WO2023142451A1

WO2023142451A1 - Workflow generation methods and apparatuses, and electronic device

Info

Publication number: WO2023142451A1
Application number: PCT/CN2022/113402
Authority: WO
Inventors: 李金麒; 施恩; 胡鸣人; 钱正宇; 袁正雄
Original assignee: 北京百度网讯科技有限公司
Priority date: 2022-01-29
Filing date: 2022-08-18
Publication date: 2023-08-03
Also published as: CN114445047A

Abstract

The present disclosure provides workflow generation methods and apparatuses, an electronic device, a storage medium and a computer program product, and relates to the technical field of computers, in particular to the field of artificial intelligence technical development. A specific implementation solution is as follows: receiving a workflow generation request, the workflow generation request carrying description information of a workflow; according to the description information, determining workflow nodes; processing the workflow nodes, and acquiring workflow meta-information on the basis of a processing result; and according to the workflow meta-information, generating a target workflow. Since the workflow nodes are determined according to the description information of the workflow and are integrated to generate the target workflow, the target workflow can effectively adapt to the description information of the workflow. The individual description and adjustment of workflow nodes are supported, workflow customization requirements of different users can be effectively met, and the flexibility and applicability of a workflow generation method are effectively improved.

Description

Workflow generation method, device, electronic device

Cross References to Related Applications

This application is based on a Chinese patent application with application number 202210113007.9 and a filing date of January 29, 2022, and claims the priority of this Chinese patent application. The entire content of this Chinese patent application is hereby incorporated by reference into this application.

technical field

The present disclosure relates to the field of computer technology, in particular to the field of artificial intelligence technology development, and in particular to a workflow generation method, device, electronic equipment, storage medium and computer program product.

Background technique

Artificial intelligence is a discipline that studies the use of computers to simulate certain human thinking processes and intelligent behaviors (such as learning, reasoning, thinking, planning, etc.), both at the hardware level and at the software level. Artificial intelligence hardware technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, and big data processing; artificial intelligence software technologies mainly include computer vision technology, speech recognition technology, natural language processing technology, and machine learning, Deep learning, big data processing technology, knowledge map technology and other major directions.

In related technologies, the generation convenience and adaptability of artificial intelligence AI workflow are not good.

Contents of the invention

The disclosure provides a workflow generation method, device, electronic equipment, storage medium and computer program product.

According to the first aspect of the present disclosure, a workflow generation method is provided, including: receiving a workflow generation request, wherein the workflow generation request carries workflow description information; determining workflow nodes according to the description information; processing The workflow node obtains workflow meta-information based on the processing result; and generates a target workflow according to the workflow meta-information.

According to the second aspect of the present disclosure, a workflow generation method is provided, including: receiving a workflow description request, wherein the workflow description request carries scenario information; determining workflow description information that matches the scenario information; The workflow description information is used to generate a workflow generation request; the workflow generation request is provided to the workflow producer to trigger the workflow producer to generate a target workflow according to the workflow generation request.

According to a third aspect of the present disclosure, a workflow generation device is provided, including: a first receiving module, configured to receive a workflow generation request, wherein the workflow generation request carries workflow description information; the first determination A module, configured to determine a workflow node according to the description information; a first processing module, configured to process the workflow node, and obtain workflow meta information based on the processing result; and a first generating module, configured to obtain workflow meta information based on the workflow meta information , to generate the target workflow.

According to a fourth aspect of the present disclosure, a workflow generating device is provided, including: a second receiving module, configured to receive a workflow description request, wherein the workflow description request carries scene information; a second determining module, configured to to determine the description information of the workflow matching the scene information; the second generation module is used to generate a workflow generation request according to the description information of the workflow; the second processing module is used to provide the workflow generation request to the workflow production Party, to trigger the workflow producer to generate the target workflow according to the workflow generation request.

According to a fifth aspect of the present disclosure, an electronic device is provided, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by At least one processor executes, so that at least one processor can execute the workflow generation method according to the first aspect, or execute the workflow generation method according to the second aspect.

