Sperm library management system and method based on data sharing and storage medium

Abstract

The invention discloses a sperm library management system and method based on data sharing and a storage medium, belongs to the technical field of data sharing, and solves the problems that an existing sperm library management platform cannot comprehensively evaluate sperm demand information based on user information and cannot optimally distribute sperm supply and sperm use demands. The management system is composed of a data acquisition end, a priority determination module, a precise distribution module and an interaction database. In the embodiment of the invention, the priority determination module and the data acquisition end are arranged, and the data acquisition end can acquire the sperm associated information from at least one group of sub-databases and perform normalization processing on the sperm associated information, so that the data identification capability and the processing efficiency of the priority determination module are improved; and the priority determination module can comprehensively evaluate sperm demand information based on a priority scheduling algorithm and a fuzzy clustering algorithm, so that the data sharing capability of the sperm library is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of data sharing, and in particular relates to a sperm bank management system, method and storage medium based on data sharing. Background Art

[0002] Sperm database refers to the information used to store and manage its stock sperm to meet customer needs. These databases usually contain detailed parameters of sperm, health information of donors, genetic background, etc., and the data from different data sources are integrated so that different systems can share and interact with each other to achieve data consistency and uniformity. This helps to conduct in-depth analysis and mining of large amounts of data. By sharing databases, sperm donors and demanders can be matched more effectively, reducing the backlog and waste of sperm inventory. For example, some sperm banks may have an oversupply of certain types of sperm, while other types of sperm are relatively scarce. After sharing, they can be reasonably allocated according to demand to maximize the utilization of resources.

[0003] Chinese patent CN112164449A discloses a sperm bank management platform based on data sharing, including: a login module; a consultation and reservation auxiliary module, which is used to generate sperm donation reservation information and sperm collection room reservation information according to user input; a database, which is used to associate and store user information and role information; and is used to associate and store sperm collection room information and sperm collection room opening information; a system authority management module, which is used to allocate system permissions corresponding to each role information for users whose role information is administrator; it also includes a QR code and an electronic lock installed on the sperm collection room door and corresponding to the sperm collection room one by one, and a code scanning and unlocking module. However, the existing sperm bank management platform cannot comprehensively evaluate sperm demand information based on user information, nor can it optimize the allocation of sperm supply and sperm use needs. In response to the above problems, we propose a sperm bank management system, method and storage medium based on data sharing. Summary of the invention

[0004] The purpose of the present invention is to address the deficiencies of the prior art and provide a sperm bank management system, method and storage medium based on data sharing, which solves the problem that the existing sperm bank management platform cannot comprehensively evaluate sperm demand information based on user information, nor can it optimize the allocation of sperm supply and sperm use demand.

[0005] The existing sperm bank management platform cannot comprehensively evaluate sperm demand information based on user information, nor can it optimize the allocation of sperm supply and sperm use. In response to the above problems, we propose a sperm bank management system, method and storage medium based on data sharing. In short, the sperm bank management system based on data sharing consists of a data acquisition end, a priority determination module, a sperm supply allocation module, an interactive database and an early warning trigger module. When working, the data acquisition end first obtains sperm-related information from the sub-database and normalizes the sperm-related information. Then, the priority determination module assigns priority to the sperm demand information based on the priority scheduling algorithm, and combines the fuzzy clustering algorithm to cluster and evaluate the sperm quality value of the sperm demand information and the sperm parameter information, and outputs at least one group of cluster association clusters. The sperm supply allocation module identifies the corresponding sperm demand information and sperm parameter information in the cluster association cluster, and pushes the shared sperm supply instruction to the data acquisition end based on the sperm demand information and sperm parameter information. In the embodiment of the present invention, a priority determination module and a data acquisition terminal are provided. The data acquisition terminal can collect and obtain sperm-related information from at least one group of sub-databases, and normalize the sperm-related information, thereby improving the data recognition capability and processing efficiency of the priority determination module. The priority determination module can comprehensively evaluate the sperm demand information based on the priority scheduling algorithm and the fuzzy clustering algorithm, thereby optimizing the allocation of sperm supply and sperm use needs through sperm demand information and sperm parameter information, thereby improving the data sharing capability of the sperm bank, and overcoming the problem that the existing sperm bank management platform cannot comprehensively evaluate the sperm demand information based on user information, nor can it optimize the allocation of sperm supply and sperm use needs.

[0006] The present invention is implemented in this way: a sperm bank management system based on data sharing, the sperm bank management system based on data sharing comprises:

[0007] The data acquisition terminal is used to obtain sperm-related information and normalize the sperm-related information, wherein the sperm-related information includes sperm parameter information of sperm donation volunteers, sperm demand information, and sperm information of the sub-database;

[0008] The priority determination module loads and identifies sperm-related information, assigns priority to sperm demand information based on a priority scheduling algorithm, and performs cluster evaluation and analysis on the priority of sperm demand information and sperm quality value of sperm parameter information using a fuzzy clustering algorithm, and outputs at least one set of cluster association clusters;

[0009] The sperm supply allocation module obtains at least one group of cluster association clusters, identifies the corresponding sperm demand information and sperm parameter information in the cluster association clusters, and pushes the shared sperm supply instruction to the data acquisition end based on the sperm demand information and sperm parameter information.

[0010] An interactive database for storing sperm-related information, the interactive database includes at least one group of sub-databases, and interactively shares information on stored sperm managed by the database with at least one group of sub-databases, and

[0011] The early warning triggering module responds to at least one set of sperm demand information, traverses at least one set of sub-databases in combination with the sperm demand information, and triggers an inventory early warning instruction based on information on inventory sperm managed by the sub-databases.

