Method and apparatus for creating intelligent application, electronic device, and medium

Abstract

The application provides a method and device for creating an intelligent application, electronic equipment and a medium, which can be widely applied in the field of computer technology. The method for creating an intelligent application comprises: obtaining a target requirement of a target object, and collecting training data from a target data source based on the target requirement; processing the training data through a model training scaffold of a machine learning platform to obtain preprocessed data; establishing a pre-training model through the model training scaffold of the machine learning platform, and training the pre-training model according to the preprocessed data to obtain a target pre-training model; storing the target pre-training model in a product library; and creating an intelligent application based on the target pre-training model in the product library through an agent application scaffold or an inference service scaffold of a technical platform. The application integrates a machine learning platform and a technical platform to realize the whole-process deployment of an intelligent application, which is conducive to improving the efficiency of intelligent application development.

Description

Technical Field

[0001] This application relates to the field of computer technology, and more specifically, to a method, apparatus, electronic device, and medium for creating intelligent applications. Background Technology

[0002] With the rapid development of intelligent technologies, the demand for intelligent applications in the aviation retail sector is surging. To help airlines quickly build standardized intelligent applications and enrich the functionality of retail technology platforms, the intelligent construction of the retail technology platform development framework is urgently needed to rapidly build intelligent applications. One related technology involves using an inference framework to load artificial intelligence models for reasoning, thereby achieving intelligent construction of systems and applications. However, this solution requires developing the model architecture from scratch, resulting in low development efficiency for intelligent applications and an inability to adapt to the intelligent transformation of business operations. Summary of the Invention

[0003] The main objective of this application is to provide a method, apparatus, electronic device, and medium for creating intelligent applications, so as to at least solve the problem of low efficiency in the creation and development of intelligent applications in the prior art.

[0004] To achieve the above objectives, according to one aspect of this application, a method for creating an intelligent application is provided. The method includes: obtaining the target requirements of a target object, and collecting training data from a target data source based on the target requirements; processing the training data using a model training scaffold of a machine learning platform to obtain preprocessed data; establishing a pre-trained model using the model training scaffold of the machine learning platform, and training the pre-trained model based on the preprocessed data to obtain a target pre-trained model; storing the target pre-trained model in a product library; and creating an intelligent application based on the target pre-trained model in the product library using an intelligent agent application scaffold or an inference service scaffold of a technology platform. This application enables the development of intelligent applications in various application scenarios by building model training scaffolds, intelligent agent application scaffolds, and inference service scaffolds, and integrates machine learning platforms and technology platforms to achieve full-process deployment of intelligent applications, which is beneficial to improving the efficiency of intelligent application development.

[0005] Optionally, before processing the training data using a model training scaffolding from a machine learning platform to obtain preprocessed data, the method further includes:

[0006] A model training scaffold is built based on one or more of the Web framework, time series prediction framework and deep learning framework, so as to extract model training templates, model training template code or model training examples through the model training scaffold;

[0007] An inference service scaffold is established based on one or more of the Web framework, time series prediction framework, and deep learning framework to extract inference service templates, inference service template code, or inference service examples through the inference service scaffold.

[0008] A smart agent application scaffold is established based on the smart application framework to extract smart agent application templates, smart agent application template code, or smart agent application examples.

[0009] Optionally, the services of the intelligent application include one or more of intelligent agent services, business services, and inference services. After creating the intelligent application, the method further includes:

[0010] The intelligent agent service, the business service, the inference service, and the gateway are deployed to a container; wherein, the gateway is used to connect the intelligent application's service and the target terminal;

[0011] The intelligent agent service is registered to the registration center of the intelligent application service governance architecture through an auxiliary container corresponding to the intelligent agent service;

[0012] The auxiliary container corresponding to the intelligent agent service obtains the business configuration of the intelligent application service from the configuration center of the intelligent application service governance architecture, and performs load balancing or circuit breaking and rate limiting on the intelligent agent service.

[0013] Optionally, the intelligent agent service is registered to the registry center of the intelligent application service governance architecture through an auxiliary container corresponding to the intelligent agent service, including:

[0014] The agent service is registered to the registry center through the registry center's programming interface;

[0015] The first business service is discovered through the programming interface of the registry center, and the first business service is stored in the service discovery cache of the registry center; wherein, the first business service is a business service other than the agent service, the business service, and the inference service;

[0016] The service status of the intelligent agent service is detected by the heartbeat detection of the registration center, and the service discovery cache is updated so as to query the business service based on the service discovery cache.

[0017] Optionally, before obtaining the business configuration of the intelligent agent service from the configuration center of the intelligent application service governance architecture through the auxiliary container corresponding to the intelligent agent service, the method further includes:

[0018] The configuration center is used to modify and publish the business configuration so that the intelligent application service can detect the configuration changes.

[0019] Optionally, after creating the smart application, the method further includes:

[0020] The smart application is verified, and the verification result is obtained;

[0021] If the verification result is passed, the rendering parameters of the template engine are extracted to the parameter library, and the directory structure of the smart application is generated through the template engine.

[0022] Based on the directory structure and the service directory of the technology platform, a Giltab project is established, and services based on the intelligent application are provided to the target object based on the Giltab project.

[0023] Optionally, a pre-trained model of the scaffolding is established through model training on a machine learning platform, including:

[0024] Display the development framework interface;

[0025] In response to a trigger operation received on the intelligent application scaffolding control in the development framework interface, an information summary interface is displayed, and introductory information about the model training scaffolding, the intelligent agent application scaffolding, or the inference service scaffolding is presented in the information summary interface.