According to a sixth aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions, the computer instructions are used to make a computer execute the workflow generation method as in the first aspect, or perform the work as in the second aspect Stream generation method.

According to a seventh aspect of the present disclosure, there is provided a computer program product, including a computer program. When the computer program is executed by a processor, it implements the steps of the workflow generation method according to the first aspect, or executes the workflow according to the second aspect. The steps to generate the method.

It should be understood that what is described in this section is not intended to identify key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will be easily understood from the following description.

Description of drawings

The accompanying drawings are used to better understand the present solution, and do not constitute a limitation to the present disclosure. in:

FIG. 1 is a flow chart of a workflow generation method according to an embodiment of the present disclosure;

FIG. 2 is a flowchart of a workflow generation method according to an embodiment of the present disclosure;

FIG. 3 is a schematic structural diagram of a workflow development platform according to an embodiment of the present disclosure;

FIG. 4 is a flowchart of a workflow generation method according to an embodiment of the present disclosure;

5 is a flowchart of a workflow generation method according to an embodiment of the present disclosure;

Fig. 6 is a block diagram of a workflow generation device according to an embodiment of the present disclosure;

Fig. 7 is a block diagram of a workflow generating device according to an embodiment of the present disclosure;

Fig. 8 is a block diagram of a workflow generation device according to an embodiment of the present disclosure;

Fig. 9 is a block diagram of a workflow generating device according to an embodiment of the present disclosure;

Fig. 10 shows a schematic block diagram of an example electronic device for implementing the workflow generation method of the embodiment of the present disclosure.

Detailed ways

Exemplary embodiments of the present disclosure are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding, and they should be regarded as exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

Fig. 1 is a flowchart of a workflow generation method according to an embodiment of the present disclosure.

Wherein, it should be noted that the execution subject of the workflow generation method in this embodiment is a workflow generation device, which can be implemented by software and/or hardware, and which can be configured in an electronic device, and the electronic device can include But not limited to terminals, servers, etc.

Embodiments of the present disclosure relate to the field of artificial intelligence technology development.

Among them, artificial intelligence (Artificial Intelligence), the English abbreviation is AI. It is a new technical science that studies and develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence.

Among them, artificial intelligence technology development refers to the completion of corresponding technology development tasks based on artificial intelligence technology combined with actual business application scenarios, for example, developing an easy-to-use development framework, an out-of-the-box development environment, rich artificial intelligence The intelligent skills market and cloud management platform also support a series of development tasks such as the development of artificial intelligence applications such as vision and hearing, and the online deployment of artificial intelligence models.

As shown in Figure 1, the workflow generation method includes:

S101: Receive a workflow generation request, wherein the workflow generation request carries workflow description information.

Wherein, the request for triggering the generation of the workflow may be referred to as a workflow generation request, and the workflow request may include: description information of the workflow.

Among them, the information used to describe the flow logic, execution order, execution task information, node type, etc. between different workflow nodes in the workflow can be called workflow description information, and workflow description information It may also be, for example, the description information of the function of the workflow, the description information of the storage location of the workflow, etc., which are not limited.

Among them, the workflow refers to the automation of part and/or the overall process of the business operation process in the computer application environment, that is, it can rely on the pre-built workflow to realize the automatic completion of the corresponding business operation process in the computer application environment, Therefore, based on the workflow, the execution cost of the corresponding business operation process can be effectively reduced, and the execution efficiency of the corresponding business process can be effectively improved. The specific process can be, for example, an image recognition process, a model training process, etc., without limitation.

The workflow in the embodiments of the present disclosure may specifically be a workflow in artificial intelligence AI, which is not limited.

The workflow generation method described in the embodiments of the present disclosure may be applied to a workflow producer, without limitation.

Among them, the producer of the workflow can be an electronic device on the producer side who is proficient in the workflow development process. The electronic device on the producer side generates various adaptations according to the needs of different users for the workflow in actual business scenarios. In addition, the workflow producer can also support the popularization of workflow functions and applicable scenarios to users who use workflows, so that users can call workflows according to their own needs.