[0012] Preferably, the data acquisition terminal includes:

[0013] An information input unit is used to collect sperm parameter information and sperm demand information of sperm donation volunteers;

[0014] An interactive transmission unit, used for interactively collecting sperm information from the sub-database;

[0015] A normalization unit is connected to the information input unit and the interactive transmission unit for normalization of sperm-related information;

[0016] The data uploading unit loads the normalized sperm-related information and uploads the sperm-related information to the priority determination module and the interactive database.

[0017] Preferably, the method for normalizing sperm-related information specifically includes:

[0018] Load sperm-related information and process missing values ​​and abnormal values ​​of sperm-related information;

[0019] Based on Kalman filtering and graph neural network, sperm-related information is processed to obtain parameter feature vectors, demand feature vectors, and sperm image feature vectors.

[0020] The parameter feature vector, the requirement feature vector and the sperm image feature vector are loaded, the parameter feature vector, the requirement feature vector and the sperm image feature vector are spliced ​​into a feature matrix, and the obtained multiple feature matrices are determined as a correlation information feature set.

[0021] Preferably, the priority determination module comprises:

[0022] A priority calculation unit, used to traverse sperm-related information and assign priority to sperm demand information based on a priority scheduling algorithm;

[0023] Among them, the method of assigning priority to sperm demand information based on the priority scheduling algorithm includes:

[0024] Based on the Monte Carlo algorithm, the age characteristics, blood type characteristics, diversity characteristics, and urgency characteristics in the sperm demand information are extracted, and the age characteristics, blood type characteristics, diversity characteristics, and urgency characteristics are weighted for dimensionality reduction, and the demand dimensionality reduction set is output;

[0025] Among them, the required dimension reduction set is expressed as:

[0026]

[0027]

[0028] Among them, x i is the output requirement dimensionality reduction set, x T represents the dimension reduction input representation of sperm demand information, θ i is the initial weight of sperm-related information, is the initial weight mean of age characteristics, blood type characteristics, diversity characteristics, and urgency characteristics, K represents the type of sperm demand information, and w T represents the sperm demand information matrix, m is the sperm demand information dimension, λ is the weighting coefficient, b T represents the bias vector;

[0029] Load the demand dimension reduction set and perform feature fusion on the demand dimension reduction set based on the sparse kernel reduced rank regression model;

[0030] Combine the priority scheduling algorithm to give priority to the demand dimension reduction set, and output the priority of the demand dimension reduction set;

[0031]

[0032] Among them, x(θ,i) represents the priority of the required dimension reduction set, w(x) is the fusion output result of the sparse kernel reduced rank regression model, and g is the coupling coefficient of the sparse kernel reduced rank regression model. represents the mean of the demand dimension reduction set, α is the priority scheduling coefficient of the priority scheduling algorithm;

[0033] A sperm evaluation unit, used for identifying sperm-related information and determining a sperm quality value of sperm parameter information based on the sperm-related information;

[0034] The associated cluster determination unit is used to combine the fuzzy clustering algorithm to cluster the sperm quality value of the sperm demand information and the sperm parameter information to evaluate and analyze the sperm quality value, and output at least one group of cluster associated clusters.

[0035] Preferably, the method for determining the sperm quality value of sperm parameter information based on sperm association information specifically comprises:

[0036] Load sperm-related information and extract sperm parameter information from the sperm-related information;

[0037] Acquire sperm parameter information, perform statistical analysis on sperm characteristics in the sperm parameter information, and obtain at least one set of parameter statistical values;

[0038] Load parameter statistics, and calculate the correlation coefficient between parameter statistics and sperm quality parameters by using the association algorithm;

[0039] The parameter correlation coefficient is expressed as:

[0040]

[0041] Among them, c l represents the parameter correlation coefficient, l represents the type of sperm parameter, β 0 is the initial weight of sperm parameters, c(y), are parameter statistics and statistical means respectively;

[0042] The parameter statistics are screened based on a preset correlation coefficient threshold to obtain the parameter statistics that affect the sperm quality value and the parameter correlation coefficient corresponding to the parameter statistics;

[0043] The Bayesian formula was used to calculate the posterior probability of parameter statistics and parameter correlation coefficients, and the posterior probability was used as the sperm quality value of sperm parameter information.

[0044] Preferably, the method for clustering and evaluating the sperm quality value of the sperm requirement information and sperm parameter information in combination with the fuzzy clustering algorithm specifically includes:

[0045] Obtain the priority of sperm demand information and sperm quality value;

[0046] Determine at least one set of cluster centers composed of the priority of the demand information based on a fuzzy clustering algorithm;

[0047] Calculate the membership degree between the sperm quality value and the cluster center, and select the sperm quality value with the maximum membership degree as the cluster center associated with the sperm quality value;

[0048] The priorities of sperm demand information and sperm quality values ​​corresponding to the cluster centers are integrated as cluster association clusters, and at least one group of cluster association clusters is output.

[0049] Preferably, the semen supply distribution module specifically comprises:

[0050] An associated cluster identification unit, used to obtain at least one group of cluster associated clusters, and identify the corresponding sperm demand information and sperm parameter information in the cluster associated clusters;

[0051] A sperm supply allocation unit generates a shared sperm supply instruction based on sperm demand information and sperm parameter information;

[0052] The shared push unit is used to load the shared sperm supply instruction and push the shared sperm supply instruction to the data acquisition end.

[0053] On the other hand, the present invention also provides a sperm bank management method based on data sharing, and the sperm bank management method based on data sharing specifically includes:

[0054] Acquire sperm-related information and normalize the sperm-related information;

[0055] In response to at least one set of sperm demand information, traverse at least one set of sub-databases in combination with the sperm demand information, and determine whether to trigger an inventory warning instruction based on an inventory threshold;

[0056] If the information of the stored sperm is lower than the preset inventory threshold, the information of the stored sperm managed by the sub-database triggers the inventory warning instruction;

[0057] If the information of the stored sperm is not less than the preset inventory threshold, the sperm-related information is loaded and identified, the sperm demand information is given priority based on the priority scheduling algorithm, and the priority of the sperm demand information and the sperm quality value of the sperm parameter information are clustered and evaluated and analyzed by combining the fuzzy clustering algorithm, and at least one group of cluster association clusters is output;

[0058] At least one group of cluster association clusters is obtained, sperm demand information and sperm parameter information corresponding to the cluster association clusters are identified, and a shared sperm supply instruction is pushed to a data acquisition end based on the sperm demand information and sperm parameter information.

