A service operation method and device

Abstract

The embodiment of the present application provides a service operation method and device, including: obtaining service configuration template information sent by a user; using the service configuration template information to generate an image file containing a preset model and an operating environment deployment file; using the image file and the operating environment deployment file to run a service based on the preset model at a preset service node. Through the service operation method of the embodiment of the present application, the service configuration template information is used to generate an image file and an operating environment deployment file, and the image file and the operating environment deployment file are used to run a service based on the preset model at a preset service node. Therefore, the service configuration template information can be used to realize the rapid deployment and operation of services based on the preset model, thereby improving the deployment and operation efficiency of services based on the preset model.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a service operation method and a service operation device. Background Art

[0002] With the development of technology, the demand for model-based services such as speech recognition and face detection is gradually expanding. Model-based services can be deployed to at least one server for operation according to the actual needs of users. However, since the models used by model-based services need to be updated, the operating environments of different servers are different, the usage of model-based services at different times is different, resulting in the need to adjust the number of services running in real time, etc., users may need to frequently deploy model-based services on multiple servers, resulting in cumbersome deployment and operation of model-based services.

[0003] Application Contents

[0004] In view of the above problems, embodiments of the present application are proposed to provide a service operation method and a corresponding service operation device that overcome the above problems or at least partially solve the above problems.

[0005] In order to solve the above problems, the present application discloses a service operation method, including:

[0006] Get the service configuration template information sent by the user;

[0007] Generate an image file and an operating environment deployment file using the service configuration template information;

[0008] The image file and the operating environment deployment file are used to run the service based on the preset model on the preset service node.

[0009] Optionally, the step of using the service configuration template information to generate an image file containing a preset model and an operating environment deployment file includes:

[0010] Extracting model configuration information and container deployment configuration information from the service configuration template information;

[0011] Using the model configuration information, determine the dependency library corresponding to the service based on the preset model;

[0012] Generate an image file using the dependency library and the model configuration information;

[0013] The container deployment configuration information is used to generate an operating environment deployment file adapted to a preset service node.

[0014] Optionally, the step of using the dependent library and the model configuration information to generate an image file includes:

[0015] Using the model configuration information, determine the model calling file of the preset model;

[0016] Creating calling interface information for the model calling file;

[0017] The dependent library, the calling interface information, and the model calling file are used to generate an image file.

[0018] Optionally, the step of using the container deployment configuration information to generate an operating environment deployment file adapted to a preset service node includes:

[0019] Parsing the container deployment configuration information to determine the operation requirement resource information corresponding to the service based on the preset model;

[0020] The operation requirement resource information is used to generate an operation environment deployment file adapted to a preset service node.

[0021] Optionally, the service node includes an edge service node;

[0022] The step of using the image file and the operating environment deployment file to run the service based on the preset model on the preset service node includes:

[0023] The image file and the operating environment deployment file are used to run the service based on the preset model at the preset edge service node.

[0024] The embodiment of the present application also discloses a service operation device, including:

[0025] The acquisition module is used to obtain the service configuration template information sent by the user;

[0026] A generation module, used to use the service configuration template information to generate an image file containing a preset model and an operating environment deployment file;

[0027] The running module is used to use the image file and the running environment deployment file to run the service based on the preset model on the preset service node.

[0028] Optionally, the generating module includes:

[0029] An extraction submodule, used to extract model configuration information and container deployment configuration information from the service configuration template information;

[0030] A determination submodule, configured to use the model configuration information to determine a dependency library corresponding to the service based on the preset model;

[0031] A first generation submodule, used to generate an image file using the dependency library and the model configuration information;

[0032] The second generation submodule is used to use the container deployment configuration information to generate an operating environment deployment file adapted to a preset service node.

[0033] Optionally, the first step of generating a submodule includes:

[0034] A determination unit, configured to determine a model calling file of the preset model using the model configuration information;

[0035] A creation unit, used for creating calling interface information for the model calling file;

[0036] The first generating unit is used to generate an image file by using the dependent library, the calling interface information, and the model calling file.

