Upstream and downstream aligned test tube sampling timing optimization method and system

Abstract

The present application provides a method and system for optimizing the timing of test tube sampling with upstream and downstream alignment, and relates to the technical field of timing optimization. The method includes: obtaining the historical test tube sample arrival record of the first upstream source, and obtaining the first historical test tube sample arrival record based on the first task type screening; generating the first historical test tube sample arrival timing; obtaining the first timing feature set; activating the task quantity prediction model for prediction analysis, and obtaining the first target task quantity prediction value of the first task type under the target time zone; comparing the first test tube inventory of the first upstream source with the first predetermined inventory threshold to obtain the first inventory deviation; obtaining the first sampling priority index; and performing priority control of the test tube sampling of the first task type. The technical goal of optimizing the sample processing flow is achieved, and the technical effect of providing a scientific and reasonable resource allocation reference for downstream operations and thus improving the overall test tube circulation operation efficiency is achieved.

Description

Technical Field

[0001] The present application relates to the technical field of timing optimization, and in particular to a method and system for optimizing the timing of upstream and downstream aligned test tube sampling. Background Art

[0002] The correct handling and timely analysis of test tube samples are crucial to ensure the accuracy of experimental results and the effectiveness of clinical decisions. With the continuous advancement of detection technology and the increase in sample processing volume, how to efficiently process and analyze test tube samples from upstream sources has become a problem that needs to be solved urgently. For example, when processing test tube samples, a large number of historical sample arrival records are usually accumulated. These records contain sample information of different task types. However, how to effectively extract sample data of specific task types from these records, and at the same time combine the time regularity of the arrival of test tube samples to conduct more targeted timing analysis, and provide support for subsequent pre-test tube sample arrival quantity analysis, has not yet been solved. In other words, it is an urgent problem to generate a priority sequence for downstream test tube sampling based on the predicted value of the number of tasks, achieve the goal of optimizing the sample processing process, and provide a scientific and reasonable resource allocation reference for downstream operations, thereby improving overall operational efficiency.

[0003] To sum up, the existing technology lacks the time series feature mining of historical sample arrival records, and thus cannot effectively predict the arrival number of test tube samples. Furthermore, it is impossible to generate the downstream priority processing order based on the accurate number of test tube sample tasks, which is not conducive to the rational allocation of downstream resources and the efficient processing of operations, and ultimately leads to the technical problem of low efficiency of the entire test tube operation flow. Summary of the invention

[0004] The purpose of this application is to provide a method and system for optimizing the timing of test tube sampling with upstream and downstream alignment, so as to solve the problem that the prior art lacks the timing feature mining of historical sample arrival records, and cannot provide a scientific reference for the priority order of downstream test tube sample processing, thereby affecting the overall operation efficiency.

[0005] In view of the above problems, the present application provides a method and system for optimizing the timing of upstream and downstream aligned test tube sampling.

[0006] In a first aspect, the present application provides an upstream and downstream aligned test tube sampling timing optimization method, which is implemented by an upstream and downstream aligned test tube sampling timing optimization system, wherein the upstream and downstream aligned test tube sampling timing optimization method comprises: obtaining a historical test tube sample arrival record of a first upstream source, and screening the historical test tube sample arrival record based on a first task type to obtain a first historical test tube sample arrival record; generating a first historical test tube sample arrival timing sequence based on a plurality of sample arrival time zones with task quantity identifiers in the first historical test tube sample arrival record; obtaining a predetermined timing feature collection strategy, and based on the predetermined timing sequence The feature collection strategy collects features of the first historical test tube sample arrival timing to obtain a first timing feature set; activates the task quantity prediction model to perform predictive analysis on the first historical test tube sample arrival timing and the first timing feature set to obtain a first target task quantity prediction value for the first task type under the target time zone; compares the first test tube inventory of the first upstream source with a first predetermined inventory threshold to obtain a first inventory deviation; obtains a first sampling priority index of the first upstream source based on the first target task quantity prediction value and the first inventory deviation; and performs priority control of test tube sampling of the first task type based on the first sampling priority index.