That is to say, in the embodiment of the present disclosure, receiving the workflow generation request may be that the workflow producer provides the corresponding Application Programming Interface (Application Programming Interface, API) in advance, and then receives the workflow generation request via the API, or, To receive the workflow generation request, it is also possible to pre-configure the corresponding monitoring device for the workflow producer, and monitor the workflow generation request of different users through the monitoring device, so as to trigger the subsequent steps according to the workflow generation request, and do not do this limit.

S102: Determine the workflow node according to the description information.

Among them, all kinds of task nodes involved in the process of creating artificial intelligence AI workflow can be called workflow nodes. A complete AI creation process can include basic information selection nodes, initiation training nodes, effect evaluation nodes, model Deployment nodes, batch prediction nodes and other types of nodes are not limited.

In some embodiments, according to the description information, determining the workflow node may be based on the description information of the workflow, comparing the corresponding multiple nodes in the artificial intelligence AI workflow creation process, so as to determine the work flow node from the multiple nodes. The description information of the flow corresponds to the workflow node.

In the embodiment of the present disclosure, multiple workflow nodes may have corresponding execution order and data flow logic, and multiple workflow nodes jointly form a complete workflow that can be used in actual production according to the corresponding execution data and data flow logic. .

In the embodiment of the present disclosure, the workflow node is determined according to the description information, or the workflow description information can be analyzed and processed, and the candidate workflow node corresponding to the description information is determined, and then according to the execution sequence of the requirements in the description information Configure the execution order of the candidate workflow nodes, configure the data flow logic of the candidate workflow nodes according to the required data flow logic in the description information, and obtain the workflow nodes, or use any other possible way to realize the determination based on the description information Workflow nodes, there is no restriction on this.

S103: Process the workflow nodes, and obtain workflow meta-information based on the processing results.

Among them, meta-information is information about information, which is used to describe the structure, semantics, purpose and usage of information, etc. Correspondingly, the information used to describe the structure, semantics, purpose, and usage of the workflow can be called workflow meta-information, which can be, for example, the functional information of the workflow, identification information of the workflow, etc. For this No restrictions.

In some embodiments, the processing of workflow nodes may be to sequentially splicing multiple workflow nodes after determining multiple workflow nodes to obtain corresponding processing results, or it may also be the user according to the actual business scenario According to the workflow development requirements, the execution order of multiple workflow nodes is determined, and then the multiple workflow nodes are spliced according to the aforementioned execution order to obtain corresponding processing results.

In the embodiment of the present disclosure, after processing the workflow node to obtain the corresponding processing result, the corresponding workflow meta-information can be obtained based on the processing result, that is, the corresponding processing result can be parsed to obtain the corresponding parsing and processing result, and the The foregoing analysis and processing results are used as workflow meta-information.

For example, to analyze and process the corresponding processing results may be to input the corresponding processing results into the pre-trained deep learning model after the corresponding processing workflow node generates the corresponding processing results, and the corresponding processing results are processed by the deep learning model The results are parsed and processed, and the corresponding parsing and processing results are output, and the parsing and processing results are used as workflow metadata, or any other possible method can be used to parse and process the corresponding processing results, such as semantic parsing, There is no limitation on the manner of feature analysis and the like.

S104: Generate a target workflow according to the workflow meta-information.

In the embodiments of the present disclosure, after processing the workflow nodes and obtaining the workflow meta-information based on the processing results, the aforementioned workflow can be processed according to the workflow meta-information (that is, the information describing the structure, semantics, purpose, usage, etc. of the workflow). The flow node performs description and configuration processing, and takes the workflow obtained from the foregoing description and configuration processing as the target workflow.

In some embodiments, according to the workflow meta-information, generating the target workflow may be parsing the workflow meta-information (that is, information describing the structure, semantics, usage, usage, etc. of the workflow) to obtain the corresponding parsing file, and then use the parsed file to edit and configure the workflow nodes to obtain the target workflow.

