DNA detection data synchronization and classification method based on decision tree model

Abstract

The invention relates to a DNA detection data synchronization and classification method based on a decision tree model, and belongs to the technical field of DNA data classification processing. And finally, generating a first synchronization strategy or a second synchronization strategy according to the file size information of the detection data after DNA classification and the real-time network communication data of the communication channel, and performing data synchronization according to the first synchronization strategy or the second synchronization strategy. According to the method, the Bayesian network is fused in the decision tree model, the situation that the decision tree model is not high in precision in the DNA detection data classification process can be optimized, the data transmission situation of the DNA detection data in the data synchronization process can be optimized, the DNA detection data can be synchronized to a medical platform in time, and the accuracy of the DNA detection data is improved. And the query efficiency of the DNA detection data is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of DNA data classification, and in particular to a DNA detection data synchronization and classification method based on a decision tree model. Background Art

[0002] Gene is a functional fragment on the DNA molecule, the basic unit of genetic information, and the most basic factor that determines all biological species; Gene determines the birth, aging, illness and death of a person, is the cause of health, beauty and longevity, and is the manipulator and regulator of life. Genetic testing is a technology that detects DNA through blood, other body fluids, or cells. Genetic testing is a technology that detects DNA through blood, other body fluids or cells. It takes oral mucosal cells or other tissue cells shed by the person being tested, amplifies their genetic information, and then uses specific equipment to detect the DNA molecular information in the cells of the person being tested, predicts the risk of the body developing diseases, and analyzes the various genetic conditions it contains, so that people can understand their own genetic information, and thus avoid or delay the occurrence of diseases by improving their living environment and living habits.

[0003] Genetic testing can be used to diagnose diseases and predict disease risks. Disease diagnosis is to use genetic testing technology to detect mutated genes that cause genetic diseases. Currently, the most widely used genetic testing is the detection of genetic diseases in newborns, the diagnosis of genetic diseases, and the auxiliary diagnosis of certain common diseases. Currently, there are more than 1,000 genetic diseases that can be diagnosed through genetic testing technology. Predictive genetic testing is to use genetic testing technology to discover the risk of disease before the disease occurs, and to prevent or take effective intervention measures in advance. Currently, more than 20 diseases can be predicted by genetic testing methods. During the test, the genes of the subject are first extracted from the blood or other cells. Then, primers that can identify genes that may have mutations and PCR technology are used to copy these genes many times, and mutant gene probe methods with special markers, enzyme cutting methods, gene sequence detection methods, etc. are used to determine whether these genes have mutations or sensitive genotypes. However, after genetic testing, most of the genetic testing data are massive data, which needs to be classified and processed to identify and classify abnormal data. The decision tree model algorithm is one of the classification algorithms. However, the problems caused by the model in real-world applications are endless. For example, the decision tree algorithm has low classification accuracy. How to improve the classification accuracy of the decision tree algorithm is a crucial aspect in the field of machine learning. Summary of the invention

[0004] The present invention overcomes the deficiencies of the prior art and provides a DNA detection data synchronization and classification method based on a decision tree model.

[0005] To achieve the above object, the technical solution adopted by the present invention is: The first aspect of the present invention provides a DNA detection data synchronization and classification method based on a decision tree model, which is characterized by specifically comprising: Acquire DNA test data, construct a decision tree model, input the DNA test data into the decision tree model for initial classification, and fuse the Bayesian network; The classification process of DNA detection data is monitored through the Bayesian network, and each leaf node is observed and processed to obtain the detection data after DNA classification and the real-time network communication data of each communication channel; Preliminarily selecting a number of candidate communication channels according to the real-time network communication data of each communication channel, and obtaining file size information of the detection data after DNA classification and the real-time network communication data of the candidate communication channels; A first synchronization strategy or a second synchronization strategy is generated according to the file size information of the detection data after the DNA classification and the real-time network communication data of the communication channel, and data synchronization is performed according to the first synchronization strategy or the second synchronization strategy.