[0026] In response to the trigger operation received on the information introduction interface for the model training scaffold control, the model training scaffold details interface is displayed, and the video introduction control, template creation steps control, and template creation control are displayed on the model training scaffold details interface;

[0027] In response to the trigger operation of the create template control received on the model training scaffold details interface, the create model training template interface is displayed, and a pre-trained model is established based on the input operations of the framework and information received on the create model training template interface.

[0028] To achieve the above objectives, according to another aspect of this application, an apparatus for creating intelligent applications is provided, comprising:

[0029] The acquisition module is used to acquire the target requirements of the target object and collect training data from the target data source based on the target requirements;

[0030] The processing module is used to process the training data through the model training scaffold of the machine learning platform to obtain preprocessed data;

[0031] The training module is used to establish a pre-trained model through the model training scaffold of the machine learning platform, and to train the pre-trained model according to the pre-processed data to obtain a target pre-trained model; and to store the target pre-trained model in the product library.

[0032] A module is created to create intelligent applications based on the target pre-trained model in the product library, using an intelligent agent application scaffolding or inference service scaffolding of the technology platform.

[0033] According to another aspect of this application, an electronic device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the above-described method for creating a smart application through the computer program.

[0034] According to another aspect of this application, a computer-readable storage medium is provided, including a stored program, wherein, when the program is executed, it controls the device on which the computer-readable storage medium is located to perform the above-described method for creating a smart application.

[0035] According to another aspect of this application, a computer program product is provided, including computer instructions that, when executed by a processor, implement the steps of the method for creating the above-described intelligent application.

[0036] By applying the technical solution of this application, this application realizes the development of intelligent applications in various application scenarios by building model training scaffolding, intelligent agent application scaffolding and inference service scaffolding, and integrates machine learning platform and technology platform to realize the full-process deployment of intelligent applications, which is conducive to improving the efficiency of intelligent application development. Attached Figure Description

[0037] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:

[0038] Figure 1 The illustration shows an application scenario diagram of a method for creating an intelligent application provided in an embodiment of this application;

[0039] Figure 2 A flowchart illustrating a method for creating a smart application according to an embodiment of this application is shown.

[0040] Figure 3 A schematic diagram of the architecture of a smart application creation and development framework provided according to embodiments of this application is shown;

[0041] Figure 4 A flowchart illustrating the intelligent application creation and development process according to embodiments of this application is shown.

[0042] Figure 5 A schematic diagram of the service governance architecture provided according to an embodiment of this application is shown;

[0043] Figure 6 A schematic flowchart of an auxiliary container design according to an embodiment of this application is shown;

[0044] Figure 7 A schematic diagram of the structure of a smart application scaffolding provided according to an embodiment of this application is shown;

[0045] Figure 8 A flowchart illustrating an intelligent application scaffolding provided according to an embodiment of this application is shown;

[0046] Figure 9 A schematic diagram of the development framework interface provided according to an embodiment of this application is shown;

[0047] Figure 10 A schematic diagram of an information summary interface provided according to an embodiment of this application is shown;

[0048] Figure 11 A schematic diagram of the model training scaffolding details interface provided according to an embodiment of this application is shown;

[0049] Figure 12 A schematic diagram of the interface for creating a model training template according to an embodiment of this application is shown;

[0050] Figure 13 A schematic diagram of the structure of a smart application creation apparatus provided in an embodiment of this application is shown;

[0051] The above figures include the following reference numerals:

[0052] 102, Processor; 104, Memory; 106, Transmission device; 108, Input / output device; 310, Acquisition module; 320, Processing module; 330, Training module; 340, Creation module. Detailed Implementation

[0053] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0054] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0055] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of this application described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0056] As introduced in the background section, with the rapid development of intelligent technologies, the demand for intelligent applications in the airline retail sector is surging. To help airlines quickly build standardized intelligent applications and enrich the functionality of their retail technology platforms, the intelligent construction of the retail technology platform development framework is urgently needed. Furthermore, the construction of an intelligent scaffolding framework, as a core component, is crucial for achieving efficient development and expanding functionality, playing a vital role in promoting the intelligent transformation of airline retail.

[0057] In response, embodiments of this application provide a method for creating intelligent applications. By building model training scaffolding, intelligent agent application scaffolding, and inference service scaffolding, intelligent application development can be realized in various application scenarios. Furthermore, by integrating machine learning platforms and technology platforms, the entire process of intelligent application deployment can be realized, which is conducive to improving the efficiency of intelligent application development.

[0058] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

[0059] The methods and embodiments provided in this application can be executed on a mobile terminal, computer terminal, or similar computing device. Taking running on a mobile terminal as an example, Figure 1 This is a hardware structure block diagram of a mobile terminal for a method of creating a smart application according to an embodiment of the present invention. For example... Figure 1 As shown, a mobile terminal may include one or more ( Figure 1 Only one is shown in the diagram. A processor 102 (which may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data are also shown. The mobile terminal may further include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the mobile terminal described above. For example, the mobile terminal may also include components that are more... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0060] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the intelligent application creation method in this embodiment of the invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, thereby implementing the above-described method. The memory 104 may include high-speed random access memory and non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of the aforementioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof. The transmission device 106 is used to receive or send data via a network. Specific examples of the aforementioned networks may include wireless networks provided by the mobile terminal's communication provider. In one instance, the transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to communicate with the Internet. In one instance, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0061] This embodiment provides a method for creating an intelligent application that runs on a mobile terminal, computer terminal, or similar computing device. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Also, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0062] It should be noted that the information collected in this application is information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, storage, use, processing, transmission, provision, disclosure, and application of this data all comply with the relevant laws, regulations, and standards of the relevant countries and regions, and necessary confidentiality measures have been taken. This process does not violate public order and good morals, and corresponding access points are provided for users to choose whether to authorize or refuse. The automated decision-making involved in this application provides users with corresponding access points to choose whether to agree to or refuse the automated decision-making results; if the user chooses to refuse, the process proceeds to the expert decision-making stage.

