Artificial intelligence-based data synchronization method and related device

Abstract

The application provides an artificial intelligence-based data synchronization method and device, electronic equipment and storage medium. The artificial intelligence-based data synchronization method comprises the following steps: constructing a data synchronization template; classifying the data synchronization template according to the type of a source database and the type of a target database to obtain a first category, and constructing a training data set according to the category to train a template classification model; replacing variable parameters in the data synchronization template with parameter placeholders; constructing feature data to be classified according to database information in a data synchronization requirement; inputting the feature data to be classified into the template classification model to obtain a second category to screen a candidate template; replacing the parameter placeholders in the candidate template with variable parameters in the data synchronization requirement to obtain an executable candidate template, screening a target template from the executable candidate template, and executing the target template to complete data synchronization. The method can efficiently query a data synchronization template meeting a requirement, thereby improving the efficiency of data synchronization.

Description

Artificial intelligence-based data synchronization methods and related equipment Technical Field

[0001] This application relates to the field of data processing technology, and in particular to a data synchronization method, apparatus, electronic device and storage medium based on artificial intelligence. Background Technology

[0002] With the development of big data technology, more and more enterprises are inclined to build data platforms to improve the efficiency of data processing. The function of a data platform is to calculate and transform the interactive data between the front-end and back-end of the data system to improve the response speed of the data system. Synchronizing the data flowing through the data system is a crucial step in the construction of a data platform.

[0003] Currently, in engineering practice, various existing data synchronization tools such as Sqoop, DataX, and Kettle are usually encapsulated into data synchronization templates. For different data synchronization tasks, the appropriate data synchronization template is selected manually. This method consumes a lot of human resources and results in low processing efficiency of data synchronization tasks. Summary of the Invention

[0004] In view of the above, it is necessary to provide an artificial intelligence-based data synchronization method and related equipment to solve the technical problem of how to improve the efficiency of data synchronization. The related equipment includes an artificial intelligence-based data synchronization device, electronic equipment, and storage medium.

[0005] This application provides a data synchronization method based on artificial intelligence, the method comprising:

[0006] The data synchronization tool is constructed into a variety of data synchronization templates, which are used to synchronize data from the source database to the destination database.

[0007] The data synchronization template is classified according to the type of the source database and the type of the destination database in the data synchronization template to obtain the first category and feature data of the data synchronization template;

[0008] A training dataset is constructed based on the first category of the data synchronization template and the feature data, and a template classification model is trained based on the training dataset;

[0009] The data synchronization template is parsed to filter out the variable parameters, and the variable parameters are replaced with preset parameter placeholders to update the data synchronization template.

[0010] The received data synchronization requirements are parsed to obtain the database information to be classified. Based on the database information to be classified, the feature data to be classified is constructed. The database information to be classified includes at least the source database type and the destination database type to be classified.

[0011] The feature data to be classified is input into the template classification model to obtain the second category of the data synchronization requirement. The second category is compared with the first category of the data synchronization template to filter candidate templates.

[0012] Query the variable parameters from the data synchronization requirements, replace the parameter placeholders in the candidate templates with the variable parameters to obtain executable candidate templates, calculate the priority of the executable candidate templates, select the executable candidate template with the highest priority as the target template, and run the target template to complete data synchronization.

[0013] In some embodiments, classifying the data synchronization template according to the type of the source database and the type of the destination database in the data synchronization template to obtain the first category and feature data of the data synchronization template includes:

[0014] The source database type and the destination database type in the data synchronization template are combined to form the feature data of the data synchronization template;

[0015] According to the preset adaptation rules, the data synchronization tools that are compatible with the source database type and the destination database type are queried, and the name of the data synchronization tool is used as the first category of the data synchronization template.

[0016] In some embodiments, constructing a training dataset based on the first category of the data synchronization template and the feature data, and training a template classification model based on the training dataset, includes:

[0017] For each of the data synchronization templates, tag data for the data synchronization templates is constructed based on the first category and the names of all data synchronization tools;

[0018] The feature data and the label data are mapped one-to-one to construct a training dataset;

[0019] Construct an initial classification model by inputting the feature data from the training dataset into the initial classification model to obtain a predicted classification result, and inputting the predicted classification result and the label data into a preset loss function to obtain the loss value of the initial classification model;

[0020] The initial classification model is updated using gradient descent until the loss value of the initial classification model no longer changes, at which point the update is stopped and a template classification model is obtained.

[0021] In some embodiments, parsing the data synchronization template to filter variable parameters therein, and replacing the variable parameters with preset parameter placeholders to update the data synchronization template, includes:

[0022] The data synchronization template is segmented to obtain multiple template words;

[0023] The template vocabulary is input into a preset template vocabulary classification model to obtain the category of the template vocabulary. The category includes at least static parameters and dynamic parameters. The template vocabulary with the category of static parameters and the template vocabulary with the category of dynamic parameters are used as variable parameters in the data synchronization template.

[0024] The preset parameter placeholders include static parameter placeholders and dynamic parameter placeholders. The template words in the data synchronization template that are classified as static parameters are replaced with the preset static placeholders, and the template words in the data synchronization template that are classified as dynamic parameters are replaced with the preset dynamic placeholders to obtain the updated data synchronization template.

[0025] In some embodiments, the process of parsing the received data synchronization requirements to obtain database information to be classified, and constructing feature data to be classified based on the database information to be classified, includes:

[0026] The data synchronization requirements are segmented into words to obtain multiple requirement terms;

[0027] Each of the required terms is classified to obtain a category for each required term. The categories of the required terms include at least the source database and the destination database.

[0028] The required vocabulary categorized as source database and the required vocabulary categorized as destination database are combined to form the unclassified feature data corresponding to the preset synchronization requirement.

[0029] In some embodiments, the step of inputting the feature data to be classified into the template classification model to obtain a second category of the data synchronization requirement, and comparing the second category with a first category of the data synchronization template to filter candidate templates includes:

[0030] Input the feature data to be classified into the template classification model to obtain the predicted probability list corresponding to the data to be classified, and take the name of the data synchronization tool corresponding to the non-zero value in the predicted probability list as the second category;

[0031] Compare the second category with the first category of the data synchronization template. If the first category is the same as the second category, then the data synchronization template is used as the alternative template.

