An organization cell storage information management system, method and storage medium

Abstract

The application discloses a kind of tissue cell storage information management system, method and storage medium, it is related to cell storage technical field, the system includes: storage condition setting module, for collecting cell storage label and setting stable storage condition;Temperature fluctuation analysis module, for continuously monitoring temperature fluctuation and comparing with stable condition, generate fluctuation data;Cell recovery rate prediction module is used to predict recovery rate based on initial cryopreservation data and temperature fluctuation data;Recovery rate update module is used to trigger sampling audit reminder or update storage label according to predicted recovery rate.The application solves the technical problem that existing tissue cell storage is difficult to monitor the influence of temperature fluctuation on cell activity in real time, leading to cell activity evaluation lag, cannot timely optimize storage condition, reaches through real-time monitoring temperature fluctuation and accurately predicts cell recovery rate, realizes the dynamic evaluation of cell activity and the real-time optimization of storage condition, improves the technical effect of cell storage quality.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of cell storage, in particular to a tissue cell storage information management system, method and storage medium. BACKGROUND

[0002] With the continuous development of cell storage technology, liquid nitrogen tanks have become the main method for long-term preservation of tissue cells and are widely used in the fields of stem cells, immune cells, tissue engineering, etc. As a commonly used cell storage device, liquid nitrogen tanks can provide an extremely low temperature environment, effectively slow down cell metabolism and extend the active preservation time of cells. However, the storage of cells in liquid nitrogen tanks is not completely stable, and factors such as temperature fluctuations, cryopreservation liquid formulations, and cell types can affect cell activity and recovery rate. The existing technology mainly relies on periodic sampling detection to evaluate cell activity, which is not only time-consuming and laborious, but also cannot monitor the cell state in real time, making it difficult to find potential problems in a timely manner. SUMMARY

[0003] The present application provides a tissue cell storage information management system, method and storage medium to solve the technical problem that the existing tissue cell storage cannot monitor the influence of temperature fluctuations on cell activity in real time, leading to delayed cell activity evaluation and inability to timely optimize storage conditions.

[0004] In a first aspect, the present application provides a tissue cell storage information management system, which comprises: a storage condition setting module for collecting the storage label of tissue cells stored in a liquid nitrogen tank and the set stable storage condition; a temperature fluctuation analysis module for deploying a temperature sensing network in the liquid nitrogen tank, continuously collecting real-time temperature time series data of the storage position corresponding to the tissue cells, and comparing with the stable storage condition to generate temperature fluctuation data; a cell recovery rate prediction module for analyzing the storage label, if the current fluctuation is the first temperature fluctuation after cryopreservation, obtaining the initial cryopreservation related data of the tissue cells at the first cryopreservation, combining the temperature fluctuation data to perform cell recovery rate prediction under the current temperature fluctuation, and generating a predicted recovery rate; a recovery rate updating module for triggering a sampling audit reminder information if the predicted recovery rate is less than a target recovery rate threshold, and performing recovery rate write update on the storage label with the predicted recovery rate if the predicted recovery rate is greater than or equal to the target recovery rate threshold.

[0005] In a second aspect of the present application, a tissue cell storage information management method is provided, which comprises: collecting a storage label of tissue cells stored in a liquid nitrogen tank and a set stable storage condition; deploying a temperature sensing network in the liquid nitrogen tank to continuously collect real-time temperature time series data of a storage position corresponding to the tissue cells and compare the data with the stable storage condition to generate temperature fluctuation data; analyzing the storage label, if the current fluctuation is the first temperature fluctuation after cryopreservation, obtaining initial cryopreservation related data of the tissue cells at the first cryopreservation, combining the temperature fluctuation data to perform cell recovery rate prediction under the current temperature fluctuation, and generating a predicted recovery rate; if the predicted recovery rate is less than a target recovery rate threshold, triggering a sampling audit reminder information, and if the predicted recovery rate is greater than or equal to the target recovery rate threshold, writing and updating the recovery rate of the storage label with the predicted recovery rate.

[0006] In a third aspect of the present application, a computer readable storage medium is provided, and the storage medium stores a computer program, which is executed by a processor to implement the method of the first aspect.

[0007] The one or more technical solutions provided in the present application have at least the following technical effects or advantages:

[0008] The tissue cell storage information management system, method and storage medium provided in the present application relate to the technical field of cell storage, and through the integration of storage condition setting, temperature fluctuation analysis, recovery rate prediction and updating mechanism, the temperature fluctuation in the liquid nitrogen tank is monitored in real time, and the cell recovery rate is predicted in combination with the initial cryopreservation data, so that the storage label is dynamically adjusted, the temperature stability and recovery rate in the cell storage process are ensured, and the technical problem that the existing tissue cell storage cannot monitor the influence of temperature fluctuation on cell activity in real time, resulting in lag of cell activity evaluation and inability to timely optimize the storage condition is solved, the technical effect that the cell activity is dynamically evaluated and the storage condition is optimized in real time by monitoring the temperature fluctuation and accurately predicting the cell recovery rate is achieved, and the cell storage quality is improved. BRIEF DESCRIPTION OF DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0010] Figure 1 A structure schematic diagram of a tissue cell storage information management system provided in the embodiments of the present application is shown in the figure.

[0011] Figure 2This is a schematic flowchart of a tissue cell storage information management method provided in an embodiment of this application.

