Artificial intelligence umbilical cord stem cell quality detection data analysis method and system

Abstract

The invention provides an artificial intelligence umbilical cord stem cell quality detection data analysis method and system, and relates to the technical field of cell quality detection.The method comprises the steps that umbilical cord stem cell dyeing monitoring parameters are obtained and compared with umbilical cord stem cell dyeing expected parameters, and umbilical cord stem cell dyeing parameter deviation vectors are obtained; a first umbilical cord stem cell activity detection sample set is collected, centralized value evaluation is executed, and an umbilical cord stem cell activity value confidence interval is obtained; when the umbilical cord stem cell activity detection value does not belong to the umbilical cord stem cell activity value confidence interval, carrying out abnormal quality detection data identification on the umbilical cord stem cell activity detection value; and when the umbilical cord stem cell activity detection value belongs to the umbilical cord stem cell activity value confidence interval, performing normal quality detection data identification on the umbilical cord stem cell activity detection value. The technical problem of poor stability of umbilical cord stem cell quality detection results in the prior art is solved.

Description

Technical Field

[0001] This invention relates to the field of cell quality testing, and more particularly to an artificial intelligence-based method and system for analyzing umbilical cord stem cell quality testing data. Background Technology

[0002] Umbilical cord stem cells have significant application value in regenerative medicine, and their quality directly determines clinical efficacy and safety. However, current quality control methods, to address the variability in the testing process, typically require multiple repeated tests on the same sample, using the mean or median as the final quality report value. While this method aims to suppress random errors through averaging, its drawback is that outliers in the test results significantly affect the representative value. In other words, traditional methods struggle to identify some abnormal data in the test results, leading to poor stability of quality test results. Summary of the Invention

[0003] This invention addresses the technical problem of poor stability in umbilical cord stem cell quality testing results in existing technologies by providing an artificial intelligence-based method and system for analyzing umbilical cord stem cell quality testing data.

[0004] The technical solution of the present invention to solve the above-mentioned technical problems is as follows:

[0005] In a first aspect, the present invention provides an artificial intelligence-based method for analyzing umbilical cord stem cell quality detection data, comprising:

[0006] The staining monitoring parameters of umbilical cord stem cells in the umbilical cord stem cell activity test sample are obtained and compared with the expected staining parameters of umbilical cord stem cells to obtain the umbilical cord stem cell staining parameter deviation vector.

[0007] Constrained by the umbilical cord stem cell staining parameter deviation vector, the umbilical cord stem cell staining expected parameters, and the umbilical cord stem cell collection conditions, a first set of umbilical cord stem cell activity detection samples is collected, a central value assessment is performed, and the confidence interval of umbilical cord stem cell activity value is obtained, wherein the umbilical cord stem cell activity value is characterized by the proportion of live cells.

[0008] When the umbilical cord stem cell activity test value does not fall within the confidence interval of the umbilical cord stem cell activity value, the umbilical cord stem cell activity test value is marked as abnormal quality test data;

[0009] When the umbilical cord stem cell activity test value falls within the confidence interval of the umbilical cord stem cell activity value, the umbilical cord stem cell activity test value is marked as normal quality test data.

[0010] Secondly, the present invention provides an artificial intelligence-based umbilical cord stem cell quality detection data analysis system, comprising:

[0011] The deviation comparison module is used to obtain the umbilical cord stem cell staining monitoring parameters of the umbilical cord stem cell activity detection sample, compare them with the expected umbilical cord stem cell staining parameters, and obtain the umbilical cord stem cell staining parameter deviation vector.

[0012] The confidence analysis module is used to collect a first set of umbilical cord stem cell activity detection samples, perform central value assessment, and obtain the confidence interval of umbilical cord stem cell activity value, constrained by the umbilical cord stem cell staining parameter deviation vector, the umbilical cord stem cell staining expected parameters, and the umbilical cord stem cell collection conditions. The umbilical cord stem cell activity value is characterized by the proportion of live cells.

[0013] An anomaly identification module is used to identify abnormal quality test data for umbilical cord stem cell activity test values ​​when the umbilical cord stem cell activity test value does not fall within the confidence interval of the umbilical cord stem cell activity value.

[0014] The normal identification module is used to identify the umbilical cord stem cell activity detection value as normal quality detection data when the umbilical cord stem cell activity detection value falls within the confidence interval of the umbilical cord stem cell activity value.

[0015] The beneficial effects of this invention are:

[0016] Compared to existing technologies, this application first obtains the umbilical cord stem cell staining monitoring parameters of the umbilical cord stem cell activity test samples, compares them with the expected umbilical cord stem cell staining parameters, and obtains the umbilical cord stem cell staining parameter deviation vector. This accurately identifies the key combination of staining control attributes, shifting the attribution of activity decline from cell culture results to staining process parameters. It provides correlation-filtered, dimensionality-reduced data (retaining only key attribute deviations) for subsequent activity confidence interval calculation, quantifying the deviation's mapping of biological effects and providing a core data foundation for the standardization of stem cell industrial production. Secondly, constrained by the umbilical cord stem cell staining parameter deviation vector, the expected umbilical cord stem cell staining parameters, and the umbilical cord stem cell collection conditions, a first set of umbilical cord stem cell activity test samples is collected. Central tendency assessment is performed to obtain the umbilical cord stem cell activity value confidence interval. This yields an umbilical cord stem cell activity value confidence interval that can dynamically reflect the reasonable range of activity fluctuations under the current technological level, providing a comparison standard for subsequent abnormal data identification. Secondly, when the umbilical cord stem cell activity test value is outside the confidence interval, the value is marked as abnormal quality data. This accurately identifies the abnormal data, allowing managers to make targeted selections and ensuring the stability of the quality test data. Finally, when the umbilical cord stem cell activity test value is within the confidence interval, it is marked as normal quality data. This clear numerical range determination replaces traditional empirical judgment, achieving standardization and automation of umbilical cord stem cell quality assessment. This reduces human subjective error and provides a clear classification basis for subsequent quality traceability and data analysis.

[0017] Through the above technical solution, this application employs a recursive k-item combination screening (k increasing from 1 to N) and cluster analysis of collection conditions to accurately identify key influencing factor combinations from multi-dimensional staining control attributes. Constrained by the umbilical cord stem cell staining parameter deviation vector, the expected umbilical cord stem cell staining parameters, and the umbilical cord stem cell collection conditions, homogeneous samples are collected, and central tendency processing is performed to obtain the confidence interval for umbilical cord stem cell activity values. Based on this, abnormal or normal quality detection data are identified for evaluating umbilical cord stem cell activity. This effectively identifies abnormal quality detection data for umbilical cord stem cell activity values, improving the reliability and stability of the quality detection results. Attached Figure Description

[0018] Figure 1 A flowchart illustrating an artificial intelligence-based method for analyzing umbilical cord stem cell quality detection data provided by this invention;

[0019] Figure 2In the artificial intelligence-based umbilical cord stem cell quality detection data analysis method provided by this invention, when k≤N, the k-item correlation of umbilical cord stem cell staining control attributes is sorted to obtain the flowchart of the k-item cell activity correlation control attributes.

[0020] Figure 3 This is a schematic diagram of the structure of an artificial intelligence-based umbilical cord stem cell quality detection data analysis system provided by the present invention.