[0037] Optionally, the second generating submodule includes:

[0038] A parsing unit, used to parse the container deployment configuration information and determine the operation demand resource information corresponding to the service based on the preset model;

[0039] The second generating unit is used to generate an operating environment deployment file adapted to a preset service node by using the operating requirement resource information.

[0040] Optionally, the service node includes an edge service node;

[0041] The operation module includes:

[0042] The running submodule is used to use the image file and the running environment deployment file to run the service based on the preset model at the preset edge service node.

[0043] The present application also discloses a device, including:

[0044] one or more processors; and

[0045] One or more machine-readable media having instructions stored thereon, when executed by the one or more processors, cause the device to perform one or more methods as described in the embodiments of the present application.

[0046] The embodiments of the present application also disclose one or more machine-readable media on which instructions are stored, which, when executed by one or more processors, enable the processors to execute one or more methods described in the embodiments of the present application.

[0047] The embodiments of the present application include the following advantages:

[0048] Through the service operation method of the embodiment of the present application, the service configuration template information is used to generate an image file and an operation environment deployment file, and the image file and the operation environment deployment file are used to run the service based on the preset model on the preset service node. Therefore, the service configuration template information can be used to realize the rapid generation of the image file and the operation environment deployment file of the service based on the preset model, and realize the rapid deployment and operation of the service based on the preset model, thereby improving the deployment and operation efficiency of the service based on the preset model. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 It is a flowchart of the steps of an embodiment of a service operation method of the present application;

[0050] Figure 2 is a flowchart of another embodiment of a service operation method of the present application;

[0051] Figure 3 It is a flow chart of an embodiment of a service operation method of the present application;

[0052] Figure 4 It is a structural block diagram of an embodiment of a service operation device of the present application. DETAILED DESCRIPTION

[0053] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0054] Reference Figure 1 , shows a flow chart of the steps of an embodiment of a service operation method of the present application, which may specifically include the following steps:

[0055] Step 101, obtaining service configuration template information sent by the user;

[0056] In an embodiment of the present application, the service may be applied to at least one server. The server may be a local server or a cloud server, and the present application does not limit this. Specifically, the servers may form a cloud server cluster, and the cloud server cluster may include several service nodes distributed in different locations. The service node may be composed of at least one server. A user may connect to the service node through a network and operate the service node. The service node may include a central service node and an edge service node. The central service node may be closer to the manager of the cloud service cluster, so that the manager can manage the cloud service cluster through the central service node and provide higher computing power. The edge service node may be closer to the users of the cloud service cluster, so that users can access the services provided in the service node more quickly.

[0057] In the embodiment of the present application, the service may be a service implemented based on a preset model, such as speech recognition, face detection, text classification, etc. The service may include sample data collection, sample data cleaning, model training, model deployment, model reasoning, etc.

[0058] In an embodiment of the present application, the preset model may be a model based on supervised learning, such as a decision tree, a random forest, a support vector machine, a relevance vector machine, etc. The model may also be a model based on semi-supervised learning, such as a generative model, a semi-supervised support vector machine, etc. The model may also be a neural network model, such as an autoencoder, a multi-layer perceptron, a recurrent neural network model, a convolutional neural network model, etc., which is not limited in the present application.

[0059] In an embodiment of the present application, different contents in the service can be assigned to different servers according to actual needs. For example, in a cloud server cluster, the tasks of sample data collection, sample data cleaning, and model training in the service are handled by the central service node in the cloud server cluster, while the tasks of model deployment and model reasoning are handled by the edge service node in the cloud server cluster. It is also possible to assign all contents in the service to at least one server for joint processing according to actual needs. For example, the tasks of sample data collection, sample data cleaning, model training, model deployment, and model reasoning are all handled by the central service node in a cloud server cluster. This application does not impose any restrictions on this.