[0012] Explanation of reference numerals in the attached diagram: Storage condition setting module 10, temperature fluctuation analysis module 20, cell recovery rate prediction module 30, recovery rate update module 40. Detailed Implementation

[0013] This application provides a tissue cell storage information management system, method, and storage medium to solve the technical problem that existing tissue cell storage systems are unable to monitor the impact of temperature fluctuations on cell viability in real time, resulting in delayed cell viability assessment and the inability to optimize storage conditions in a timely manner.

[0014] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0015] It should be noted that the terms "first," "second," etc., in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules not explicitly listed or inherent to such processes, methods, products, or devices.

[0016] Example 1, as Figure 1 As shown, this application provides a tissue cell storage information management system, which includes:

[0017] The storage condition setting module 10 is used to collect the storage tags of tissue cells stored in the liquid nitrogen tank, as well as the set stable storage conditions.

[0018] Furthermore, in the storage condition setting module 10, the storage tag stores the initial cryopreservation-related data of the tissue cells during the first cryopreservation and the predicted recovery rate updated each time after cryopreservation; wherein, the initial cryopreservation-related data includes cell viability, cell concentration, cell purity characterization information before cryopreservation, as well as the programmed cooling curve and cryopreservation solution formulation during cryopreservation.

[0019] It should be understood that the main function of the storage condition setting module 10 of this application is to collect and manage the storage information of tissue cells in the liquid nitrogen tank, and to set the stable storage conditions for the cells. Specifically, this module not only records the basic information of the cell sample through storage tags, including the initial cryopreservation-related data of the sample during its first cryopreservation, but also the predicted recovery rate data updated each time during the cryopreservation process, so as to ensure that the cryopreservation and recovery status of each cell sample can be accurately tracked during the cell storage process.

[0020] Specifically, the storage tag collected by the storage condition setting module 10 stores initial cryopreservation-related data for the first cryopreservation of tissue cells, as well as the predicted recovery rate updated each time after cryopreservation. Here, the storage tag refers to an electronic or physical tag used to record and identify tissue cell storage information, capable of storing a large amount of cell-related data.

[0021] Initial cryopreservation data is a crucial component of the storage label, including pre-cryopreservation cell viability, cell concentration, cell purity characterization information, as well as programmed cooling profiles and cryopreservation solution formulations. Pre-cryopreservation cell viability refers to the physiological activity state of cells before cryopreservation, typically assessed using specific biochemical methods such as cell metabolic activity assays and cell proliferation capacity assays. This data reflects the health status of cells before cryopreservation, providing an important benchmark for subsequent cell viability prediction. Cell concentration refers to the number of cells per unit volume, reflecting the density of the cell sample. During cryopreservation, excessively high or low cell concentrations can affect cell survival and recovery rates. Therefore, accurately recording cell concentration is essential for subsequent cell processing and management.

[0022] Cell purity characterization information refers to the ratio of target cells to non-target cells in a cell sample, as well as the cell purity level. Recording cell purity characterization information ensures the quality of cell samples and improves the success rate of subsequent applications. Programmed cooling profiles refer to the process of cooling cells according to a pre-set temperature change program during cryopreservation. Setting this profile effectively reduces the formation of intracellular ice crystals and minimizes cell damage during cryopreservation. Different cell types and experimental requirements may require different programmed cooling profiles; therefore, recording this data in the storage label helps in the subsequent optimization and management of the cell cryopreservation process. Cryopreservation solution formulations refer to the liquid formulations used to protect cells from damage at low temperatures. Cryopreservation solutions typically contain various components, such as cryoprotectants and nutrients, which reduce intracellular ice crystal formation and maintain cell structure and function. Different cell types and cryopreservation conditions may require different cryopreservation solution formulations; therefore, recording the cryopreservation solution formulation helps ensure the safety and effectiveness of cell cryopreservation.

[0023] Furthermore, the predicted recovery rate in the storage tag is dynamically updated based on various data during cell cryopreservation, including temperature fluctuations and cryoprotectant effectiveness. Whenever new temperature fluctuation data emerges or cryopreservation conditions change, the system automatically updates the predicted recovery rate. This predicted value provides crucial decision-making support for the subsequent recovery process, ensuring that the cell recovery rate meets the expected requirements.

[0024] The temperature fluctuation analysis module 20 is used to deploy a temperature sensing network in the liquid nitrogen tank, continuously collect real-time temperature time-series data of the storage location corresponding to the tissue cells, compare it with the stable storage conditions, and generate temperature fluctuation data.

[0025] Furthermore, when generating temperature fluctuation data, the temperature fluctuation analysis module 20 is also used to perform the following steps:

[0026] P21: Compare the real-time temperature time series data with the stable storage conditions to obtain the number of temperature fluctuations, the average fluctuation amplitude, and the cumulative fluctuation time within the phase transition temperature range in one monitoring cycle; wherein, the phase transition temperature range is the sensitive temperature range in which ice crystals form and recrystallize in the intracellular and extracellular fluids.

[0027] Optionally, the main function of the temperature fluctuation analysis module 20 in this application is to continuously monitor the temperature of the tissue cell storage location inside the liquid nitrogen tank by deploying a temperature sensor network, and compare the real-time collected temperature data with preset stable storage conditions to generate temperature fluctuation data. This module is designed to ensure that cell samples are always in a stable and suitable temperature environment during cryopreservation, avoiding damage to cell structures caused by temperature fluctuations, especially ice crystal damage caused by excessively rapid or unstable temperatures.