[0021] In the attached diagram, the components represented by each number are as follows:

[0022] Deviation comparison module 11, confidence analysis module 12, anomaly identification module 13, and normal identification module 14. Detailed Implementation

[0023] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0024] In the description of this invention, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the stated features. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0025] In the description of this invention, the term "for example" is used to mean "used as an example, illustration, or description." Any embodiment described as "for example" in this invention is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use the invention. Details are set forth in the following description for purposes of explanation. It should be understood that those skilled in the art will recognize that the invention can be made without using these specific details. In other instances, well-known structures and processes will not be described in detail to avoid obscuring the description of the invention with unnecessary detail. Therefore, the invention is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed herein.

[0026] Example 1, as Figure 1 As shown, this embodiment of the invention provides an artificial intelligence-based method for analyzing umbilical cord stem cell quality detection data, including:

[0027] S10: Obtain the umbilical cord stem cell staining monitoring parameters of the umbilical cord stem cell activity detection sample, compare them with the expected umbilical cord stem cell staining parameters, and obtain the umbilical cord stem cell staining parameter deviation vector.

[0028] The staining process of umbilical cord stem cells is dynamically affected by multiple parameters such as dye concentration, temperature, and pH. Traditional methods cannot identify key abnormal parameters, leading to ambiguity in the attribution of abnormalities. For example, it is difficult to distinguish between dye failure and temperature fluctuations, and the method relies on human experience for passive correction, resulting in a delayed response.

[0029] To address the aforementioned issues, this application collects inflammatory feature parameters of target users within a preset time window to obtain a historical inflammatory feature parameter sequence. This historical inflammatory feature parameter sequence is then input into a pre-trained inflammatory feature predictor, which outputs inflammatory feature parameters for predicting a future preset time.

[0030] Specifically, step S10 in the method includes:

[0031] When k≤N, the staining control attributes of umbilical cord stem cells are sorted by the correlation of k items of umbilical cord stem cell activity to obtain k cell activity-related control attributes. N≥k≥1, k is an integer, the initial value of k is equal to 1, and N represents the total number of control attributes.

[0032] When k > N, take the union of the k cell activity-related control attributes to obtain the cell activity-related control attributes.

[0033] Based on the cell activity-related control attributes, the umbilical cord stem cell staining monitoring parameters of the umbilical cord stem cell activity detection samples are collected and compared with the expected umbilical cord stem cell staining parameters to obtain the umbilical cord stem cell staining parameter deviation vector.

[0034] In this embodiment, the umbilical cord stem cell staining process involves multi-dimensional control attributes, such as temperature, time, and dye batch. However, not all control attributes have the same impact on cell viability. To accurately identify key control attributes, this application adopts a dynamic recursive correlation sorting mechanism. An incremental integer k is set (initial value k = 1, upper limit is the total number of control attributes N). When k ≤ N, k correlation sorting is performed. By screening out the k control attribute combinations most significantly related to cell viability, and based on the screened cell viability-related control attributes, the deviation vector between the actual umbilical cord stem cell staining monitoring parameters and the expected umbilical cord stem cell staining parameters is calculated as a retrieval constraint for subsequent viability confidence interval assessment. Specifically:

[0035] First, when k≤N, the staining control attributes of umbilical cord stem cells are sorted by the correlation of k items to umbilical cord stem cell activity to obtain k cell activity-related control attributes, where N≥k≥1, k is an integer representing the number of attributes to be screened, the initial value of k is equal to 1, and it is recursively increased from 1, and N represents the total number of control attributes. For example, if there are 4 control attributes, such as dye concentration, incubation time, pH value, and temperature, then N=4. The correlation sorting uses statistical methods to screen out the control attributes that have the greatest impact on umbilical cord stem cell activity and avoids noise interference.

[0036] Secondly, when k > N, the union of the k cell activity-related control attributes is taken to obtain the cell activity-related control attributes. Specifically, when k increases to more than N (k > N), it means that all control attributes have been traversed. The union of all k cell activity-related control attributes selected in the past is taken to form a complete set of cell activity-related control attributes, which is used as the cell activity-related control attributes.

[0037] Finally, based on the cell viability-related control attributes, umbilical cord stem cell staining monitoring parameters of umbilical cord stem cell viability detection samples were collected and compared with the expected umbilical cord stem cell staining parameters to obtain the umbilical cord stem cell staining parameter deviation vector. The umbilical cord stem cell staining monitoring parameters refer to key indicator data reflecting staining effectiveness and cell status, quantified and collected using experimental equipment (such as microscopes, flow cytometers, and image analysis systems) after umbilical cord stem cells have undergone staining treatment (e.g., trypan blue, fluorescent dyes, etc.). These include staining positivity rate and fluorescence intensity. The staining positivity rate refers to the proportion of successfully stained live or dead cells in the total number of cells. For example, dead cells appear blue in trypan blue staining, which directly correlates with cell viability; live cell proportion = 1 - dead cell staining positivity rate. Fluorescence intensity is the mean, peak, or standard deviation of the fluorescence signal intensity of the cell population after fluorescent dye labeling. Abnormal fluorescence intensity indicates uneven staining or impaired cell membrane integrity. The expected umbilical cord stem cell staining parameters are ideal standard values ​​pre-configured by the user. The umbilical cord stem cell staining parameter deviation vector = umbilical cord stem cell staining monitoring parameters - umbilical cord stem cell staining expected parameters.

[0038] For example, based on the screened cell activity-related control attributes, umbilical cord stem cell staining monitoring parameters of umbilical cord stem cell activity detection samples are collected, such as staining positivity rate of 92% and mean fluorescence intensity of 1500AU. The preset expected parameters for umbilical cord stem cell staining are staining positivity rate of 95% and mean fluorescence intensity of 1600AU. The umbilical cord stem cell staining monitoring parameters are compared with the expected parameters for umbilical cord stem cell staining to obtain the umbilical cord stem cell staining parameter deviation vector: [Δ staining positivity rate = -3%, Δ mean fluorescence intensity = -100AU].

[0039] In this way, by progressively optimizing the data dimensions through attribute screening, the bias vector is ensured to focus on the staining variables that have a significant impact on cell viability. This not only improves computational efficiency but also enhances the reliability of subsequent confidence interval assessments of viability values, providing a precise data foundation for automated stem cell quality testing.

[0040] Specifically, such as Figure 2 As shown, the phrase "when k≤N, perform k-item correlation sorting of umbilical cord stem cell activity control attributes to obtain k cell activity correlation control attributes" includes:

[0041] One cell viability-related control attribute up to k-1 cell viability-related control attributes are removed from the umbilical cord stem cell staining control attributes to obtain the retained umbilical cord stem cell staining control attributes.

[0042] When the total number of staining control attributes of the retained umbilical cord stem cells is ≤k-1, the process stops and outputs that k cell activity-related control attributes are empty.

[0043] When the total number of staining control attributes of the retained umbilical cord stem cells is greater than k-1, the staining control attributes of the retained umbilical cord stem cells are sorted by the correlation of k items of umbilical cord stem cell activity to obtain k cell activity-related control attributes.