[0059] A computer-readable storage medium stores computer program instructions, which implement the sperm bank management method based on data sharing when executed.

[0060] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0061] In the embodiment of the present invention, a priority determination module and a data acquisition terminal are provided. The data acquisition terminal can collect and obtain sperm-related information from at least one group of sub-databases, and normalize the sperm-related information, thereby improving the data recognition capability and processing efficiency of the priority determination module. The priority determination module can comprehensively evaluate the sperm demand information based on the priority scheduling algorithm and the fuzzy clustering algorithm, thereby optimizing the allocation of sperm supply and sperm use needs through sperm demand information and sperm parameter information, thereby improving the data sharing capability of the sperm bank, and overcoming the problem that the existing sperm bank management platform cannot comprehensively evaluate the sperm demand information based on user information, nor can it optimize the allocation of sperm supply and sperm use needs.

[0062] In an embodiment of the present invention, sperm-related information is normalized to convert data from different sources to the same scale or range, which facilitates the integration and unified management of these data, providing a basis for subsequent analysis and research. At the same time, normalization combined with Kalman filtering and graph neural network processing can also enable data to be compared on the same scale, thereby improving the accuracy and reliability of the evaluation.

[0063] In an embodiment of the present invention, sperm demand information is given priority based on a priority scheduling algorithm and a sparse kernel reduced rank regression model. The sparse kernel reduced rank regression model can perform feature selection while reducing the dimension, automatically screen out the features that contribute most to the prediction task, and remove redundant and noise features. This allows the sperm demand information priority to integrate multiple features such as age, blood type, diversity, and urgency, and can more accurately predict sperm demand.

[0064] In the embodiment of the present invention, the parameter statistics and the parameter correlation coefficient of sperm quality are calculated by combining the association algorithm, the posterior probability of the parameter statistics and the parameter correlation coefficient is calculated using the Bayesian formula, and the posterior probability is used as the sperm quality value. This can solve the problem that the prior probability may not be able to fully and accurately reflect the individual's condition. By calculating the posterior probability through the Bayesian formula, the prior probability can be adjusted according to the specific observation data of each volunteer, so as to better adapt to individual differences and provide each volunteer with a personalized sperm quality assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Figure 1 It is a structural schematic diagram of the sperm bank management system based on data sharing provided by the present invention.

[0066] Figure 2 A schematic diagram of the implementation process of the method for normalizing sperm-related information is shown.

[0067] Figure 3 A schematic diagram of the implementation process of a method for assigning priority to sperm demand information based on a priority scheduling algorithm is shown.

[0068] Figure 4 A schematic diagram of a method for determining a sperm quality value based on sperm-related information is shown.

[0069] Figure 5 The schematic diagram of the implementation process of the sperm quality value clustering evaluation and analysis method combining the fuzzy clustering algorithm with the priority of sperm demand information and sperm parameter information is shown.

[0070] Figure 6 A schematic diagram of the implementation process of the sperm bank management method based on data sharing is shown. DETAILED DESCRIPTION

[0071] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of this application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of this application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0072] The existing sperm bank management platform cannot comprehensively evaluate sperm demand information based on user information, nor can it optimize the allocation of sperm supply and sperm use. In response to the above problems, we propose a sperm bank management system, method and storage medium based on data sharing. In short, the sperm bank management system based on data sharing consists of a data acquisition terminal 100, a priority determination module 200, a sperm supply allocation module 300, an interactive database 400 and an early warning trigger module 500. When working, the data acquisition terminal 100 first obtains sperm-related information from the sub-database 410 and normalizes the sperm-related information. Then, the priority determination module 200 assigns priority to the sperm demand information based on the priority scheduling algorithm, combines the fuzzy clustering algorithm to cluster and evaluate the sperm quality value of the sperm demand information and the sperm parameter information, and outputs at least one group of cluster association clusters. The sperm supply allocation module 300 identifies the corresponding sperm demand information and sperm parameter information in the cluster association cluster, and pushes the shared sperm supply instruction to the data acquisition terminal 100 based on the sperm demand information and sperm parameter information. In the embodiment of the present invention, a priority determination module 200 and a data acquisition terminal 100 are provided. The data acquisition terminal 100 can collect and obtain sperm-related information from at least one group of sub-databases 410, and normalize the sperm-related information, thereby improving the data recognition capability and processing efficiency of the priority determination module 200. The priority determination module 200 can comprehensively evaluate the sperm demand information based on the priority scheduling algorithm and the fuzzy clustering algorithm, thereby optimizing the allocation of sperm supply and sperm use needs through sperm demand information and sperm parameter information, thereby improving the data sharing capability of the sperm bank, and overcoming the problem that the existing sperm bank management platform cannot comprehensively evaluate the sperm demand information based on user information, nor can it optimize the allocation of sperm supply and sperm use needs.

[0073] The embodiment of the present invention provides a sperm bank management system based on data sharing. Figure 1 A schematic diagram of a sperm bank management system based on data sharing is shown, wherein the sperm bank management system based on data sharing specifically includes:

[0074] The data acquisition terminal 100 is used to acquire sperm-related information and normalize the sperm-related information, wherein the sperm-related information includes sperm parameter information of sperm donation volunteers, sperm demand information, and sperm information of the sub-database 410;

[0075] In this embodiment, the data acquisition terminal 100 is communicatively connected with the sub-database 410 of the interactive database 400, and the data acquisition terminal 100 can obtain data including but not limited to sperm parameter information of sperm donation volunteers, sperm demand information, and sperm information of the sub-database 410 from the sub-database, thereby realizing data interactive sharing.