[0032] In some embodiments, the step of querying variable parameters from the data synchronization requirement, replacing parameter placeholders in the candidate template with the variable parameters to obtain an executable candidate template, and calculating the priority of the executable candidate template includes:

[0033] Each of the required words is classified according to a preset semantic classification model to obtain a second category for each of the required words. The second category of the required words includes at least static and dynamic categories, with static and dynamic required words used as variable parameters.

[0034] Replace the static placeholders in the candidate template with static requirement words, and replace the dynamic placeholders in the candidate template with dynamic requirement words to obtain an executable candidate template;

[0035] The executable candidate templates are tested based on preset sample data to obtain the resource utilization rate of each candidate template, and the reciprocal of the resource utilization rate is used as the priority of the executable candidate template.

[0036] The highest priority executable alternative template is selected as the target template, and the target template is run to complete data synchronization.

[0037] This application embodiment also provides a data synchronization device based on artificial intelligence, the device comprising:

[0038] A building unit is used to build the data synchronization tool into various data synchronization templates, which are used to synchronize data from the source database to the destination database.

[0039] The first classification unit is used to classify the data synchronization template according to the type of the source database and the type of the destination database in the data synchronization template, and obtain the first category and feature data of the data synchronization template.

[0040] The training unit is used to construct a training dataset based on the first category of the data synchronization template and the feature data, and to train a template classification model based on the training dataset.

[0041] The parsing unit is used to parse the data synchronization template to filter the variable parameters therein, and replace the variable parameters with preset parameter placeholders to update the data synchronization template;

[0042] The feature construction unit is used to parse the received data synchronization requirements to obtain the database information to be classified, and to construct the feature data to be classified based on the database information to be classified. The database information to be classified includes at least the source database type to be classified and the destination database type to be classified.

[0043] The second classification unit is used to input the feature data to be classified into the template classification model to obtain the second category of the data synchronization requirement, and compare the second category with the first category of the data synchronization template to filter candidate templates.

[0044] An execution unit is used to query variable parameters from the data synchronization requirements, replace the parameter placeholders in the candidate templates with the variable parameters to obtain executable candidate templates, calculate the priority of the executable candidate templates, select the executable candidate template with the highest priority as the target template, and run the target template to complete data synchronization.

[0045] This application embodiment also provides an electronic device, the electronic device comprising:

[0046] Memory, which stores computer-readable instructions; and

[0047] The processor executes computer-readable instructions stored in the memory to implement the artificial intelligence-based data synchronization method.

[0048] This application also provides a computer-readable storage medium storing computer-readable instructions, which are executed by a processor in an electronic device to implement the artificial intelligence-based data synchronization method.

[0049] The aforementioned AI-based data synchronization method categorizes data synchronization templates by marking the source and destination databases within the template and then trains a template classification model using these categories. This allows the method to provide category guidance for data synchronization templates based on data synchronization requirements when selecting a template, thereby efficiently identifying suitable templates and improving the efficiency of data synchronization. Attached Figure Description

[0050] Figure 1 is a flowchart of a preferred embodiment of an artificial intelligence-based data synchronization method involved in this application.

[0051] Figure 2 is a functional block diagram of a preferred embodiment of the artificial intelligence-based data synchronization device involved in this application.

[0052] Figure 3 is a schematic diagram of the structure of an electronic device according to a preferred embodiment of the artificial intelligence-based data synchronization method involved in this application. Detailed Implementation

[0053] To better understand the purpose, features, and advantages of this application, a detailed description of the application is provided below with reference to the accompanying drawings and specific embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in the embodiments of this application can be combined with each other. Numerous specific details are set forth in the following description to provide a thorough understanding of this application; the described embodiments are only a part of the embodiments of this application, and not all of them.

[0054] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the stated features. In the description of this application, "a plurality of" means two or more, unless otherwise explicitly specified.

[0055] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0056] This application provides an artificial intelligence-based data synchronization method that can be applied to one or more electronic devices. The electronic device is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions. Its hardware includes, but is not limited to, microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0057] The electronic device can be any electronic product that can interact with the user, such as a personal computer, tablet computer, smartphone, personal digital assistant (PDA), game console, interactive network television (IPTV), smart wearable device, etc.

[0058] The electronic device may also include network devices and / or user devices. The network devices include, but are not limited to, a single network server, a server group consisting of multiple network servers, or a cloud based on cloud computing consisting of a large number of hosts or network servers.

[0059] The networks in which the electronic devices are located include, but are not limited to, the Internet, wide area networks, metropolitan area networks, local area networks, and virtual private networks (VPNs).

[0060] Example 1

[0061] Figure 1 shows a flowchart of a preferred embodiment of the data synchronization method based on artificial intelligence according to this application. The order of the steps in this flowchart can be changed, and some steps can be omitted, depending on different requirements.

[0062] S10, The data synchronization tool is constructed into a data synchronization template, which is used to synchronize data from the source database to the destination database.

[0063] In this optional embodiment, a data synchronization tool can be constructed as a data synchronization template using a preset programming language. The preset programming language can be an existing programming language such as Java, Python, or SQL, and the data synchronization tool can be an existing data synchronization tool such as Sqoop, DataX, Kettle, SeaTunnel, or Nifi. This application does not limit the type of the data synchronization tool or the type of the preset programming language.

[0064] In this optional embodiment, the interface of the data synchronization tool in a preset programming language can be queried. The interface is one or more lines of code, and its function is to call the data synchronization tool using the preset programming language. For example, when the data synchronization tool is Sqoop and the preset programming language is Python, the interface of the Sqoop tool in Python is `import Sqoop`; when the preset data synchronization tool is DataX and the preset programming language is Java, the interface corresponding to the DataX tool is `import com.alibaba.datax.core.Engine`.

[0065] In this optional embodiment, the interface can be written into a preset position in a data synchronization script written in a preset programming language to obtain a data synchronization template. The preset position depends on the programming specifications corresponding to the preset programming language. For example, when the preset programming language is Python or Java, the preset position is the beginning of the data synchronization script.