[0044] In the embodiments of this application, such as Figure 2 As shown, firstly, up to k-1 cell activity-related control attributes are removed from the umbilical cord stem cell staining control attributes to obtain the remaining umbilical cord stem cell staining control attributes. For example, starting from k=1, the value of k is increased round by round: k=1, 2, 3, ... Before each round of correlation sorting, the cell activity-related control attributes selected in the previous k-1 rounds are deleted. For example, when k=3, the cell activity-related control attributes selected in the previous 2 rounds are deleted, ensuring that each round focuses on unselected attribute combinations. When k=1, the optimal solution for a single attribute is screened; when k=2, the synergistic effect of two attributes is screened from the remaining umbilical cord stem cell staining control attributes.

[0045] Secondly, when the total number of staining control attributes of retained umbilical cord stem cells is ≤k-1, the process stops, and the output shows that k cell viability-related control attributes are empty. This is because there are not enough retained umbilical cord stem cell staining control attributes to form k combinations. For example, if the total number of staining control attributes of retained umbilical cord stem cells is 2, k=3, since it is impossible to make a 3-item combination from 2 umbilical cord stem cell staining control attributes, the process stops directly, and the output shows that the 3 cell viability-related control attributes are empty.

[0046] Finally, when the total number of staining control attributes of the retained umbilical cord stem cells is greater than k-1, the staining control attributes of the retained umbilical cord stem cells are sorted for k cell viability-related control attributes to obtain k cell viability-related control attributes. In this way, by progressively removing the confirmed cell viability-related control attributes, the search space is narrowed, and duplicate calculations are avoided. When there are insufficient staining control attributes of the retained umbilical cord stem cells, the search is automatically returned to an empty set to prevent invalid calculations and ensure that each round of sorting focuses on the unexplored related control attributes.

[0047] For example, if the complete set of umbilical cord stem cell staining control attributes is [dye concentration, incubation time, pH value, temperature, centrifugal force], when k=1, k-1=0 cell viability-related control attributes are deleted from the umbilical cord stem cell staining control attributes, resulting in the remaining umbilical cord stem cell staining control attributes [dye concentration, incubation time, pH value, temperature, centrifugal force]. Since the total number of remaining umbilical cord stem cell staining control attributes (5) > k-1=0, one cell viability-related control attribute is selected from the remaining umbilical cord stem cell staining control attributes, resulting in one cell viability-related control attribute, such as [dye concentration]. When k=2, k-1=1 cell viability-related control attributes are deleted from the umbilical cord stem cell staining control attributes, resulting in the remaining umbilical cord stem cell staining control attributes [dye concentration, incubation time, pH value, temperature, centrifugal force]. The process involves storing umbilical cord stem cell staining control attributes [incubation time, pH, temperature, centrifugation force]. Since the total number of stored umbilical cord stem cell staining control attributes is 4 > k-1 = 1, the process performs two-item correlation sorting on the stored umbilical cord stem cell staining control attributes to obtain two cell activity-related control attributes, such as [incubation time, pH]. When k = 3, one cell activity-related control attribute is deleted from the umbilical cord stem cell staining control attributes until k-1 = 2 cell activity-related control attributes are obtained, resulting in the stored umbilical cord stem cell staining control attributes [temperature, centrifugation force]. Since the total number of stored umbilical cord stem cell staining control attributes is 2 ≤ k-1 = 2, the process stops, and the output shows that k cell activity-related control attributes are empty.

[0048] Furthermore, the phrase "sorting the staining control attributes of the retained umbilical cord stem cells according to the k-item correlation of umbilical cord stem cell activity to obtain k-item cell activity-related control attributes" includes:

[0049] Retrieve the staining control attribute deviation threshold pre-configured by the user terminal for the staining control attributes of the retained umbilical cord stem cells;

[0050] The staining control attributes of the preserved umbilical cord stem cells are combined with k items to obtain a set of k staining control attribute combinations.

[0051] Based on the staining control attribute deviation threshold, the set of k staining control attribute combinations is traversed to perform k-item correlation sorting of umbilical cord stem cell activity, thereby obtaining k cell activity correlation control attributes.

[0052] In this embodiment, the staining control attribute deviation thresholds pre-configured by the user terminal for the staining control attributes of the retained umbilical cord stem cells are first retrieved. These thresholds represent the maximum allowable fluctuation range of the staining control attributes. For example, if the staining control attributes of the retained umbilical cord stem cells are [pH value, temperature, centrifugal force], the pre-configured staining control attribute deviation thresholds by the user terminal are retrieved, such as pH deviation ±0.3, temperature deviation ±1℃, and centrifugal force deviation ±5%, providing quantitative standards for subsequent combination screening.

[0053] Secondly, k combinations of staining control attributes of the preserved umbilical cord stem cells were performed to obtain a set of k staining control attribute combinations. Where X represents the total number of staining control attributes for retained umbilical cord stem cells. For example, if the complete set of staining control attributes for retained umbilical cord stem cells is [dye concentration, incubation time, pH value, temperature, centrifugal force], when k = 2, there are a total of... A set of two staining control attributes, such as [incubation time, pH], [pH, temperature], [temperature, centrifugal force], etc., is used as a set of two staining control attributes.

[0054] Finally, based on the staining control attribute deviation threshold, the k-item staining control attribute combination set is traversed to perform k-item correlation sorting of umbilical cord stem cell activity to obtain k-item cell activity correlation control attributes.

[0055] Specifically, the phrase "based on the staining control attribute deviation threshold, traversing the set of k staining control attribute combinations to perform k-item correlation sorting of umbilical cord stem cell activity to obtain k-item cell activity correlation control attributes" includes:

[0056] Extract the first k-item combination of staining control attributes from the set of k-item combination of staining control attributes;

[0057] Retrieve a second set of umbilical cord stem cell activity detection samples, wherein the second set of umbilical cord stem cell activity detection samples has a one-to-one corresponding set of first umbilical cord stem cell activity detection record values, a set of staining control attribute record values, and a set of umbilical cord stem cell collection condition record values;

[0058] Cluster analysis was performed on the set of recorded values ​​of umbilical cord stem cell collection conditions to obtain multi-cluster recorded values ​​of umbilical cord stem cell collection conditions;

[0059] Based on the first cluster of umbilical cord stem cell collection condition record values ​​from the set of multi-cluster umbilical cord stem cell collection condition record values, the first cluster of staining control attribute record values ​​is extracted from the set of staining control attribute record values.

[0060] Extract the first staining control attribute record value and the second staining control attribute record value from the first cluster of staining control attribute record values;

[0061] Based on the first k-item combination of staining control attributes, extract the first set of staining control attribute deviation thresholds from the staining control attribute deviation thresholds, and store the remaining staining control attribute deviation thresholds as the second set of staining control attribute deviation thresholds.

[0062] When the first group of staining control attribute deviations of the first staining control attribute record value and the second staining control attribute record value are respectively greater than the first group of staining control attribute deviation threshold, and the second group of staining control attribute deviations are respectively less than or equal to the second group of staining control attribute deviation threshold, based on the first staining control attribute record value and the second staining control attribute record value, the first activity detection fluctuation value is obtained by comparing with the first umbilical cord stem cell activity detection record value set, and added to the activity detection fluctuation value set;

[0063] Once the collection conditions and recorded values ​​of the multi-cluster umbilical cord stem cells have been traversed, the mean of the set of activity detection fluctuation values ​​is calculated and set as the correlation coefficient of the first k-th staining control attribute combination.