[0006] Furthermore, in the DNA detection data synchronization and classification method based on the decision tree model, DNA detection data is obtained, a decision tree model is constructed, the DNA detection data is input into the decision tree model for initialization classification, and a Bayesian network is integrated, specifically: Acquire DNA test data, build a decision tree model, build a sample data set according to the DNA test data, use the sample data set as the root node in the decision tree model, and set a splitting standard threshold; Calculating the Euclidean distance value between each sample data set in the root node, and combining the sample data whose Euclidean distance value is not greater than the splitting standard threshold into one data set to form a leaf node; The sample data whose Euclidean distance value is greater than the splitting standard threshold value is separated into another data set to form leaf nodes. Through continuous splitting, no new leaf nodes are generated in the decision tree model, and the Bayesian network is integrated.

[0007] Furthermore, in the DNA test data synchronization and classification method based on the decision tree model, the classification process of the DNA test data is monitored through the Bayesian network, and each leaf node is observed and processed to obtain the test data after DNA classification, specifically: Obtaining the leaf nodes after initialization and classification, and taking each sample data in the leaf nodes after initialization and classification as an observation node, and performing sample search with one observation node in each leaf node after initialization and classification; Constructing an association relationship between observation nodes, connecting the current observation node with another observation node based on the association relationship between the observation nodes, constructing a directed acyclic graph, and calculating the joint probability value between the observation nodes in the directed acyclic graph; When the joint probability value between the observation nodes in the directed acyclic graph is greater than the joint probability threshold, the current observation node and another observation node are maintained unchanged in the current leaf node; When the joint probability value between the observation nodes in the directed acyclic graph is not greater than the joint probability threshold, the current observation node and another observation node are separated into different leaf nodes until the observation of all the initialized classified leaf nodes is completed, and the final DNA detection data is output and output as the detection data after DNA classification.

[0008] Furthermore, in the DNA detection data synchronization and classification method based on the decision tree model, a number of candidate communication channels are initially selected according to the real-time network communication data of each communication channel, specifically: Setting a network communication data threshold, and determining whether the real-time network communication data of each communication channel is greater than the network communication data threshold; When the real-time network communication data is greater than the network communication data threshold, the communication channel whose real-time network communication data is greater than the network communication data threshold is used as a candidate communication channel; When the real-time network communication data is greater than the network communication data threshold, the communication channel whose real-time network communication data is greater than the network communication data threshold is used as a non-candidate communication channel.

[0009] Further, in the DNA detection data synchronization and classification method based on the decision tree model, the first synchronization strategy or the second synchronization strategy is generated according to the file size information of the detection data after the DNA classification and the real-time network communication data of the candidate communication channel, specifically including: Setting a data transmission requirement time, and calculating the required rate information of the detection data after DNA classification when performing data transmission according to the file size information of the detection data after DNA classification and the data transmission requirement time; Determine whether the required rate information of the detection data after the DNA classification during data transmission is greater than the real-time network communication data of the communication channel; When there is at least one communication channel whose required rate information of the detection data after DNA classification is not greater than the real-time network communication data of the communication channel during data transmission, the communication channel with the smallest real-time network communication data is selected as the final communication channel, a first synchronization strategy is generated, and the first synchronization strategy is output; When there is no communication channel in which the required rate information of the detection data after DNA classification during data transmission is greater than the real-time network communication data of the communication channel, each candidate communication channel is used as a communication transmission channel, a second synchronization strategy is generated, and the second synchronization strategy is output.

[0010] Furthermore, in the DNA detection data synchronization and classification method based on the decision tree model, data synchronization is performed according to the first synchronization strategy or the second synchronization strategy, specifically including: When the first synchronization strategy is used, the detection data after DNA classification is continuously transmitted according to the first synchronization strategy, and the real-time network communication data of the current communication channel is monitored; When the first synchronization strategy is used, the file size information of the detection data after DNA classification is obtained, and the file size information of the detection data after DNA classification is divided into a plurality of new file data for transmission, and the size information of each new file data is initialized; Calculating the required rate information of each new file data according to the size information of each new file data and the required data transmission time, and initializing several candidate data transmission channels for data transmission; Allocate candidate data transmission channels one by one to perform data transmission on each new file data, and determine whether the real-time network communication data of each candidate data transmission channel is greater than the required rate information of the new file data; When the real-time network communication data of each candidate data transmission channel is greater than the required rate information of the new file data, data synchronization is performed according to the new file data; When the real-time network communication data of each candidate data transmission channel is not all larger than the required rate information of the new file data, the size information of each new file data is readjusted until all are larger than the required rate information of the new file data.