In the embodiments of the present disclosure, different workflows can be respectively adapted to different business scenarios.

Correspondingly, generating the target workflow according to the workflow meta-information may be to determine the business scenario adapted to the workflow node corresponding to the workflow meta-information according to the workflow meta-information, and compare the business scenario with the user's current When the actual business scenario matches, the workflow node corresponding to the workflow meta-information is taken as the target workflow.

Alternatively, any other possible manner may be used to generate the target workflow according to the workflow meta-information, which is not limited.

That is to say, the description information in the embodiment of the present disclosure can describe the type, quantity, execution sequence, and data flow logic of the workflow nodes required by the business, so as to determine the matching workflow nodes based on the description information. When regenerating the target workflow, the artificial intelligence AI workflow can be effectively adapted to the description information of the workflow, and the personalized description and adjustment of the workflow nodes can be realized based on different description information, which can effectively meet the workflow of different users Customized needs.

In this embodiment, by receiving a workflow generation request, wherein the workflow generation request carries the description information of the workflow, and according to the description information, the workflow node is determined, the workflow node is processed, and the workflow is obtained based on the processing result meta-information, and generate the target workflow based on the workflow meta-information, because the workflow node is determined according to the description information of the workflow, and the workflow node is integrated to generate the target workflow, so that the target workflow can It effectively adapts the description information of the workflow, supports the personalized description and adjustment of the workflow nodes, can effectively meet the workflow customization needs of different users, and effectively improves the flexibility and applicability of the workflow generation method.

Fig. 2 is a flowchart of a workflow generating method according to an embodiment of the present disclosure.

As shown in Figure 2, the workflow generation method includes:

S201: Receive a workflow generation request, wherein the workflow generation request carries workflow description information.

In the embodiment of the present disclosure, the workflow producer and workflow user can work together with the workflow development platform to complete the creation process of the target workflow. When the workflow user needs to use specific artificial intelligence AI technology to enable production, he only needs to follow the instructions for using the artificial intelligence AI workflow given by the workflow producer to select the appropriate workflow , which can meet its workflow requirements in actual business scenarios.

In the embodiment of the present disclosure, the embodiment of the present disclosure can be explained in combination with FIG. 3 , as shown in FIG. 3 , which is a schematic structural diagram of a workflow development platform according to an embodiment of the disclosure. Including: workflow generation service module, workflow management service module, workflow node meta-information warehouse, workflow template warehouse, front-end page and development platform back-end. The specific functions of each module are as follows:

The workflow template repository refers to a database for storing workflow templates, which can be used to store workflow templates.

The workflow management service module can be used to manage the workflow templates stored in the workflow template warehouse, and provide workflow startup, shutdown, query and other functions.

The workflow node meta-information warehouse refers to a database for storing workflow nodes, which can be used to store the most fine-grained workflow nodes.

The workflow generation service module can be used to receive the workflow generation request created by the workflow producer, determine the workflow node according to the description information in the workflow generation request, and process the workflow node to form a workflow template, and then store the workflow template In the workflow template repository.

The front-end page refers to the user interaction page, on which the workflow user can select the required workflow and develop the corresponding workflow.

The backend of the development platform is the platform for workflow operation. It integrates the data required for workflow operation, the interface for obtaining models, and the interfaces required for initiating model training and model prediction. It can provide the basis for workflow operation. To assist in completing a complete workflow production work.

In the embodiments of the present disclosure, receiving a workflow generation request may be a workflow generation request received by the workflow generation service module through the API interface, and made by the workflow producer according to actual business needs. The workflow request may have the corresponding following: The description information of the workflow described in JavaScript Object Notation (JSON) format is not limited.

In the embodiment of the present disclosure, after receiving the workflow generation request, the workflow generation service module can analyze and process the description information of the workflow described in JSON format, and then determine the corresponding workflow node according to the aforementioned analysis and processing results , for details, please refer to the following examples.