[0076] The priority determination module 200 loads and identifies sperm-related information, assigns priority to sperm demand information based on a priority scheduling algorithm, and clusters and evaluates the sperm quality value of sperm demand information and sperm parameter information using a fuzzy clustering algorithm to output at least one set of cluster association clusters;

[0077] The sperm supply allocation module 300 obtains at least one group of cluster association clusters, identifies the corresponding sperm demand information and sperm parameter information in the cluster association clusters, and pushes the shared sperm supply instruction to the data acquisition terminal 100 based on the sperm demand information and sperm parameter information.

[0078] An interactive database 400 is used to store sperm-related information. The interactive database 400 includes at least one group of sub-databases 410, and interactively shares the information of the stored sperm managed by the database with at least one group of sub-databases 410, and

[0079] The warning triggering module 500 responds to at least one set of sperm demand information, traverses at least one set of sub-databases 410 in combination with the sperm demand information, and triggers an inventory warning instruction based on the information of the inventory sperm managed by the sub-database 410.

[0080] The interactive database 400 is an Oracle database, which has the characteristics of strong portability, high security, and excellent performance. The Oracle database is collected from a variety of semantic knowledge base products such as DBpedia, Yago, MusicBrainz, and DrugBank, and also provides users with more learning opportunities and more practical resources. The interactive database 400 has multiple knowledge graphs and can integrate sub-databases 410 with associated external relationships.

[0081] In this embodiment, the data acquisition terminal 100, the priority determination module 200, the sperm allocation module 300, the interactive database 400 and the early warning trigger module 500 can be connected by 5G, Bluetooth or local area network communication, and the interactive database 400 is connected to at least one group of sub-databases 410 in a one-to-n manner. The sub-database 410 is used to store the number of sperm stored in various institutions and hospitals, inventory information, and freezing information. The sub-database 410 is also associated with sperm demand information, and the sperm demand information includes the demander's blood type, age, race, ethnicity, genetic background, and urgency of the demand.

[0082] During operation, the data acquisition terminal 100 first obtains sperm-related information from the sub-database 410 and normalizes the sperm-related information. Then, the priority determination module 200 assigns priority to the sperm demand information based on the priority scheduling algorithm, and combines the fuzzy clustering algorithm to cluster and evaluate the sperm quality value of the sperm demand information and the sperm parameter information, and outputs at least one group of cluster-related clusters. The sperm supply allocation module 300 identifies the corresponding sperm demand information and sperm parameter information in the cluster-related clusters, and pushes the shared sperm supply instruction to the data acquisition terminal 100 based on the sperm demand information and sperm parameter information.

[0083] In the embodiment of the present invention, a priority determination module 200 and a data acquisition terminal 100 are provided. The data acquisition terminal 100 can collect and obtain sperm-related information from at least one group of sub-databases 410, and normalize the sperm-related information, thereby improving the data recognition capability and processing efficiency of the priority determination module 200. The priority determination module 200 can comprehensively evaluate the sperm demand information based on the priority scheduling algorithm and the fuzzy clustering algorithm, thereby optimizing the allocation of sperm supply and sperm use needs through sperm demand information and sperm parameter information, thereby improving the data sharing capability of the sperm bank, and overcoming the problem that the existing sperm bank management platform cannot comprehensively evaluate the sperm demand information based on user information, nor can it optimize the allocation of sperm supply and sperm use needs.

[0084] In this embodiment, the data acquisition terminal 100 includes:

[0085] The information input unit 110 is used to collect sperm parameter information and sperm demand information of sperm donation volunteers;

[0086] An interactive transmission unit 120 is used for interactively collecting sperm information from the sub-database 410;

[0087] The normalization unit 130 is connected to the information input unit 110 and the interactive transmission unit 120 for normalization of sperm-related information;

[0088] The data uploading unit 140 loads the normalized sperm-related information and uploads the sperm-related information to the priority determination module 200 and the interactive database 400 .

[0089] In an embodiment of the present invention, the information entry unit 110, the interactive transmission unit 120, the normalization unit 130, and the data upload unit 140 are electrically or Bluetooth connected, and the information entry unit 110 supports manual and automatic information entry, while the interactive transmission unit 120 can establish a communication connection with the sub-database 410 and obtain sperm information from the sub-database 410 using hash encryption.

[0090] The embodiment of the present invention provides a method for normalizing sperm-related information. Figure 2 The schematic diagram of the implementation process of the method for normalizing sperm-related information is shown. The method for normalizing sperm-related information specifically includes:

[0091] Step S101, loading sperm-related information, and processing missing values ​​and abnormal values ​​of the sperm-related information;

[0092] In this embodiment, when processing missing values ​​and outliers in sperm-related information, mean filling, Lagrange difference, and deletion methods can be used to process missing values, while outliers can be processed by interquartile range, box plot, and cluster analysis methods.

[0093] Step S102, processing sperm-related information based on Kalman filtering and graph neural network to obtain parameter feature vectors, demand feature vectors, and sperm image feature vectors;

[0094] Step S103, loading the parameter feature vector, the requirement feature vector and the sperm image feature vector, splicing the parameter feature vector, the requirement feature vector and the sperm image feature vector into a feature matrix, and determining the obtained multiple feature matrices as a correlation information feature set.

[0095] It should be noted that before concatenating feature vectors, a feature selection algorithm (such as recursive feature elimination, principal component analysis, etc.) is used to screen each feature vector, remove unimportant features, and then concatenate them according to the set weights. In this way, a weighted feature matrix can be obtained.