[0007] In a second aspect, the present application further provides an upstream and downstream aligned test tube sampling timing optimization system, which is used to execute the upstream and downstream aligned test tube sampling timing optimization method as described in the first aspect, wherein the upstream and downstream aligned test tube sampling timing optimization system includes: a historical record acquisition module, the historical record acquisition module is used to obtain the historical test tube sample arrival record of the first upstream source, and filter the historical test tube sample arrival record based on the first task type to obtain the first historical test tube sample arrival record; a timing generation module, the timing generation module is used to generate the first historical test tube sample arrival timing based on multiple sample arrival time zones with task quantity identification in the first historical test tube sample arrival record; a feature collection module, the feature collection module is used to obtain a predetermined timing feature collection strategy, and filter the first historical test tube sample arrival record based on the predetermined timing feature collection strategy The invention relates to a method for preparing a test tube sample arrival sequence for feature collection to obtain a first time series feature set; a task quantity prediction module, wherein the task quantity prediction module is used to activate the task quantity prediction model to perform prediction analysis on the first historical test tube sample arrival sequence and the first time series feature set to obtain a first target task quantity prediction value of the first task type under the target time zone; an inventory analysis module, wherein the inventory analysis module is used to compare the first test tube inventory of the first upstream source with a first predetermined inventory threshold to obtain a first inventory deviation; a priority analysis module, wherein the priority analysis module is used to obtain a first sampling priority index of the first upstream source according to the first target task quantity prediction value and the first inventory deviation; and a control execution module, wherein the control execution module is used to perform priority control of test tube sampling of the first task type based on the first sampling priority index.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0009] The first historical test tube sample arrival record is obtained by obtaining the historical test tube sample arrival record of the first upstream source, and the historical test tube sample arrival record is screened based on the first task type to obtain the first historical test tube sample arrival record; the first historical test tube sample arrival timing sequence is generated based on multiple sample arrival time zones with task quantity identification in the first historical test tube sample arrival record; a predetermined timing feature collection strategy is obtained, and the first historical test tube sample arrival timing sequence is collected based on the predetermined timing feature collection strategy to obtain a first timing feature set; the task quantity prediction model is activated to perform prediction analysis on the first historical test tube sample arrival timing sequence and the first timing feature set to obtain a first target task quantity prediction value of the first task type under the target time zone; the first test tube inventory of the first upstream source is compared with the first predetermined inventory threshold to obtain a first inventory deviation; the first sampling priority index of the first upstream source is obtained according to the first target task quantity prediction value and the first inventory deviation; and priority control of test tube sampling of the first task type is performed based on the first sampling priority index. By generating a priority sequence for downstream test tube sampling based on the predicted value of the number of tasks, the technical goal of optimizing the sample processing process is achieved, and the technical effect of providing a scientific and reasonable resource allocation reference for downstream operations and thereby improving the overall test tube flow operation efficiency is achieved.

[0010] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0012] Figure 1 A schematic diagram of the process flow of the test tube sampling timing optimization method for upstream and downstream alignment in this application;

[0013] Figure 2 This is a schematic diagram of the structure of the test tube sampling timing optimization system with upstream and downstream alignment in this application.

[0014] Description of reference numerals:

[0015] History record acquisition module 11, time series generation module 12, feature collection module 13, task quantity prediction module 14, inventory analysis module 15, priority analysis module 16, control execution module 17. DETAILED DESCRIPTION

[0016] This application solves the problem that the prior art lacks time series feature mining of historical sample arrival records, and thus cannot effectively predict the number of arrivals of test tube samples, by providing a method and system for optimizing the timing of test tube sampling with upstream and downstream alignment. Furthermore, it is impossible to generate the downstream priority processing order based on the accurate number of test tube sample tasks, which is not conducive to the rational allocation of downstream resources and the efficient processing of operations, and ultimately leads to the technical problem of low efficiency of the entire test tube operation flow. The technical goal of providing a priority reference for the downstream to continue processing test tube samples is achieved, and the technical effect of improving the scientific nature of downstream operations and the rationality of resource allocation, thereby improving the efficiency of the entire test tube operation flow, is achieved.

[0017] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0018] For example, please refer to the attached Figure 1 The present application provides a method for optimizing the timing of test tube sampling with upstream and downstream alignment, wherein the method for optimizing the timing of test tube sampling with upstream and downstream alignment is applied to a system for optimizing the timing of test tube sampling with upstream and downstream alignment, and the method for optimizing the timing of test tube sampling with upstream and downstream alignment specifically comprises the following steps:

[0019] A historical test tube sample arrival record of a first upstream source is obtained, and the historical test tube sample arrival record is screened based on a first task type to obtain a first historical test tube sample arrival record.

[0020] Specifically, obtaining and filtering specific historical test tube sample arrival records first involves collecting historical data from the first upstream source, i.e., records of test tube sample arrival. These records may contain information such as timestamps, sample identifiers, and receipt status. Next, these records are filtered based on the first task type, with the goal of extracting sample records related to a specific task from a large amount of data. Such filtering can more effectively process and analyze sample information related to a specific task, thereby improving work efficiency and the accuracy of data analysis.

[0021] First, the first upstream source is accessed, which may be a database, file storage system or other data source, to obtain the record of historical test tube sample arrival. Then, according to the predetermined first task type, the screening conditions are set. These conditions may include the type of sample, time range, sample status, etc. For example, if the downstream is a cleaning and disinfection link, the task type of this link may include cleaning tasks, disinfection tasks, and cleaning and disinfection tasks. Next, a screening operation is performed to extract the records that meet the conditions to form the first historical test tube sample arrival record. In addition, in order to ensure the accuracy and efficiency of the screening, it may be necessary to adopt an efficient data processing algorithm and a reasonable storage strategy. Finally, the screened records can be used for further analysis, report generation or decision support. By efficiently screening out the test tube sample arrival records related to a specific task from a large amount of historical data, not only the pertinence of data processing is improved, but also the accuracy and practicality of data analysis are enhanced.

[0022] A first historical test tube sample arrival time sequence is generated based on a plurality of sample arrival time zones with identifications of task quantities in the first historical test tube sample arrival record.

[0023] Specifically, based on the specific historical test tube sample arrival records, a sequence about the sample arrival timing is generated. Specifically, for those samples with multiple task quantity identifications, the arrival time zones are analyzed to reveal the time pattern or trend of sample arrival, thus providing a basis for subsequent task allocation, resource planning or data analysis.