[0028] Specifically, when generating temperature fluctuation data, the temperature fluctuation analysis module performs the following steps. First, real-time temperature time-series data is collected, representing temperature changes at different points in time within the liquid nitrogen tank. The acquisition of this temperature time-series data relies on a network of temperature sensors deployed within the liquid nitrogen tank, which continuously monitor temperature changes in the area where the cell samples are located. Next, this real-time temperature data is compared with preset stable storage conditions. Stable storage conditions refer to the ideal temperature range that should be maintained during cell storage; this range is typically configured in the storage condition setting module 10 to ensure that the temperature environment for the cells remains as stable as possible during cryopreservation.

[0029] After comparing real-time temperature data with stable storage conditions, the temperature fluctuation analysis module 20 calculates several important temperature fluctuation parameters to further analyze the impact of temperature changes on cell storage and resuscitation. For example, it first calculates the number of temperature fluctuations within a monitoring period. This parameter reflects the frequency of temperature changes within the monitoring period. Excessively high temperature fluctuation frequency usually indicates temperature instability, which may cause some damage to cells, especially as small ice crystals inside the cells repeatedly melt and recrystallize due to temperature fluctuations, potentially leading to cell damage.

[0030] Next, the average amplitude of temperature fluctuations is calculated. The amplitude describes the intensity or magnitude of the temperature change. Larger amplitude fluctuations indicate drastic temperature changes, potentially exacerbating ice crystal formation and cell membrane damage. Smaller, more stable amplitude fluctuations result in less cell damage and a higher success rate of recovery.

[0031] Secondly, the cumulative fluctuation time within the phase transition temperature range is calculated. The phase transition temperature range refers to the temperature range during cryopreservation where the intracellular and extracellular fluids undergo ice crystal formation and recrystallization. This temperature range has a significant impact on cell survival. Within this temperature range, intracellular water undergoes ice crystal formation and dissolution. The recrystallization process may cause intracellular ice crystals to continuously grow, puncture the cell membrane, and lead to cell rupture or death. The cumulative fluctuation time is the duration of temperature fluctuations within this temperature range. If the cell storage environment remains within the phase transition temperature range for an extended period, cell damage will significantly increase, and the recovery rate will significantly decrease.

[0032] Through the steps described above, the temperature fluctuation analysis module 20 generates detailed temperature fluctuation data, including not only the number and magnitude of temperature fluctuations but also the cumulative fluctuation time within the key phase transition temperature range. This data provides crucial input for the subsequent cell recovery rate prediction module 30 and recovery rate update module 40, enabling the system to predict and manage cell activity based on accurate temperature fluctuation data.

[0033] The cell recovery rate prediction module 30 is used to parse the stored tag. If the current fluctuation is the first temperature fluctuation after cryopreservation, it obtains the initial cryopreservation-related data of the tissue cells at the time of the first cryopreservation, and performs cell recovery rate prediction under the current temperature fluctuation in combination with the temperature fluctuation data to generate a predicted recovery rate.

[0034] Furthermore, if the current fluctuation is the first temperature fluctuation after cryopreservation, the cell recovery rate prediction module 30 is also used to perform the following steps:

[0035] P31: Collect the cell types of the tissue cells, train a model of the relationship between cell activity and cryopreservation parameters and cryopreservation time under a stable state, and obtain a cell activity relationship model; P32: Collect the cryopreservation duration from the first cryopreservation to the current real-time time, combine it with the initial cryopreservation related data, and input it into the cell activity relationship model to establish predicted cell activity parameters; P33: Combine the predicted cell activity parameters, the temperature fluctuation data, and the cryopreservation solution formulation in the initial cryopreservation related data to perform recovery rate identification under the current temperature fluctuation, and generate the predicted recovery rate.

[0036] Specifically, the main function of the cell recovery rate prediction module 30 in this application is to accurately predict the cell recovery rate based on real-time collected data and assess the cell recovery potential under the current storage conditions. Especially when the first temperature fluctuation occurs after cryopreservation, the cell recovery rate prediction module 30 will parse the storage tag, extract initial cryopreservation-related data, and combine it with temperature fluctuation data to perform a recovery rate prediction.

[0037] When the system detects that the current temperature fluctuation is the first temperature fluctuation since cryopreservation, the cell recovery rate prediction module 30 first needs to parse the storage tag to obtain the cell type of the tissue cells and the initial cryopreservation-related data. This data includes cell viability, cell concentration, cell purity characterization information before cryopreservation, as well as the programmed cooling curve and cryopreservation solution formulation during cryopreservation. Cell type is one of the key factors affecting cell recovery rate; different cell types exhibit different characteristics during cryopreservation and recovery. The initial cryopreservation-related data provides the basic parameters for subsequent recovery rate prediction.

[0038] Subsequently, cell types were collected from tissue cells, and a model was trained to model the relationship between cell viability and cryopreservation parameters and cryopreservation time under stable conditions. Even at extremely low temperatures of -196°C, cellular metabolism does not completely cease; certain physicochemical processes may still occur extremely slowly, leading to cell damage and a gradual decrease in cell viability with prolonged storage time. Therefore, although cells are frozen, their viability and metabolism may still gradually decrease with prolonged storage time. To establish this relationship, the system needs to collect sufficient data to describe the changes in cell viability with cryopreservation time and train a cell viability relationship model based on this data. This model can help the system assess the natural decline in cell viability over time under stable temperature conditions.