[0066] In this optional embodiment, the information in the data synchronization template includes at least: template name, source database type, and destination database type.

[0067] The template name is used to represent the unique identifier of the data synchronization template. The template name may be the name, version number, or other information of the data synchronization tool in the data synchronization template. This application does not limit this.

[0068] The source database is used to characterize the type of source of the data to be synchronized that the data synchronization template can process, and the destination database is used to characterize the type of database to which the data to be synchronized flows that the data synchronization template can process. The types of the source database and the destination database both include existing database types such as MySQL, PostgreSQL, Oracle, and Hive, and this application does not limit them.

[0069] In this way, by building various data synchronization templates based on preset scripts and the interfaces of existing data synchronization tools, multiple templates can be provided for data synchronization tasks, thereby improving the efficiency of data synchronization.

[0070] S11, classify the data synchronization template according to the type of the source database and the type of the destination database in the data synchronization template to obtain the first category and feature data of the data synchronization template.

[0071] In an optional embodiment, classifying the data synchronization template according to the type of the source database and the type of the destination database in the data synchronization template to obtain the first category and feature data of the data synchronization template includes:

[0072] The source database type and the destination database type in the data synchronization template are combined to form the feature data of the data synchronization template;

[0073] According to the preset adaptation rules, the data synchronization tools that are compatible with the source database type and the destination database type are queried, and the name of the data synchronization tool is used as the first category of the data synchronization template.

[0074] In this optional embodiment, the type of the source database can be placed first and the type of the destination database can be placed last to combine them into feature data. Alternatively, the type of the destination database can be placed first and the type of the source database can be placed last to combine them into feature data. This application does not limit the order of the types of the source database and the type of the destination database in the feature data.

[0075] For example, when the source database type in the data synchronization template is MySQL and the destination database type is hive, the feature data can be [MySQL, hive] or [hive, MySQL].

[0076] In this optional embodiment, the preset adaptation rules are used to record data synchronization tools that can perform data synchronization between the source database and the destination database. For example, the preset adaptation rules may be: Sqoop tool adapted to MySQL database and Hive database; DataX tool adapted to MySQL database and Hive database; Nifi tool adapted to PostSQL database and Elasticsearch database, etc. This application does not limit these.

[0077] In this optional embodiment, the name of the data synchronization tool adapted to the source and destination databases can be used as the first category of the data synchronization template corresponding to the feature data. For example, when the feature data corresponding to the data synchronization template is [MySQL, hive], and the preset adaptation rules include: Sqoop tool adapts to MySQL and hive databases, and DataX tool adapts to MySQL and hive databases, then the first category of the data synchronization template includes Sqoop and DataX. It should be noted that the first category of the data synchronization template can be one or more.

[0078] In this way, by finding the appropriate data synchronization tool based on the type of the source database and the type of the destination database in the data synchronization template, and by labeling the category of the data synchronization template according to the name of the data synchronization tool, the applicable scenarios of the data synchronization template can be divided according to the name of the data synchronization tool, providing category guidance for the subsequent selection of data synchronization templates.

[0079] S12, construct a training dataset based on the first category of the data synchronization template and the feature data, and train a template classification model based on the training dataset.

[0080] In an optional embodiment, the step of constructing a training dataset based on the first category of the data synchronization template and the feature data, and training a template classification model based on the training dataset, includes:

[0081] For each of the data synchronization templates, tag data for the data synchronization templates is constructed based on the first category and the names of all data synchronization tools;

[0082] The feature data and the label data are mapped one-to-one to construct a training dataset;

[0083] Construct an initial classification model by inputting the feature data from the training dataset into the initial classification model to obtain a predicted classification result, and inputting the predicted classification result and the label data into a preset loss function to obtain the loss value of the initial classification model;

[0084] The initial classification model is updated using gradient descent until the loss value of the initial classification model no longer changes, at which point the update is stopped and a template classification model is obtained.

[0085] In this optional embodiment, the tag data of the data synchronization template can be constructed based on the first category of each data synchronization template and the names of all data synchronization tools. Let any data synchronization template be template A, and taking template A as an example, the construction of the tag data for template A includes:

[0086] Store the names of all data synchronization tools as a category list. For example, if the names of the data synchronization tools include: Sqoop, DataX, Kettle, SeaTunnel, Nifi, then the category list is [Sqoop, DataX, Kettle, SeaTunnel, Nifi].

[0087] Initialize the preset count variable T to 0, traverse the name of each data synchronization tool in the category list, if the traversed name is the first category of the A template, mark the name as "supported" and increment T by 1, otherwise mark the name as "not supported" and keep T unchanged, until all the names of the data synchronization tools have been traversed, and obtain the mark of each name in the category list and the value of the count variable T;

[0088] Calculate the reciprocal of the count variable T and assign the reciprocal to each name marked "Supported" in the category list, and assign 0 to all names marked "Unsupported" in the category list to obtain the tag data corresponding to the template A. For example, if the feature data is [MySQL, hive], and the names of all data synchronization tools include: Sqoop, DataX, Kettle, SeaTunnel, Nifi, and the data synchronization tools adapted to MySQL database and hive database include Sqoop and DataX, then the preset count variable T takes the value of 2, and 0.5 can be assigned to the first category Sqoop and DataX, and the tag data corresponding to the feature data is [0.5, 0.5, 0, 0, 0]. This tag data is used to characterize that the probability of the data synchronization template corresponding to the feature data belonging to the Sqoop category is 0.5, the probability of belonging to the DataX category is also 0.5, and the probability of belonging to the other first categories is 0.

[0089] In this optional embodiment, the feature data and the label data can be mapped one-to-one to serve as training data, and all the training data can be stored to obtain a training dataset.

[0090] In this optional embodiment, the initial classification model can be an existing classification model such as a decision tree model, GBDT model, or XGBoost model, and this application does not limit it to this. The feature data from the training dataset can be sequentially input into the initial classification model to obtain initial classification results. The initial classification results are in the form of a predicted probability list, used to characterize the categories of the feature data predicted by the initial classification model. The initial classification results and the label data are simultaneously input into a preset loss function to obtain the loss value of the initial classification model. The preset loss function can be a cosine distance function. The lower the loss value of the initial classification model, the more similar the predicted probability list is to the label data, and the better the performance of the initial classification model, i.e., the more accurate the prediction result for the category of the feature data.