[0011] The second aspect of the present invention provides a DNA detection data synchronization and classification system based on a decision tree model, comprising a memory and a processor, wherein the memory includes a DNA detection data synchronization and classification method program based on a decision tree model, and when the DNA detection data synchronization and classification method program based on a decision tree model is executed by the processor, any step of the DNA detection data synchronization and classification method based on the decision tree model is implemented.

[0012] The third aspect of the present invention provides a computer-readable storage medium, including a DNA detection data synchronization and classification method program based on a decision tree model. When the DNA detection data synchronization and classification method program based on a decision tree model is executed by a processor, any step of the DNA detection data synchronization and classification method based on a decision tree model is implemented.

[0013] The present invention solves the defects existing in the background technology and has the following beneficial effects: The present invention obtains DNA detection data, constructs a decision tree model, inputs the DNA detection data into the decision tree model for initialization classification, and fuses the Bayesian network, and then monitors the process of DNA detection data during classification through the Bayesian network, and observes and processes each leaf node, obtains the detection data after DNA classification, obtains the real-time network communication data of each communication channel, thereby preliminarily selecting a number of candidate communication channels according to the real-time network communication data of each communication channel, and obtains the file size information of the detection data after DNA classification and the real-time network communication data of the communication channel, and finally generates the first synchronization strategy or the second synchronization strategy according to the file size information of the detection data after DNA classification and the real-time network communication data of the communication channel, and performs data synchronization according to the first synchronization strategy or the second synchronization strategy. The present invention can optimize the situation that the accuracy of the decision tree model is not high in the process of classifying DNA detection data by fusing the Bayesian network in the decision tree model, and secondly, the present invention can also optimize the data transmission of DNA detection data during data synchronization, so that the DNA detection data can be synchronized to the medical platform in time, and the query efficiency of DNA detection data is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, drawings of other embodiments can be obtained based on these drawings without paying creative work.

[0015] Figure 1 The overall flow chart of the DNA detection data synchronization and classification method based on the decision tree model is shown; Figure 2 A partial method flow chart of a DNA detection data synchronization and classification method based on a decision tree model is shown; Figure 3 The system block diagram of the DNA detection data synchronization and classification system based on the decision tree model is shown. DETAILED DESCRIPTION

[0016] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0017] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0018] like Figure 1 As shown, the first aspect of the present invention provides a DNA detection data synchronization and classification method based on a decision tree model, which is characterized by specifically comprising: S102: Acquire DNA test data, build a decision tree model, input the DNA test data into the decision tree model for initial classification, and integrate the Bayesian network; S104: monitoring the classification process of DNA detection data through the Bayesian network, observing and processing each leaf node, obtaining the detection data after DNA classification, and obtaining the real-time network communication data of each communication channel; S106: Preliminarily selecting a number of candidate communication channels according to the real-time network communication data of each communication channel, and obtaining file size information of the detection data after DNA classification and the real-time network communication data of the candidate communication channels; S108: Generate a first synchronization strategy or a second synchronization strategy according to the file size information of the detection data after DNA classification and the real-time network communication data of the communication channel, and perform data synchronization according to the first synchronization strategy or the second synchronization strategy.

[0019] It should be noted that the present invention can optimize the situation where the accuracy of the decision tree model is not high in the process of classifying DNA test data by integrating the Bayesian network into the decision tree model. Secondly, the present invention can also optimize the data transmission of DNA test data during data synchronization, thereby enabling the DNA test data to be synchronized to the medical platform in a timely manner, thereby improving the query efficiency of the DNA test data.