[0039] After training the cell viability relationship model, the cryopreservation duration from the first cryopreservation to the current time is collected. Cryopreservation duration is an important parameter for predicting cell viability, reflecting the length of time cells are in a frozen state. Increased cryopreservation time is often accompanied by a decrease in cell viability and survival rate. Therefore, by combining the cryopreservation duration with the initial cryopreservation data and inputting it into the trained cell viability relationship model, a predicted cell viability parameter can be calculated. This parameter will reflect the impact of the current cryopreservation duration on cell viability, providing basic data for predicting the recovery rate.

[0040] Finally, combining predicted cell viability parameters, temperature fluctuation data, and cryopreservation solution formulations from initial cryopreservation data, a predicted recovery rate is generated by identifying the recovery rate under the current temperature fluctuations. This process comprehensively considers changes in cell viability in a stable state, the additional impact of temperature fluctuations on cell viability, and the protective effect of the cryopreservation solution formulation. A pre-trained recovery rate identification model is used to assess cell performance during the recovery process under current temperature fluctuation conditions. The recovery rate identification model can be trained using algorithms, including regression analysis, machine learning models, or statistical methods, to identify key factors related to the recovery rate and generate a predicted recovery rate. This recovery rate reflects the probability of successful cell recovery under current storage conditions and temperature fluctuations, providing a scientific basis for subsequent recovery operations and helping operators determine the feasibility of cell recovery.

[0041] Furthermore, when generating the predicted recovery rate, the cell recovery rate prediction module 30 is also used to perform the following steps:

[0042] P33-1: Based on the cryopreservation solution formulation and the cell type of the tissue cells, collect cell sampling and detection data under different temperature fluctuations. The cell sampling and detection data includes predicted activity before sampling, temperature fluctuation, and recovery rate label obtained from sampling and detection. P33-2: Train the temperature fluctuation-recovery rate recognition model using the cell sampling and detection data. P33-3: Input the predicted cell activity parameters and the temperature fluctuation data into the temperature fluctuation-recovery rate recognition model to generate the predicted recovery rate.

[0043] In one possible embodiment of this application, the cell recovery rate prediction module 30 further performs refined operation steps in the process of generating the predicted recovery rate to ensure that the prediction results can accurately reflect the changes in cell activity under actual storage conditions.

[0044] When the cell recovery rate prediction module 30 analyzes that the current temperature fluctuation is the first temperature fluctuation after cryopreservation, it will begin collecting cell sampling and detection data under different temperature fluctuations based on the cell type and cryopreservation solution formulation information. At this time, the system will acquire multidimensional data related to the cell sample, including: predicted activity before sampling, i.e., the expected survival and activity level of the cells before the temperature fluctuation occurs; temperature fluctuation data, which reflects the temperature changes during storage; and recovery rate labels obtained from sampling and detection, which represent the survival rate of cells after recovery under specific temperature fluctuations. Through the collection of this data, the system can construct the relationship between temperature fluctuations and cell recovery, providing accurate empirical data for subsequent model training and recovery rate prediction.

[0045] Next, based on the collected cell sampling and detection data, the training of the temperature fluctuation-resuscitation rate identification model was initiated. During the training process, the model used machine learning algorithms to deeply learn the intrinsic relationship between temperature fluctuation data and cell resuscitation rate. It comprehensively considered multiple dimensions, including the number of temperature fluctuations, average amplitude, and the cumulative time of temperature fluctuations within the sensitive temperature range where ice crystals form and recrystallize in intracellular and extracellular fluids. Simultaneously, it combined the predicted activity values ​​before sampling with the actual resuscitation rate label to optimize the model parameters, enabling it to accurately grasp the specific impact of temperature fluctuations on cell resuscitation rate.

[0046] After model training is complete, the previously calculated predicted cell viability parameters, along with real-time monitored temperature fluctuation data, are input into the pre-trained temperature fluctuation-resuscitation rate recognition model. The model, based on its internal logic, comprehensively analyzes this input data and, through complex calculations, ultimately outputs the predicted resuscitation rate. This predicted resuscitation rate not only integrates the cell viability prediction results derived from the cell viability relationship model but also fully considers the potential impact of actual temperature fluctuations on cell viability. Therefore, it provides a highly valuable scientific basis for subsequent storage condition assessments, cell usage decisions, and storage scheme optimization. This helps staff accurately monitor the cell storage status, predict cell viability trends in advance, and thus take appropriate measures to ensure cell storage quality and availability.

[0047] Furthermore, if the current fluctuation is not the first temperature fluctuation after cryopreservation, the cell recovery rate prediction module 30 is also used to perform the following steps:

[0048] P34: If the current fluctuation is not the first temperature fluctuation after cryopreservation, parse the storage tag and obtain the previous predicted recovery rate after the last temperature fluctuation; P35: Call the recovery rate-activity conversion template, perform cell activity prediction in a fluctuation-free state with the previous predicted recovery rate, and generate the previous activity prediction result; P36: Combine the previous activity prediction result with the temperature fluctuation data and input it into the temperature fluctuation-recovery rate recognition model to generate the predicted recovery rate.