[0024] First, samples with multiple task quantity identifiers are identified from the first historical test tube sample arrival records. These identifiers may represent different task types or priorities. Then, these samples are assigned to different time zones according to their arrival time. These time zones can be fixed time periods, such as every hour or every day, or dynamic, divided according to the density of sample arrival. Next, the number of samples arriving in each time zone is counted to generate a time series data about the number of sample arrivals. In addition, these time series data can be further analyzed, such as displaying the peaks and troughs of sample arrival through visualization, or predicting future sample arrival trends through statistical methods. Finally, the generated first historical test tube sample arrival time series can be used to optimize workflows, predict resource requirements, or perform other types of data analysis. By extracting useful information about sample arrival time series from complex historical data, it not only helps to understand the time pattern of sample arrival, but also supports more effective resource allocation and work planning.

[0025] A predetermined timing feature collection strategy is obtained, and based on the predetermined timing feature collection strategy, feature collection is performed on the first historical test tube sample arrival timing to obtain a first timing feature set.

[0026] Specifically, a predetermined time series feature collection strategy is used to process the first historical test tube sample arrival time series to obtain a feature set. The "predetermined time series feature collection strategy" here may include a series of algorithms or rules for extracting key features from time series data, such as peaks, valleys, trends, periodicity, etc. In this way, valuable information can be mined from the sample arrival time series.

[0027] First, it is necessary to obtain a predetermined timing feature collection strategy. These strategies may be pre-set by experts or automatically learned through machine learning algorithms. Then, based on these strategies, the first historical test tube sample arrival time series is analyzed. This may involve calculating the statistical characteristics of the time series data, such as the mean, standard deviation, or more complex features, such as autocorrelation function, Fourier transform, etc. Next, the analyzed features are sorted and stored to form the first time series feature set. In addition, the feature set may need to be verified and optimized to ensure that the extracted features can accurately reflect the essential characteristics of the sample arrival time series. Finally, the first time series feature set obtained can be used for various downstream applications, such as predicting future sample arrivals, optimizing resource allocation, or improving workflows. By effectively extracting key features from the first historical test tube sample arrival time series to form a useful feature set, it not only helps to deeply understand the dynamic changes of sample arrival, but also supports more accurate data analysis and decision-making.

[0028] The task quantity prediction model is activated to perform prediction analysis on the first historical test tube sample arrival time series and the first time series feature set to obtain a first target task quantity prediction value of the first task type in the target time zone.

[0029] Specifically, the task quantity prediction model is used to analyze the first historical test tube sample arrival time series and the first time series feature set to predict the number of tasks of a specific task type in the target time zone. The "task quantity prediction model" here may be a machine learning model trained based on historical data, which can learn the pattern and trend of sample arrival from time series data and make future predictions based on it. This prediction can be used to better plan resources, arrange workflows, or make other related decisions.

[0030] First, the pre-trained task quantity prediction model needs to be activated. Then, the first historical test tube sample arrival timing and the first timing feature set are used as input and sent to the prediction model for training or prediction analysis. Next, the model will output the predicted value of the task quantity of the first task type in the target time zone based on these input data. In addition, the prediction results may need to be evaluated and verified to ensure the accuracy and reliability of the prediction. Finally, the predicted values ​​obtained can be used for various practical applications, such as making work plans, optimizing resource allocation, or conducting risk assessment. By analyzing the historical test tube sample arrival timing and timing feature set using the task quantity prediction model, predicting the number of tasks of a specific task type in a specific time zone in the future, it will not only help improve the accuracy and efficiency of resource planning, but also support more scientific decision making.

[0031] The first test tube inventory of the first upstream source is compared with a first predetermined inventory threshold to obtain a first inventory deviation.

[0032] Specifically, a task quantity prediction model is used to predict the number of tasks of a specific task type in the target time zone using the first historical test tube sample arrival time series and the first time series feature set. First, a trained task quantity prediction model is loaded and activated. This model may be based on a machine learning algorithm that can identify and predict patterns from time series data. Then the first historical test tube sample arrival time series and the first time series feature set are used as input data and fed into the prediction model. The model will analyze this data and predict the number of tasks in the target time zone based on historical patterns. In addition, the prediction results may be verified to ensure their accuracy and reliability. Finally, the predicted number of tasks can be used to guide actual operations, such as adjusting human resources, optimizing inventory management, or improving service processes. By predicting the number of tasks in a specific time zone in the future based on historical data, it helps related fields to carry out resource planning and process optimization more effectively.

[0033] A first sampling priority index of the first upstream source is obtained according to the first target task quantity forecast value and the first inventory deviation.