[0060] In an embodiment of the present application, a user can deploy and run a service based on a preset model in at least one server. Configuration template information sent by a user can be obtained, and the service configuration template information can include service configuration information filled in by the user based on a preset configuration template. Therefore, based on the service configuration template information, information such as the type of service that the user needs to deploy, the service node on which the service is to be deployed, and the computing resources that need to be reserved for the service can be obtained.

[0061] Step 102, using the service configuration template information to generate an image file containing a preset model and an operating environment deployment file;

[0062] In the embodiment of the present application, after the model has been pre-trained, the user can deploy the model to actual applications to implement tasks such as speech recognition, face detection, and text classification. Since different service nodes may have different operating environments, the service configuration template information can be used to generate an image file containing a preset model and an operating environment deployment file, so that the service based on the preset model can be run on the service node.

[0063] In an embodiment of the present application, the image file containing the preset model can be used to run the reasoning service. The image file may include a service based on the preset model and data required to run the service based on the preset model. Thus, the service node can realize the operation of the service based on the preset model by loading the image file. The operating environment deployment file can be used to describe the environment required to run the service based on the preset model in the service node and the loading method of the image file, so that the service node can use the operating environment deployment file to prepare the operating environment and load the image file.

[0064] In the embodiment of the present application, the user can use the service configuration template information to quickly generate the image file and the operating environment deployment file required for running the service based on the preset model in the service node. In particular, in the case of running the service based on the preset model in the edge service node, due to the large number of edge service nodes and different resource conditions, the image file and the operating environment deployment file adapted to the edge service node can be efficiently generated through the service configuration template information, which is convenient for quickly deploying the service based on the preset model in the edge service node.

[0065] Step 103: Use the image file and the operating environment deployment file to run the service based on the preset model on the preset service node.

[0066] In an embodiment of the present application, the image file and the operating environment deployment file can be used to run the service based on the preset model on the preset service node, thereby realizing rapid deployment of the service based on the preset model on the service node.

[0067] In a specific implementation, the operating environment deployment file can be used to prepare the environment required for running the service based on the preset model. For example, the amount of CPU resources, memory resources, and GPU resources required for the service based on the preset model are prepared in the service node, and the loading method and life cycle of the image file are set. Afterwards, the service node can load the image file, thereby loading the data required for running the service based on the preset model and the preset model used by the service based on the preset model, thereby realizing the loading of the service based on the preset model in the service node.

[0068] Through the service operation method of the embodiment of the present application, the service configuration template information is used to generate an image file and an operation environment deployment file, and the image file and the operation environment deployment file are used to run the service based on the preset model on the preset service node. Therefore, the service configuration template information can be used to realize the rapid generation of the image file and the operation environment deployment file of the service based on the preset model, and realize the rapid deployment and operation of the service based on the preset model, thereby improving the deployment and operation efficiency of the service based on the preset model.

[0069] Reference Figure 2 , shows a flowchart of another service operation method embodiment of the present application, which may specifically include the following steps:

[0070] Step 201, obtaining service configuration template information sent by the user;

[0071] In an embodiment of the present application, the service may be applied to at least one server. The server may be a local server or a cloud server, and the present application does not limit this. Specifically, the servers may form a cloud server cluster, and the cloud server cluster may include several service nodes distributed in different locations. The service node may be composed of at least one server. A user may connect to the service node through a network and operate the service node. The service node may include a central service node and an edge service node. The central service node may be closer to the manager of the cloud service cluster, so that the manager can manage the cloud service cluster through the central service node and provide higher computing power. The edge service node may be closer to the users of the cloud service cluster, so that users can access the services provided in the service node more quickly.

[0072] In the embodiment of the present application, the service may be a service implemented based on a preset model, such as speech recognition, face detection, text classification, etc. The service may include sample data collection, sample data cleaning, model training, model deployment, model reasoning, etc.