[0063] Figure 2 This is a flowchart illustrating a method for creating a smart application according to an embodiment of this application. The method for creating a smart application includes:

[0064] Step S100: Obtain the target requirements of the target object, and collect training data from the target data source based on the target requirements;

[0065] Step S200: The training data is processed by the model training scaffold of the machine learning platform to obtain preprocessed data;

[0066] Step S300: Establish a pre-trained model using the model training scaffolding of the machine learning platform, and train the pre-trained model according to the preprocessed data to obtain the target pre-trained model; store the target pre-trained model in the product library;

[0067] Step S400: Using the intelligent agent application scaffolding or inference service scaffolding of the technology platform, an intelligent application is created based on the target pre-trained model in the product library.

[0068] The target object in this application can be a target user or a target terminal corresponding to a target user. The target requirement can be the need to create an intelligent application, which can be an application related to an artificial intelligence model. For example, an intelligent application can be a material-related system within an aviation system; an intelligent application can also be an intelligent question-and-answer system within an aviation system; an intelligent application can also be a data prediction system in any field. This application does not limit the application field and scenario of the intelligent application. The creation of the intelligent application in this application is based on... Figure 3 The illustrated intelligent backend scaffolding implementation enables rapid construction of intelligent applications through intelligent agent application scaffolding, inference service scaffolding, and model training scaffolding. Understandably, a scaffolding is typically a pre-built infrastructure or framework that provides developers with a way to quickly start a project. In one embodiment, the scaffolding might include the following: Pre-defined directory structure: Establishing a unified folder and file organization method for the project, helping team members understand the project layout more quickly and follow consistent coding standards. Basic code templates: Providing basic code snippets, such as functions, classes, and modules, which already handle common issues (such as error handling and logging), allowing developers to focus on writing business logic. Tool and library integration: Pre-installing and configuring a series of tools and libraries needed during development, such as build tools, testing frameworks, and database drivers, reducing manual configuration and installation time. Automated tasks: Setting up automated build, deployment, and testing processes to improve development efficiency and code quality. Documentation and guides: Providing detailed usage instructions to help new developers get started quickly. This application enables rapid model construction and training, and on-demand creation of intelligent applications by establishing intelligent agent application scaffolding, inference service scaffolding, and model training scaffolding.

[0069] Specifically, refer to Figure 4The flowchart shown represents one embodiment. Upon receiving the target requirements of the target object, this application collects training data from the target data source. The specific type and location of the target data source can be set according to requirements, and this application does not impose specific limitations. In this application, the machine learning platform corresponds to the model training scaffold. This application preprocesses the training data using the model training scaffold corresponding to the machine learning platform. Preprocessing may include one or more of data cleaning, data transformation, feature selection, feature engineering, data segmentation, data augmentation, dataset balancing, and dimensionality reduction. This application does not limit the specific type of preprocessing. This application rapidly establishes a pre-trained model using the model training scaffold and trains the established pre-trained model based on the machine learning platform to obtain a trained target pre-trained model. The pre-trained model in this application can be any artificial intelligence model. The target training model is stored in a model library and synchronized to the product library for easy access by business applications.

[0070] The target entity can use the intelligent agent application scaffolding or inference service scaffolding of the technology platform to create intelligent applications corresponding to the target requirements based on the target pre-trained model. Based on these intelligent applications, inference services or intelligent agent applications can be developed. Specifically, this application creates intelligent agent applications using the intelligent agent application scaffolding of the technology platform and intelligent applications using inference service scaffolding. This application connects the machine platform and the technology platform through the intelligent agent application scaffolding, inference service scaffolding, and model training scaffolding, enabling rapid construction of intelligent applications and improving development efficiency. It then provides services based on these intelligent applications to the target entity to respond to its target requirements.

[0071] Optionally, before processing the training data using a model training scaffolding from a machine learning platform to obtain preprocessed data, the method further includes:

[0072] A model training scaffold is built based on one or more of the Web framework, time series prediction framework and deep learning framework, so as to extract model training templates, model training template code or model training examples through the model training scaffold;

[0073] An inference service scaffold is established based on one or more of the Web framework, time series prediction framework, and deep learning framework to extract inference service templates, inference service template code, or inference service examples through the inference service scaffold.

[0074] A smart agent application scaffold is established based on the smart application framework to extract smart agent application templates, smart agent application template code, or smart agent application examples.

[0075] In this application, the Web framework can be a basic framework, the time series prediction framework can be Prophet, the deep learning framework can be PyTorch, and the intelligent application framework can be LangChain. Of course, the above frameworks can also be other architectures. This application does not limit the specific type of framework.

[0076] Optionally, the services of the intelligent application include one or more of intelligent agent services, business services, and inference services. After creating the intelligent application, the method further includes:

[0077] The intelligent agent service, the business service, the inference service, and the gateway are deployed to a container; wherein, the gateway is used to connect the intelligent application's service and the target terminal;

[0078] The intelligent agent service is registered to the registration center of the intelligent application service governance architecture through an auxiliary container corresponding to the intelligent agent service;

[0079] The auxiliary container corresponding to the intelligent agent service obtains the business configuration of the intelligent application service from the configuration center of the intelligent application service governance architecture, and performs load balancing or circuit breaking and rate limiting on the intelligent agent service.