[0091] The cosine distance function satisfies the following relationship:

[0092]

[0093] Where Loss represents the loss value of the initial classification model, A represents the list of predicted probabilities, and A i B represents the value of the i-th dimension in the predicted probability list; B represents the label data, and B i represents the value of the i-th dimension in the label data; k represents the dimension of the predicted probability list and the label data, i.e., the number of data synchronization tools.

[0094] For example, when the preset loss function is the cosine distance function, the predicted probability list is [0.4, 0.6, 0, 0, 0], and the label data is [0.5, 0.5, 0, 0, 0], the calculation method of the loss value of the initial classification model satisfies the following relationship:

[0095]

[0096] That is, the loss value of the initial classification model is 0.98.

[0097] In this optional embodiment, the initial classification model can be continuously updated using gradient descent. When the loss value of the initial classification model stops changing, it indicates that the performance of the initial classification model is no longer changing, so updating the initial classification model stops, and a template classification model is obtained. The input of the template classification model is the feature data, and the output of the template classification model is a list of predicted probabilities. The list of predicted probabilities is used to characterize the type of data synchronization tool applicable to the data synchronization template corresponding to the feature data.

[0098] For example, when the predicted probability list is [0.2, 0.4, 0.3, 0.1, 0], it indicates that the probability of the data synchronization template corresponding to the feature data being of type Sqoop is 0.2, the probability of type DataX is 0.4, the probability of type Kettle is 0.3, the probability of type SeaTunnel is 0.1, and the probability of type Nifi is 0.

[0099] Thus, by constructing label data through the first category in the data synchronization template and training the template classification model using the label data and feature data, category guidance can be provided for subsequent selection of data synchronization templates, thereby improving the efficiency of data synchronization.

[0100] S13, parse the data synchronization template to filter the variable parameters therein, and replace the variable parameters with preset parameter placeholders to update the data synchronization template.

[0101] In an optional embodiment, parsing the data synchronization template to locate its variable parameters, and replacing the variable parameters with preset parameter placeholders to update the data synchronization template, includes:

[0102] The data synchronization template is segmented to obtain multiple template words;

[0103] The template vocabulary is input into a preset template vocabulary classification model to obtain the category of the template vocabulary. The category includes at least static parameters and dynamic parameters. The template vocabulary with the category of static parameters and the template vocabulary with the category of dynamic parameters are used as variable parameters in the data synchronization template.

[0104] The preset parameter placeholders include static parameter placeholders and dynamic parameter placeholders. The template words in the data synchronization template that are classified as static parameters are replaced with the preset static placeholders, and the template words in the data synchronization template that are classified as dynamic parameters are replaced with the preset dynamic placeholders to obtain the updated data synchronization template.

[0105] In this optional embodiment, the data synchronization template can be segmented using a preset word segmentation tool to obtain multiple template words. The preset word segmentation tool can be an existing word segmentation tool such as jieba or NLTK, and this application does not limit its use. For example, when the content of the data synchronization template includes:

[0106] username (username);

[0107] password"password\;

[0108] The multiple template words include: [username, username, password, password].

[0109] In this optional embodiment, each template word can be sequentially input into a preset template word classification model to obtain the category of each template word. The category includes at least static parameters and dynamic parameters. The preset template word classification model can be an existing classification model such as a pre-trained logistic regression model, a random forest model, or a long short-term memory model. This application does not limit the category of the template word classification model.

[0110] In this optional embodiment, the template terms categorized as static parameters in the data synchronization template can be replaced with preset static placeholders, and the template terms categorized as dynamic parameters in the data synchronization template can be replaced with preset dynamic placeholders to obtain an updated data synchronization template. For example, the format of the static placeholder can be: ${{parameter name}}; the format of the dynamic placeholder can be: ${parameter name}.

[0111] For example, if the static parameters include source database type, destination database type, etc., and the dynamic parameters include synchronization time, synchronization frequency, template execution duration, etc., then the static placeholders include ${{source database type}} and ${{destination database type}}, and the dynamic placeholders include ${synchronization time}, ${synchronization frequency}, and ${execution duration}.

[0112] In this way, by replacing the variable parameters in the data synchronization template with parameter placeholders, the scalability of the template is increased and the reusability of the data synchronization template is improved, thereby enhancing the flexibility of using the data synchronization template.

[0113] S14, parse the received data synchronization requirements to obtain the database information to be classified, and construct the feature data to be classified based on the database information to be classified. The database information to be classified includes at least the source database type to be classified and the destination database type to be classified.

[0114] The data synchronization requirement refers to a new requirement received to synchronize data from the source database to the destination database. For example, the data synchronization requirement could be "synchronize table A in the Hive database to table B in the MySQL database, once per minute, for a valid duration of 24 hours".

[0115] In an optional embodiment, the process of parsing the received data synchronization requirements to obtain the database information to be classified, and constructing the feature data to be classified based on the database information to be classified, includes:

[0116] The data synchronization requirements are segmented into words to obtain multiple requirement terms;

[0117] Each of the required terms is classified to obtain a category for each required term. The categories of the required terms include at least the source database and the destination database.

[0118] The required vocabulary from the source database and the required vocabulary from the destination database are combined to form the unclassified feature data corresponding to the preset synchronization requirement.

[0119] In this optional embodiment, the data synchronization requirement can be segmented using a preset word segmentation tool to obtain multiple requirement words. The preset word segmentation tool can be an existing word segmentation tool such as jieba or NLTK, and this application does not limit it. For example, when the data synchronization requirement is "synchronize table A in the Hive database to the MySQL database, once per minute, with a valid duration of 24 hours", then the requirement words include ["synchronize, hive, database, in, of, table A, synchronize, to, MySQL, database, every, minute, synchronize, once, valid duration, 24 hours"].

[0120] In this optional embodiment, each demand word can be classified according to a preset demand word classification model to obtain the category of each demand word. The preset demand word classification model can be an existing classification model such as a pre-trained decision tree model, gradient ascending tree model, or support vector machine model, and this application does not limit it.