[0096] In an embodiment of the present invention, sperm-related information is normalized to convert data from different sources to the same scale or range, which facilitates the integration and unified management of these data, providing a basis for subsequent analysis and research. At the same time, normalization combined with Kalman filtering and graph neural network processing can also enable data to be compared on the same scale, thereby improving the accuracy and reliability of the evaluation.

[0097] In this embodiment, the priority determination module 200 includes:

[0098] The priority calculation unit 210 is used to traverse the sperm-related information and assign a priority to the sperm demand information based on a priority scheduling algorithm.

[0099] A sperm evaluation unit 220, configured to identify sperm-related information and determine a sperm quality value of sperm parameter information based on the sperm-related information;

[0100] The associated cluster determination unit 230 is used to perform cluster evaluation and analysis on the priority of sperm demand information and sperm quality value of sperm parameter information in combination with a fuzzy clustering algorithm, and output at least one group of cluster associated clusters.

[0101] It should be noted that the cluster association cluster is a cluster group that combines the priority of sperm demand information, the moderate age of sperm quality value, the short period of infertility, the spouse with a reproductive history, the medium sperm concentration, the good motility, and the high proportion of normal morphological sperm. The cluster association cluster refers to the combination of sperm characteristics of different categories obtained by clustering analysis of sperm-related data. In the management of the sperm bank, sperm can be classified, stored and managed according to the cluster association cluster to improve the utilization rate of sperm and the matching success rate.

[0102] The embodiment of the present invention provides a method for assigning priority to sperm demand information based on a priority scheduling algorithm. Figure 3 The schematic diagram of the implementation process of the method for assigning priority to sperm demand information based on the priority scheduling algorithm is shown. The method for assigning priority to sperm demand information based on the priority scheduling algorithm specifically includes:

[0103] Step S201, extracting age characteristics, blood type characteristics, diversity characteristics, and urgency characteristics from sperm demand information based on the Monte Carlo algorithm, reducing and weighting the age characteristics, blood type characteristics, diversity characteristics, and urgency characteristics, and outputting a demand reduction set;

[0104] In this embodiment, when extracting the age feature in the sperm demand information, the generated random age data can be statistically analyzed to obtain information such as the demand ratio of each age group, average age, age distribution, etc. For example, it may be found that men aged 30-40 have a higher demand for sperm, or that the age distribution shows a certain skewness.

[0105] Among them, the required dimension reduction set is expressed as:

[0106]

[0107] Among them, x i is the output requirement dimensionality reduction set, x T represents the dimension reduction input representation of sperm demand information, θ i is the initial weight of sperm-related information, is the initial weight mean of age feature, blood type feature, diversity feature, and urgency feature, K represents the type of sperm demand information. In this embodiment, the type of sperm demand information can be 4, w T represents the sperm demand information matrix, m is the sperm demand information dimension, which can be 2-8, λ is the weighting coefficient, which can be 0.1-0.8, b T represents the bias vector;

[0108] Step S202, loading the demand dimension reduction set, and performing feature fusion on the demand dimension reduction set based on a sparse kernel reduced rank regression model;

[0109] Step S203, assigning a priority to the demand dimension reduction set in combination with a priority scheduling algorithm, and outputting the priority of the demand dimension reduction set;

[0110]

[0111] Wherein, x(θ,i) represents the priority of the demand dimension reduction set, w(x) is the fusion output result of the sparse kernel reduced rank regression model, and g is the coupling coefficient of the sparse kernel reduced rank regression model. In this embodiment, the coupling coefficient can be 1-4. represents the mean of the demand dimension reduction set, α is the priority scheduling coefficient of the priority scheduling algorithm, and in this embodiment, the priority scheduling coefficient can be 1.5-2.5.

[0112] In an embodiment of the present invention, sperm demand information is given priority based on a priority scheduling algorithm and a sparse kernel reduced rank regression model. The sparse kernel reduced rank regression model can perform feature selection while reducing the dimension, automatically screen out the features that contribute most to the prediction task, and remove redundant and noise features. This allows the sperm demand information priority to integrate multiple features such as age, blood type, diversity, and urgency, and can more accurately predict sperm demand.

[0113] The embodiment of the present invention provides a method for determining a sperm quality value of sperm parameter information based on sperm associated information. Figure 4 A schematic diagram of a method for determining a sperm quality value of sperm parameter information based on sperm association information is shown. The method for determining a sperm quality value of sperm parameter information based on sperm association information specifically includes:

[0114] Step S301, loading sperm-related information, and extracting sperm parameter information from the sperm-related information;

[0115] Step S302, obtaining sperm parameter information, performing statistical analysis on sperm characteristics in the sperm parameter information, and obtaining at least one set of parameter statistical values;

[0116] It should be noted that sperm characteristics include but are not limited to sperm concentration, sperm motility, sperm morphology, sperm DNA fragmentation rate, sperm survival rate, semen volume, pH, liquefaction time, white blood cell content and other characteristics. Sperm motility refers to the motility of sperm, including fast linear motion (Grade A), slow linear motion (Grade B) and swinging in place (Grade C). The higher the ratio of grade A and grade B sperm, the better the sperm motility, which is more conducive to fertilization with the egg. Generally, the motility of grade A+B sperm is required to be ≥32%. The sperm survival rate refers to the proportion of sperm that survive normally within a certain period of time after ejaculation, which is generally 60-80%. A low survival rate will affect the fertilization ability of sperm.

[0117] Step S303, loading parameter statistics, and calculating the parameter correlation coefficient between the parameter statistics and sperm quality in combination with the association algorithm;

[0118] The parameter correlation coefficient is expressed as:

[0119]

[0120] Among them, c l represents the parameter correlation coefficient, l represents the type of sperm parameter, β 0 is the initial weight of sperm parameters. In this embodiment, the initial weight of sperm parameters is set to 0.1-0.6, c(y), are parameter statistics and statistical means respectively;

[0121] Step S304, screening the parameter statistics based on a preset correlation coefficient threshold to obtain the parameter statistics that have a high impact on sperm quality and the parameter correlation coefficients corresponding to the parameter statistics;

[0122] In this embodiment, the correlation coefficient threshold may be 0.5-0.6.