[0080] Reference Figure 5 The service governance architecture diagram shown illustrates how, after creating an intelligent application, this application uses a service governance architecture to register, configure, load-balance, and handle circuit breakers for related services of the intelligent application. It can be understood that intelligent agent services provide a series of functions and services utilizing artificial intelligence technology. They can autonomously learn, understand, and adapt based on the environment, user behavior, or data input, thereby performing complex tasks. Intelligent agent services may include, but are not limited to, natural language processing, machine vision, speech recognition, and recommendation systems, helping applications achieve automated decision-making, interaction, and analysis. Business services focus more on specific application scenarios and business processes; they are services designed to solve specific business problems or meet specific business needs. Business services do not necessarily use artificial intelligence technology; they can be any software function or module that supports business operations. For example, inventory management, order processing, and customer relationship management are typical business services. When combined with intelligent agent services, business services can become more efficient and intelligent, such as using AI to predict inventory demand and optimize order allocation strategies. Inference services are the implementation of artificial intelligence technology under specific needs, using pre-trained models to predict data. In this application, the gateway, agent service, business service, and inference service are all deployed on the gateway, and the agent service, business service, and inference service are all deployed in corresponding auxiliary containers (i.e., Figure 5 (sidecar in the middle). Figure 5User requests, which is the target requirement in this application, are connected to various services via a gateway. Each service is then registered with the registry center via its corresponding auxiliary container. Finally, the configuration center configures the services to achieve load balancing or circuit breaking / rate limiting. The registry center and configuration center are... Figure 3 This application relates to the service registration and configuration management of intelligent application service governance. It is understood that the business services and inference services in this application are registered and configured in the same way as the intelligent agent services; that is, the business service is registered to the registration center of the intelligent application service governance architecture through an auxiliary container corresponding to the business service; the business configuration of the business service is obtained from the configuration center of the intelligent application service governance architecture through the auxiliary container corresponding to the business service, and load balancing or circuit breaking and rate limiting are performed on the business service. Similarly, the inference service is registered to the registration center of the intelligent application service governance architecture through an auxiliary container corresponding to the inference service; the business configuration of the inference service is obtained from the configuration center of the intelligent application service governance architecture through the auxiliary container corresponding to the inference service, and load balancing or circuit breaking and rate limiting are performed on the inference service. This application achieves high-speed and efficient operation of intelligent applications through service governance functions, thereby improving user satisfaction.

[0081] Optionally, the intelligent agent service is registered to the registry center of the intelligent application service governance architecture through an auxiliary container corresponding to the intelligent agent service, including:

[0082] The agent service is registered to the registry center through the registry center's programming interface;

[0083] The first business service is discovered through the programming interface of the registry center, and the first business service is stored in the service discovery cache of the registry center; wherein, the first business service is a business service other than the agent service, the business service, and the inference service;

[0084] The service status of the intelligent agent service is detected by the heartbeat detection of the registration center, and the service discovery cache is updated so as to query the business service based on the service discovery cache.

[0085] The programming interface in this application is... Figure 6 This application utilizes the OpenAPI of the service registry to discover and register business services, and performs heartbeat checks through the service registry to ensure the normal operation of each service. Simultaneously, this application stores the first discovered business service in a service discovery cache via a programming interface, allowing users to query business services and their corresponding instances through the service discovery cache. This application achieves the registration and discovery of intelligent application services through the service registry, facilitating the efficient construction of intelligent applications and enabling users to access intelligent applications efficiently and accurately.

[0086] Optionally, before obtaining the business configuration of the intelligent agent service from the configuration center of the intelligent application service governance architecture through the auxiliary container corresponding to the intelligent agent service, the method further includes:

[0087] The configuration center is used to modify and publish the business configuration so that the intelligent application service can detect the configuration changes.

[0088] This application modifies and publishes business configurations through a configuration center, enabling intelligent applications to detect configuration changes, obtain the new configuration, and perform service governance based on the new configuration. This application also utilizes service commands to achieve real-time maintenance of intelligent applications, thereby improving their operational stability.

[0089] Optionally, after creating the smart application, the method further includes:

[0090] The smart application is verified, and the verification result is obtained;

[0091] If the verification result is passed, the rendering parameters of the template engine are extracted to the parameter library, and the directory structure of the smart application is generated through the template engine.

[0092] Based on the directory structure and the service directory of the technology platform, a Giltab project is established, and services based on the intelligent application are provided to the target object based on the Giltab project.

[0093] like Figure 7 As shown, this application constructs the services, projects, and methods of an intelligent application scaffolding through the construction of an interface layer, service layer, and implementation layer. (Refer to...) Figure 8 The process of building a smart application using the smart application scaffolding involves first building the smart application using the scaffolding, then performing parameter validity checks. If the validity check passes, the rendering parameters from the template engine FreeMarker are extracted into the parameter library templateParamMap, and the directory structure and content of the smart application are generated. Finally, a Giltab project is created based on the service directory of the technology platform to facilitate the subsequent provision of smart application services to the target audience.

[0094] Optionally, a pre-trained model of the scaffolding is established through model training on a machine learning platform, including:

[0095] Display the development framework interface;

[0096] In response to a trigger operation received on the intelligent application scaffolding control in the development framework interface, an information summary interface is displayed, and introductory information about the model training scaffolding, the intelligent agent application scaffolding, or the inference service scaffolding is presented in the information summary interface.