[0049] Optionally, if the current fluctuation is not the first temperature fluctuation after cryopreservation, the cell recovery rate prediction module 30 will continue to dynamically predict the cell recovery rate based on the stored previous data and the recovery rate prediction model to ensure that the prediction results can accurately reflect the changes in cell activity after multiple temperature fluctuations.

[0050] First, the stored tags are parsed to retrieve the previously predicted recovery rate after the last temperature fluctuation. This data, derived from previous temperature fluctuation analysis and recovery rate predictions, provides an important benchmark for current predictions. Using this benchmark, the system can understand the cell activity status after the last temperature fluctuation, thus providing a starting point for subsequent predictions.

[0051] Next, the recovery rate-activity conversion template is invoked. This template is a pre-defined model based on cell biology principles and historical data, capable of converting the recovery rate into a predicted value of cell viability. Using the recovery rate-activity conversion template, based on the previously obtained predicted recovery rate, cell viability prediction under stable conditions is performed, generating the previous activity prediction result. This result reflects the expected changes in cell viability without new temperature fluctuations. It takes into account the natural decline in cell viability during storage; even under stable storage conditions, cell viability gradually decreases over time.

[0052] Then, the previous activity prediction result is combined with the currently monitored temperature fluctuation data. This combined data includes the cell activity status after the previous temperature fluctuation and the specific details of the current temperature fluctuation. This combined data is input into the previously trained temperature fluctuation-resilience rate recognition model. By analyzing this comprehensive data, the model ultimately generates the current predicted resilience rate. This predicted resilience rate integrates the changes in cell activity after multiple temperature fluctuations, providing a more accurate reference for subsequent storage condition assessments and cell usage decisions.

[0053] The recovery rate update module 40 is used to trigger a sampling audit reminder if the predicted recovery rate is less than the target recovery rate threshold, and to update the storage tag with the recovery rate by writing the predicted recovery rate if the predicted recovery rate is greater than or equal to the target recovery rate threshold.

[0054] Furthermore, after triggering the sampling audit alert information, the recovery rate update module 40 is also used to perform the following steps:

[0055] P41: Enter the measured results of the sampled tissue cells after resuscitation, including the measured activity and function test results; P42: Based on the measured results, generate disposal recommendations for all samples in the same batch of the tissue cells using pre-constructed sample disposal rules, wherein the disposal recommendations include continued storage, priority use, or batch destruction.

[0056] Optionally, the recovery rate update module 40 of this application functions to take corresponding measures to ensure the quality and safety of the cell storage process based on the comparison between the predicted recovery rate and the target recovery rate threshold. Specifically, if the predicted recovery rate is less than the target recovery rate threshold, the system will trigger a sampling audit reminder, prompting operators to conduct a more detailed inspection; while if the predicted recovery rate is greater than or equal to the target recovery rate threshold, the system will update the storage tag, writing the current predicted recovery rate to ensure the accuracy and timeliness of the information.

[0057] Furthermore, in order to further optimize management, the recovery rate update module 40 will also perform a series of steps to handle sample disposal after triggering the sampling audit reminder.

[0058] The first step is to input the measured activity and function results of the sampled cells after resuscitation (step P41). This process directly verifies the post-resuscitation state of the cells, ensuring that the accuracy of the predicted resuscitation rate and the actual effect of cell resuscitation are confirmed through measured data. Post-resuscitation activity is usually assessed using methods such as flow cytometry and MTT assays, while functional testing can confirm whether the cells possess the expected biological functions, such as cell proliferation and differentiation capabilities, through specific cell function testing methods. By collecting these measured results, the system can provide a practical basis for subsequent sample processing, ensuring the quality of cell sample resuscitation.

[0059] Next, based on the entered test results, the system generates disposal recommendations for all samples from the same batch of tissue cells using pre-built sample disposal rules. These rules are established from extensive historical data and experimental results. By analyzing the performance of cells after resuscitation, the system can automatically determine the quality of each batch of cell samples and provide corresponding disposal recommendations. The disposal recommendations typically include three options:

[0060] If the measured results show that the cell viability and functional status are good, and the predicted recovery rate is lower than the threshold due to accidental temperature fluctuations or other correctable factors, the recovery rate update module 40 will suggest continuing to store the batch of cell samples. If the measured results show that although the cell viability and functional status are lower than ideal, they still have some application value, it can be suggested to prioritize the use of this batch of cell samples. This suggestion is suitable for applications where cell viability requirements are not extremely high; prioritizing the use of these cells can avoid wasting resources. If the measured results show that the cell viability and functional status are extremely poor and cannot meet any application requirements, it can be suggested to destroy all samples in the same batch in bulk to avoid potential risks to experiments or treatments from unqualified samples, while saving storage space and resources.

[0061] Through the above steps, the recovery rate update module 40 can not only trigger sampling audit reminders in a timely manner based on the predicted recovery rate, but also generate scientific and reasonable disposal suggestions based on the actual measurement results after the audit, thereby ensuring the efficiency and safety of cell storage management.

[0062] Furthermore, after the recovery rate update module 40 inputs the measured results of the recovered sample, including the measured activity and functional test results, it is also used to perform the following steps:

[0063] P43: Analyze the prediction error based on the measured results and construct new error samples; P44: Train and optimize the temperature fluctuation-recovery rate identification model using the new error samples.

