Solution for implementing computing service based on structured query language statement

A non-transitory, computer-readable medium storing one or more instructions executable by a computer system to perform operations comprising:

• performing syntax parsing on a SQL statement to determine whether an extended syntax identifier exists in the SQL statement, wherein the extended syntax identifier indicates a target computing service for the SQL statement, wherein the target computing service comprises a training service or a prediction service based on a machine learning model, wherein the SQL statement comprises a data query element for obtaining a training dataset to be used in the machine learning model;
• determining that the extended syntax identifier exists in the SQL statement and that the SQL statement is an extended SQL statement;
• determining that the extended SQL statement includes a computing element for configuring the machine learning model when executing the machine learning model based on the training dataset obtained, wherein the computing element comprises configuration parameters including a machine learning model name, a machine learning model parameter, a machine learning model feature, a machine learning model label, and a machine learning computation result storage address of the machine learning model;
• generating a computing service description statement in a first statement format based on the extended SQL statement comprising:
• generating data query program code in a first statement format based on the data query element in the extended SQL statement;
• and
• generating machine learning program code in the first statement format based on the computing element in the extended SQL statement, wherein the first statement format is a statement format that can be recognized by a target computing framework;
• and
• submitting the computing service description statement to the target computing framework, which i) executes the data query program code to obtain the training dataset queried by the data query element in the extended SQL statement for the machine learning model and ii) executes the machine learning program code with the training dataset obtained, using the configuration parameters included in the computing element in the extended SQL statement to perform the target computing service.

A computer-implemented system, comprising:

• one or more computers;
• and
• one or more computer memory devices interoperably coupled with the one or more computers and having tangible, non-transitory, machine-readable media storing one or more instructions that, when executed by the one or more computers, perform one or more operations comprising:
• performing syntax parsing on a SQL statement to determine whether an extended syntax identifier exists in the SQL statement, wherein the extended syntax identifier indicates a target computing service for the SQL statement, wherein the target computing service comprises a training service or a prediction service based on a machine learning model, wherein the SQL statement comprises a data query element for obtaining a training dataset to be used in the machine learning model;
• determining that the extended syntax identifier exists in the SQL statement and that the SQL statement is an extended SQL statement;
• determining that the extended SQL statement includes a computing element for configuring the machine learning model when executing the machine learning model based on the training dataset obtained, wherein the computing element comprises configuration parameters including a machine learning model name, a machine learning model parameter, a machine learning model feature, a machine learning model label, and a machine learning computation result storage address of the machine learning model;
• generating a computing service description statement in a first statement format based on the extended SQL statement comprising:
• generating data query program code in a first statement format based on the data query element in the extended SQL statement;
• and
• generating machine learning program code in the first statement format based on the computing element in the extended SQL statement, wherein the first statement format is a statement format that can be recognized by a target computing framework;
• and
• submitting the computing service description statement to the target computing framework, which i) executes the data query program code to obtain the training dataset queried by the data query element in the extended SQL statement for the machine learning model and ii) executes the machine learning program code with the training dataset obtained, using the configuration parameters included in the computing element in the extended SQL statement to perform the target computing service.