[0020] Furthermore, in the DNA test data synchronization and classification method based on the decision tree model, DNA test data is obtained, a decision tree model is constructed, the DNA test data is input into the decision tree model for initial classification, and the Bayesian network is integrated, specifically: Obtain DNA test data and build a decision tree model. Build a sample data set based on the DNA test data, use the sample data set as the root node in the decision tree model, and set a splitting standard threshold. Calculate the Euclidean distance between each sample data set in the root node, and combine the sample data whose Euclidean distance value is not greater than the splitting standard threshold into one data set to form a leaf node; The sample data with Euclidean distance values ​​greater than the splitting standard threshold are separated into another data set to form leaf nodes. Through continuous splitting, no new leaf nodes are generated in the decision tree model, and the Bayesian network is integrated.

[0021] It should be noted that since the smaller the Euclidean distance, the more similar the samples are, the splitting standard threshold is the Euclidean distance standard threshold; the decision tree models include CART decision tree, C5.0 decision tree, CHAID decision tree, ID3 decision tree, etc. DNA detection data includes DNA nucleotide sequence data, genome information, data source information, etc.

[0022] like Figure 2 As shown, further, in the DNA detection data synchronization and classification method based on the decision tree model, the classification process of the DNA detection data is monitored by the Bayesian network, and each leaf node is observed and processed to obtain the detection data after DNA classification, specifically: S202: Obtain the leaf nodes after initialization and classification, and use each sample data in the leaf nodes after initialization and classification as an observation node, and perform sample search with one observation node in each leaf node after initialization and classification; S204: constructing an association relationship between observation nodes, connecting the current observation node with another observation node based on the association relationship between the observation nodes, constructing a directed acyclic graph, and calculating the joint probability value between the observation nodes in the directed acyclic graph; S206: When the joint probability value between the observation nodes in the directed acyclic graph is greater than the joint probability threshold, the current observation node and another observation node are maintained unchanged in the current leaf node; S208: When the joint probability value between the observation nodes in the directed acyclic graph is not greater than the joint probability threshold, the current observation node and another observation node are separated into different leaf nodes until the observation of all the initialized classified leaf nodes is completed, and the final DNA detection data is output and output as the detection data after DNA classification.

[0023] It should be noted that by fusing the decision tree model, the association relationship between the observation nodes is constructed, and then the joint probability value between the observation nodes in the directed acyclic graph is calculated according to the association relationship between the observation nodes. The relationship between the observation nodes is determined by judging the joint probability value. When the joint probability value is greater than the preset joint probability value, it means that the correlation between the two sample data is high and can be understood as the same sample data, thereby further improving the classification accuracy of the decision tree model.

[0024] Furthermore, in the DNA detection data synchronization and classification method based on the decision tree model, several candidate communication channels are initially selected according to the real-time network communication data of each communication channel, specifically: Set a network communication data threshold and determine whether the real-time network communication data of each communication channel is greater than the network communication data threshold; When the real-time network communication data is greater than the network communication data threshold, the communication channel whose real-time network communication data is greater than the network communication data threshold is used as a candidate communication channel; When the real-time network communication data is greater than the network communication data threshold, the communication channel whose real-time network communication data is greater than the network communication data threshold is used as a non-candidate communication channel.

[0025] It should be noted that the network communication data includes upload information transmission rate, download information transmission rate, information transmission volume per unit time, etc. The method can select a suitable communication channel, wherein the communication channel includes expressions such as communication mode and communication link.

[0026] Furthermore, in the DNA detection data synchronization and classification method based on the decision tree model, the first synchronization strategy or the second synchronization strategy is generated according to the file size information of the detection data after DNA classification and the real-time network communication data of the candidate communication channel, specifically including: The data transmission requirement time is set, and the required rate information of the data transmission of the DNA classification detection data is calculated according to the file size information of the DNA classification detection data and the data transmission requirement time; Determine whether the required rate information of the detection data after DNA classification during data transmission is greater than the real-time network communication data of the communication channel; When there is at least one piece of DNA classified detection data whose required rate information during data transmission is not greater than the communication channel of the real-time network communication data of the communication channel, the communication channel of the minimum real-time network communication data is selected as the final communication channel, a first synchronization strategy is generated, and the first synchronization strategy is output; When there is no communication channel in which the required rate information of the detection data after DNA classification during data transmission is greater than the real-time network communication data of the communication channel, each candidate communication channel is used as a communication transmission channel, a second synchronization strategy is generated, and the second synchronization strategy is output.