[0073] In an embodiment of the present application, the preset model may be a model based on supervised learning, such as a decision tree, a random forest, a support vector machine, a relevance vector machine, etc. The model may also be a model based on semi-supervised learning, such as a generative model, a semi-supervised support vector machine, etc. The model may also be a neural network model, such as an autoencoder, a multi-layer perceptron, a recurrent neural network model, a convolutional neural network model, etc., which is not limited in the present application.

[0074] In an embodiment of the present application, different contents in the service can be assigned to different servers according to actual needs. For example, in a cloud server cluster, the tasks of sample data collection, sample data cleaning, and model training in the service are handled by the central service node in the cloud server cluster, while the tasks of model deployment and model reasoning are handled by the edge service node in the cloud server cluster. It is also possible to assign all contents in the service to at least one server for joint processing according to actual needs. For example, the tasks of sample data collection, sample data cleaning, model training, model deployment, and model reasoning are all handled by the central service node in a cloud server cluster. This application does not impose any restrictions on this.

[0075] In an embodiment of the present application, a user can deploy and run a service based on a preset model in at least one server. The service configuration template information sent by the user can be obtained, and the service configuration template information can include the service configuration information filled in by the user based on the preset configuration template. Therefore, based on the service configuration template information, the user can know the type of service to be deployed, the service node to be deployed, the computing resources to be reserved for the service, and other information.

[0076] Step 202: extracting model configuration information and container deployment configuration information from the service configuration template information;

[0077] In the embodiment of the present application, after the model has been pre-trained, the user can deploy the model to actual applications to implement tasks such as speech recognition, face detection, and text classification. Since different service nodes may have different operating environments, the service configuration template information can be used to generate an image file and an operating environment deployment file so that the service based on the preset model can run on the service node.

[0078] In an embodiment of the present application, the service configuration template information may include model configuration information required for configuring a preset model and container deployment configuration information required for deploying the preset model in a container manner.

[0079] In a specific implementation, the service configuration template information may include brief configuration information for the service based on the preset model filled in by the user based on the preset template. As an example of the present application, the preset template may include: the name of the preset model, the file path corresponding to the calling method of the preset model, the access port provided by the preset model to the outside, the amount of CPU resources required by the preset model, the amount of memory resources required by the preset model, the amount of GPU resources required by the preset model, the service node for deploying the preset model, and other information. The user can fill in the corresponding information in the preset template to obtain the service configuration template information. Thereafter, in the service configuration template information, the model configuration information required to configure the preset model and the container deployment configuration information required to deploy the preset model in a container manner can be extracted respectively, so as to prepare for the rapid deployment of the preset model.

[0080] In a specific implementation, the service node for deploying the preset model can be determined based on the information filled in by the user in the service configuration template information, or the cloud server cluster can determine at least one service node with a fast connection speed for the user based on the user's location. This application does not impose any restrictions on this.

[0081] In a specific implementation, the service node can run several services based on a preset model at the same time, so that the external access port in the service configuration template information may have been occupied. At this time, the external access port of the service based on the preset model can be adaptively modified to other available ports.

[0082] Step 203, using the model configuration information to determine the dependency library corresponding to the service based on the preset model;

[0083] In an embodiment of the present application, the preset model may be a model required for running the service based on the preset model. Based on the model configuration information, the model required for the service based on the preset model may be determined, and the dependent library required for the service node to run the preset model may be determined.

[0084] In a specific implementation, the preset model required by the service based on the preset model can be determined based on the model configuration information, and the model loading path, loading method, input data format and output data format of the service based on the preset model specified by the model configuration information can be further determined. Thereafter, based on the preset model, model loading path, loading method, input data format and output data format of the service based on the preset model, as well as the resource status and operating environment in the service node, the dependent library required to run the preset model can be determined.

[0085] Step 204, using the dependency library and the model configuration information to generate an image file containing the preset model;

[0086] In an embodiment of the present application, the dependency library and the model configuration information can be used to generate an image file containing the preset model. The image file may include the dependency library and may also include a preset model obtained based on the model configuration information. Thus, the service node can load the dependency library and the preset model in a container by loading the image file, and process the data through the preset model to implement a service based on the preset model.