[0121] In this optional embodiment, the input of the demand vocabulary classification model is the demand vocabulary, and the output is the category corresponding to the demand vocabulary. The category includes at least the source database and the destination database.

[0122] In this optional embodiment, the required vocabulary categorized as source database and the required vocabulary categorized as destination database can be combined to form the unclassified feature data corresponding to the preset synchronization requirement. For example, the unclassified feature data can be source database type + destination database type, or destination database type + source database type. This application does not limit the order of the required vocabulary in the unclassified feature data.

[0123] In this way, by classifying each word in the preset synchronization requirements, the source database and the destination database in the synchronization requirements are selected, and the source database and the destination database are combined to obtain the feature data to be classified, which can provide data support for the subsequent selection of data synchronization templates.

[0124] S15, input the feature data to be classified into the template classification model to obtain the second category of the data synchronization requirement, and compare the second category with the first category of the data synchronization template to filter candidate templates.

[0125] In an optional embodiment, the step of inputting the feature data to be classified into the template classification model to obtain a second category of the data synchronization requirement, and comparing the second category with the first category of the data synchronization template to filter candidate templates, includes:

[0126] Input the feature data to be classified into the template classification model to obtain the predicted probability list corresponding to the data to be classified, and take the name of the data synchronization tool corresponding to the non-zero value in the predicted probability list as the second category;

[0127] Compare the second category with the first category of the data synchronization template. If the first category is the same as the second category, then the data synchronization template is used as the alternative template.

[0128] In this optional embodiment, the feature data can be input into the template classification model to obtain a list of predicted probabilities corresponding to the feature data to be classified, and the name of the data synchronization tool corresponding to the non-zero value in the list of predicted probabilities can be used as the second category corresponding to the feature data to be classified.

[0129] For example, when the predicted probability list corresponding to the feature data to be classified is [0.5, 0.4, 0.1, 0, 0], then the second category corresponding to the feature data to be classified is [Sqoop, DataX, Kettle].

[0130] In this optional embodiment, the second category is used to characterize the category of data synchronization templates adapted to the data synchronization requirements. The first category and the second category can be compared; if the second category is the same as the first category, the data synchronization template corresponding to the second category can be used as a candidate template. For example, when the second category corresponding to the data synchronization requirement is [Sqoop, DataX, Kettle], and the first category corresponding to a certain data synchronization template is [Sqoop, DataX, Kettle], then that data synchronization template can be used as a candidate template corresponding to the data synchronization requirement.

[0131] In another optional embodiment, the first category of each data synchronization template can be traversed, i.e., the name of the data synchronization tool to which the data synchronization template is adapted. If the traversed first category matches the source database type and the destination database type to be classified, then the data synchronization template is used as a candidate template. The source database type and the destination database type corresponding to the data to be synchronized are identified and considered. The first category is then filtered using the source database type and the destination database type.

[0132] For example, when the first category of the data template being traversed includes [Sqoop, DataX], and the source database type to be classified is mysql, and the destination database type to be classified is hive, since both the Sqoop synchronization tool and the DataX synchronization tool are adapted for data synchronization between mysql database and hive database, this data synchronization template can be used as an alternative template.

[0133] Thus, by using the synchronization template classification model to determine the category of the data synchronization requirement and finding a data synchronization template that matches the requirement based on the category, the efficiency of data synchronization can be improved.

[0134] S16, query the variable parameters from the data synchronization requirements, replace the parameter placeholders in the candidate templates with the variable parameters to obtain executable candidate templates, calculate the priority of the executable candidate templates, take the executable candidate template with the highest priority as the target template, and run the target template to complete data synchronization.

[0135] In an optional embodiment, the step of querying variable parameters from the data synchronization requirement, replacing parameter placeholders in the candidate template with the variable parameters to obtain an executable candidate template, and calculating the priority of the executable candidate template includes:

[0136] Each of the required words is classified according to a preset semantic classification model to obtain a second category for each of the required words. The second category of the required words includes at least static and dynamic categories, with static and dynamic required words used as variable parameters.

[0137] Replace the static placeholders in the candidate template with static requirement words, and replace the dynamic placeholders in the candidate template with dynamic requirement words to obtain an executable candidate template;

[0138] The executable candidate templates are tested based on preset sample data to obtain the resource utilization rate of each candidate template, and the reciprocal of the resource utilization rate is used as the priority of the executable candidate template.

[0139] The highest priority executable alternative template is selected as the target template, and the target template is run to complete data synchronization.

[0140] In this optional embodiment, the preset semantic classification model is used to classify each of the required words to obtain a second category corresponding to each of the required words. The preset semantic classification model can be an existing classification model such as the textCNN model or the fastText model, and this application does not limit it.

[0141] In this optional embodiment, the preset sample data can be any data. The sample data can be input into each of the executable candidate templates, and the resource utilization rate of the candidate templates during the test is recorded. The reciprocal of the resource utilization rate is used as the priority of the candidate template. The resource utilization rate includes CPU utilization, memory utilization, disk bandwidth utilization, etc., which are not limited in this application. The lower the resource utilization rate, the better the performance of the candidate template, and the higher the priority of the candidate template, indicating that the data synchronization template should be selected for execution first. The candidate template with the highest priority can be used as the target template for data synchronization.

[0142] In this way, by replacing the parameter placeholders in the alternative templates with the variable parameters in the data synchronization requirements, it is ensured that all alternative templates can be executed. The executable alternative templates are tested to obtain the priority of each executable alternative template. The alternative template with the highest priority is selected to execute the data synchronization task, thereby improving the efficiency of data synchronization.

[0143] The aforementioned AI-based data synchronization method categorizes data synchronization templates by marking the source and destination databases within the template and then trains a template classification model using these categories. This allows the method to provide category guidance for data synchronization templates based on data synchronization requirements when selecting a template, thereby efficiently identifying suitable templates and improving the efficiency of data synchronization.