[0064] It should be understood that after the recovery rate update module 40 inputs the measured activity and function test results of the sampled samples after recovery, it can further improve the prediction accuracy and improve the recovery rate prediction process by analyzing the prediction error, constructing error samples and optimizing the model.

[0065] First, the prediction error is analyzed based on the entered measured results to assess the accuracy of the current recovery rate prediction model, particularly the deviation between the predicted results and the measured data in actual operation. Specifically, the difference between the measured activity and function test results and the previously predicted recovery rate is calculated through a detailed comparison. This difference reflects the deviation between the predicted value and the actual observed value, i.e., the prediction error. In-depth analysis of these errors can identify potential problems with the model's prediction accuracy. For example, if the predicted recovery rate is higher than the measured result in most cases, it may mean that the model overestimates the cell's sensitivity to temperature fluctuations; conversely, if the predicted value is generally lower than the measured value, it may indicate that the model underestimates the cell's protective mechanisms in some aspects. The system analyzes the sources of error and generates new error samples. These new error samples reflect the shortcomings of the current model in practical applications and represent new data samples for further optimization of the existing model.

[0066] Subsequently, these newly added error samples were used to train and optimize the temperature fluctuation-recovery rate recognition model. Specifically, the newly added error samples were incorporated into the existing training dataset, and the model relearned and adjusted its internal parameters based on this, with the core objective of minimizing prediction errors. For example, during this optimization training process, the model focused on the following key factors: Regarding temperature fluctuation characteristics, the model reassessed the appropriateness of its sensitivity settings to temperature fluctuation frequency based on the fluctuation frequency information recorded in the newly added error samples; simultaneously, it finely adjusted the weights of fluctuations of different amplitudes based on the average fluctuation amplitude data in the newly added error samples; and, combined with the cumulative fluctuation time in the newly added error samples, it reconsidered the intensity of attention paid to temperature fluctuations within the phase transition temperature range. Regarding cell activity and function detection results, the model optimized its prediction logic for cell activity based on the measured activity values ​​in the newly added error samples, making the prediction results more realistic; for the function detection results, the evaluation method for cell functional status was adjusted accordingly to more accurately reflect the true state of the cells.

[0067] Through these steps, the recovery rate update module 40 can not only effectively identify and analyze errors in the recovery rate prediction, but also improve the system's understanding of the complex relationship between temperature fluctuations and recovery rate through continuous model optimization, thereby providing a more reliable and accurate basis for subsequent assessments of storage conditions and cell usage decisions.

[0068] In summary, the embodiments of this application have at least the following technical effects:

[0069] This application ensures cells are stored in a stable temperature environment by real-time monitoring of temperature fluctuations during liquid nitrogen storage, reducing the negative impact of temperature fluctuations on cell recovery rates. By combining initial cryopreservation data and temperature fluctuation data, it accurately predicts cell recovery rates, assesses the likelihood of cell recovery in advance, and optimizes cell recovery management. By automatically updating storage labels or triggering sampling audit reminders, it ensures the transparency and traceability of the cell storage process, improving the accuracy of storage quality control. Through intelligent management decisions based on recovery rate prediction, it ensures the efficient utilization and safety of cell samples.

[0070] This technology achieves the goal of improving cell storage quality by dynamically assessing cell viability and optimizing storage conditions in real time through real-time monitoring of temperature fluctuations and accurate prediction of cell recovery rate.

[0071] Example 2, based on the same inventive concept as the tissue cell storage information management method in the foregoing examples, such as... Figure 2 As shown, this application provides a method for managing tissue cell storage information. The system and method embodiments in this application are based on the same inventive concept. The method includes:

[0072] The process involves collecting storage tags for tissue cells stored in a liquid nitrogen tank, along with established stable storage conditions. A temperature sensing network is deployed within the liquid nitrogen tank to continuously collect real-time temperature data at the storage location of the tissue cells, comparing this data with the stable storage conditions to generate temperature fluctuation data. The storage tags are then analyzed. If the current fluctuation is the first temperature fluctuation after cryopreservation, the initial cryopreservation-related data for the tissue cells at the time of the first cryopreservation is obtained. Combined with the temperature fluctuation data, a cell recovery rate prediction is performed under the current temperature fluctuation to generate a predicted recovery rate. If the predicted recovery rate is less than a target recovery rate threshold, a sampling audit alert is triggered. If the predicted recovery rate is greater than or equal to the target recovery rate threshold, the storage tags are updated with the predicted recovery rate.

[0073] Furthermore, the storage tag stores the initial cryopreservation-related data of the tissue cells during their first cryopreservation and the predicted recovery rate updated each time after cryopreservation; wherein, the initial cryopreservation-related data includes cell viability, cell concentration, cell purity characterization information before cryopreservation, as well as the programmed cooling curve and cryopreservation solution formulation during cryopreservation.

[0074] Furthermore, temperature fluctuation data is generated, including:

[0075] The real-time temperature time series data is compared with the stable storage conditions to obtain the number of temperature fluctuations, the average fluctuation amplitude, and the cumulative fluctuation time within the phase transition temperature range in one monitoring cycle; wherein, the phase transition temperature range is the sensitive temperature range in which ice crystals form and recrystallize in the intracellular and extracellular fluids.