[0087] In an embodiment of the present application, the service node can run at least one container at the same time, and the containers can not interfere with each other. The service node can achieve rapid deployment of services based on a preset model by establishing a new container and loading the image file in the container.

[0088] In one embodiment of the present application, the step of using the dependent library and the model configuration information to generate an image file containing the preset model includes:

[0089] S11, using the model configuration information to determine a model calling file of the preset model;

[0090] In the embodiment of the present application, the model configuration information may include information such as the name and calling path of the model calling file, so that the model calling file of the preset model to be used by the preset model-based service may be determined by using the model configuration information. The model calling file may include information such as the storage location of the preset model, the loading method, the data input format of the preset model, and the data output format.

[0091] S12, creating calling interface information for the model calling file;

[0092] In an embodiment of the present application, calling interface information for the model calling file can be created to generate a calling interface for the model calling file through the calling interface information, and the model calling file can be started through the calling interface, so that the service based on the preset model can be used in the form of an interface call, so that the service based on the preset model can have a certain degree of independence, which is convenient for quickly calling the service based on the preset model, as well as subsequent updates, expansions, and other needs of the service based on the preset model.

[0093] In a specific implementation, a Restful API (Representational State Transfer Application Programming Interface) builder can be used to create the calling interface information for the model calling file, so that the model calling file can be started in the form of a Restful API. Based on container technology and Restful API, the service based on the preset model can be built into a microservice architecture, so that the service based on the preset model can have a certain degree of independence, which is convenient for quickly calling the service based on the preset model, as well as the subsequent update, expansion and other needs of the service based on the preset model.

[0094] S13, using the dependent library, the calling interface information, and the model calling file to generate an image file containing the preset model.

[0095] In an embodiment of the present application, the dependency library, the calling interface information, and the model calling file can be used to generate an image file containing the preset model. Specifically, the dependency library can be used to generate an image build file, and the calling interface information can be added to the image build file. Thereafter, the image build file and the model calling file can be used to generate an image file. The image file may include the dependency library, the calling interface information, and may also include a preset model obtained based on the model calling file, or include a calling path of a preset model obtained based on the model calling file, so that the preset model can be obtained based on the calling path of the preset model when loading the image file.

[0096] Step 205, using the container deployment configuration information to generate an operating environment deployment file adapted to a preset service node;

[0097] In an embodiment of the present application, the container deployment configuration information can be used to generate an operating environment deployment file adapted to the service node based on factors such as the resource situation and operating environment of the service node. The operating environment deployment file can be used to describe the environment required to run the service based on the preset model in the service node and the loading method of the image file, so that the service node can use the operating environment deployment file to prepare the operating environment.

[0098] In one embodiment of the present application, the step of using the container deployment configuration information to generate an operating environment deployment file adapted to a preset service node includes:

[0099] S21, parsing the container deployment configuration information to determine the operation requirement resource information corresponding to the service based on the preset model;

[0100] In an embodiment of the present application, the container deployment configuration information may include information such as the amount of CPU resources required by the preset model, the amount of memory resources required by the preset model, the amount of GPU resources required by the preset model, and the service node where the preset model is deployed. The operation requirement resource information corresponding to the preset service can be determined by parsing the container deployment configuration information. The operation requirement resource information may be information about the resources that the service node needs to prepare to run the preset service.

[0101] S22, using the operation requirement resource information to generate an operation environment deployment file adapted to a preset service node.

[0102] In an embodiment of the present application, the operation environment deployment file adapted to the preset service node can be generated by using the operation requirement resource information according to the operation status of the service node. The operation environment deployment file can be used to describe the environment, resource quantity and image file loading method required to run the service based on the preset model in the service node, so that the service node can use the operation environment deployment file to prepare the operation environment and prepare corresponding computing resources for the service based on the preset model.