[0144] Example 2

[0145] Figure 2 shows a functional block diagram of a preferred embodiment of the AI-based data synchronization device provided in this application. The AI-based data synchronization device 11 includes a construction unit 110, a first classification unit 111, a training unit 112, a parsing unit 113, a feature construction unit 114, a second classification unit 115, and an execution unit 116. The module / unit referred to in this application refers to a series of computer program segments that can be executed by the processor 13 and perform a fixed function, and are stored in the memory 12. In this embodiment, the functions of each module / unit will be described in detail in subsequent embodiments.

[0146] The construction unit 110 is used to build the data synchronization tool into multiple data synchronization templates, and the data synchronization templates are used to synchronize data from the source database to the destination database.

[0147] The first classification unit 111 is used to classify the data synchronization template according to the type of the source database and the type of the destination database in the data synchronization template, and obtain the first category and feature data of the data synchronization template;

[0148] The training unit 112 is used to construct a training dataset based on the first category of the data synchronization template and the feature data, and to train a template classification model based on the training dataset.

[0149] The parsing unit 113 is used to parse the data synchronization template to filter the variable parameters therein, and replace the variable parameters with preset parameter placeholders to update the data synchronization template.

[0150] The feature construction unit 114 is used to parse the received data synchronization requirements to obtain the database information to be classified, and to construct the feature data to be classified based on the database information to be classified. The database information to be classified includes at least the source database type to be classified and the destination database type to be classified.

[0151] The second classification unit 115 is used to input the feature data to be classified into the template classification model to obtain the second category of the data synchronization requirement, and compare the second category with the first category of the data synchronization template to filter candidate templates;

[0152] The execution unit 116 is used to query variable parameters from the data synchronization requirements, replace the parameter placeholders in the candidate templates with the variable parameters to obtain executable candidate templates, calculate the priority of the executable candidate templates, take the executable candidate template with the highest priority as the target template, and run the target template to complete data synchronization.

[0153] In some optional implementations, the first classification unit 111 is further configured to:

[0154] The source database type and the destination database type in the data synchronization template are combined to form the feature data of the data synchronization template;

[0155] According to the preset adaptation rules, the data synchronization tools that are compatible with the source database type and the destination database type are queried, and the name of the data synchronization tool is used as the first category of the data synchronization template.

[0156] In some optional implementations, the training unit 112 is further configured to:

[0157] For each of the data synchronization templates, tag data for the data synchronization templates is constructed based on the first category and the names of all data synchronization tools;

[0158] The feature data and the label data are mapped one-to-one to construct a training dataset;

[0159] Construct an initial classification model by inputting the feature data from the training dataset into the initial classification model to obtain a predicted classification result, and inputting the predicted classification result and the label data into a preset loss function to obtain the loss value of the initial classification model;

[0160] The initial classification model is updated using gradient descent until the loss value of the initial classification model no longer changes, at which point the update is stopped and a template classification model is obtained.

[0161] In some optional implementations, the parsing unit 113 is further configured to:

[0162] The data synchronization template is segmented to obtain multiple template words;

[0163] The template vocabulary is input into a preset template vocabulary classification model to obtain the category of the template vocabulary. The category includes at least static parameters and dynamic parameters. The template vocabulary with the category of static parameters and the template vocabulary with the category of dynamic parameters are used as variable parameters in the data synchronization template.

[0164] The preset parameter placeholders include static parameter placeholders and dynamic parameter placeholders. The template words in the data synchronization template that are classified as static parameters are replaced with the preset static placeholders, and the template words in the data synchronization template that are classified as dynamic parameters are replaced with the preset dynamic placeholders to obtain the updated data synchronization template.

[0165] In some optional implementations, the feature building unit 114 is further configured to:

[0166] The data synchronization requirements are segmented into words to obtain multiple requirement terms;

[0167] Each of the required terms is classified to obtain a category for each required term. The categories of the required terms include at least the source database and the destination database.

[0168] The required vocabulary categorized as source database and the required vocabulary categorized as destination database are combined to form the unclassified feature data corresponding to the preset synchronization requirement.

[0169] In some alternative implementations, the second classification unit 115 is further configured to:

[0170] Input the feature data to be classified into the template classification model to obtain the predicted probability list corresponding to the data to be classified, and take the name of the data synchronization tool corresponding to the non-zero value in the predicted probability list as the second category;

[0171] Compare the second category with the first category of the data synchronization template. If the first category is the same as the second category, then the data synchronization template is used as the alternative template.

[0172] In some optional embodiments, the execution unit 116 is further configured to:

[0173] Each of the required words is classified according to a preset semantic classification model to obtain a second category for each of the required words. The second category of the required words includes at least static and dynamic categories, with static and dynamic required words used as variable parameters.

[0174] Replace the static placeholders in the candidate template with static requirement words, and replace the dynamic placeholders in the candidate template with dynamic requirement words to obtain an executable candidate template;

[0175] The executable candidate templates are tested based on preset sample data to obtain the resource utilization rate of each candidate template, and the reciprocal of the resource utilization rate is used as the priority of the executable candidate template.

[0176] The highest priority executable alternative template is selected as the target template, and the target template is run to complete data synchronization.

[0177] The aforementioned AI-based data synchronization device marks the categories of data synchronization templates by identifying the source and destination databases in the data synchronization template, and uses these categories to train a template classification model. When selecting a data synchronization template, it can provide category guidance based on data synchronization needs, thereby efficiently identifying suitable data synchronization templates and improving the efficiency of data synchronization.

[0178] Example 3

[0179] Figure 3 shows a schematic diagram of an electronic device provided in an embodiment of this application. The electronic device 1 includes a memory 12 and a processor 13. The memory 12 is used to store computer-readable instructions, and the processor 13 uses the computer-readable instructions stored in the memory to implement the artificial intelligence-based data synchronization method of any of the above embodiments.

[0180] In an alternative embodiment, the electronic device 1 further includes a bus and a computer program stored in the memory 12 and executable on the processor 13, such as an artificial intelligence-based data synchronization program.

[0181] Figure 3 only shows an electronic device 1 with a memory 12 and a processor 13. Those skilled in the art will understand that the structure shown in Figure 3 does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0182] Referring to Figure 1, the memory 12 in the electronic device 1 stores multiple computer-readable instructions to implement an artificial intelligence-based data synchronization method, and the processor 13 can execute multiple instructions to achieve:

[0183] The data synchronization tool is constructed into a variety of data synchronization templates, which are used to synchronize data from the source database to the destination database.