[0034] Specifically, the first sampling priority index of the first upstream source is calculated based on the first target task quantity forecast value and the first inventory deviation. The "sampling priority index" here is a measurement indicator used to indicate the priority of sampling in the first upstream source. By combining the forecast value of the task quantity and the inventory deviation, the solution aims to help users or systems arrange sampling work more reasonably, thereby optimizing inventory management and improving work efficiency. First, it is necessary to obtain the first target task quantity forecast value, which is obtained by the previous task quantity forecast model. Then it is also necessary to obtain the first inventory deviation, which may be the difference between the current inventory and the ideal inventory. Next, the system uses these two values ​​as input and uses a predetermined algorithm or formula to calculate the first sampling priority index of the first upstream source. This calculation may involve more complex mathematical models, such as weighted average, exponential smoothing, etc. In addition, it may be necessary to verify and adjust the calculation results to ensure the accuracy and practicality of the sampling priority index. Finally, the obtained first sampling priority index can be used to guide the actual sampling work, such as deciding which samples need to be processed first, or adjusting the sampling plan to optimize the inventory level. By calculating the sampling priority index of the first upstream source based on the predicted value of the task quantity and inventory deviation, it helps to arrange the sampling work more scientifically, optimize inventory management, and improve work efficiency.

[0035] Priority control of the test tube sampling of the first task type is performed based on the first sampling priority index.

[0036] Specifically, the first sampling priority index is used to control the priority of the test tube sampling of the first task type. By optimizing the test tube sampling process, key tasks can be prioritized, thereby improving overall work efficiency and service quality. This is especially important for scenarios that require efficient processing of a large number of samples, such as medical testing or scientific research experiments.

[0037] First, the calculated first sampling priority index needs to be obtained. This index reflects the importance and urgency of different samples or tasks. Then, the test tube sampling of the first task type is prioritized according to this index. Test tubes with high rankings will be processed first, which may mean that they will be tested, analyzed or other related operations will be performed faster. Next, this priority ranking is applied to the actual sampling process to guide staff or automated equipment to operate. In addition, the sampling priority can be dynamically adjusted based on real-time feedback and data updates to ensure the flexibility and adaptability of the process. Finally, this priority control based on the sampling priority index can ensure that key tasks are handled in a timely manner, thereby optimizing the overall workflow and resource allocation. Priority control is performed on the test tube sampling of the first task type based on the sampling priority index. This not only helps to improve the response speed and processing efficiency of key tasks, but also ensures the rational allocation and utilization of resources.

[0038] Further, it includes: the predetermined time series feature collection strategy includes a time domain feature collection strategy, a frequency domain feature collection strategy and a time-frequency fusion domain feature collection strategy, including: based on the time domain feature collection strategy, a first time domain feature set of the first historical test tube sample arrival time series is collected; based on the frequency domain feature collection strategy, a first frequency domain feature set of the first historical test tube sample arrival spectrum after Fourier transformation of the first historical test tube sample arrival time series is collected; based on the time-frequency fusion domain feature collection strategy, a first target feature value of the first target component of the first historical test tube sample arrival time series after modal decomposition is collected, and the first target feature value is used as the first time-frequency fusion domain feature; the first time domain feature set, the first frequency domain feature set and the first time-frequency fusion domain feature constitute the first time series feature set.

[0039] Specifically, a predetermined time series feature collection strategy is used to extract key features from the first historical test tube sample arrival time series to form the first time series feature set. This feature set contains features collected from three different angles: time domain, frequency domain, and time-frequency fusion domain, and can fully reflect the characteristics of the sample arrival time series. Such a feature set is very important for subsequent data analysis and model prediction, and can provide richer and deeper information.

[0040] First, based on the time domain feature collection strategy, the arrival time series of the first historical test tube samples is analyzed to extract the first time domain feature set. These features may include the time point, duration, peak value, valley value, etc. of sample arrival. Then, using the frequency domain feature collection strategy, the time series data is processed by Fourier transform to obtain the arrival spectrum of the first historical test tube samples, and the first frequency domain feature set is extracted from it. These features may involve the frequency components and energy distribution of sample arrival. Next, the time-frequency fusion domain feature collection strategy is adopted to process the time series data by modal decomposition (such as Hilbert-Huang transform) to obtain the first target eigenvalue of the first target component as the first time-frequency fusion domain feature. These features can reflect the properties of time series data in the time-frequency joint domain. Finally, these three feature sets - the first time domain feature set, the first frequency domain feature set, and the first time-frequency fusion domain feature - together constitute the first time series feature set, which provides a comprehensive information basis for subsequent data analysis and model prediction. By extracting rich features from the arrival time series of the first historical test tube samples, a comprehensive time series feature set is formed. This not only helps to deeply understand the dynamic changes of sample arrival, but also supports more accurate data analysis and decision-making.

[0041] Further, it includes: obtaining a first modal decomposition result of the first historical test tube sample arrival timing, the first modal decomposition result including multiple modal components; performing weight evaluation on a first modal component among the multiple modal components to obtain a first component weight; and determining the first target component by comparing the first component weight.

[0042] Specifically, the modal decomposition results are obtained from the first historical test tube sample arrival time series, and a target component is determined from it. Through modal decomposition, the time series data is decomposed into multiple modal components, each of which represents a different feature or pattern in the data. By evaluating the weights of these modal components, the most important component is found as the target component for more in-depth analysis or prediction.