[0064] When the correlation coefficient of the first k-item staining control attribute combination is greater than or equal to the correlation coefficient threshold, the first k-item staining control attribute combination is added to the k-item cell activity correlation control attribute.

[0065] In this embodiment of the application, a k-item staining control attribute combination is first randomly extracted from the set of k-item staining control attribute combinations as the first k-item staining control attribute combination, for example, [pH value, temperature].

[0066] Secondly, a second set of umbilical cord stem cell activity detection samples was retrieved from historical data. This second set of umbilical cord stem cell activity detection samples has a one-to-one correspondence with the first set of umbilical cord stem cell activity detection record values, staining control attribute record values, and umbilical cord stem cell collection condition record values. Umbilical cord stem cell activity refers to the percentage of live cells. Umbilical cord stem cell collection conditions include donor physical conditions (such as donor physical condition), umbilical cord collection conditions (such as time window), umbilical cord site selection, isolation and culture, and cryopreservation and thawing conditions, which are prerequisites for activity detection.

[0067] Next, cluster analysis was performed on the set of recorded values ​​of umbilical cord stem cell collection conditions to obtain multi-cluster recorded values ​​of umbilical cord stem cell collection conditions. This was to eliminate environmental interference. The sample collection conditions of the set of recorded values ​​of umbilical cord stem cell collection conditions in the same cluster were similar. At this time, the interference of collection conditions can be ruled out, and the difference in activity can be attributed to staining parameters.

[0068] Furthermore, based on the first cluster of umbilical cord stem cell collection condition record values ​​from the set of multi-cluster umbilical cord stem cell collection condition record values, the first cluster of staining control attribute record values ​​are extracted from the set of staining control attribute record values. Then, the first staining control attribute record values ​​are extracted from the first cluster of staining control attribute record values, for example, pH=7.2, temperature=25℃, centrifugal force 3050rpm, and the second staining control attribute record values, for example, pH=6.8, temperature=27℃, centrifugal force 3000rpm.

[0069] Furthermore, based on the first k-item combination of staining control attributes, a first set of staining control attribute deviation thresholds is extracted from the staining control attribute deviation thresholds, for example, pH value ±0.3, temperature ±1℃, and the remaining staining control attribute deviation thresholds, for example, centrifugal force ±100rpm, are stored as a second set of staining control attribute deviation thresholds.

[0070] Furthermore, when the first set of staining control attribute deviations of the first staining control attribute record value and the second set of staining control attribute record values ​​are respectively greater than the first set of staining control attribute deviation threshold, and the second set of staining control attribute deviations are respectively less than or equal to the second set of staining control attribute deviation threshold, based on the first set of staining control attribute record values ​​and the second set of staining control attribute record values, the first set of activity detection record values ​​is compared with the first set of umbilical cord stem cell activity detection record values ​​to obtain the first activity detection fluctuation value, which is added to the activity detection fluctuation value set. Here, setting the first set of staining control attribute deviation threshold and the second set of staining control attribute deviation threshold is to focus on the first set of staining control attributes and isolate the target variable (first set of staining control attributes) from the noise variable (second set of staining control attributes). For example, the deviations of the first set of staining control attributes recorded values ​​and the second set of staining control attributes are calculated. For example, pH deviation |7.2-6.8| = 0.4, temperature deviation |25-27| = 2℃, and the deviations of the second set of staining control attributes are calculated. For example, centrifugal force deviation |3000-3050| = 50 rpm. The first set of staining control attribute deviation thresholds and the second set of staining control attribute deviation thresholds are then compared. Since the first set of staining control attribute deviations 0.4 > 0.3 and 2℃ > 1℃, and the second set of staining control attribute deviations 50 rpm < 100 ± 100 rpm, the conditions are met. Based on the first set of umbilical cord stem cell activity detection recorded values, the activity detection recorded values ​​of the two sets of samples are obtained, for example, 92% and 85%. The first activity detection fluctuation value = |92%-85%| = 7% is calculated and added to the activity detection fluctuation value set. The first activity detection fluctuation value can quantify the degree of activity detection fluctuation caused by changes in target attributes.

[0071] Furthermore, following the same method, the recorded values ​​of multiple clusters of umbilical cord stem cell collection conditions are iterated. Once the iteration of the recorded values ​​of multiple clusters of umbilical cord stem cell collection conditions is completed, the mean of the set of activity detection fluctuation values ​​is calculated and set as the correlation coefficient of the first k-th staining control attribute combination. For example, by iterating through the recorded values ​​of multiple clusters of umbilical cord stem cell collection conditions, the activity detection fluctuation value of cluster 1 is calculated to be 7%, the activity detection fluctuation value of cluster 2 is 9%, and so on. The mean is calculated to obtain the correlation coefficient of the first k-th staining control attribute combination, for example, 8%, which represents the average influence intensity of the first k-th staining control attribute combination on the activity detection fluctuation within the recorded values ​​of multiple clusters of umbilical cord stem cell collection conditions.

[0072] Finally, when the correlation coefficient of the first k-item staining control attribute combination is greater than or equal to the correlation coefficient threshold, the first k-item staining control attribute combination is added to the k-item cell viability correlation control attributes. The correlation coefficient threshold is used to filter weakly correlated staining control attribute combinations and avoid noise interference. Those skilled in the art can dynamically set this threshold according to actual conditions, such as 5%. For example, if the correlation coefficient of the first k-item staining control attribute combination is 8% and the correlation coefficient threshold is 5%, then the first k-item staining control attribute combination, for example, [pH, temperature], is added to the k-item cell viability correlation control attributes.

[0073] Specifically, the phrase "performing cluster analysis on the set of umbilical cord stem cell collection condition record values ​​to obtain multi-cluster umbilical cord stem cell collection condition record values" includes:

[0074] Configure the Euclidean distance threshold for data collection conditions via the user terminal;

[0075] Extract the first umbilical cord stem cell collection condition record value and the second umbilical cord stem cell collection condition record value from the set of umbilical cord stem cell collection condition record values;

[0076] The same attribute deviation is calculated for the first umbilical cord stem cell collection condition record value and the second umbilical cord stem cell collection condition record value to obtain the first umbilical cord stem cell collection condition deviation set;

[0077] After traversing the first set of deviations for umbilical cord stem cell collection conditions and performing normalization, Euclidean distance calculation is performed to obtain the Euclidean distance of the collection conditions.

[0078] If the Euclidean distance of the acquisition conditions is greater than the threshold value of the Euclidean distance of the acquisition conditions, the recorded values ​​of the first umbilical cord stem cell acquisition conditions and the second umbilical cord stem cell acquisition conditions are considered to be of different categories; otherwise, the recorded values ​​of the first umbilical cord stem cell acquisition conditions and the second umbilical cord stem cell acquisition conditions are considered to be in the same cluster.

[0079] In this embodiment, the user first configures the Euclidean distance threshold for the collection conditions to determine the clustering standard based on the similarity of the collection conditions. For example, the Euclidean distance threshold for the collection conditions is configured to be 0.25. The smaller the Euclidean distance threshold, the more similar the collection conditions of samples in the same cluster.