[0123] Step S305, using the Bayesian formula to calculate the posterior probability of the parameter statistical value and the parameter correlation coefficient, and using the posterior probability as the sperm quality value of the sperm parameter information.

[0124] In the embodiment of the present invention, the parameter statistics and the parameter correlation coefficient of sperm quality are calculated by combining the association algorithm, the posterior probability of the parameter statistics and the parameter correlation coefficient is calculated using the Bayesian formula, and the posterior probability is used as the sperm quality value. This can solve the problem that the prior probability may not be able to fully and accurately reflect the individual's condition. By calculating the posterior probability through the Bayesian formula, the prior probability can be adjusted according to the specific observation data of each volunteer, so as to better adapt to individual differences and provide each volunteer with a personalized sperm quality assessment.

[0125] The embodiment of the present invention provides a method for clustering and evaluating the sperm quality value of sperm demand information and sperm parameter information by combining a fuzzy clustering algorithm. Figure 5 The schematic diagram of the implementation flow of the method for clustering and evaluating the sperm quality value of sperm parameter information and the priority of sperm demand information combined with the fuzzy clustering algorithm is shown. The method for clustering and evaluating the sperm quality value of sperm parameter information and the priority of sperm demand information combined with the fuzzy clustering algorithm specifically includes:

[0126] Step S401, obtaining the priority and sperm quality value of sperm demand information;

[0127] Step S402, determining at least one set of cluster centers composed of the priorities of the demand information based on a fuzzy clustering algorithm;

[0128] Step S403, calculating the membership degree between the sperm quality value and the cluster center, and selecting the sperm quality value with the maximum membership degree as the cluster center associated with the sperm quality value;

[0129] Step S404: Integrate the priorities of sperm demand information and sperm quality values ​​corresponding to the cluster centers as cluster association clusters, and output at least one group of cluster association clusters.

[0130] In the embodiment of the present invention, when at least one set of cluster centers composed of the priority of demand information is determined based on the fuzzy clustering algorithm, the cluster centers represent the combination of demand information of different priorities. For example, the three cluster centers finally obtained may correspond to the demand information characteristics of high priority (patients who urgently need sperm and other treatment methods are not effective), medium priority, and low priority, respectively.

[0131] In this embodiment, the sperm supply distribution module 300 specifically includes:

[0132] The associated cluster identification unit 310 is used to obtain at least one group of cluster associated clusters and identify the sperm demand information and sperm parameter information corresponding to the cluster associated clusters;

[0133] The sperm supply allocation unit 320 generates a shared sperm supply instruction based on sperm demand information and sperm parameter information;

[0134] The shared push unit 330 is used to load the shared sperm supply instruction and push the shared sperm supply instruction to the data acquisition end 100 .

[0135] The shared push unit 330 supports pushing shared sperm supply instructions by SMS push, email push, in-application push, APP / website push, and Aurora push, and the associated cluster identification unit 310, sperm supply allocation unit 320, and shared push unit 330 are interactively transmitted through electricity or Bluetooth.

[0136] The embodiment of the present invention provides a sperm bank management method based on data sharing. Figure 6 The schematic diagram of the implementation process of the sperm bank management method based on data sharing is shown. The sperm bank management method based on data sharing specifically includes:

[0137] Step S10, obtaining sperm-related information and normalizing the sperm-related information;

[0138] Step S20, in response to at least one set of sperm demand information, traverse at least one set of sub-databases 410 in combination with the sperm demand information;

[0139] Step S30, judging whether to trigger an inventory warning instruction based on the inventory threshold;

[0140] Step S40, if the information of the stored sperm is lower than the preset inventory threshold, triggering an inventory warning instruction based on the information of the stored sperm managed by the sub-database 410;

[0141] Step S50, if the information of the stored sperm is not less than the preset inventory threshold, load and identify the sperm-related information, assign priority to the sperm demand information based on the priority scheduling algorithm, combine the fuzzy clustering algorithm to cluster the sperm quality value of the sperm demand information and sperm parameter information, and output at least one group of cluster association clusters;

[0142] Step S60, obtaining at least one group of cluster association clusters, identifying the corresponding sperm demand information and sperm parameter information in the cluster association clusters, and pushing the shared sperm supply instruction to the data acquisition terminal 100 based on the sperm demand information and sperm parameter information.

[0143] On the other hand, an embodiment of the present invention further provides a computer device, which includes a display screen, a memory, a processor, and a computer program, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the sperm bank management method based on data sharing.

[0144] It is understandable that, in the preferred embodiment provided by the present invention, the computer device may also be a notebook computer, a personal digital assistant (PDA), a mobile phone or other device capable of communication.

[0145] On the other hand, an embodiment of the present invention further provides a readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the processor executes the steps of the sperm bank management method based on data sharing.

[0146] Exemplarily, the computer program may be divided into one or more modules, one or more modules are stored in a memory and executed by a processor to complete the present invention. One or more modules may be a series of computer program instruction segments capable of completing specific functions, and the instruction segments are used to describe the execution process of the computer program in a terminal device. For example, the above-mentioned computer program may be divided into units or modules of the sperm bank management system based on data sharing provided by the above-mentioned various system embodiments.

[0147] Those skilled in the art will understand that the description of the terminal device above is merely an example and does not constitute a limitation on the terminal device. The terminal device may include more or fewer components than described above, or a combination of certain components, or different components, for example, input and output devices, network access devices, buses, etc.

[0148] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the terminal device, and uses various interfaces and lines to connect various parts of the entire user terminal.