[0027] It should be noted that when there is at least one communication channel in which the required rate information of the detection data after DNA classification is not greater than the real-time network communication data of the communication channel during data transmission, it means that there is at least one communication channel that is sufficient to support data transmission, otherwise it is not sufficient to support data transmission.

[0028] Further, in the DNA detection data synchronization and classification method based on the decision tree model, data synchronization is performed according to the first synchronization strategy or the second synchronization strategy, specifically including: When the first synchronization strategy is used, the detection data after DNA classification is continuously transmitted according to the first synchronization strategy, and the real-time network communication data of the current communication channel is monitored; When the first synchronization strategy is used, the file size information of the detection data after DNA classification is obtained, and the file size information of the detection data after DNA classification is divided into a number of new file data for transmission, and the size information of each new file data is initialized; Calculate the required rate information of each new file data according to the size information of each new file data and the required data transmission time, and initialize several candidate data transmission channels for data transmission; Allocate candidate data transmission channels one by one to transmit data for each new file data, and determine whether the real-time network communication data of each candidate data transmission channel is greater than the required rate information of the new file data; When the real-time network communication data of each candidate data transmission channel is greater than the required rate information of the new file data, data synchronization is performed according to the new file data; When the real-time network communication data of each candidate data transmission channel is not all larger than the required rate information of the new file data, the size information of each new file data is readjusted until all are larger than the required rate information of the new file data.

[0029] It should be noted that this method further optimizes the data transmission of DNA test data during the data synchronization process, so that the DNA test data can be synchronized to the medical platform in a timely manner, thereby improving the query efficiency of the DNA test data.

[0030] In addition, the method further comprises: Obtaining data storage rate information of DNA test data under different DNA test data storage capacities through big data, and introducing a graph neural network to input the data storage rate information of DNA test data under different DNA test data storage capacities into the graph neural network; The amount of DNA detection data stored is used as the first node of the graph neural network, the data storage rate information of the DNA detection data is used as the second node of the graph neural network, and a topological structure diagram is constructed based on the first node and the second node; Obtaining a relevant adjacency matrix based on the topological structure diagram, constructing a knowledge graph, inputting the relevant adjacency matrix into the knowledge graph for storage, and obtaining a real-time storage capacity of a DNA detection database; The real-time storage capacity of the DNA detection database is input into the knowledge graph for prediction, the data storage rate information of the DNA detection data under the current DNA detection data storage capacity is obtained, and the relevant data synchronization plan is formulated according to the data storage rate information of the DNA detection data under the current DNA detection data storage capacity.

[0031] It should be noted that different data storage amounts will affect the data storage speed when the data is synchronized and stored. This method can dynamically adjust the transmission of new file data within a unit time, thereby improving the rationality of data synchronization.

[0032] Wherein, a relevant data synchronization plan is formulated according to the data storage rate information of the DNA detection data under the current DNA detection data storage capacity, specifically: Setting a data storage rate threshold for DNA test data, and determining whether the data storage rate information for DNA test data under the current DNA test data storage capacity is greater than the data storage rate threshold for DNA test data; When the data storage rate information of the DNA detection data under the current DNA detection data storage capacity is not greater than the data storage rate threshold of the DNA detection data, the data storage area of ​​the DNA detection database is expanded, and the storage capacity of the storage area to be expanded is calculated; The DNA detection database is expanded according to the storage capacity of the storage area that needs to be expanded, and the storage capacity of the data storage area of ​​the DNA detection database is continuously monitored, so that the data storage rate information of the DNA detection data under the current DNA detection data storage capacity in each timestamp is greater than the data storage rate threshold of the DNA detection data; When the data storage rate information of the DNA detection data under the current DNA detection data storage amount is greater than the data storage rate threshold of the DNA detection data, the current DNA detection data is stored.