[0080] Next, extract the first umbilical cord stem cell collection condition record value and the second umbilical cord stem cell collection condition record value from the set of umbilical cord stem cell collection condition record values. For example, extract the first umbilical cord stem cell collection condition record value, such as {age 30 years old, temperature 4℃}, and the second umbilical cord stem cell collection condition record value, such as {age 28 years old, temperature 5℃}, from the set of umbilical cord stem cell collection condition record values.

[0081] Next, the same-attribute deviation is calculated for the first and second recorded values ​​of umbilical cord stem cell collection conditions to obtain the deviation set of the first umbilical cord stem cell collection conditions. The same-attribute deviation calculation can calculate the absolute deviation. For example, if the first recorded value of umbilical cord stem cell collection conditions is {age 30 years, temperature 4℃}, and the second recorded value is {age 28 years, temperature 5℃}, the same-attribute deviation calculation is performed: Δage = |30-28| = 2, Δtemperature = |4-5| = 1. Thus, following the same method, the deviation set of the first umbilical cord stem cell collection conditions is calculated as: {Δage = 2, Δtemperature = 1}.

[0082] Further, after normalizing the first set of umbilical cord stem cell collection condition deviations, Euclidean distance calculation is performed to obtain the Euclidean distance of the collection conditions. Normalization is performed to eliminate dimensional differences between different condition attributes. Normalization can be based on the maximum value of the same attribute in the first and second recorded values ​​of the umbilical cord stem cell collection conditions. For example, if the maximum age value in the first and second recorded values ​​of the umbilical cord stem cell collection conditions is 50 years and the maximum temperature value is 5℃, then Δage = 2 and Δtemperature = 1 are normalized to 2 / 50 = 0.04 and 1 / 5 = 0.2, respectively, resulting in the normalized deviation set {0.04, 0.2}. Then, the Euclidean distance calculation is performed again. For example… Obtain the Euclidean distance for the data collection conditions.

[0083] Finally, if the Euclidean distance of the collection conditions is greater than the threshold value, the recorded values ​​of the first and second umbilical cord stem cell collection conditions are considered to be in different clusters; otherwise, they are considered to be in the same cluster. For example, if the threshold value is 0.25 and the Euclidean distance is 0.204, and the recorded values ​​of the first and second umbilical cord stem cell collection conditions are considered to be in the same cluster, it indicates that the sample collection conditions are similar. In this case, interference from the collection conditions can be ruled out, and the difference in activity can be attributed to staining parameters. Conversely, if they are in different clusters, it indicates a large difference in sample collection conditions, and the difference in activity may be due to the collection conditions.

[0084] In summary, compared to existing technologies, this application obtains umbilical cord stem cell staining monitoring parameters from umbilical cord stem cell viability testing samples and compares them with expected umbilical cord stem cell staining parameters to obtain an umbilical cord stem cell staining parameter deviation vector. This accurately identifies key combinations of staining control attributes, shifting the attribution of viability decline from cell culture results to staining process parameters. It provides correlation-filtered, dimensionality-reduced data (retaining only key attribute deviations) for subsequent viability confidence interval calculations, quantifies the deviations to map biological effects, and provides a core data foundation for the standardization of stem cell industrial production.

[0085] S20: Constrained by the umbilical cord stem cell staining parameter deviation vector, the umbilical cord stem cell staining expected parameters, and the umbilical cord stem cell collection conditions, a first set of umbilical cord stem cell activity detection samples is collected, a central value assessment is performed, and the confidence interval of umbilical cord stem cell activity value is obtained, wherein the umbilical cord stem cell activity value is characterized by the proportion of live cells.

[0086] In this embodiment, the umbilical cord stem cell staining parameter deviation vector, the expected umbilical cord stem cell staining parameters (standard values ​​preset by the user), and the umbilical cord stem cell collection conditions (such as donor age and storage temperature) are used as constraints to select a homogeneous sample set from the historical database. This ensures that the samples are highly comparable in terms of staining deviation range and collection conditions. Then, the first umbilical cord stem cell activity detection sample set is evaluated for central tendency using methods such as box plots to obtain the confidence interval of umbilical cord stem cell activity values.

[0087] For example, using the umbilical cord stem cell staining parameter deviation vector, such as [Δ staining positivity rate = -3%, Δ mean fluorescence intensity = -100AU], the expected staining parameters for umbilical cord stem cells, such as a staining positivity rate of 95% and a mean fluorescence intensity of 1600AU, and the umbilical cord stem cell collection conditions, such as donor age of 25-30 years, as screening constraints, several umbilical cord stem cell activity test samples meeting the above constraints are collected from the database as the first umbilical cord stem cell activity test sample set, with the viable cell percentage ranging from [90.1%, 96.3%]. After removing outliers using the box plot method, the confidence interval for umbilical cord stem cell activity value is calculated to be [92.8%, 95.4%]. In this way, a confidence interval for umbilical cord stem cell activity value that can dynamically reflect the reasonable range of activity fluctuation under the current process level is obtained, providing a comparison standard for subsequent abnormal data identification.

[0088] S30: When the umbilical cord stem cell activity detection value does not fall within the confidence interval of the umbilical cord stem cell activity value, the umbilical cord stem cell activity detection value is marked as abnormal quality detection data.

[0089] In this embodiment, the confidence interval for umbilical cord stem cell activity is used as the standard threshold range. This confidence interval represents the reasonable fluctuation range of umbilical cord stem cell activity under normal circumstances. When the actual activity detection value of a sample exceeds the confidence interval, the umbilical cord stem cell activity detection value is marked as abnormal quality detection data. This marking indicates that the activity status of the sample deviates from the normal range, potentially posing a quality risk, and requiring further investigation into the cause, such as sample contamination, detection operation errors, or abnormal stem cell activity itself. In this way, abnormal data is accurately identified, allowing subsequent management personnel to make targeted selections based on the indication, ensuring the stability of the quality detection data.

[0090] S40: When the umbilical cord stem cell activity test value falls within the confidence interval of the umbilical cord stem cell activity value, the umbilical cord stem cell activity test value is marked as normal quality test data.

[0091] In this embodiment of the application, the confidence interval of umbilical cord stem cell activity value is used as the standard threshold range. The confidence interval of umbilical cord stem cell activity value represents the reasonable fluctuation range of umbilical cord stem cell activity value under normal circumstances. When the actual activity detection value of the sample falls within the confidence interval of umbilical cord stem cell activity value, it is marked as normal quality detection data, indicating that the activity status of the sample meets the expected reasonable range, and has normal quality characteristics from the activity index, and can enter the subsequent application or storage process.

[0092] In this way, by replacing traditional empirical judgment with a clear numerical range, the standardization and automation of umbilical cord stem cell quality assessment are achieved, which not only reduces human subjective error, but also provides a clear classification basis for subsequent quality traceability and data analysis.

[0093] Furthermore, this application also includes: when the number of umbilical cord stem cell activity detection values ​​with normal quality detection data identification is greater than or equal to the number of fitted values, a fitting prompt is sent to the user terminal.