[0097] In response to the trigger operation received on the information introduction interface for the model training scaffold control, the model training scaffold details interface is displayed, and the video introduction control, template creation steps control, and template creation control are displayed on the model training scaffold details interface;

[0098] In response to the trigger operation of the create template control received on the model training scaffold details interface, the create model training template interface is displayed, and a pre-trained model is established based on the input operations of the framework and information received on the create model training template interface.

[0099] This application achieves a highly simplified construction of smart applications through a visual interface combined with a smart application scaffolding. Users only need to perform simple operations on the modular controls of the smart application scaffolding to create smart applications. (See reference...) Figure 9 The development framework interface shown includes an intelligent scaffolding area, which is the intelligent application scaffolding control in this application. It is understood that this system can also establish front-end and back-end scaffolding, enabling simple construction of the front-end and back-end architectures and efficient deployment of front-end and back-end functions. The information summary interface can be a sub-area of ​​the development framework interface or a new interface from which the user navigates; this application does not limit the connection relationships and implementation logic of the various interfaces. (See reference...) Figure 10 The information summary interface described in this application may include information such as a brief overview of the scaffolding structure and its version number. Figure 10 The area corresponding to "View Details" is the model training scaffolding control in this application. The triggering operation in this application can be a click operation, a touch operation, a selection operation, etc., and this application does not limit the specific type of triggering operation. (See reference...) Figure 11 The model training scaffold details interface shown here allows you to introduce the model training scaffold using a video introduction control and demonstrate the usage process using a template creation step control, such as... Figure 11 The process area displays steps, and the creation of model training targets is triggered by creating template controls. This is achieved by triggering the creation of template controls (such as...). Figure 11 (Create area in the middle), which displays the interface for creating model training templates, such as Figure 12As shown, in the model training template creation interface, the operator needs to determine information such as framework type, project, and development language by inputting operations. Then, based on the information corresponding to the input operations, a pre-trained model is built. This realizes the construction of intelligent applications through model training scaffolding and visual interface controls, reducing the difficulty of building intelligent applications and improving the efficiency of building intelligent applications.

[0100] Of course, it is understood that the process of building intelligent applications based on reasoning service scaffolding or model training scaffolding is the same as the process of building intelligent agent application scaffolding, and will not be shown in this application. Those skilled in the art can build intelligent applications according to their needs.

[0101] Optionally, after creating an intelligent application based on the target pre-trained model in the product library, the method further includes:

[0102] Establish an intelligent application service governance architecture to perform service registration and service configuration for the intelligent applications.

[0103] This application utilizes an intelligent application service governance architecture to register and configure services for intelligent applications. Specifically, the intelligent application service governance architecture includes a registration center and a configuration center, which respectively manage the registration and configuration of services for intelligent applications.

[0104] After creating an intelligent application based on the target pre-trained model in the product library, the method further includes:

[0105] The intelligent application is packaged through the pipeline of the technology platform to obtain service components;

[0106] The service components are deployed on the delivery platform to provide services based on the intelligent application to the target object through the delivery platform.

[0107] To enable those skilled in the art to better understand the technical solution of this application, the implementation process of the method for creating intelligent applications of this application will be described in detail below with reference to specific embodiments.

[0108] This application provides intelligent application scaffolding construction: training model scaffolding and inference service scaffolding construction based on Prophet, Pytorch and Temsorflow, intelligent agent application scaffolding construction based on LangChain framework, while supporting the integration and access of multiple data sources for each scaffolding, and realizing the visualization of intelligent scaffolding functions.

[0109] Construction of intelligent application service governance functions: Construction of intelligent application service governance functions, such as intelligent application function service registration, configuration management, load balancing and circuit breaking and rate limiting; at the same time, overall integration with the retail technology platform, including service catalog, pipeline, application delivery, service governance and service monitoring.

[0110] like Figure 3 As shown, the intelligent backend scaffolding comprises two modules: intelligent application scaffolding and intelligent application service governance. The intelligent application scaffolding includes an agent application scaffolding based on the LangChain framework, providing project templates, template code, and examples to support airlines in quickly and standardizedly building agent applications; a model training scaffolding, leveraging existing machine learning platform features to support basic frameworks, Prophet, PyTorch, and TensorFlow frameworks, while providing corresponding model training project templates, model training template code, and examples to support airlines in quickly and standardized building model training projects; and an inference service scaffolding, supporting basic frameworks, Prophet, PyTorch, and TensorFlow frameworks, while providing corresponding inference service project templates, inference service template code, and examples to support airlines in quickly and standardized building inference service functions. The intelligent application service governance module includes functions such as tracing, log management, configuration management, circuit breaking and rate limiting, metric monitoring, load balancing, and service registration, providing service governance capabilities for the intelligent scaffolding. The model training scaffold supports integration with multiple data sources, including the Xuanji platform, object storage, FTP, and Elasticsearch. The intelligent agent application scaffold needs to support integration with various LLM services, such as Qwen, LLaMA, or large language models deployed privately by airlines. The intelligent backend scaffold is integrated with the retail technology platform, including service catalogs, pipelines, application delivery, service governance, and service monitoring. Finally, through the visualization capabilities of the intelligent backend scaffold, airlines are provided with the ability to quickly build intelligent applications, effectively reducing the complexity of intelligent application engineering and improving delivery efficiency.