[0033] It should be noted that this method can further improve the rationality of data synchronization.

[0034] like Figure 3 As shown, the second aspect of the present invention provides a DNA detection data synchronization and classification system 4 based on a decision tree model, including a memory 41 and a processor 42. The memory 41 includes a DNA detection data synchronization and classification method program based on a decision tree model. When the DNA detection data synchronization and classification method program based on a decision tree model is executed by the processor 42, the following technical solutions are implemented: Obtain DNA test data, build a decision tree model, input the DNA test data into the decision tree model for initial classification, and integrate the Bayesian network; The classification process of DNA detection data is monitored through the Bayesian network, and each leaf node is observed and processed to obtain the detection data after DNA classification and the real-time network communication data of each communication channel; Preliminarily selecting a number of candidate communication channels according to the real-time network communication data of each communication channel, and obtaining file size information of the detection data after DNA classification and the real-time network communication data of the communication channel; A first synchronization strategy or a second synchronization strategy is generated according to the file size information of the detection data after DNA classification and the real-time network communication data of the communication channel, and data synchronization is performed according to the first synchronization strategy or the second synchronization strategy.

[0035] Furthermore, in the DNA test data synchronization and classification system based on the decision tree model, DNA test data is obtained, a decision tree model is constructed, the DNA test data is input into the decision tree model for initial classification, and the Bayesian network is integrated, specifically: Obtain DNA test data and build a decision tree model. Build a sample data set based on the DNA test data, use the sample data set as the root node in the decision tree model, and set a splitting standard threshold. Calculate the Euclidean distance between each sample data set in the root node, and combine the sample data whose Euclidean distance value is not greater than the splitting standard threshold into one data set to form a leaf node; The sample data with Euclidean distance values ​​greater than the splitting standard threshold are separated into another data set to form leaf nodes. Through continuous splitting, no new leaf nodes are generated in the decision tree model, and the Bayesian network is integrated.

[0036] Furthermore, in the DNA test data synchronization and classification system based on the decision tree model, the classification process of the DNA test data is monitored through the Bayesian network, and each leaf node is observed and processed to obtain the test data after DNA classification, specifically: Obtain the leaf nodes after the initialization classification, and use each sample data in the leaf nodes after the initialization classification as an observation node, and perform sample search with one of the observation nodes in each leaf node after the initialization classification; Construct the association relationship between observation nodes, connect the current observation node with another observation node based on the association relationship between observation nodes, construct a directed acyclic graph, and calculate the joint probability value between observation nodes in the directed acyclic graph; When the joint probability value between observation nodes in the directed acyclic graph is greater than the joint probability threshold, the current observation node and another observation node are maintained unchanged in the current leaf node; When the joint probability value between the observation nodes in the directed acyclic graph is not greater than the joint probability threshold, the current observation node and another observation node are separated into different leaf nodes until the observation of all the initialized classified leaf nodes is completed, and the final DNA detection data is output and output as the detection data after DNA classification.

[0037] Furthermore, in the DNA detection data synchronization and classification system based on the decision tree model, several candidate communication channels are initially selected according to the real-time network communication data of each communication channel, specifically: Set a network communication data threshold and determine whether the real-time network communication data of each communication channel is greater than the network communication data threshold; When the real-time network communication data is greater than the network communication data threshold, the communication channel whose real-time network communication data is greater than the network communication data threshold is used as a candidate communication channel; When the real-time network communication data is greater than the network communication data threshold, the communication channel whose real-time network communication data is greater than the network communication data threshold is used as a non-candidate communication channel.

[0038] Further, in the DNA detection data synchronization and classification system based on the decision tree model, the first synchronization strategy or the second synchronization strategy is generated according to the file size information of the detection data after DNA classification and the real-time network communication data of the candidate communication channel, specifically including: The data transmission requirement time is set, and the required rate information of the data transmission of the DNA classification detection data is calculated according to the file size information of the DNA classification detection data and the data transmission requirement time; Determine whether the required rate information of the detection data after DNA classification during data transmission is greater than the real-time network communication data of the communication channel; When there is at least one piece of DNA classified detection data whose required rate information during data transmission is not greater than the communication channel of the real-time network communication data of the communication channel, the communication channel of the minimum real-time network communication data is selected as the final communication channel, a first synchronization strategy is generated, and the first synchronization strategy is output; When there is no communication channel in which the required rate information of the detection data after DNA classification during data transmission is greater than the real-time network communication data of the communication channel, each candidate communication channel is used as a communication transmission channel, a second synchronization strategy is generated, and the second synchronization strategy is output.