[0043] First, the first historical test tube sample arrival time series needs to be modally decomposed. This is usually done through algorithms such as the Hilbert-Huang Transform (HHT), which is able to decompose complex time series data into multiple intrinsic mode functions (IMFs). Then, the first of these modal components will be weighted. The weight evaluation may involve calculating the contribution or importance of each component to the original data, which may be done by comparing the energy, frequency content, or other statistical properties of the components. Next, these weights will be compared to determine which modal component is the most important. This most important modal component will be determined as the first target component. Finally, the first target component can be used for further analysis or prediction because it may contain the most critical information in the time series data.

[0044] By effectively identifying the most important modal component from the first historical test tube sample arrival time series as the target component, it helps to focus the analysis and attention on the most critical part of the data, thereby improving the accuracy and efficiency of data analysis.

[0045] Further, it includes: using the first time series feature set as input information of the first predictor in the task quantity prediction model to obtain output information, wherein the output information includes a first prediction value; performing regression fitting prediction on the first historical test tube sample arrival timing by the second predictor in the task quantity prediction model to obtain a second prediction value under the target time zone; and taking the average of the first prediction value and the second prediction value as the first target task quantity prediction value.

[0046] Specifically, the first time series feature set is used to predict the number of tasks of the first task type in the target time zone through the task quantity prediction model. Two different predictors are used, one based on the time series feature set and the other based on the arrival time series of historical test tube samples. By taking the average of these two prediction values, the scheme aims to improve the accuracy and reliability of the prediction.

[0047] First, the first time series feature set needs to be fed as input information into the first predictor in the task quantity prediction model. This predictor may be based on a machine learning algorithm, such as a random forest, support vector machine, or neural network, which can learn and predict the number of tasks from the feature set. Then, the first predictor will output a first prediction value, which is a prediction result based on the time series feature set. Next, the second predictor in the task quantity prediction model is used to perform regression fitting prediction on the first historical test tube sample arrival time series. This predictor may be a time series analysis model, such as ARIMA or LSTM, which can learn and predict future trends from time series data. The second predictor will output a second prediction value, which is a prediction result based on the historical test tube sample arrival time series. Finally, the average of the first prediction value and the second prediction value is taken as the first target task quantity prediction value. This method can combine the advantages of the two predictors to improve the stability and accuracy of the prediction.

[0048] Two different forecasters are used to predict the number of tasks in the target time zone. This comprehensive forecasting method can improve the accuracy and reliability of the forecast, thereby helping related fields to more effectively carry out resource planning and process optimization.

[0049] Further, it includes: obtaining the first historical test tube sample arrival record segment of the first task type of the first upstream source, and obtaining the first historical target time zone of the first historical test tube sample arrival record segment; performing supervised learning and verification on a data set composed of the first historical segment timing feature set based on the first historical test tube sample arrival record segment and the first historical task quantity corresponding to the first historical target time zone to obtain the first predictor.

[0050] Specifically, the historical test tube sample arrival record segments of the first task type of the first upstream source and the historical target time zones of these record segments are used to train and obtain a first predictor for task quantity prediction. A model that can predict the task quantity based on a time series feature set is established through a supervised learning method.

[0051] First, the first historical test tube sample arrival record fragments of the first task type are obtained from the first upstream source. These record fragments may contain sample arrival data within a specific time period. Then determine the first historical target time zone corresponding to these record fragments, that is, the time interval where the number of tasks needs to be predicted. Next, the first historical fragment time series feature set based on these record fragments and the first historical task number corresponding to the first historical target time zone are combined into a data set. This data set will be used in a supervised learning process, with the feature set as input and the number of tasks as the output label. This data set will be used to train the first predictor, which may be a machine learning model such as a regression tree, a neural network, etc. During the training process, the model also needs to be tested to evaluate its predictive performance and generalization ability. Finally, after training and testing, the first predictor will be obtained, which can be used to predict the number of tasks based on the time series feature set.

[0052] By utilizing historical test tube sample arrival record segments and the corresponding historical target time zones, a first predictor for task quantity prediction is obtained through supervised learning training.

[0053] Further, it includes: introducing a predetermined priority evaluation function to perform a priority evaluation analysis on the first target task quantity forecast value and the first inventory deviation to obtain the first sampling priority index; wherein the expression of the predetermined priority evaluation function is as follows: ; Characterizing the First Upstream Source the first sampling priority index of the first task type, Characterizes the predicted value of the quantity of the first target task, Characterizes the impact coefficient of the number of tasks, Characterizing the first inventory deviation, Characterizes the impact coefficient of inventory deviation.

[0054] Specifically, a predetermined priority evaluation function is introduced to perform a priority evaluation analysis on the first target task quantity forecast value and the first inventory deviation to obtain the first sampling priority index; wherein the expression of the predetermined priority evaluation function is as follows: ; Characterizing the First Upstream Source the first sampling priority index of the first task type, Characterizes the predicted value of the quantity of the first target task, Characterizes the impact coefficient of the number of tasks, Characterizing the first inventory deviation, Characterizes the inventory deviation impact coefficient. The first target task quantity forecast value and the first inventory deviation are both proportional to their sampling priority index. The first target task quantity forecast value directly affects the downstream operation quality, and the first inventory deviation directly affects the downstream operation efficiency.

[0055] Further, it includes: obtaining a second sampling priority index of the first task type of the second upstream source; sorting the first upstream source and the second upstream source according to the first sampling priority index and the second sampling priority index to obtain a first sampling priority sequence of the first task type; and controlling the test tube sampling of the first task type according to the first sampling priority sequence.