[0076] Furthermore, the storage tag is parsed to obtain the initial cryopreservation-related data of the tissue cells during the first cryopreservation. Combined with the temperature fluctuation data, a cell recovery rate prediction is performed under the current temperature fluctuation to generate a predicted recovery rate, including:

[0077] The cell types of the tissue cells are collected, and a model is trained to represent the relationship between cell viability and cryopreservation parameters and cryopreservation time under a stable condition, resulting in a cell viability relationship model. The cryopreservation duration from the first cryopreservation to the current real-time time is collected and combined with the initial cryopreservation-related data, then input into the cell viability relationship model to establish predicted cell viability parameters. The predicted cell viability parameters, the temperature fluctuation data, and the cryopreservation solution formulation in the initial cryopreservation-related data are combined to perform recovery rate identification under the current temperature fluctuation, generating the predicted recovery rate.

[0078] Furthermore, by combining the predicted cell viability parameters, the temperature fluctuation data, and the cryopreservation solution formulation from the initial cryopreservation-related data, the recovery rate under the current temperature fluctuation is identified, and the predicted recovery rate is generated, including:

[0079] Based on the cryopreservation solution formulation and the cell type of the tissue cells, cell sampling and detection data under different temperature fluctuations are collected. The cell sampling and detection data includes predicted activity before sampling, temperature fluctuation, and recovery rate label obtained from sampling and detection. The temperature fluctuation-recovery rate recognition model is trained using the cell sampling and detection data. The predicted cell activity parameters and the temperature fluctuation data are input into the temperature fluctuation-recovery rate recognition model to generate the predicted recovery rate.

[0080] Furthermore, after triggering the sampling audit alert message, it also includes:

[0081] The system records the measured results of the resuscitation of the sampled tissue, including the measured activity and function test results. Based on the measured results, the system generates disposal recommendations for all samples from the same batch of tissue cells using pre-constructed sample disposal rules. The disposal recommendations include continued storage, priority use, or batch destruction.

[0082] Furthermore, after entering the measured results of the resuscitation of the sampled samples, including the measured activity and function test results, it also includes:

[0083] Based on the measured results, the prediction error is analyzed, and new error samples are constructed. The temperature fluctuation-recovery rate identification model is then trained and optimized using the new error samples.

[0084] Furthermore, if the current fluctuation is not the first temperature fluctuation after cryopreservation, the storage tag is parsed to obtain the previous predicted recovery rate after the last temperature fluctuation; the recovery rate-activity conversion template is called to perform cell activity prediction under the fluctuation-free state with the previous predicted recovery rate to generate the previous activity prediction result; the previous activity prediction result is combined with the temperature fluctuation data and input into the temperature fluctuation-recovery rate recognition model to generate the predicted recovery rate.

[0085] In Example 3, based on the same inventive concept as the tissue cell storage information management method in the foregoing embodiments, this application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the method as described in Example 1.

[0086] Through the foregoing detailed description of a tissue cell storage information management method, those skilled in the art can clearly understand the tissue cell storage information management system, method, and storage medium in this embodiment. Therefore, for the sake of brevity, further details are omitted here. As for the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant parts can be found in the method section.

[0087] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily 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 this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0088] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this specification. Additionally, the processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are possible or may be advantageous.

[0089] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

[0090] This specification and accompanying drawings are merely illustrative examples of this application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from its scope. Therefore, if such modifications and modifications fall within the scope of this application and its equivalents, this application intends to include such modifications and modifications.

Claims

1. A tissue cell storage information management system characterized by, The application comprises the following steps: A storage condition setting module is used to collect the storage label of the tissue cells stored in the liquid nitrogen tank and the set stable storage condition; A temperature fluctuation analysis module is used to deploy a temperature sensing network in the liquid nitrogen tank, continuously collect real-time temperature time series data of the storage position of the tissue cells, and compare the data with the stable storage condition to generate temperature fluctuation data; A cell recovery rate prediction module is used to analyze the storage label, obtain the initial freezing-related data of the tissue cells at the first freezing if the current fluctuation is the first temperature fluctuation after freezing, and perform cell recovery rate prediction under the current temperature fluctuation by combining the temperature fluctuation data to generate a predicted recovery rate; A recovery rate updating module is used to trigger a sampling audit reminder if the predicted recovery rate is less than a target recovery rate threshold, and update the storage label with the predicted recovery rate if the predicted recovery rate is greater than or equal to the target recovery rate threshold; In the storage condition setting module, the storage label stores the initial freezing-related data of the tissue cells at the first freezing and the predicted recovery rate updated after freezing each time; The initial freezing-related data includes cell activity, cell concentration, and cell purity characterization information before freezing, and a programmed cooling curve and a freezing solution formula during freezing; If the current fluctuation is the first temperature fluctuation after freezing, the cell recovery rate prediction module is further used to: Collect the cell type of the tissue cells, train a relationship model of cell activity, freezing parameters, and freezing time in a non-fluctuation state to obtain a cell activity relationship model; Collect the freezing duration from the first freezing to the current real-time time, input the freezing duration combined with the initial freezing-related data into the cell activity relationship model to establish a predicted cell activity parameter; Combine the predicted cell activity parameter, the temperature fluctuation data, and the freezing solution formula in the initial freezing-related data to perform recovery rate identification under the current temperature fluctuation to generate the predicted recovery rate; When generating the predicted recovery rate, the cell recovery rate prediction module is further used to: Collect cell sampling detection data under different temperature fluctuations according to the freezing solution formula and the cell type of the tissue cells, the cell sampling detection data including a predicted activity before sampling, temperature fluctuation, and a recovery rate label obtained by sampling detection; Train a temperature fluctuation-recovery rate identification model with the cell sampling detection data; Input the predicted cell activity parameter and the temperature fluctuation data into the temperature fluctuation-recovery rate identification model to generate the predicted recovery rate; After triggering the sampling audit reminder, the recovery rate updating module is further used to: Enter the measured results of the recovery after sampling, including measured activity and functional detection results; Generate a disposal suggestion for all samples of the same batch of tissue cells by using a pre-constructed sample disposal rule according to the measured results, wherein the disposal suggestion includes continued storage, priority use, or batch destruction; After entering the measured results of the recovery after sampling, including measured activity and functional detection results, the recovery rate updating module is further used to: According to the measured result analysis prediction error, build new error sample; With the new error sample, the temperature fluctuation-recovery rate identification model is trained and optimized.