S202: Determine the workflow node according to the description information.

In the embodiment of the present disclosure, after parsing and obtaining the description information of the corresponding workflow from the workflow generation request, the workflow node corresponding to the description information can be determined from the multiple workflow nodes stored in the workflow node meta-information warehouse according to the description information. Workflow node.

S203: Process the workflow nodes to form a workflow template.

Wherein, a workflow template refers to a workflow that exists in the form of a template and can be used to execute a specific workflow. The workflow template can be, for example, an object detection process template, an image classification process template, a text recognition process template, etc. This is not limited.

In some embodiments, processing a workflow node may be to integrate multiple workflow nodes in the form of a template to obtain a workflow template, or call a template configuration file to process multiple workflow nodes according to the template configuration file , to form a workflow template, which is not limited.

In the embodiments of the present disclosure, workflow nodes are processed to form workflow templates, which can support workflow users to directly call workflow templates, thereby effectively improving the utilization efficiency of workflow templates.

Optionally, in some embodiments, processing workflow nodes to form a workflow template may be to determine the node meta-information corresponding to each workflow node, and perform splicing processing on multiple workflow nodes according to the node meta-information to form a workflow template .

Among them, the meta information refers to the information used to describe the structure, semantics, purpose and usage of the information corresponding to the meta information, and correspondingly, the information used to describe the structure, semantics, purpose and usage of the workflow nodes, namely It may be referred to as node meta information, and the node meta information may specifically include, for example, the storage location of the workflow node in the node meta information warehouse, the function information of the workflow node, etc., without limitation.

In the embodiment of the present disclosure, multiple workflow nodes can be stored in the node meta-information warehouse, which can be a database for storing the most fine-grained workflow nodes, and the workflow node can be, for example, a data merge process Nodes, image segmentation process nodes, batch prediction process nodes, etc., are not limited.

In the embodiment of the present disclosure, determining the node meta-information corresponding to the workflow node may be determining the storage location of the workflow node in the node meta-information warehouse, the functional information of the workflow node, etc., and using the above-mentioned determined information together as the The node meta-information corresponding to the workflow node is not limited.

That is to say, in the embodiment of the present disclosure, after determining the node meta-information corresponding to each workflow node, multiple workflow nodes can be spliced according to the node meta-information and in combination with the node work order among multiple workflow nodes Since not all workflow nodes support splicing to obtain corresponding workflow templates, it is possible to effectively filter out workflow nodes that do not support splicing processing during the splicing process of multiple workflow nodes, thereby It can effectively improve the usability of the workflow template obtained by splicing. In addition, in the process of splicing workflows, it can also support adaptive adjustment of the order of workflow nodes, so that the workflow obtained by the aforementioned splicing processing The workflow nodes of the template can effectively adapt to the workflow requirements of different users.

In some other embodiments, when processing workflow nodes to form a workflow template, it can also support verification processing on the workflow template (verification processing means that it can be judged whether the workflow template has logic error, whether it is an available workflow template), that is, the workflow generation service module in the workflow development platform shown in Figure 3 above can verify the workflow template, and pass the workflow template verification (passing the verification means that the workflow template has no logical errors and is a usable workflow template), store the workflow template that passes the verification process in the workflow template warehouse, and refer to the subsequent embodiments for details.

S204: Obtain workflow meta information according to the workflow template.

Among them, meta-information is information about information, which is used to describe the structure, semantics, purpose and usage of information, etc.

In the embodiments of the present disclosure, the information used to describe the structure, semantics, purpose, and usage of workflow templates can be called workflow meta-information, and workflow meta-information can specifically be, for example, the storage location of workflow templates Information, function information of the workflow template, identification information of the workflow template, etc., are not limited.

That is to say, in the embodiment of the present disclosure, after the workflow nodes are processed to form the workflow template, the storage location information of the workflow template, the function information of the workflow template, the identification information of the workflow template and other information can be determined, and the All or part of the above-mentioned determined information is used as workflow meta-information, which is not limited.