[0056] Specifically, the second sampling priority index of the first task type of the second upstream source is obtained, and combined with the first sampling priority index of the first upstream source, the test tube sampling of the two upstream sources is prioritized to obtain the first sampling priority sequence of the first task type. This sequence will be used to control the priority of the test tube sampling to optimize the sampling process and improve work efficiency.

[0057] First, the second sampling priority index of the first task type of the second upstream source is obtained. This index reflects the priority of sampling this task type in the second upstream source. Then, the first sampling priority index of the first upstream source and the second sampling priority index of the second upstream source are combined to prioritize the test tube sampling of the two upstream sources. The basis for sorting may be the relative size of the two indexes, or a combination according to a specific priority rule. Next, the first sampling priority sequence of the first task type will be obtained based on this sorting. This sequence indicates the priority order of sampling in different upstream sources. Finally, the test tube sampling control of the first task type will be performed according to this sampling priority sequence. This means that the upstream source with a higher priority will be sampled first, or its sample will be processed faster.

[0058] Based on the different sampling priority indexes of the two upstream sources, a sampling priority sequence is generated to control the priority of test tube sampling of the first task type. This helps to optimize the sampling process, improve work efficiency, and ensure that key tasks can be handled in a timely manner.

[0059] Further, it includes: acquiring a second sampling priority sequence of a second task type; performing test tube sampling control of the second task type according to the second sampling priority sequence; wherein the first task type and the second task type are parallel sampling controls.

[0060] Specifically, the second sampling priority sequence of the second task type is obtained, and the test tube sampling control of the second task type is performed according to this sequence. At the same time, the test tube sampling control of the first task type is also involved, and the two task types will be sampled and controlled in parallel. This design is intended to improve the efficiency and flexibility of the sampling process, especially when multiple task types need to be processed simultaneously.

[0061] First, obtain the second sampling priority sequence of the second task type. This sequence may be based on a method similar to the first task type, that is, by calculating the sampling priority index and sorting it. Then the test tube sampling control of the second task type will be performed according to the second sampling priority sequence. This means that tasks with higher priority will be sampled first, or their samples will be processed faster. At the same time, the system also needs to perform test tube sampling control of the first task type in parallel, which may involve the first sampling priority sequence mentioned earlier. In this process, sampling of the two task types can be carried out at the same time, but each follows its own priority order. This parallel control mechanism ensures that both task types can be processed effectively while improving the overall sampling efficiency.

[0062] Parallel sampling control is achieved by acquiring and applying the sampling priority sequences of two task types simultaneously. This helps to improve the efficiency and responsiveness of the sampling process, especially in complex scenarios that require multiple task types to be processed simultaneously.

[0063] In summary, the upstream and downstream aligned test tube sampling timing optimization method provided by this application has the following technical effects:

[0064] The first historical test tube sample arrival record is obtained by obtaining the historical test tube sample arrival record of the first upstream source, and the historical test tube sample arrival record is screened based on the first task type to obtain the first historical test tube sample arrival record; the first historical test tube sample arrival timing sequence is generated based on multiple sample arrival time zones with task quantity identification in the first historical test tube sample arrival record; a predetermined timing feature collection strategy is obtained, and the first historical test tube sample arrival timing sequence is collected based on the predetermined timing feature collection strategy to obtain a first timing feature set; the task quantity prediction model is activated to perform prediction analysis on the first historical test tube sample arrival timing sequence and the first timing feature set to obtain a first target task quantity prediction value of the first task type under the target time zone; the first test tube inventory of the first upstream source is compared with the first predetermined inventory threshold to obtain a first inventory deviation; the first sampling priority index of the first upstream source is obtained according to the first target task quantity prediction value and the first inventory deviation; and priority control of test tube sampling of the first task type is performed based on the first sampling priority index. By generating a priority sequence for downstream test tube sampling based on the predicted value of the number of tasks, the technical goal of optimizing the sample processing process is achieved, and the technical effect of providing a scientific and reasonable resource allocation reference for downstream operations and thereby improving the overall test tube flow operation efficiency is achieved.

[0065] Embodiment 2, based on the same inventive concept as the upstream and downstream aligned test tube sampling timing optimization method in the aforementioned embodiment, the present application also provides an upstream and downstream aligned test tube sampling timing optimization system, please refer to the attached Figure 2 , the upstream and downstream aligned test tube sampling timing optimization system comprises:

[0066] The historical record acquisition module 11 is used to acquire historical test tube sample arrival records of a first upstream source, and filter the historical test tube sample arrival records based on a first task type to obtain a first historical test tube sample arrival record.

[0067] The timing generation module 12 is used to generate a first historical test tube sample arrival timing based on a plurality of sample arrival time zones with task quantity identifiers in the first historical test tube sample arrival record.

[0068] The feature collection module 13 is used to obtain a predetermined timing feature collection strategy, and collect features of the first historical test tube sample arrival timing based on the predetermined timing feature collection strategy to obtain a first timing feature set.

[0069] The task quantity prediction module 14 is used to activate the task quantity prediction model to perform prediction analysis on the first historical test tube sample arrival timing and the first timing feature set to obtain a first target task quantity prediction value of the first task type under the target time zone.