[0094] In this embodiment, when the cumulative number of activity detection values ​​with normal quality indicators reaches a preset fitting threshold (e.g., 1000 cases), a fitting prompt signal is automatically sent to the user terminal, triggering a confidence interval refitting process based on the new dataset. This eliminates process lag: traditional static confidence intervals (e.g., [92.3%, 95.7%]) cannot adapt to the new standard after process upgrades. For example, if the mean activity increases to 94.5%, this application continuously incorporates recently qualified samples to recalculate the interval, for example, updating it to [94.1%, 96.5%], avoiding misjudging high-activity samples under the new process as abnormal.

[0095] In summary, the embodiments of this application have at least the following technical effects:

[0096] Compared to existing technologies, this application first obtains the umbilical cord stem cell staining monitoring parameters of the umbilical cord stem cell viability test samples, compares them with the expected umbilical cord stem cell staining parameters, and obtains the umbilical cord stem cell staining parameter deviation vector. In this way, the key combination of staining control attributes is accurately identified, attributing the decline in viability from cell culture results to staining process parameters. This provides correlation-filtered, dimensionality-reduced data (retaining only key attribute deviations) for subsequent viability confidence interval calculations, quantifies the deviations to map biological effects, and provides a core data foundation for the standardization of stem cell industrial production.

[0097] Secondly, this application uses the umbilical cord stem cell staining parameter deviation vector, the expected umbilical cord stem cell staining parameters, and the umbilical cord stem cell collection conditions as constraints to collect a first set of umbilical cord stem cell activity detection samples, performs central tendency evaluation, and obtains the confidence interval of umbilical cord stem cell activity values. In this way, a confidence interval of umbilical cord stem cell activity values ​​that can dynamically reflect the reasonable range of activity fluctuations under the current process level is obtained, providing a comparison standard for subsequent abnormal data identification.

[0098] Furthermore, this application identifies abnormal quality test data when the umbilical cord stem cell activity test value does not fall within the confidence interval of the umbilical cord stem cell activity value. This accurately identifies abnormal data, allowing administrators to make targeted selections based on the identification, thus ensuring the stability of the quality test data.

[0099] Finally, this application identifies umbilical cord stem cell activity test values ​​as normal quality test data when the values ​​fall within the confidence interval for umbilical cord stem cell activity. In this way, by replacing traditional empirical judgment with a clearly defined numerical range, the standardization and automation of umbilical cord stem cell quality assessment are achieved. This reduces human subjective error and provides a clear classification basis for subsequent quality traceability and data analysis.

[0100] Through the above technical solution, this application employs a recursive k-item combination screening (k increasing from 1 to N) and cluster analysis of collection conditions to accurately identify key influencing factor combinations from multi-dimensional staining control attributes. Constrained by the umbilical cord stem cell staining parameter deviation vector, the expected umbilical cord stem cell staining parameters, and the umbilical cord stem cell collection conditions, homogeneous samples are collected, and central tendency processing is performed to obtain the confidence interval for umbilical cord stem cell activity values. Based on this, abnormal or normal quality detection data are identified for evaluating umbilical cord stem cell activity. This effectively identifies abnormal quality detection data for umbilical cord stem cell activity values, improving the reliability and stability of the quality detection results.

[0101] Example 2, as Figure 3 As shown, based on the same inventive concept as the artificial intelligence-based umbilical cord stem cell quality detection data analysis method provided in Embodiment 1, this embodiment of the invention also provides an artificial intelligence-based umbilical cord stem cell quality detection data analysis system, including:

[0102] The deviation comparison module 11 is used to obtain the umbilical cord stem cell staining monitoring parameters of the umbilical cord stem cell activity detection sample, compare them with the expected umbilical cord stem cell staining parameters, and obtain the umbilical cord stem cell staining parameter deviation vector.

[0103] Confidence analysis module 12 is used to collect a first set of umbilical cord stem cell activity detection samples, perform central value evaluation, and obtain the confidence interval of umbilical cord stem cell activity value, constrained by the umbilical cord stem cell staining parameter deviation vector, the umbilical cord stem cell staining expected parameters, and the umbilical cord stem cell collection conditions. The umbilical cord stem cell activity value is characterized by the proportion of live cells.

[0104] Anomaly identification module 13 is used to identify abnormal quality detection data of umbilical cord stem cell activity detection value when the umbilical cord stem cell activity detection value does not belong to the confidence interval of the umbilical cord stem cell activity value.

[0105] The normal identification module 14 is used to identify the umbilical cord stem cell activity detection value as normal quality detection data when the umbilical cord stem cell activity detection value falls within the confidence interval of the umbilical cord stem cell activity value.

[0106] Specifically, the deviation comparison module 11 is used for:

[0107] When k≤N, the staining control attributes of umbilical cord stem cells are sorted by the correlation of k items of umbilical cord stem cell activity to obtain k cell activity-related control attributes. N≥k≥1, k is an integer, the initial value of k is equal to 1, and N represents the total number of control attributes.

[0108] When k > N, take the union of the k cell activity-related control attributes to obtain the cell activity-related control attributes.

[0109] Based on the cell activity-related control attributes, the umbilical cord stem cell staining monitoring parameters of the umbilical cord stem cell activity detection samples are collected and compared with the expected umbilical cord stem cell staining parameters to obtain the umbilical cord stem cell staining parameter deviation vector.

[0110] Specifically, the phrase "when k≤N, perform k-item correlation sorting of umbilical cord stem cell activity control attributes to obtain k cell activity correlation control attributes" includes:

[0111] One cell viability-related control attribute up to k-1 cell viability-related control attributes are removed from the umbilical cord stem cell staining control attributes to obtain the retained umbilical cord stem cell staining control attributes.

[0112] When the total number of staining control attributes of the retained umbilical cord stem cells is ≤k-1, the process stops and outputs that k cell activity-related control attributes are empty.

[0113] When the total number of staining control attributes of the retained umbilical cord stem cells is greater than k-1, the staining control attributes of the retained umbilical cord stem cells are sorted by the correlation of k items of umbilical cord stem cell activity to obtain k cell activity-related control attributes.

[0114] Specifically, the phrase "sorting the staining control attributes of the retained umbilical cord stem cells according to the k-item correlation of umbilical cord stem cell activity to obtain k-item cell activity-related control attributes" includes:

[0115] Retrieve the staining control attribute deviation threshold pre-configured by the user terminal for the staining control attributes of the retained umbilical cord stem cells;

[0116] The staining control attributes of the preserved umbilical cord stem cells are combined with k items to obtain a set of k staining control attribute combinations.

[0117] Based on the staining control attribute deviation threshold, the set of k staining control attribute combinations is traversed to perform k-item correlation sorting of umbilical cord stem cell activity, thereby obtaining k cell activity correlation control attributes.

[0118] Specifically, the phrase "based on the staining control attribute deviation threshold, traversing the set of k staining control attribute combinations to perform k-item correlation sorting of umbilical cord stem cell activity to obtain k-item cell activity correlation control attributes" includes:

[0119] Extract the first k-item combination of staining control attributes from the set of k-item combination of staining control attributes;

[0120] Retrieve a second set of umbilical cord stem cell activity detection samples, wherein the second set of umbilical cord stem cell activity detection samples has a one-to-one corresponding set of first umbilical cord stem cell activity detection record values, a set of staining control attribute record values, and a set of umbilical cord stem cell collection condition record values;

[0121] Cluster analysis was performed on the set of recorded values ​​of umbilical cord stem cell collection conditions to obtain multi-cluster recorded values ​​of umbilical cord stem cell collection conditions;

[0122] Based on the first cluster of umbilical cord stem cell collection condition record values ​​from the set of multi-cluster umbilical cord stem cell collection condition record values, the first cluster of staining control attribute record values ​​is extracted from the set of staining control attribute record values.