[0184] The data synchronization template is classified according to the type of the source database and the type of the destination database in the data synchronization template to obtain the first category and feature data of the data synchronization template;

[0185] A training dataset is constructed based on the first category of the data synchronization template and the feature data, and a template classification model is trained based on the training dataset;

[0186] The data synchronization template is parsed to filter out the variable parameters, and the variable parameters are replaced with preset parameter placeholders to update the data synchronization template.

[0187] The received data synchronization requirements are parsed to obtain the database information to be classified. Based on the database information to be classified, the feature data to be classified is constructed. The database information to be classified includes at least the source database type and the destination database type to be classified.

[0188] The feature data to be classified is input into the template classification model to obtain the second category of the data synchronization requirement. The second category is compared with the first category of the data synchronization template to filter candidate templates.

[0189] Query the variable parameters from the data synchronization requirements, replace the parameter placeholders in the candidate templates with the variable parameters to obtain executable candidate templates, calculate the priority of the executable candidate templates, select the executable candidate template with the highest priority as the target template, and run the target template to complete data synchronization.

[0190] Specifically, the specific implementation method of the processor 13 for the above instructions can be referred to the description of the relevant steps in the embodiment corresponding to Figure 1, which will not be repeated here.

[0191] Those skilled in the art will understand that the schematic diagram is merely an example of electronic device 1 and does not constitute a limitation on electronic device 1. Electronic device 1 can be either a bus topology or a star topology. Electronic device 1 may also include more or fewer other hardware or software than shown in the diagram, or different component arrangements. For example, electronic device 1 may also include input / output devices, network access devices, etc.

[0192] It should be noted that electronic device 1 is only an example. Other existing or future electronic products that are suitable for this application should also be included within the scope of protection of this application and are incorporated herein by reference.

[0193] The memory 12 includes at least one type of readable storage medium, which can be non-volatile or volatile. The readable storage medium includes flash memory, portable hard drives, multimedia cards, card-type memory (e.g., SD or DX memory), magnetic storage, magnetic disks, optical disks, etc. In some embodiments, the memory 12 can be an internal storage unit of the electronic device 1, such as a portable hard drive of the electronic device 1. In other embodiments, the memory 12 can be an external storage device of the electronic device 1, such as a plug-in portable hard drive, Smart Media Card (SMC), Secure Digital (SD) card, Flash Card, etc., equipped on the electronic device 1. Furthermore, the memory 12 can include both internal storage units and external storage devices of the electronic device 1. The memory 12 can be used not only to store application software and various types of data installed on the electronic device 1, such as the code of an artificial intelligence-based data synchronization program, but also to temporarily store data that has been output or will be output.

[0194] In some embodiments, the processor 13 may be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 13 is the control unit of the electronic device 1, connecting various components of the electronic device 1 through various interfaces and lines. It executes programs or modules stored in the memory 12 (e.g., executing AI-based data synchronization programs) and calls data stored in the memory 12 to perform various functions and process data in the electronic device 1.

[0195] The processor 13 executes the operating system of the electronic device 1 and various installed applications. The processor 13 executes the applications to implement the steps in the various embodiments of the artificial intelligence-based data synchronization method described above, such as the steps shown in FIG1.

[0196] For example, the computer program may be divided into one or more modules / units, which are stored in memory 12 and executed by processor 13 to complete this application. The one or more modules / units may be a series of computer-readable instruction segments capable of performing specific functions, which describe the execution process of the computer program in electronic device 1. For example, the computer program may be divided into a construction unit 110, a first classification unit 111, a training unit 112, a parsing unit 113, a feature construction unit 114, a second classification unit 115, and an execution unit 116.

[0197] The integrated unit implemented as a software functional module described above can be stored in a computer-readable storage medium. This software functional module, stored in a storage medium, includes several instructions to cause a computer device (which may be a personal computer, computer equipment, or network device, etc.) or processor to execute portions of the artificial intelligence-based data synchronization method described in the various embodiments of this application.

[0198] If the modules / units integrated in electronic device 1 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware devices. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above.

[0199] The computer program includes computer program code, which may be in the form of source code, object code, executable file, or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording media, USB flash drive, portable hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory, and other memory.

[0200] Furthermore, the computer-readable storage medium may primarily include a stored program area and a stored data area, wherein the stored program area may store the operating system, an application program required for at least one function, etc.; and the stored data area may store data created based on the use of blockchain nodes, etc.

[0201] The bus can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This bus can be divided into address bus, data bus, control bus, etc. For ease of illustration, only one arrow is used in Figure 3, but this does not mean that there is only one bus or one type of bus. The bus is configured to implement communication between memory 12 and at least one processor 13, etc.

[0202] This application also provides a computer-readable storage medium (not shown) storing computer-readable instructions, which are executed by a processor in an electronic device to implement the artificial intelligence-based data synchronization method described in any of the above embodiments.

[0203] Furthermore, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices described in the specification may also be implemented by a single unit or device through software or hardware. Terms such as "first," "second," etc., are used to indicate names and do not indicate any specific order.

[0204] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application and are not intended to limit it. Although this application has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of this application without departing from the spirit and scope of the technical solutions of this application.