[0149] The memory can be used to store computer programs and / or modules. The processor can realize various functions of the terminal device by running or executing the computer programs and / or modules stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system and at least one application required for a function; the data storage area can store data created according to the use of a sperm bank management system based on data sharing, etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0150] Finally, it should be noted that the computer-readable storage medium (e.g., memory) herein may be a volatile memory or a nonvolatile memory, or may include both a volatile memory and a nonvolatile memory. As an example and not by way of limitation, a nonvolatile memory may include a read-only memory (ROM), a programmable ROM (PROM), an electrically programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), or a flash memory. A volatile memory may include a random access memory (RAM), which may act as an external cache memory. As an example and not by way of limitation, RAM may be obtained in a variety of forms, such as synchronous RAM (DRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), and direct Rambus RAM (DRRAM). The storage devices of the disclosed aspects are intended to include, but are not limited to, these and other suitable types of memory.

[0151] In summary, the present invention provides a sperm bank management system, method and storage medium based on data sharing. When working, the data acquisition terminal 100 first obtains sperm-related information from the sub-database 410 and normalizes the sperm-related information. Then, the priority determination module 200 assigns priority to the sperm demand information based on the priority scheduling algorithm, and combines the fuzzy clustering algorithm to cluster and evaluate the sperm quality value of the sperm demand information and sperm parameter information, and outputs at least one group of cluster-related clusters. The sperm supply allocation module 300 identifies the corresponding sperm demand information and sperm parameter information in the cluster-related clusters, and pushes the shared sperm supply instruction to the data acquisition terminal 100 based on the sperm demand information and sperm parameter information.

[0152] In the embodiment of the present invention, a priority determination module 200 and a data acquisition terminal 100 are provided. The data acquisition terminal 100 can collect and obtain sperm-related information from at least one group of sub-databases 410, and normalize the sperm-related information, thereby improving the data recognition capability and processing efficiency of the priority determination module 200. The priority determination module 200 can comprehensively evaluate the sperm demand information based on the priority scheduling algorithm and the fuzzy clustering algorithm, thereby optimizing the allocation of sperm supply and sperm use needs through sperm demand information and sperm parameter information, thereby improving the data sharing capability of the sperm bank, and overcoming the problem that the existing sperm bank management platform cannot comprehensively evaluate the sperm demand information based on user information, nor can it optimize the allocation of sperm supply and sperm use needs.

[0153] In an embodiment of the present invention, sperm demand information is given priority based on a priority scheduling algorithm and a sparse kernel reduced rank regression model. The sparse kernel reduced rank regression model can perform feature selection while reducing the dimension, automatically screen out the features that contribute most to the prediction task, and remove redundant and noise features. This allows the sperm demand information priority to integrate multiple features such as age, blood type, diversity, and urgency, and can more accurately predict sperm demand.

[0154] In the embodiment of the present invention, the parameter statistics and the parameter correlation coefficient of sperm quality are calculated by combining the association algorithm, the posterior probability of the parameter statistics and the parameter correlation coefficient is calculated using the Bayesian formula, and the posterior probability is used as the sperm quality value. This can solve the problem that the prior probability may not be able to fully and accurately reflect the individual's condition. By calculating the posterior probability through the Bayesian formula, the prior probability can be adjusted according to the specific observation data of each volunteer, so as to better adapt to individual differences and provide each volunteer with a personalized sperm quality assessment.

[0155] It should be noted that, for the above-mentioned embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the described order of actions, because according to the present invention, some steps may be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0156] In the several embodiments provided in the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the above-mentioned units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection between devices or units can be in the form of telecommunication or other forms.

[0157] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the scope of protection of the invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on these embodiments, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in this field can still combine, add, delete or make other adjustments to the features in the various embodiments of the present invention according to the circumstances without conflict, without making creative work, so as to obtain different other technical solutions that do not deviate from the concept of the present invention in essence, and these technical solutions also belong to the scope of protection of the present invention.

Claims

1. A sperm bank management system based on data sharing, characterized in that: The sperm bank management system based on data sharing includes: The data acquisition terminal is used to obtain sperm-related information and normalize the sperm-related information, wherein the sperm-related information includes sperm parameter information of sperm donation volunteers, sperm demand information, and sperm information of the sub-database; The priority determination module loads and identifies sperm-related information, assigns priority to sperm demand information based on a priority scheduling algorithm, and performs cluster evaluation and analysis on the priority of sperm demand information and sperm quality value of sperm parameter information using a fuzzy clustering algorithm, and outputs at least one set of cluster association clusters; The sperm supply allocation module obtains at least one group of cluster association clusters, identifies the corresponding sperm demand information and sperm parameter information in the cluster association clusters, and pushes the shared sperm supply instruction to the data acquisition end based on the sperm demand information and sperm parameter information.

2. The sperm bank management system based on data sharing according to claim 1, characterized in that: The system further comprises: An interactive database for storing sperm-related information, the interactive database includes at least one group of sub-databases, and interactively shares information on stored sperm managed by the database with at least one group of sub-databases, and The early warning triggering module responds to at least one set of sperm demand information, traverses at least one set of sub-databases in combination with the sperm demand information, and triggers an inventory early warning instruction based on information on inventory sperm managed by the sub-databases.

3. The sperm bank management system based on data sharing as claimed in claim 2, characterized in that: The data acquisition end includes: An information input unit is used to collect sperm parameter information and sperm demand information of sperm donation volunteers; An interactive transmission unit, used for interactively collecting sperm information from the sub-database; A normalization unit is connected to the information input unit and the interactive transmission unit for normalization of sperm-related information; The data uploading unit loads the normalized sperm-related information and uploads the sperm-related information to the priority determination module and the interactive database.