[0111] like Figure 4 As shown in the interactive diagram of the intelligent application scaffolding, after receiving intelligent requirements, developers can use the technology platform's model training scaffolding to train models and create applications. Developers can maintain and test models locally. After initial data collection from the data source, they can perform data processing (such as data access, data cleaning, data labeling, and feature engineering), model development and training (such as model development, model training, model evaluation, and model optimization), and model management on the machine learning platform. The model code will be maintained in a code repository, such as GitRepo. The model will be stored in the model repository through the model management function and finally synchronized to object storage, exposed to business applications by the product repository.

[0112] After completing model training and synchronizing the model to object storage, developers can create the required intelligent applications using the technology platform's inference service scaffolding or intelligent agent application scaffolding, and then develop the inference service or intelligent agent application. The intelligent applications are packaged into service artifacts or component artifacts through a pipeline, and deployed through a delivery platform. Finally, the inference service or intelligent agent application is monitored through service monitoring, and its online operation is managed through service governance functions.

[0113] The service governance function mainly targets inference services and agent services, as shown in the architecture diagram below. Figure 5 As shown, the Gateway, Agent Service A (Python), Business Service B (Java), and Inference Service C (Python) are all deployed in a container environment. Agent Service A (Python) and Inference Service C (Python) register the intelligent services with the registry center through their respective Sidecars (Python) and obtain business configurations through the configuration center. Through the service governance functions of the technology platform, and with the help of the registry center and configuration center, service registration, configuration management, load balancing, and circuit breaking / rate limiting are performed on the intelligent services. Load balancing between intelligent services and between intelligent services and ordinary business services is achieved through the Sidecar (Python) component. Finally, it is fully integrated with the existing service governance, service catalog, pipeline, application delivery, and service monitoring functions of the technology platform, ensuring comprehensive compatibility.

[0114] Sidecar (Python) component design and workflow design, such as Figure 6 As shown, the Sidecar (Python) component uses nacos-sdk-python as its basic technology stack to implement service governance functions such as service registration, load balancing, configuration management, and circuit breaking and rate limiting. It also integrates monitoring tracing, log management, and metric monitoring functions, ultimately providing a comprehensive Sidecar (Python) component for business applications. The component is designed as follows:

[0115] After a business application depends on this component, upon service startup, it first registers its own service with the registry center via the registry center's OpenAPI. It then discovers other business services through the registry center's OpenAPI, completing service discovery and storing the results locally. Utilizing the registry center's CheckHeartBeat mechanism, a heartbeat detection mechanism is used to monitor service status in real time and update the local service discovery cache. After the service starts, users can query the service and its instance on the technical platform. They can also use the platform's service governance functions to modify and publish configurations, enabling configuration management, circuit breaker and rate limiting configuration publishing, and service on / off functionality. Business applications monitor configuration changes in real time and dynamically obtain the latest configuration.

[0116] Reference Figure 7 The specific implementation of the present invention includes the following steps: In the interface layer ScaffoldApplicationApi interface and its inherited class ScaffoldController, add the methods createModelTrainingScaffoldApplication, createAIAgentScaffoldApplication and createInferenceServiceScaffoldApplication to satisfy the creation functions of model training scaffold, agent application scaffold and inference service scaffold.

[0117] In the service layer, a new ScaffoldModelTrainingBuildImplService is added, which implements the main construction logic of the model training scaffold through the buildModelTrainingScaffold method; a new ScaffoldInferenceServiceBuildImplService is added, which implements the main construction logic of the inference service scaffold through the buildInferenceServiceScaffold method; and a new ScaffoldAIAgentBuildImplService is added, which implements the main construction logic of the agent application scaffold through the buildAIAgentScaffold method.

[0118] At the implementation layer, the specific implementation of the model training scaffold, agent application scaffold, and inference service scaffold construction functions is completed through TemplateParamService and by reusing ScaffoldApplicationService, GitlabService, and ZipService.

[0119] Specifically, regarding the interface layer design:

[0120] ScaffoldApplicationApi: This is a top-level interface used to define the basic methods for creating different types of scaffolded applications. The "scaffolding" mentioned here can be understood as a template or framework used to quickly build the basic structure of an application, reducing repetitive work. `createModelTrainingScaffoldApplication`: This is a method in `ScaffoldApplicationApi` used to create a model training scaffolded application. `createAIAgentScaffoldApplication`: This is another method used to create an agent application scaffold. `createInferenceServiceScaffoldApplication`: Used to create an inference service scaffold. `ScaffoldController`: This is likely an implementation class of `ScaffoldApplicationApi`, responsible for handling requests from the user or frontend and calling the corresponding service layer methods to create the scaffolded application.

[0121] Service layer implementation:

[0122] `ScaffoldModelTrainingBuildImplService`: This service implements the specific model training scaffold. It includes the `buildModelTrainingScaffold` method, which constructs the model training scaffold according to requirements. `ScaffoldInferenceServiceBuildImplService`: This service implements the inference service scaffold; its core method is `buildInferenceServiceScaffold`. `ScaffoldAIAgentBuildImplService`: This service implements the agent application scaffold; its core method is `buildAIAgentScaffold`. These service layer methods are responsible for calling various tools and services from the implementation layer to complete the specific logic for creating the scaffold.

[0123] Implementation layer tools:

[0124] TemplateParamService: May be used to process template parameters and customize the specific configuration for each scaffold application. ScaffoldApplicationService: Provides basic services for creating application scaffolds, potentially including some common creation logic. GitlabService: May be used to initialize or update the project repository in GitLab, storing the scaffold application's code and resources. ZipService: May be used to package or unpack the scaffold application's code and resources for easy download or deployment.

