combinations thereof. Some or all of the physical components can be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer-readable medium, which can include computer storage media (or non-transitory media) and communication media (or transient media). As is known to those skilled in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible to a computer. Furthermore, as is known to those skilled in the art, communication media typically include computer-readable instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0043] The foregoing has provided a detailed description of the preferred embodiments of this application. However, this application is not limited to the above-described embodiments. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of this application. All such equivalent modifications or substitutions are included within the scope defined in this application.

Claims

1. A digital management method for the detection process of water-soluble vitamin content, characterized in that, include: Obtain the sample and physical sample to be processed; The identity identifier of the sample to be processed is determined according to the preset detection task queue, and the identity identifier of the sample to be processed is pushed to the current operation table; The physical sample is decoded using a scanning device; Obtain the verification result of the user's comparison of the identifier of the physical sample with the identity identifier of the sample to be processed through the current operation console; When the identification of the physical sample is worn out, causing the scanning device to be unable to fully decode it, the information captured by the scanning device is intelligently matched with the identification of the sample to be processed to obtain an intelligent matching result; Based on the verification results and the intelligent matching results, the physical sample is controlled to perform subsequent processing procedures.

2. The method according to claim 1, characterized in that, After obtaining the verification result of the user comparing the identifier of the physical sample with the identity identifier of the sample to be processed through the current operating console, the method further includes: When the identifier of the physical sample matches the identifier of the sample to be processed, the physical sample is controlled to enter the subsequent detection operation; If the identifier of the physical sample is inconsistent with the identifier of the sample to be processed, an identity mismatch warning is triggered, and the physical sample is prevented from entering subsequent detection operations. The user is prompted to re-verify the identifier of the physical sample with the identifier of the sample to be processed through the current operation console until the verification result is consistent, at which point the warning stops.

3. The method according to claim 1, characterized in that, After determining the identity identifier of the sample to be processed according to the preset detection task queue and pushing the identity identifier of the sample to be processed to the current operation console, the process further includes: When the preset detection task queue is adjusted, the preset detection task queue is updated to obtain the updated detection task queue. Based on the updated detection task queue, the identity of the sample to be processed is re-determined; A timestamp is appended to the identity of the redefined sample to be processed; Verify the difference between the timestamp and the current system time; When the difference exceeds a preset threshold, a request is made to re-push the identity identifier of the sample to be processed.

4. The method according to claim 2, characterized in that, The step of triggering an identity mismatch warning when the identifier of the physical sample does not match the identifier of the sample to be processed, preventing the physical sample from entering subsequent detection operations, and prompting the user to re-verify the identifier of the physical sample against the identifier of the sample to be processed through the current operation console until the verification result matches, and then stopping the warning, further includes: Record the current console identifier, user identifier, timestamp of inconsistency occurrence, identifier of the sample to be processed, and environmental parameters of the current console; Query the operation records of the control panel during the period before the inconsistency occurred, and the equipment operation log of the sample corresponding to the identity of the sample to be processed in the upstream preprocessing stage. Obtain the initial image of the sample tag corresponding to the identity identifier of the sample to be processed in the receiving stage; Aggregate the identifier of the current operating console, the user's identity identifier, the timestamp of the inconsistency occurrence, the identity identifier of the sample to be processed, the environmental parameters of the current operating console, the operation record, the device operation log, and the initial image to obtain aggregated information; Analyze the aggregated information to identify the root causes of the identity inconsistencies and generate a root cause report.

5. The method according to claim 4, characterized in that, The analysis of the aggregated information, identification of the root causes of identity inconsistencies, and generation of a root cause report include: A preliminary evaluation is performed on each type of data in the aggregated information, and the direct correlation strength between each type of data and the event that is inconsistent with the identity is calculated to obtain a preliminary evaluation result; Based on the preliminary evaluation results, and combined with the preset priority rules and mutual influence relationships, multi-dimensional cross-validation and weight allocation are performed to obtain the results of multi-dimensional cross-validation and weight allocation. Based on the results of the multi-dimensional cross-validation and the weight allocation, the root causes leading to identity inconsistencies are identified and a root cause report is generated, wherein the root cause report includes one or more root causes with the highest impact.