[0103] In the embodiment of the present application, the user can use the service configuration template information to quickly generate the image file and the operating environment deployment file required for running the service based on the preset model in the service node. In particular, in the case of running the service based on the preset model in the edge service node, due to the large number of edge service nodes and different resource conditions, the image file and the operating environment deployment file adapted to the edge service node can be efficiently generated through the service configuration template information, which is convenient for quickly deploying the service based on the preset model in the edge service node.

[0104] Step 206: Use the image file and the operating environment deployment file to run the service based on the preset model on a preset service node.

[0105] In an embodiment of the present application, the image file and the operating environment deployment file can be used to run the service based on the preset model on the preset service node, thereby realizing rapid deployment of the service based on the preset model on the service node.

[0106] In a specific implementation, the operating environment deployment file can be used to prepare the environment required for running the service based on the preset model. For example, the amount of CPU resources, memory resources, and GPU resources required for the service based on the preset model are prepared in the service node, and the loading method and life cycle of the image file are set. Thereafter, the service node can load the image file, thereby loading the data and the preset model required for running the preset model, thereby realizing the loading of the service based on the preset model in the service node.

[0107] As an example of this application, Figure 3 The service configuration template information 301 sent by the user can be obtained, and the service configuration template information 301 can be:

[0108]

[0109] Among them, name:image-classifier indicates that the title of the service configuration template information 301 is image classification. Predictor indicates model-related information, where path:ImageClassifier.py indicates that the file path corresponding to the graphic classification model is ImageClassifier.py; model_name:ImageClassifier indicates that the model name is image classification; api_port:5000 indicates that the API interface is 5000. compute indicates computing resource-related information, where cpu:2 indicates that the cpu requirement is 2; mem:4G indicates that the memory requirement is 4G. region indicates the service node to be deployed for the service based on the preset model, where beijing-cmcc indicates Beijing Mobile, beijing-unicom indicates Beijing Unicom, and beijing-telecom indicates Beijing Telecom.

[0110] The service configuration template information 301 can be read, and the model configuration information 302 and the container deployment configuration information 303 can be extracted from the service configuration template information. Among them, the path, model_name, and api_port information under predictor can be model configuration information, and the cpu information, mem information, and region under compute can be container deployment configuration information.

[0111] Thereafter, the model configuration information 302 may be parsed to determine the dependency library and model call file corresponding to the service based on the preset model, and the Restful API builder 304 and the model call file may be used to create the call interface information for the model call file. The call interface information may include API startup command information, so as to facilitate the subsequent use of the API startup command to call the model call file, thereby calling the preset model to process the service based on the preset model. The dependency library may be used to generate an image build file 305, and the call interface information may be added to the image build file 305. Thereafter, the image build file 305 and the model call file may be used to generate an image file 306.

[0112] At the same time, the container deployment configuration information 303 can be parsed to determine the operation requirement resource information corresponding to the service based on the preset model, and the operation requirement resource information is used to generate an operation environment deployment file 307 adapted to the preset service node.

[0113] The service node may use the image file 306 and the operating environment deployment file 307 to run the service 308 based on the preset model, so as to quickly load the service 308 based on the preset model in the service node.

[0114] In one embodiment of the present application, the service node includes an edge service node;

[0115] The step of using the image file and the operating environment deployment file to run the service based on the preset model on the preset service node includes:

[0116] S31, using the image file and the operating environment deployment file to run the service based on the preset model at the preset edge service node.

[0117] In an embodiment of the present application, the server may form a cloud server cluster, and the cloud server cluster may include several service nodes distributed in different locations. The service node may be composed of at least one server. The service node may include a central service node and an edge service node. The central service node may be closer to the manager of the cloud service cluster, so that the manager can manage the cloud service cluster through the central service node and provide higher computing power. The edge service node may be closer to the user of the cloud service cluster, so that the user can access the services provided in the service node faster.