[0070] The inventory analysis module 15 is used to compare the first test tube inventory of the first upstream source with a first predetermined inventory threshold to obtain a first inventory deviation.

[0071] The priority analysis module 16 is used to obtain a first sampling priority index of the first upstream source according to the first target task quantity forecast value and the first inventory deviation.

[0072] A control execution module 17 is used to perform priority control of the test tube sampling of the first task type based on the first sampling priority index.

[0073] Further, the feature collection module 13 in the upstream and downstream aligned test tube sampling timing optimization system is also used for: the predetermined timing feature collection strategy includes a time domain feature collection strategy, a frequency domain feature collection strategy and a time-frequency fusion domain feature collection strategy, including: based on the time domain feature collection strategy, collecting and obtaining the first time domain feature set of the first historical test tube sample arrival timing; based on the frequency domain feature collection strategy, collecting and obtaining the first frequency domain feature set of the first historical test tube sample arrival spectrum after Fourier transformation of the first historical test tube sample arrival timing; based on the time-frequency fusion domain feature collection strategy, collecting and obtaining the first target feature value of the first target component of the first historical test tube sample arrival timing after modal decomposition, and using the first target feature value as the first time-frequency fusion domain feature; the first time domain feature set, the first frequency domain feature set and the first time-frequency fusion domain feature constitute the first timing feature set.

[0074] Furthermore, the feature collection module 13 in the upstream and downstream aligned test tube sampling timing optimization system is also used to: obtain a first modal decomposition result of the first historical test tube sample arrival timing, the first modal decomposition result including multiple modal components; perform weight evaluation on a first modal component among the multiple modal components to obtain a first component weight; and determine the first target component by comparing the first component weight.

[0075] Furthermore, the task quantity prediction module 14 in the upstream and downstream aligned test tube sampling timing optimization system is also used to: use the first timing feature set as input information of the first predictor in the task quantity prediction model to obtain output information, and the output information includes a first prediction value; perform regression fitting prediction on the first historical test tube sample arrival timing through the second predictor in the task quantity prediction model to obtain a second prediction value under the target time zone; and take the average of the first prediction value and the second prediction value as the first target task quantity prediction value.

[0076] Furthermore, the task quantity prediction module 14 in the upstream and downstream aligned test tube sampling timing optimization system is also used to: obtain the first historical test tube sample arrival record segment of the first task type of the first upstream source, and obtain the first historical target time zone of the first historical test tube sample arrival record segment; perform supervised learning and verification on a data set composed of the first historical segment timing feature set based on the first historical test tube sample arrival record segment and the first historical task quantity corresponding to the first historical target time zone, to obtain the first predictor.

[0077] Furthermore, the priority analysis module 16 in the upstream and downstream aligned test tube sampling timing optimization system is further used to: introduce a predetermined priority evaluation function to perform a priority evaluation analysis on the first target task quantity forecast value and the first inventory deviation to obtain the first sampling priority index; wherein the expression of the predetermined priority evaluation function is as follows: ; Characterizing the First Upstream Source the first sampling priority index of the first task type, Characterizes the predicted value of the quantity of the first target task, Characterizes the impact coefficient of the number of tasks, Characterizing the first inventory deviation, Characterizes the impact coefficient of inventory deviation.

[0078] Furthermore, the control execution module 17 in the upstream and downstream aligned test tube sampling timing optimization system is also used to: obtain a second sampling priority index of the first task type of the second upstream source; sort the test tube sampling priorities of the first upstream source and the second upstream source according to the first sampling priority index and the second sampling priority index to obtain a first sampling priority sequence of the first task type; and perform test tube sampling control of the first task type according to the first sampling priority sequence.

[0079] Furthermore, the upstream and downstream aligned test tube sampling timing optimization system also includes a parallel control execution module, wherein the parallel control execution module is used to: obtain a second sampling priority sequence of a second task type; perform test tube sampling control of the second task type according to the second sampling priority sequence; wherein the first task type and the second task type are parallel sampling controls.

[0080] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. Figure 1 The upstream and downstream aligned test tube sampling timing optimization method and specific examples in Example 1 are also applicable to the upstream and downstream aligned test tube sampling timing optimization system of this embodiment. Through the above detailed description of the upstream and downstream aligned test tube sampling timing optimization method, those skilled in the art can clearly understand the upstream and downstream aligned test tube sampling timing optimization system of this embodiment, so for the sake of brevity of the specification, it will not be described in detail here. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0081] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0082] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims

1. A method for optimizing the timing of test tube sampling with upstream and downstream alignment, characterized in that: include: Acquire a historical test tube sample arrival record of a first upstream source, and filter the historical test tube sample arrival record based on a first task type to obtain a first historical test tube sample arrival record; Generate a first historical test tube sample arrival time sequence based on a plurality of sample arrival time zones with identifications of task quantities in the first historical test tube sample arrival record; Acquire a predetermined time series feature collection strategy, and collect features of the first historical test tube sample arrival time series based on the predetermined time series feature collection strategy to obtain a first time series feature set; Activate the task quantity prediction model to perform prediction analysis on the first historical test tube sample arrival time series and the first time series feature set to obtain a first target task quantity prediction value of the first task type in the target time zone; Comparing the first test tube inventory of the first upstream source with a first predetermined inventory threshold to obtain a first inventory deviation; Obtaining a first sampling priority index of the first upstream source according to the first target task quantity forecast value and the first inventory deviation; Performing priority control of test tube sampling of the first task type based on the first sampling priority index; Wherein, the upstream and downstream aligned test tube sampling timing optimization method also includes: Introducing a predetermined priority evaluation function to perform a priority evaluation analysis on the first target task quantity forecast value and the first inventory deviation to obtain the first sampling priority index; Wherein, the expression of the predetermined priority evaluation function is as follows: ； Characterizing the First Upstream Source the first sampling priority index of the first task type, Characterizes the predicted value of the quantity of the first target task, Characterizes the impact coefficient of the number of tasks, Characterizing the first inventory deviation, Characterize the impact coefficient of inventory deviation; The predetermined time series feature collection strategy includes a time domain feature collection strategy, a frequency domain feature collection strategy and a time-frequency fusion domain feature collection strategy, including: Based on the time domain feature collection strategy, a first time domain feature set of the first historical test tube sample arrival time sequence is obtained; Based on the frequency domain feature collection strategy, a first frequency domain feature set of the first historical test tube sample arrival frequency spectrum of the first historical test tube sample arrival time sequence after Fourier transformation is collected; Based on the time-frequency fusion domain feature collection strategy, a first target eigenvalue of a first target component of the first historical test tube sample arrival time series after modal decomposition is collected, and the first target eigenvalue is used as a first time-frequency fusion domain feature; The first time domain feature set, the first frequency domain feature set and the first time-frequency fusion domain feature set constitute the first time series feature set; Wherein, the upstream and downstream aligned test tube sampling timing optimization method also includes: Acquire a first modal decomposition result of the first historical test tube sample arrival time series, wherein the first modal decomposition result includes multiple modal components; Performing a weight evaluation on a first modal component among the multiple modal components to obtain a first component weight; Determine the first target component by comparing the first component weight; Wherein, the upstream and downstream aligned test tube sampling timing optimization method also includes: Using the first time series feature set as input information of a first predictor in the task quantity prediction model to obtain output information, wherein the output information includes a first prediction value; Performing regression fitting prediction on the first historical test tube sample arrival time series by using the second predictor in the task quantity prediction model to obtain a second prediction value in the target time zone; Taking the average of the first predicted value and the second predicted value as the first target task quantity predicted value; Wherein, the upstream and downstream aligned test tube sampling timing optimization method also includes: Acquire a first historical test tube sample arrival record segment of the first task type of the first upstream source, and acquire a first historical target time zone of the first historical test tube sample arrival record segment; Supervised learning and verification are performed on a data set formed by a first historical segment time series feature set based on the first historical test tube sample arrival record segment and a first historical task quantity corresponding to the first historical target time zone to obtain the first predictor.

2. The method for optimizing the timing of test tube sampling with upstream and downstream alignment according to claim 1, characterized in that: Also includes: Obtaining a second sampling priority index of the first task type of a second upstream source; According to the first sampling priority index and the second sampling priority index, the first upstream source and the second upstream source are prioritized for test tube sampling to obtain a first sampling priority sequence of the first task type; The test tube sampling control of the first task type is performed according to the first sampling priority sequence.

3. The method for optimizing the timing of test tube sampling with upstream and downstream alignment according to claim 2, characterized in that: Also includes: obtaining a second sampling priority sequence for a second task type; Perform test tube sampling control of the second task type according to the second sampling priority sequence; The first task type and the second task type are parallel sampling controls.

4. The upstream and downstream aligned test tube sampling timing optimization system is characterized by: The steps for implementing the method for optimizing the timing of test tube sampling with upstream and downstream alignment as described in any one of claims 1 to 3, wherein the system for optimizing the timing of test tube sampling with upstream and downstream alignment comprises: A historical record acquisition module, the historical record acquisition module is used to acquire a historical test tube sample arrival record of a first upstream source, and filter the historical test tube sample arrival record based on a first task type to obtain a first historical test tube sample arrival record; A timing generation module, the timing generation module is used to generate a first historical test tube sample arrival timing based on a plurality of sample arrival time zones with task quantity identifiers in the first historical test tube sample arrival record; A feature collection module, the feature collection module is used to obtain a predetermined time series feature collection strategy, and based on the predetermined time series feature collection strategy, perform feature collection on the first historical test tube sample arrival time series to obtain a first time series feature set; A task quantity prediction module, the task quantity prediction module is used to activate the task quantity prediction model to perform prediction analysis on the first historical test tube sample arrival time series and the first time series feature set to obtain a first target task quantity prediction value of the first task type in a target time zone; an inventory analysis module, the inventory analysis module being configured to compare the first test tube inventory of the first upstream source with a first predetermined inventory threshold to obtain a first inventory deviation; A priority analysis module, the priority analysis module is used to obtain a first sampling priority index of the first upstream source according to the first target task quantity forecast value and the first inventory deviation; A control execution module is used to perform priority control of the test tube sampling of the first task type based on the first sampling priority index.

Images