6. The method according to claim 5, characterized in that, Based on the results of the multi-dimensional cross-validation and the weight allocation, the root causes leading to identity inconsistencies are identified and a root cause report is generated. The root cause report includes one or more root causes with the highest impact, and further includes: Based on the one or more root causes with the highest impact, a root cause list is generated, which includes a description of the root cause, an impact score of the root cause, suggested areas for improvement, and the responsible department. Based on the one or more of the most influential root causes, a visualization is generated that shows the causal chain and influence path between the root causes, and highlights the root cause with the highest influence. An interactive root cause report is generated based on one or more of the most influential root causes. This interactive root cause report is used to simulate and adjust the influence of different root causes in order to evaluate the potential effects of different improvement strategies.

7. The method according to claim 6, characterized in that, Also includes: Obtain the actual historical data of the current production batch of the sample to be processed; During the simulation adjustment, the mapping relationship between the simulation adjustment parameters and the actual effect is dynamically calibrated based on the actual historical data of the current production batch to obtain the calibrated mapping relationship. When adjusting the influence of one of the root causes, the deviation between the simulated adjustment parameters and the actual historical data is calculated and displayed in real time based on the calibrated mapping relationship. Based on the deviation between the simulation adjustment parameters and the actual historical data, the confidence interval of the simulation results is dynamically adjusted, and the confidence interval is displayed in the root cause report; When the simulation adjustment parameters exceed the confidence interval, the output simulation results have high uncertainty.

8. The method according to claim 7, characterized in that, The step of dynamically adjusting the confidence interval of the simulation results based on the deviation between the simulation adjustment parameters and the actual historical data, and displaying the confidence interval in the root cause report, includes: Identify whether outliers or abnormal fluctuations exist in the actual historical data; When outliers or abnormal fluctuations exist in the actual historical data, the outliers or abnormal fluctuations are preprocessed or their weights are reduced according to the preset outlier processing rules to obtain the processed actual historical data. Based on the processed actual historical data and the deviation between the simulation adjustment parameters and the processed actual historical data, the confidence interval of the simulation results is dynamically calculated and adjusted. Based on the degree of outlier handling, the robustness of the confidence interval is dynamically assessed and the confidence interval and robustness indicators are displayed in the root cause report.

9. The method according to claim 8, characterized in that, The method of dynamically evaluating the robustness of the confidence interval based on the degree of outlier treatment and displaying the confidence interval and robustness indicators in the root cause report further includes: Calculate the skewness and kurtosis of the processed actual historical data; Based on the skewness and kurtosis, the parameters of the outlier processing rule are dynamically adjusted to obtain the dynamic adjustment range of the outlier processing rule parameters; The fitting residuals are obtained by comparing the distribution characteristics of the processed actual historical data with the fitting degree of multiple preset typical distribution patterns. When the fitting residual exceeds the preset fitting residual, a robustness assessment deviation warning is generated; Based on the dynamic adjustment range of the outlier handling rule parameters and the robustness assessment deviation warning, the robustness index is corrected.

10. A digital management system for the detection process of water-soluble vitamin content, characterized in that, include: The sample acquisition module is used to acquire the sample to be processed and the physical sample; The identification module is used to determine the identification of the sample to be processed according to the preset detection task queue, and push the identification of the sample to be processed to the current operation console; A decoding module is used to decode the physical sample using a scanning device; The verification result acquisition module is used to acquire the verification result of the user's verification of the identifier of the physical sample and the identity identifier of the sample to be processed through the current operation console; The intelligent matching module is used to intelligently match the information captured by the scanning device with the identity identifier of the sample to be processed when the identifier of the physical sample is worn out, causing the scanning device to be unable to fully decode it, and to obtain an intelligent matching result. The control module is used to control the physical sample to perform subsequent processing procedures based on the verification result and the intelligent matching result.

Images