[0118] In the embodiment of the present application, in order to improve the user's access to the service based on the preset model, the service based on the preset model can be set in the edge service node. However, since the resource conditions of the edge service nodes are different, it is difficult to simply deploy the service based on the preset model directly in the edge service node. It is necessary to manually set the operating environment of the preset model, set the calling interface and the dependent library in the edge service node according to the different conditions of the edge service node, which is more cumbersome.

[0119] In an embodiment of the present application, the service configuration template information sent by the user can be obtained, and the service configuration model information can be used to generate an image file containing a preset model and an operating environment deployment file. Thereafter, the image file and the operating environment deployment file can be used to run the service based on the preset model at the preset edge service node. Thus, the image file and the operating environment deployment file can be used to quickly deploy and run the service based on the preset model at the edge service node, reducing the difficulty of deploying the service based on the preset model at the edge service node, so that ordinary users can easily complete the deployment of the service based on the preset model in the edge service node.

[0120] Thereafter, the preset model-based service deployed on the edge service node can provide users with fast face detection, voice recognition, text classification and other services, which can further improve the efficiency of the preset model-based service.

[0121] Through the service operation method of the embodiment of the present application, the model configuration information and the container deployment configuration information are extracted from the service configuration template information, the model configuration information is used to generate an image file, the container deployment configuration information is used to generate an operating environment deployment file, and the image file and the operating environment deployment file are used to run the service based on the preset model at the preset service node. Therefore, the service configuration template information can be used to realize the rapid generation of the image file and the operating environment deployment file of the service based on the preset model, and realize the rapid deployment and operation of the service based on the preset model, thereby improving the deployment and operation efficiency of the service based on the preset model.

[0122] It should be noted that, for the method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the embodiments of the present application are not limited by the described order of actions, because according to the embodiments of the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present application.

[0123] Reference Figure 4 , shows a structural block diagram of an embodiment of a service operation device of the present application, which may specifically include the following modules:

[0124] Acquisition module 401, used to acquire service configuration template information sent by the user;

[0125] A generation module 402 is used to generate an image file containing a preset model and an operating environment deployment file using the service configuration template information;

[0126] The running module 403 is used to use the image file and the running environment deployment file to run the service based on the preset model on the preset service node.

[0127] In one embodiment of the present application, the generating module includes:

[0128] An extraction submodule, used to extract model configuration information and container deployment configuration information from the service configuration template information;

[0129] A determination submodule, configured to use the model configuration information to determine a dependency library corresponding to the service based on the preset model;

[0130] A first generation submodule, used to generate an image file containing the preset model by using the dependency library and the model configuration information;

[0131] The second generation submodule is used to use the container deployment configuration information to generate an operating environment deployment file adapted to a preset service node.

[0132] In one embodiment of the present application, the first step of generating a submodule includes:

[0133] A determination unit, configured to determine a model calling file of a preset model using the model configuration information;

[0134] A creation unit, used for creating calling interface information for the model calling file;

[0135] The first generating unit is used to use the dependent library, the calling interface information, and the model calling file to generate an image file containing the preset model.

[0136] In one embodiment of the present application, the second generation submodule includes:

[0137] A parsing unit, used to parse the container deployment configuration information and determine the operation demand resource information corresponding to the service based on the preset model;

[0138] The second generating unit is used to generate an operating environment deployment file adapted to a preset service node by using the operating requirement resource information.

[0139] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0140] In one embodiment of the present application, the service node includes an edge service node;

[0141] The operation module includes:

[0142] The running submodule is used to use the image file and the running environment deployment file to run the service based on the preset model at the preset edge service node.

[0143] The present application also provides a device, including:

[0144] one or more processors; and

[0145] One or more machine-readable media having instructions stored thereon, when executed by the one or more processors, enable the device to execute the method described in the embodiments of the present application.

[0146] The embodiments of the present application also provide one or more machine-readable media on which instructions are stored, which, when executed by one or more processors, enable the processors to execute the methods described in the embodiments of the present application.

[0147] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0148] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, devices, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented 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.