[0123] Extract the first staining control attribute record value and the second staining control attribute record value from the first cluster of staining control attribute record values;

[0124] Based on the first k-item combination of staining control attributes, extract the first set of staining control attribute deviation thresholds from the staining control attribute deviation thresholds, and store the remaining staining control attribute deviation thresholds as the second set of staining control attribute deviation thresholds.

[0125] When the first group of staining control attribute deviations of the first staining control attribute record value and the second staining control attribute record value are respectively greater than the first group of staining control attribute deviation threshold, and the second group of staining control attribute deviations are respectively less than or equal to the second group of staining control attribute deviation threshold, based on the first staining control attribute record value and the second staining control attribute record value, the first activity detection fluctuation value is obtained by comparing with the first umbilical cord stem cell activity detection record value set, and added to the activity detection fluctuation value set;

[0126] Once the collection conditions and recorded values ​​of the multi-cluster umbilical cord stem cells have been traversed, the mean of the set of activity detection fluctuation values ​​is calculated and set as the correlation coefficient of the first k-th staining control attribute combination.

[0127] When the correlation coefficient of the first k-item staining control attribute combination is greater than or equal to the correlation coefficient threshold, the first k-item staining control attribute combination is added to the k-item cell activity correlation control attribute.

[0128] Further, the phrase "performing cluster analysis on the set of recorded values ​​for umbilical cord stem cell collection conditions to obtain multi-cluster recorded values ​​for umbilical cord stem cell collection conditions" includes:

[0129] Configure the Euclidean distance threshold for data collection conditions via the user terminal;

[0130] Extract the first umbilical cord stem cell collection condition record value and the second umbilical cord stem cell collection condition record value from the set of umbilical cord stem cell collection condition record values;

[0131] The same attribute deviation is calculated for the first umbilical cord stem cell collection condition record value and the second umbilical cord stem cell collection condition record value to obtain the first umbilical cord stem cell collection condition deviation set;

[0132] After traversing the first set of deviations for umbilical cord stem cell collection conditions and performing normalization, Euclidean distance calculation is performed to obtain the Euclidean distance of the collection conditions.

[0133] If the Euclidean distance of the acquisition conditions is greater than the threshold value of the Euclidean distance of the acquisition conditions, the recorded values ​​of the first umbilical cord stem cell acquisition conditions and the second umbilical cord stem cell acquisition conditions are considered to be of different categories; otherwise, the recorded values ​​of the first umbilical cord stem cell acquisition conditions and the second umbilical cord stem cell acquisition conditions are considered to be in the same cluster.

[0134] The confidence analysis module 12 is specifically used for:

[0135] Constrained by the umbilical cord stem cell staining parameter deviation vector, the umbilical cord stem cell staining expected parameters, and the umbilical cord stem cell collection conditions, a first set of umbilical cord stem cell activity detection samples is collected, a central value assessment is performed, and the confidence interval of umbilical cord stem cell activity value is obtained, wherein the umbilical cord stem cell activity value is characterized by the proportion of live cells.

[0136] The anomaly identification module 13 is specifically used for:

[0137] When the umbilical cord stem cell activity test value does not fall within the confidence interval of the umbilical cord stem cell activity value, the umbilical cord stem cell activity test value is marked as abnormal quality test data.

[0138] Specifically, the normal identification module 14 is used for:

[0139] When the umbilical cord stem cell activity test value falls within the confidence interval of the umbilical cord stem cell activity value, the umbilical cord stem cell activity test value is marked as normal quality test data.

[0140] Furthermore, it also includes: when the number of umbilical cord stem cell activity detection values ​​with the normal quality detection data identifier is greater than or equal to the fitted number, a fitting prompt is sent to the user terminal.

[0141] In summary, the embodiments of this application have at least the following technical effects:

[0142] Compared to existing technologies, this application first uses a deviation comparison module to obtain umbilical cord stem cell staining monitoring parameters from umbilical cord stem cell activity testing samples. These parameters are then compared with expected umbilical cord stem cell staining parameters to obtain a deviation vector for umbilical cord stem cell staining parameters. This accurately identifies key combinations of staining control attributes, shifting the attribution of activity decline from cell culture results to staining process parameters. This provides correlation-filtered, dimensionality-reduced data (retaining only key attribute deviations) for subsequent activity confidence interval calculations, quantifying the deviation's mapping to biological effects and providing a core data foundation for the standardization of stem cell industrial production. Secondly, using a confidence analysis module, constrained by the umbilical cord stem cell staining parameter deviation vector, expected umbilical cord stem cell staining parameters, and umbilical cord stem cell collection conditions, a first set of umbilical cord stem cell activity testing samples is collected. Central tendency assessment is performed to obtain a confidence interval for umbilical cord stem cell activity values. This results in a confidence interval that dynamically reflects the reasonable range of activity fluctuations under the current technological level, providing a comparison standard for subsequent abnormal data identification. Secondly, the anomaly identification module identifies abnormal quality data when the umbilical cord stem cell activity test value falls outside the confidence interval, ensuring the stability of the quality test data. This precise identification allows administrators to make targeted selections based on the anomaly identification. Finally, the normality identification module identifies normal quality data when the umbilical cord stem cell activity test value falls within the confidence interval. This clear numerical range determination replaces traditional empirical judgment, standardizing and automating umbilical cord stem cell quality assessment. This reduces human error and provides a clear classification basis for subsequent quality traceability and data analysis. In this way, abnormal quality test data in umbilical cord stem cell activity test values ​​are effectively identified, improving the reliability and stability of the quality test results.

[0143] It should be noted that the descriptions of each embodiment in the above embodiments have different focuses. For parts that are not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0144] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0145] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0146] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0147] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0148] Although preferred embodiments of the invention have been described, those skilled in the art, once they have learned the basic inventive concept, can make other changes and modifications to these embodiments.

[0149] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of this invention and its equivalents, this invention also intends to include these modifications and variations.

Claims

1. A method for analyzing umbilical cord stem cell quality detection data using artificial intelligence, characterized in that, include: The staining monitoring parameters of umbilical cord stem cells in the umbilical cord stem cell activity test sample are obtained and compared with the expected staining parameters of umbilical cord stem cells to obtain the umbilical cord stem cell staining parameter deviation vector. Constrained by the umbilical cord stem cell staining parameter deviation vector, the umbilical cord stem cell staining expected parameters, and the umbilical cord stem cell collection conditions, a first set of umbilical cord stem cell activity detection samples is collected, a central value assessment is performed, and the confidence interval of umbilical cord stem cell activity value is obtained, wherein the umbilical cord stem cell activity value is characterized by the proportion of live cells. When the umbilical cord stem cell activity test value does not fall within the confidence interval of the umbilical cord stem cell activity value, the umbilical cord stem cell activity test value is marked as abnormal quality test data; When the umbilical cord stem cell activity test value falls within the confidence interval of the umbilical cord stem cell activity value, the umbilical cord stem cell activity test value is marked as normal quality test data.