[0039] Further, in the DNA detection data synchronization and classification system based on the decision tree model, data synchronization is performed according to the first synchronization strategy or the second synchronization strategy, specifically including: When the first synchronization strategy is used, the detection data after DNA classification is continuously transmitted according to the first synchronization strategy, and the real-time network communication data of the current communication channel is monitored; When the first synchronization strategy is used, the file size information of the detection data after DNA classification is obtained, and the file size information of the detection data after DNA classification is divided into a number of new file data for transmission, and the size information of each new file data is initialized; Calculate the required rate information of each new file data according to the size information of each new file data and the required data transmission time, and initialize several candidate data transmission channels for data transmission; Allocate candidate data transmission channels one by one to transmit data for each new file data, and determine whether the real-time network communication data of each candidate data transmission channel is greater than the required rate information of the new file data; When the real-time network communication data of each candidate data transmission channel is greater than the required rate information of the new file data, data synchronization is performed according to the new file data; When the real-time network communication data of each candidate data transmission channel is not all larger than the required rate information of the new file data, the size information of each new file data is readjusted until all are larger than the required rate information of the new file data.

[0040] The third aspect of the present invention provides a computer-readable storage medium, including a DNA detection data synchronization and classification method program based on a decision tree model. When the DNA detection data synchronization and classification method program based on a decision tree model is executed by a processor, the technical solution involved in the DNA detection data synchronization and classification method based on a decision tree model is implemented.

[0041] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units 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 can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0042] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0043] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0044] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: a mobile storage device, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0045] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods of each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

[0046] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A DNA detection data synchronization and classification method based on a decision tree model, characterized in that: Specifically include: Acquire DNA test data, construct a decision tree model, input the DNA test data into the decision tree model for initial classification, and fuse the Bayesian network; The classification process of DNA detection data is monitored through the Bayesian network, and each leaf node is observed and processed to obtain the detection data after DNA classification and the real-time network communication data of each communication channel; Preliminarily selecting a number of candidate communication channels according to the real-time network communication data of each communication channel, and obtaining file size information of the detection data after DNA classification and the real-time network communication data of the candidate communication channels; A first synchronization strategy or a second synchronization strategy is generated according to the file size information of the detection data after the DNA classification and the real-time network communication data of the communication channel, and data synchronization is performed according to the first synchronization strategy or the second synchronization strategy.

2. The DNA detection data synchronization and classification method based on the decision tree model according to claim 1 is characterized in that: Acquire DNA test data, build a decision tree model, input the DNA test data into the decision tree model for initial classification, and integrate the Bayesian network, specifically: Acquire DNA test data, build a decision tree model, build a sample data set according to the DNA test data, use the sample data set as the root node in the decision tree model, and set a splitting standard threshold; Calculating the Euclidean distance value between each sample data set in the root node, and combining the sample data whose Euclidean distance value is not greater than the splitting standard threshold into one data set to form a leaf node; The sample data whose Euclidean distance value is greater than the splitting standard threshold value is separated into another data set to form leaf nodes. Through continuous splitting, no new leaf nodes are generated in the decision tree model, and the Bayesian network is integrated.