[0125] Overall, this application designs a layered pattern of interface layer - service layer - implementation layer, wherein:

[0126] The interface layer defines the externally visible API, providing functionality for creating different types of scaffolding. The service layer contains the specific business logic implementation, completing tasks by calling services from the implementation layer. The implementation layer provides various tools and services to implement the specific scaffolding construction process, such as template parameter processing, Git repository management, and code packaging.

[0127] The flowchart of the program that satisfies the model training scaffold, agent application scaffold, and inference service scaffold proposed in this application is as follows: Figure 8 As shown, the process of building intelligent applications based on intelligent scaffolding includes the following steps:

[0128] Step S81: The user creates a corresponding intelligent application through the model training scaffold, the intelligent agent application scaffold, or the inference service scaffold.

[0129] Step S82, parameter validity verification, including string length, required fields, etc.;

[0130] Step S83: Extract the rendering parameters required by FreeMarker into templateParamMap;

[0131] Step S84: Generate the project directory structure and content corresponding to the model training application, inference service application, or intelligent agent application through the FreeMarker template engine.

[0132] Step S85: Create a Giltab project as needed, in accordance with the technical platform service catalog;

[0133] Step S86: Generate a compressed ZIP file and return the ZIP file result.

[0134] In another embodiment, this application also provides a simplified construction of intelligent applications through a visual interface, specifically including the following steps:

[0135] Step S91: Create a new Smart Scaffolding Tab (i.e., the development framework interface displayed in this application). Under [Development Framework] > [Scaffolding], add a [Smart Scaffolding] tab (i.e., the smart application scaffolding control), such as... Figure 9 As shown;

[0136] Step S92, add a new information summary page. Taking the [Model Training Scaffold] page (i.e., the information summary interface) as an example, such as... Figure 10 As shown.

[0137] Step S93: Add a new scaffolding details page (i.e., the model training scaffolding details interface). Taking the [Model Training Scaffolding] as an example, the functions of the model training scaffolding details page include basic information about the model training scaffolding, viewing video introductions, creating application project templates, usage procedures, development specifications, and introductions to third-party marketplaces and frameworks. Figure 11 As shown.

[0138] Step S93: Add a new intelligent application engineering template page (i.e., the model training template creation interface). Taking the [Model Training Scaffold] as an example, when the user clicks the [Create Intelligent Application Engineering Template] button in the upper right corner of the scaffold details page, the intelligent application engineering template creation page will be displayed.

[0139] Step S93: After the user completes the creation on the intelligent application engineering template page and clicks the final "Confirm" button, the model training scaffolding project zip package is exported. After unzipping the zip package, it is imported into the development tool to start the application's model training and development.

[0140] This application's intelligent backend scaffolding comprises two modules: intelligent application scaffolding and intelligent application service governance. The intelligent application scaffolding includes an agent application scaffolding based on the LangChain framework, providing project templates, template code, and examples to support airlines in rapidly and standardizedly building agent applications; a model training scaffolding, leveraging existing machine learning platform features to support basic frameworks, Prophet, PyTorch, and TensorFlow frameworks, and providing corresponding model training project templates, model training template code, and examples to support airlines in rapidly and standardized building model training projects; and an inference service scaffolding, supporting basic frameworks, Prophet, PyTorch, and TensorFlow frameworks, and providing corresponding inference service project templates, inference service template code, and examples to support airlines in rapidly and standardized building inference service functions. The intelligent application service governance module includes functions such as tracing, log management, configuration management, circuit breaking and rate limiting, metric monitoring, load balancing, and service registration, providing service governance capabilities for the intelligent scaffolding. The model training scaffold supports integration with multiple data sources, including the Xuanji platform, object storage, FTP, and Elasticsearch. The intelligent agent application scaffold needs to support integration with various LLM services, such as Qwen, LLaMA, or large language models deployed privately by airlines. The intelligent backend scaffold is integrated with the retail technology platform, including service catalogs, pipelines, application delivery, service governance, and service monitoring. Finally, through the visualization capabilities of the intelligent backend scaffold, airlines are provided with the ability to quickly build intelligent applications, effectively reducing the complexity of intelligent application engineering and improving delivery efficiency.

[0141] This application provides a model training scaffold (supporting multi-framework and multi-data source integration), an inference service scaffold, and a LangChain-based agent application scaffold; it integrates a service governance module (link tracing, log management, configuration management, etc.) and deeply integrates with the service catalog and pipeline functions of the retail technology platform; it provides visual building capabilities, covering the entire process from data processing and model training to application deployment. This invention addresses the intelligent transformation needs of the aviation retail sector, supporting various development scenarios such as model training, inference services, and agent applications (e.g., flight retail recommendation model training, user consultation agent development), and adapts to the industry characteristics of airlines through private deployment and multi-data source integration (Xuanji platform, FTP, etc.).

[0142] To achieve the above objectives, in accordance with another aspect of this application, referring to Figure 13 This application provides an apparatus for creating intelligent applications, comprising:

[0143] The acquisition module 310 is used to acquire the target requirements of the target object and collect training data from the target data source based on the target requirements;

[0144] The processing module 320 is used to process the training data through the model training scaffold of the machine learning platform to obtain preprocessed data;

[0145] The training module 330 is used to establish a pre-trained model through the model training scaffold of the machine learning platform, and to train the pre-trained model according to the pre-processed data to obtain a target pre-trained model; and to store the target pre-trained model in the product library.

[0146] Module 340 is used to create intelligent applications based on the target pre-trained model in the product library, through the intelligent agent application scaffolding or inference service scaffolding of the technology platform.

[0147] According to another aspect of this application, an electronic device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the above-described method for creating a smart application through the computer program.