Claims

1. A data synchronization method based on artificial intelligence, characterized in that, The method includes: constructing a data synchronization tool into multiple data synchronization templates, wherein the data synchronization templates are used to synchronize data from a source database to a destination database; classifying the data synchronization templates according to the types of the source database and the destination database in the data synchronization templates to obtain a first category and feature data of the data synchronization templates; constructing a training dataset based on the first category and the feature data of the data synchronization templates, and training a template classification model based on the training dataset; parsing the data synchronization templates to filter the variable parameters therein, and replacing the variable parameters with preset parameter placeholders to update the data synchronization templates, including: performing word segmentation on the data synchronization templates to obtain multiple template words; inputting the template words into a preset template word classification model to obtain the categories of the template words, wherein the categories include at least static parameters and dynamic parameters, and using the template words with static parameters and the template words with dynamic parameters as variable parameters in the data synchronization templates; the preset parameter placeholders include static parameters and dynamic parameters. The system uses static and dynamic parameter placeholders to replace the template words in the data synchronization template that are classified as static parameters with the preset static placeholders, and also replaces the template words in the data synchronization template that are classified as dynamic parameters with the preset dynamic placeholders, thus obtaining an updated data synchronization template. It parses the received data synchronization request to obtain database information to be classified, and constructs feature data to be classified based on this information. The database information to be classified includes at least the source database type and the destination database type. It inputs the feature data to be classified into the template classification model to obtain the second category of the data synchronization request, and compares the second category with the first category of the data synchronization template to filter candidate templates. It queries the variable parameters from the data synchronization request, replaces the parameter placeholders in the candidate templates with the variable parameters to obtain executable candidate templates, calculates the priority of the executable candidate templates, and selects the executable candidate template with the highest priority as the target template, running the target template to complete data synchronization.

2. The data synchronization method based on artificial intelligence as described in claim 1, characterized in that, The step of classifying the data synchronization template according to the source database type and the destination database type in the data synchronization template to obtain the first category and feature data of the data synchronization template includes: combining the source database type and the destination database type in the data synchronization template into the feature data of the data synchronization template; querying the data synchronization tools that are adapted to the source database type and the destination database type according to preset adaptation rules, and taking the name of the data synchronization tool as the first category of the data synchronization template.

3. The data synchronization method based on artificial intelligence as described in claim 1, characterized in that, The step of constructing a training dataset based on the first category of the data synchronization template and the feature data, and training a template classification model based on the training dataset, includes: for each data synchronization template, constructing label data for the data synchronization template based on the first category and the names of all data synchronization tools; mapping the feature data to the label data one-to-one to construct a training dataset; constructing an initial classification model, inputting the feature data from the training dataset into the initial classification model to obtain a predicted classification result, inputting the predicted classification result and the label data into a preset loss function to obtain the loss value of the initial classification model; updating the initial classification model using gradient descent until the loss value of the initial classification model no longer changes, then stopping the update and obtaining the template classification model.

4. The data synchronization method based on artificial intelligence as described in claim 1, characterized in that, The process of parsing the received data synchronization request to obtain database information to be classified, and constructing feature data to be classified based on the database information to be classified, includes: segmenting the data synchronization request into words to obtain multiple request words; classifying each request word to obtain the category of each request word, wherein the category of the request word includes at least the source database and the destination database; and combining the request words categorized as source database and the request words categorized as destination database into the feature data to be classified corresponding to the synchronization request.

5. The data synchronization method based on artificial intelligence as described in claim 1, characterized in that, The step of inputting the feature data to be classified into the template classification model to obtain a second category of the data synchronization requirement, and comparing the second category with the first category of the data synchronization template to filter candidate templates, includes: inputting the feature data to be classified into the template classification model to obtain a list of predicted probabilities corresponding to the data to be classified; taking the names of the data synchronization tools corresponding to the non-zero values ​​in the list of predicted probabilities as the second category; comparing the second category with the first category of the data synchronization template; if the first category is the same as the second category, then taking the data synchronization template as a candidate template.

6. The data synchronization method based on artificial intelligence as described in claim 4, characterized in that, The process of querying variable parameters from the data synchronization requirements, replacing parameter placeholders in the candidate templates with the variable parameters to obtain executable candidate templates, and calculating the priority of the executable candidate templates includes: classifying each requirement term according to a preset semantic classification model to obtain a second category for each requirement term, wherein the second category of the requirement term includes at least static and dynamic, and using static and dynamic requirement terms as variable parameters; replacing static placeholders in the candidate templates with static requirement terms, and replacing dynamic placeholders in the candidate templates with dynamic requirement terms to obtain executable candidate templates; testing the executable candidate templates according to preset sample data to obtain the resource utilization rate of each candidate template, and using the reciprocal of the resource utilization rate as the priority of the executable candidate template; and using the executable candidate template with the highest priority as the target template, and running the target template to complete data synchronization.

7. A data synchronization device based on artificial intelligence, characterized in that, The apparatus includes: a construction unit for constructing a data synchronization tool into multiple data synchronization templates, wherein the data synchronization templates are used to synchronize data from a source database to a destination database; a first classification unit for classifying the data synchronization templates according to the types of the source database and the destination database, thereby obtaining a first category and feature data of the data synchronization templates; a training unit for constructing a training dataset based on the first category and feature data of the data synchronization templates, and training a template classification model based on the training dataset; and a parsing unit for parsing the data synchronization templates to filter variable parameters, replacing the variable parameters with preset parameter placeholders to update the data synchronization templates, including: performing word segmentation on the data synchronization templates to obtain multiple template words; inputting the template words into a preset template word classification model to obtain the categories of the template words, wherein the categories include at least static parameters and dynamic parameters, and using the template words with static parameters and the template words with dynamic parameters as variable parameters in the data synchronization templates; the preset parameter placeholders include... The system includes static parameter placeholders and dynamic parameter placeholders. Template words in the data synchronization template categorized as static parameters are replaced with preset static placeholders, and template words in the data synchronization template categorized as dynamic parameters are replaced with preset dynamic placeholders to obtain an updated data synchronization template. A feature construction unit parses the received data synchronization request to obtain database information to be classified, and constructs feature data to be classified based on the database information to be classified. The database information to be classified includes at least the source database type and the destination database type to be classified. A second classification unit inputs the feature data to be classified into the template classification model to obtain a second category of the data synchronization request, and compares the second category with the first category of the data synchronization template to filter candidate templates. An execution unit queries variable parameters from the data synchronization request, replaces parameter placeholders in the candidate templates with the variable parameters to obtain executable candidate templates, calculates the priority of the executable candidate templates, selects the executable candidate template with the highest priority as the target template, and runs the target template to complete data synchronization.

8. An electronic device, characterized in that, The electronic device includes: a memory for storing computer-readable instructions; and a processor for executing the computer-readable instructions stored in the memory to implement the artificial intelligence-based data synchronization method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, which are executed by a processor in an electronic device to implement the artificial intelligence-based data synchronization method as described in any one of claims 1 to 6.

Images