4. The sperm bank management system based on data sharing as claimed in claim 3, characterized in that: The method for normalizing sperm-related information specifically includes: Load sperm-related information and process missing values ​​and abnormal values ​​of sperm-related information; Based on Kalman filtering and graph neural network, sperm-related information is processed to obtain parameter feature vectors, demand feature vectors, and sperm image feature vectors. The parameter feature vector, the requirement feature vector and the sperm image feature vector are loaded, the parameter feature vector, the requirement feature vector and the sperm image feature vector are spliced ​​into a feature matrix, and the obtained multiple feature matrices are determined as a correlation information feature set.

5. The sperm bank management system based on data sharing according to claim 1, characterized in that: The priority determination module comprises: A priority calculation unit, used to traverse sperm-related information and assign priority to sperm demand information based on a priority scheduling algorithm; Among them, the method of assigning priority to sperm demand information based on the priority scheduling algorithm includes: Based on the Monte Carlo algorithm, the age characteristics, blood type characteristics, diversity characteristics, and urgency characteristics in the sperm demand information are extracted, and the age characteristics, blood type characteristics, diversity characteristics, and urgency characteristics are weighted for dimensionality reduction, and the demand dimensionality reduction set is output; Among them, the demand dimension reduction set is expressed as: Among them, x i is the output requirement dimensionality reduction set, x T represents the dimension reduction input representation of sperm demand information, θ i is the initial weight of sperm-related information, is the initial weight mean of age characteristics, blood type characteristics, diversity characteristics, and urgency characteristics, K represents the type of sperm demand information, and w T represents the sperm demand information matrix, m is the sperm demand information dimension, λ is the weighting coefficient, b T represents the bias vector; Load the demand dimension reduction set and perform feature fusion on the demand dimension reduction set based on the sparse kernel reduced rank regression model; Combine the priority scheduling algorithm to give priority to the demand dimension reduction set, and output the priority of the demand dimension reduction set; Among them, x(θ,i) represents the priority of the required dimension reduction set, w(x) is the fusion output result of the sparse kernel reduced rank regression model, and g is the coupling coefficient of the sparse kernel reduced rank regression model. represents the mean of the demand dimension reduction set, α is the priority scheduling coefficient of the priority scheduling algorithm; A sperm evaluation unit, used for identifying sperm-related information and determining a sperm quality value of sperm parameter information based on the sperm-related information; The associated cluster determination unit is used to combine the fuzzy clustering algorithm to cluster the sperm quality value of the sperm demand information and the sperm parameter information to evaluate and analyze the sperm quality value, and output at least one group of cluster associated clusters.

6. The sperm bank management system based on data sharing according to claim 5, characterized in that: The method for determining the sperm quality value of sperm parameter information based on sperm association information specifically includes: Load sperm-related information and extract sperm parameter information from the sperm-related information; Acquire sperm parameter information, perform statistical analysis on sperm characteristics in the sperm parameter information, and obtain at least one set of parameter statistical values; Load parameter statistics, and calculate the correlation coefficient between parameter statistics and sperm quality parameters by using the association algorithm; The parameter correlation coefficient is expressed as: Among them, c l represents the parameter correlation coefficient, l represents the type of sperm parameter, β0 is the initial weight of sperm parameter, c(y), are parameter statistics and statistical means respectively; The parameter statistics are screened based on a preset correlation coefficient threshold to obtain the parameter statistics that affect the sperm quality value and the parameter correlation coefficient corresponding to the parameter statistics; The Bayesian formula was used to calculate the posterior probability of parameter statistics and parameter correlation coefficients, and the posterior probability was used as the sperm quality value of sperm parameter information.

7. The sperm bank management system based on data sharing according to claim 6, characterized in that: The method for clustering and evaluating the sperm quality value of sperm demand information and sperm parameter information by combining a fuzzy clustering algorithm specifically includes: Obtain the priority of sperm demand information and sperm quality value; Determine at least one set of cluster centers composed of the priority of the demand information based on a fuzzy clustering algorithm; Calculate the membership degree between the sperm quality value and the cluster center, and select the sperm quality value with the maximum membership degree as the cluster center associated with the sperm quality value; The priorities of sperm demand information and sperm quality values ​​corresponding to the cluster centers are integrated as cluster association clusters, and at least one group of cluster association clusters is output.

8. The sperm bank management system based on data sharing according to claim 1, characterized in that: The sperm supply distribution module specifically comprises: An associated cluster identification unit, used to obtain at least one group of cluster associated clusters, and identify the corresponding sperm demand information and sperm parameter information in the cluster associated clusters; A sperm supply allocation unit generates a shared sperm supply instruction based on sperm demand information and sperm parameter information; The shared push unit is used to load the shared sperm supply instruction and push the shared sperm supply instruction to the data acquisition end.

9. A sperm bank management method based on data sharing, implemented by the sperm bank management system based on data sharing as claimed in any one of claims 1 to 8, characterized in that: The sperm bank management method based on data sharing specifically includes: Acquire sperm-related information and normalize the sperm-related information; In response to at least one set of sperm demand information, traverse at least one set of sub-databases in combination with the sperm demand information, and determine whether to trigger an inventory warning instruction based on an inventory threshold; If the information of the stored sperm is lower than the preset inventory threshold, the information of the stored sperm managed by the sub-database triggers the inventory warning instruction; If the information of the stored sperm is not less than the preset inventory threshold, the sperm-related information is loaded and identified, the sperm demand information is given priority based on the priority scheduling algorithm, and the priority of the sperm demand information and the sperm quality value of the sperm parameter information are clustered and evaluated and analyzed by combining the fuzzy clustering algorithm, and at least one group of cluster association clusters is output; At least one group of cluster association clusters is obtained, sperm demand information and sperm parameter information corresponding to the cluster association clusters are identified, and a shared sperm supply instruction is pushed to a data acquisition end based on the sperm demand information and sperm parameter information.

10. A computer-readable storage medium, characterized in that: Computer program instructions are stored, and when the computer program instructions are executed, the sperm bank management method based on data sharing as claimed in claim 9 is implemented.

Images