2. The method according to claim 1, characterized in that, The umbilical cord stem cell staining monitoring parameters are obtained and compared with the expected umbilical cord stem cell staining parameters to obtain the umbilical cord stem cell staining parameter deviation vector, including: When k≤N, the staining control attributes of umbilical cord stem cells are sorted by the correlation of k items of umbilical cord stem cell activity to obtain k cell activity-related control attributes. N≥k≥1, k is an integer, the initial value of k is equal to 1, and N represents the total number of control attributes. When k > N, take the union of the k cell activity-related control attributes to obtain the cell activity-related control attributes. Based on the cell activity-related control attributes, the umbilical cord stem cell staining monitoring parameters of the umbilical cord stem cell activity detection samples are collected and compared with the expected umbilical cord stem cell staining parameters to obtain the umbilical cord stem cell staining parameter deviation vector.

3. The method according to claim 2, characterized in that, When k≤N, the staining control attributes of umbilical cord stem cells are sorted by the correlation of k cell viability items to obtain k cell viability-related control attributes, including: One cell viability-related control attribute up to k-1 cell viability-related control attributes are removed from the umbilical cord stem cell staining control attributes to obtain the retained umbilical cord stem cell staining control attributes. When the total number of staining control attributes of the retained umbilical cord stem cells is ≤k-1, the process stops and outputs that k cell activity-related control attributes are empty. When the total number of staining control attributes of the retained umbilical cord stem cells is greater than k-1, the staining control attributes of the retained umbilical cord stem cells are sorted by the correlation of k items of umbilical cord stem cell activity to obtain k cell activity-related control attributes.

4. The method as described in claim 3, characterized in that, The staining control attributes of the retained umbilical cord stem cells were sorted for k-item correlation with umbilical cord stem cell activity to obtain k cell activity-related control attributes, including: Retrieve the staining control attribute deviation threshold pre-configured by the user terminal for the staining control attributes of the retained umbilical cord stem cells; The staining control attributes of the preserved umbilical cord stem cells are combined with k items to obtain a set of k staining control attribute combinations. Based on the staining control attribute deviation threshold, the set of k staining control attribute combinations is traversed to perform k-item correlation sorting of umbilical cord stem cell activity, thereby obtaining k cell activity correlation control attributes.

5. The method as described in claim 4, characterized in that, Based on the aforementioned staining control attribute deviation threshold, the set of k staining control attribute combinations is traversed to perform k-item correlation sorting of umbilical cord stem cell activity, obtaining k cell activity-related control attributes, including: Extract the first k-item combination of staining control attributes from the set of k-item combination of staining control attributes; Retrieve a second set of umbilical cord stem cell activity detection samples, wherein the second set of umbilical cord stem cell activity detection samples has a one-to-one corresponding set of first umbilical cord stem cell activity detection record values, a set of staining control attribute record values, and a set of umbilical cord stem cell collection condition record values; Cluster analysis was performed on the set of recorded values ​​of umbilical cord stem cell collection conditions to obtain multi-cluster recorded values ​​of umbilical cord stem cell collection conditions; Based on the first cluster of umbilical cord stem cell collection condition record values ​​from the set of multi-cluster umbilical cord stem cell collection condition record values, the first cluster of staining control attribute record values ​​is extracted from the set of staining control attribute record values. Extract the first staining control attribute record value and the second staining control attribute record value from the first cluster of staining control attribute record values; Based on the first k-item combination of staining control attributes, extract the first set of staining control attribute deviation thresholds from the staining control attribute deviation thresholds, and store the remaining staining control attribute deviation thresholds as the second set of staining control attribute deviation thresholds. When the first group of staining control attribute deviations of the first staining control attribute record value and the second staining control attribute record value are respectively greater than the first group of staining control attribute deviation threshold, and the second group of staining control attribute deviations are respectively less than or equal to the second group of staining control attribute deviation threshold, based on the first staining control attribute record value and the second staining control attribute record value, the first activity detection fluctuation value is obtained by comparing with the first umbilical cord stem cell activity detection record value set, and added to the activity detection fluctuation value set; Once the collection conditions and recorded values ​​of the multi-cluster umbilical cord stem cells have been traversed, the mean of the set of activity detection fluctuation values ​​is calculated and set as the correlation coefficient of the first k-th staining control attribute combination. When the correlation coefficient of the first k-item staining control attribute combination is greater than or equal to the correlation coefficient threshold, the first k-item staining control attribute combination is added to the k-item cell activity correlation control attribute.

6. The method as described in claim 5, characterized in that, Cluster analysis was performed on the set of recorded values ​​for umbilical cord stem cell collection conditions to obtain multi-cluster recorded values ​​for umbilical cord stem cell collection conditions, including: Configure the Euclidean distance threshold for data collection conditions via the user terminal; Extract the first umbilical cord stem cell collection condition record value and the second umbilical cord stem cell collection condition record value from the set of umbilical cord stem cell collection condition record values; The same attribute deviation is calculated for the first umbilical cord stem cell collection condition record value and the second umbilical cord stem cell collection condition record value to obtain the first umbilical cord stem cell collection condition deviation set; After traversing the first set of deviations for umbilical cord stem cell collection conditions and performing normalization, Euclidean distance calculation is performed to obtain the Euclidean distance of the collection conditions. If the Euclidean distance of the acquisition conditions is greater than the threshold value of the Euclidean distance of the acquisition conditions, the recorded values ​​of the first umbilical cord stem cell acquisition conditions and the second umbilical cord stem cell acquisition conditions are considered to be of different categories; otherwise, the recorded values ​​of the first umbilical cord stem cell acquisition conditions and the second umbilical cord stem cell acquisition conditions are considered to be in the same cluster.

7. The method as described in claim 1, characterized in that, Also includes: When the number of umbilical cord stem cell activity detection values ​​with the normal quality detection data identifier is greater than or equal to the fitted number, a fitting prompt is sent to the user terminal.

8. An artificial intelligence-based umbilical cord stem cell quality detection data analysis system, characterized in that, For performing the method according to any one of claims 1-7, comprising: The deviation comparison module is used to obtain the umbilical cord stem cell staining monitoring parameters of the umbilical cord stem cell activity detection sample, compare them with the expected umbilical cord stem cell staining parameters, and obtain the umbilical cord stem cell staining parameter deviation vector. The confidence analysis module is used to collect a first set of umbilical cord stem cell activity detection samples, perform central value assessment, and obtain the confidence interval of umbilical cord stem cell activity value, constrained by the umbilical cord stem cell staining parameter deviation vector, the umbilical cord stem cell staining expected parameters, and the umbilical cord stem cell collection conditions. The umbilical cord stem cell activity value is characterized by the proportion of live cells. An anomaly identification module is used to identify abnormal quality test data for umbilical cord stem cell activity test values ​​when the umbilical cord stem cell activity test value does not fall within the confidence interval of the umbilical cord stem cell activity value. The normal identification module is used to identify the umbilical cord stem cell activity detection value as normal quality detection data when the umbilical cord stem cell activity detection value falls within the confidence interval of the umbilical cord stem cell activity value.

Images