[0148] According to another aspect of this application, a computer-readable storage medium is provided, including a stored program, wherein, when the program is executed, it controls the device on which the computer-readable storage medium is located to perform the above-described method for creating a smart application.

[0149] According to another aspect of this application, a computer program product is provided, including computer instructions that, when executed by a processor, implement the steps of the method for creating the above-described intelligent application.

[0150] It should be noted that the above are merely illustrative examples and do not specifically limit the implementation logic.

[0151] It is obvious to those skilled in the art that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. They can be implemented using computer-executable program code, and thus can be stored in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those described herein, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0152] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0153] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0154] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0155] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0156] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0157] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0158] Computer-readable media include both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0159] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0160] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0161] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for creating an intelligent application, characterized in that, The method for creating the intelligent application includes: Obtain the target requirements of the target object, and collect training data from the target data source based on the target requirements; The training data is processed by training the scaffold using a model from a machine learning platform to obtain preprocessed data; A pre-trained model is established by training the scaffolding model through the machine learning platform, and the pre-trained model is trained according to the preprocessed data to obtain the target pre-trained model; the target pre-trained model is then stored in the product library. Intelligent applications are created based on the target pre-trained model in the product library through the intelligent agent application scaffolding or inference service scaffolding of the technology platform.

2. The method for creating intelligent applications according to claim 1, characterized in that, Before processing the training data using a model trained on a machine learning platform to obtain preprocessed data, the method further includes: A model training scaffold is built based on one or more of the Web framework, time series prediction framework and deep learning framework, so as to extract model training templates, model training template code or model training examples through the model training scaffold; An inference service scaffold is established based on one or more of the Web framework, time series prediction framework, and deep learning framework to extract inference service templates, inference service template code, or inference service examples through the inference service scaffold. A smart agent application scaffold is established based on the smart application framework to extract smart agent application templates, smart agent application template code, or smart agent application examples.

3. The method for creating intelligent applications according to claim 1, characterized in that, The services of the intelligent application include one or more of intelligent agent services, business services, and inference services. After creating the intelligent application, the method further includes: The intelligent agent service, the business service, the inference service, and the gateway are deployed to a container; wherein, the gateway is used to connect the intelligent application's service and the target terminal; The intelligent agent service is registered to the registration center of the intelligent application service governance architecture through an auxiliary container corresponding to the intelligent agent service; The auxiliary container corresponding to the intelligent agent service obtains the business configuration of the intelligent application service from the configuration center of the intelligent application service governance architecture, and performs load balancing or circuit breaking and rate limiting on the intelligent agent service.

4. The method for creating intelligent applications according to claim 3, characterized in that, Registering the intelligent agent service to the registry center of the intelligent application service governance architecture through an auxiliary container corresponding to the intelligent agent service includes: The agent service is registered to the registry center through the registry center's programming interface; The first business service is discovered through the programming interface of the registry center, and the first business service is stored in the service discovery cache of the registry center; wherein, the first business service is a business service other than the agent service, the business service, and the inference service; The service status of the intelligent agent service is detected by the heartbeat detection of the registration center, and the service discovery cache is updated so as to query the business service based on the service discovery cache.

5. The method for creating intelligent applications according to claim 3, characterized in that, Before obtaining the business configuration of the intelligent agent service from the configuration center of the intelligent application service governance architecture through the auxiliary container corresponding to the intelligent agent service, the method further includes: The configuration center is used to modify and publish the business configuration so that the intelligent application service can detect the configuration changes.

6. The method for creating an intelligent application according to claim 1, characterized in that, After creating the smart application, the method further includes: The smart application is verified, and the verification result is obtained; If the verification result is passed, the rendering parameters of the template engine are extracted to the parameter library, and the directory structure of the smart application is generated through the template engine. Based on the directory structure and the service directory of the technology platform, a Giltab project is established, and services based on the intelligent application are provided to the target object based on the Giltab project.

7. The method for creating intelligent applications according to claim 1, characterized in that, Building a pre-trained model for the scaffolding through model training on a machine learning platform includes: Display the development framework interface; In response to a trigger operation received on the intelligent application scaffolding control in the development framework interface, an information summary interface is displayed, and introductory information about the model training scaffolding, the intelligent agent application scaffolding, or the inference service scaffolding is presented in the information summary interface. In response to the trigger operation received on the information introduction interface for the model training scaffold control, the model training scaffold details interface is displayed, and the video introduction control, template creation steps control, and template creation control are displayed on the model training scaffold details interface; In response to the trigger operation of the create template control received on the model training scaffold details interface, the create model training template interface is displayed, and a pre-trained model is established based on the input operations of the framework and information received on the create model training template interface.

8. A device for creating intelligent applications, characterized in that, The device for creating the intelligent application includes: The acquisition module is used to acquire the target requirements of the target object and, based on the target requirements, collect training data from the target data source. The processing module is used to process the training data through the model training scaffold of the machine learning platform to obtain preprocessed data; The training module is used to establish a pre-trained model through the model training scaffold of the machine learning platform, and to train the pre-trained model according to the pre-processed data to obtain a target pre-trained model; and to store the target pre-trained model in the product library. A module is created to create intelligent applications based on the target pre-trained model in the product library, using an intelligent agent application scaffolding or inference service scaffolding of the technology platform.

9. An electronic device, characterized in that, The electronic device includes: A memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute, via the computer program, the method for creating the intelligent application according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein, when the program is executed, it controls the device on which the computer-readable storage medium is located to perform the method for creating an intelligent application according to any one of claims 1 to 7.

Images