[0149] The embodiments of the present application are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0150] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0151] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable terminal device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0152] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present application.

[0153] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.

[0154] The service operation method and service operation device provided by the present application are introduced in detail above. The principles and implementation methods of the present application are explained in this article using specific examples. The description of the above embodiments is only used to help understand the method of the present application and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A service operation method, characterized in that: It is applied to edge service nodes, including: Get the service configuration template information sent by the user; The service configuration template information is used to generate an image file containing a preset model and an operating environment deployment file; wherein the operating environment deployment file is used to describe the environment required for running a service based on the preset model in the edge service node and a loading method of the image file; Using the image file and the operating environment deployment file, running the service based on the preset model on the preset service node; The step of using the service configuration template information to generate an image file containing a preset model and an operating environment deployment file includes: Extracting model configuration information and container deployment configuration information from the service configuration template information; Using the model configuration information, determine the dependency library corresponding to the service based on the preset model; Using the dependency library and the model configuration information, generate an image file containing the preset model; Using the container deployment configuration information, generate an operating environment deployment file adapted to a preset service node; The step of using the container deployment configuration information to generate a runtime environment deployment file adapted to a preset service node includes: Parsing the container deployment configuration information to determine the operation requirement resource information corresponding to the service based on the preset model; According to the operation status of the service node, the operation requirement resource information is used to generate an operation environment deployment file adapted to the preset service node.

2. The method according to claim 1, characterized in that The step of using the dependent library and the model configuration information to generate an image file containing the preset model includes: Using the model configuration information, determine the model calling file of the preset model; Creating calling interface information for the model calling file; The dependent library, the calling interface information, and the model calling file are used to generate an image file containing the preset model.

3. The method according to claim 1 or 2, characterized in that: The service node comprises an edge service node; The step of using the image file and the operating environment deployment file to run the service based on the preset model on the preset service node includes: The image file and the operating environment deployment file are used to run the service based on the preset model at the preset edge service node.

4. A service operation device, characterized in that: It is applied to edge service nodes, including: The acquisition module is used to obtain the service configuration template information sent by the user; A generation module, used to use the service configuration template information to generate an image file containing a preset model and an operating environment deployment file; wherein the operating environment deployment file is used to describe the environment required for running a service based on the preset model in the edge service node and a loading method of the image file; An operation module, used to use the image file and the operation environment deployment file to run the service based on the preset model on a preset service node; Wherein, the generation module includes: An extraction submodule, used to extract model configuration information and container deployment configuration information from the service configuration template information; A determination submodule is used to determine a dependency library corresponding to the service based on the preset model by using the model configuration information; A first generation submodule, used to generate an image file containing the preset model by using the dependency library and the model configuration information; A second generation submodule is used to generate an operating environment deployment file adapted to a preset service node using the container deployment configuration information; The second generation submodule includes: A parsing unit, used to parse the container deployment configuration information and determine the operation demand resource information corresponding to the service based on the preset model; The second generating unit is used to generate an operating environment deployment file adapted to a preset service node according to the operating status of the service node and using the operating requirement resource information.

5. The device according to claim 4, characterized in that The first step of generating a submodule includes: A determination unit, configured to determine a model calling file of the preset model using the model configuration information; A creation unit, used for creating calling interface information for the model calling file; The first generating unit is used to use the dependent library, the calling interface information, and the model calling file to generate an image file containing the preset model.

6. The device according to claim 4 or 5, characterized in that The service node comprises an edge service node; The operation module includes: The running submodule is used to use the image file and the running environment deployment file to run the service based on the preset model at the preset edge service node.

7. A device, characterized in that: include: one or more processors; and One or more machine-readable media having instructions stored thereon, when executed by the one or more processors, cause the apparatus to perform one or more of the methods of claims 1-3.

8. One or more machine-readable media having instructions stored thereon, which when executed by one or more processors cause the processors to perform one or more of the methods of claims 1-3.

Images