2. The tissue cell storage information management system of claim 1, wherein, When generating the temperature fluctuation data, the temperature fluctuation analysis module is further configured to: Compare the real-time temperature time series data with the stable storage condition to obtain the number of temperature fluctuations, the average fluctuation amplitude, and the cumulative fluctuation time in the phase change temperature interval within a monitoring period; Wherein, the phase change temperature interval is the sensitive temperature range of ice crystal formation and recrystallization of intracellular and extracellular fluid.

3. The tissue cell storage information management system of claim 1, wherein, If the current fluctuation is not the first temperature fluctuation after freezing, the cell recovery rate prediction module is further configured to: Parse the storage label to obtain the last predicted recovery rate after the last temperature fluctuation; Call the recovery rate-activity conversion template to execute cell activity prediction in the non-fluctuation state with the last predicted recovery rate to generate the last activity prediction result; Combine the last activity prediction result with the temperature fluctuation data and input them into the temperature fluctuation-recovery rate identification model to generate the predicted recovery rate.

4. A method for managing information on storage of tissue cells, characterized by, The method comprises: Collect the storage label of the tissue cells stored in the liquid nitrogen tank and the set stable storage condition; Deploy a temperature sensing network in the liquid nitrogen tank to continuously collect real-time temperature time series data of the storage location corresponding to the tissue cells and compare them with the stable storage condition to generate temperature fluctuation data; Parse the storage label, and if the current fluctuation is the first temperature fluctuation after freezing, obtain the initial freezing-related data of the tissue cells at the first freezing, combine the temperature fluctuation data to execute cell recovery rate prediction under the current temperature fluctuation, and generate a predicted recovery rate; If the predicted recovery rate is less than the target recovery rate threshold, trigger a sampling audit reminder information, and if the predicted recovery rate is greater than or equal to the target recovery rate threshold, update the recovery rate of the storage label with the predicted recovery rate; The storage label stores the initial freezing-related data of the tissue cells at the first freezing and the predicted recovery rate updated after freezing; wherein the initial freezing-related data includes cell activity, cell concentration, and cell purity characterization information before freezing, as well as the programmed cooling curve and the freezing solution formula at freezing; Parse the storage label to obtain the initial freezing-related data of the tissue cells at the first freezing, combine the temperature fluctuation data to execute cell recovery rate prediction under the current temperature fluctuation, and generate a predicted recovery rate, comprising: Collect the cell type of the tissue cells, train a relationship model of cell activity and freezing parameters and freezing time in the non-fluctuation state to obtain a cell activity relationship model; collect the freezing duration from the first freezing to the current real-time time, combine it with the initial freezing-related data, and input them into the cell activity relationship model to establish a predicted cell activity parameter; combine the predicted cell activity parameter, the temperature fluctuation data, and the freezing solution formula in the initial freezing-related data to execute recovery rate identification under the current temperature fluctuation to generate the predicted recovery rate; In combination with the predicted cell activity parameter, the temperature fluctuation data and the cryopreservation solution formula in the initial cryopreservation related data, the recovery rate under the current temperature fluctuation is identified, the predicted recovery rate is generated, and the steps include: According to the cryopreservation solution formula and the cell type of the tissue cells, cell sampling detection data under different temperature fluctuations is collected, the cell sampling detection data includes the predicted activity before sampling, the temperature fluctuation and the recovery rate label obtained by sampling detection; The temperature fluctuation-recovery rate identification model is trained by using the cell sampling detection data; The predicted cell activity parameter and the temperature fluctuation data are input into the temperature fluctuation-recovery rate identification model, and the predicted recovery rate is generated; After triggering the sampling audit reminder information, the steps further include: The measured results of the real activity and the functional detection results contained in the recovered sampling sample are input; according to the measured results, the pre-constructed sample handling rules are used to generate the handling suggestions for all samples of the same batch of tissue cells, wherein the handling suggestions include continuing to store, preferentially using or destroying in batches; After inputting the measured results of the real activity and the functional detection results contained in the recovered sampling sample, the steps further include: According to the measured results, the prediction error is analyzed, and a new error sample is constructed; The temperature fluctuation-recovery rate identification model is trained and optimized by using the new error sample.

5. A computer readable storage medium, characterized in that, The storage medium stores a computer program, and the computer program is executed by the processor to realize the steps of the system of any one of claims 1 to 3.

Images