3. The DNA detection data synchronization and classification method based on the decision tree model according to claim 1, characterized in that: The classification process of DNA test data is monitored through the Bayesian network, and each leaf node is observed and processed to obtain the test data after DNA classification, specifically: Obtaining leaf nodes after initialization and classification, and using each sample data in the leaf nodes after initialization and classification as an observation node, and performing sample search with one observation node in each leaf node after initialization and classification; Constructing an association relationship between observation nodes, connecting the current observation node with another observation node based on the association relationship between the observation nodes, constructing a directed acyclic graph, and calculating the joint probability value between the observation nodes in the directed acyclic graph; When the joint probability value between the observation nodes in the directed acyclic graph is greater than the joint probability threshold, the current observation node and another observation node are maintained unchanged in the current leaf node; When the joint probability value between the observation nodes in the directed acyclic graph is not greater than the joint probability threshold, the current observation node and another observation node are separated into different leaf nodes until the observation of all the initialized classified leaf nodes is completed, and the final DNA detection data is output and output as the detection data after DNA classification.

4. The DNA detection data synchronization and classification method based on the decision tree model according to claim 1, characterized in that: According to the real-time network communication data of each communication channel, a number of candidate communication channels are initially selected, specifically: Setting a network communication data threshold, and determining whether the real-time network communication data of each communication channel is greater than the network communication data threshold; When the real-time network communication data is greater than the network communication data threshold, the communication channel whose real-time network communication data is greater than the network communication data threshold is used as a candidate communication channel; When the real-time network communication data is greater than the network communication data threshold, the communication channel whose real-time network communication data is greater than the network communication data threshold is used as a non-candidate communication channel.

5. The DNA detection data synchronization and classification method based on the decision tree model according to claim 1, characterized in that: Generating a first synchronization strategy or a second synchronization strategy according to the file size information of the detection data after the DNA classification and the real-time network communication data of the candidate communication channel specifically includes: Setting a data transmission requirement time, and calculating the required rate information of the detection data after DNA classification when performing data transmission according to the file size information of the detection data after DNA classification and the data transmission requirement time; Determine whether the required rate information of the detection data after the DNA classification during data transmission is greater than the real-time network communication data of the communication channel; When there is at least one communication channel whose required rate information of the detection data after DNA classification is not greater than the real-time network communication data of the communication channel during data transmission, the communication channel with the smallest real-time network communication data is selected as the final communication channel, a first synchronization strategy is generated, and the first synchronization strategy is output; When there is no communication channel in which the required rate information of the detection data after DNA classification during data transmission is greater than the real-time network communication data of the communication channel, each candidate communication channel is used as a communication transmission channel, a second synchronization strategy is generated, and the second synchronization strategy is output.

6. The DNA detection data synchronization and classification method based on the decision tree model according to claim 1, characterized in that: Performing data synchronization according to the first synchronization strategy or the second synchronization strategy specifically includes: When the first synchronization strategy is used, the detection data after DNA classification is continuously transmitted according to the first synchronization strategy, and the real-time network communication data of the current communication channel is monitored; When the first synchronization strategy is used, the file size information of the detection data after DNA classification is obtained, and the file size information of the detection data after DNA classification is divided into a plurality of new file data for transmission, and the size information of each new file data is initialized; Calculating the required rate information of each new file data according to the size information of each new file data and the required data transmission time, and initializing a plurality of candidate data transmission channels for data transmission; Allocate candidate data transmission channels one by one to perform data transmission on each new file data, and determine whether the real-time network communication data of each candidate data transmission channel is greater than the required rate information of the new file data; When the real-time network communication data of each candidate data transmission channel is greater than the required rate information of the new file data, data synchronization is performed according to the new file data; When the real-time network communication data of each candidate data transmission channel is not all larger than the required rate information of the new file data, the size information of each new file data is readjusted until all are larger than the required rate information of the new file data.

7. A DNA detection data synchronization and classification system based on a decision tree model, characterized in that: It comprises a memory and a processor, wherein the memory comprises a DNA detection data synchronization and classification method program based on a decision tree model, and when the DNA detection data synchronization and classification method program based on a decision tree model is executed by the processor, the steps of the DNA detection data synchronization and classification method based on a decision tree model as described in any one of claims 1 to 6 are implemented.

8. A computer-readable storage medium, characterized in that: It includes a DNA detection data synchronization and classification method program based on a decision tree model. When the DNA detection data synchronization and classification method program based on a decision tree model is executed by a processor, the steps of the DNA detection data synchronization and classification method based on a decision tree model as described in any one of claims 1-6 are implemented.

Images