Optionally, in some embodiments, obtaining the workflow meta-information according to the workflow template may be storing the workflow template in the workflow template warehouse, and determining the storage location information of the workflow template in the workflow template warehouse, And store location information as workflow meta information.

In the embodiment of the present disclosure, after the workflow nodes are processed to form the workflow template, the workflow template can be stored in the workflow template warehouse, thus, in the execution process of the subsequent workflow generation method, the workflow template warehouse can be realized , directly call the corresponding workflow template, which can effectively assist in improving the efficiency of workflow template acquisition.

Wherein, the information used to describe the storage location of the workflow template in the workflow template warehouse can be referred to as storage location information, and the storage location information can specifically be, for example, the storage address information of the workflow template in the workflow template warehouse, There is no restriction on this.

That is to say, after the workflow template is stored in the workflow template warehouse in the embodiment of the present disclosure, the storage address information of the workflow template in the workflow template warehouse can be determined, and the storage address information can be used as the workflow template in the Storage location information in the workflow template repository.

In the embodiment of the present disclosure, after determining the storage location information of the workflow template in the workflow template warehouse, the storage location information can be used as the workflow meta-information, and then the subsequent workflow generation method can be executed based on the workflow meta-information. For details, see Subsequent examples.

In the embodiment of the present disclosure, because the workflow template is first stored in the workflow template warehouse, and the storage location information of the workflow template in the workflow template warehouse is determined, and the storage location information is used as the workflow metadata, so that Effectively improve the comprehensiveness and referenceability of the workflow meta-information, and can also directly call the corresponding workflow template from the workflow template warehouse based on the workflow meta-information during the execution of the subsequent workflow generation method , so that the reusability of the workflow template can be effectively improved, and the time for generating the workflow template by splicing the workflow nodes can be effectively saved, thereby effectively assisting in improving the efficiency of workflow template acquisition.

Optionally, in some other embodiments, the workflow meta-information is obtained according to the workflow template, and the node meta-information may also be used as the workflow meta-information.

That is to say, in the embodiment of the present disclosure, after the workflow nodes are processed to form the workflow template, the node meta-information corresponding to each workflow node determined above can be used as the workflow meta-information, and then, based on the workflow meta-information , to generate a target workflow, for details, refer to subsequent embodiments.

S205: Feedback the workflow meta-information to the workflow producer.

In the embodiment of the present disclosure, after the workflow element information is determined, the workflow element information can be fed back to the workflow producer. Since the workflow element information is fed back to the workflow producer, it can effectively facilitate the workflow producer to The acquisition of meta-information enables the work producer to quickly capture the workflow meta-information, and based on the workflow meta-information, effectively assists in improving the workflow production efficiency of the workflow producer.

S206: In response to the workflow management request, acquire the workflow template from the workflow template warehouse according to the storage location information.

Wherein, the request for triggering workflow management may be referred to as a workflow management request.

That is to say, in the embodiment of the present disclosure, the workflow management request can be received through the instruction interface provided by the workflow development platform, and then the workflow management service module can respond to the workflow management request and determine the workflow template according to the storage location information The storage location in the workflow template warehouse, and obtain the workflow template corresponding to the storage location.

S207: Describe the workflow template according to the node meta-information, and obtain the workflow to be rendered.

In the embodiment of the present disclosure, after the workflow template is obtained from the workflow template warehouse according to the storage location information, the workflow template can be described according to the node meta-information to obtain the described and processed workflow, which can be called The workflow to be rendered can be rendered, and then the workflow to be rendered can be rendered to obtain an interactive interface for user operations corresponding to the workflow, and then the corresponding interactive processing operation can be performed on the workflow to be rendered based on the user interface, so as to The target workflow is obtained, for details, please refer to the subsequent embodiments.

Wherein, describing the workflow template refers to the workflow management service module of the workflow development platform shown in FIG. 3 above, which performs functional operations such as starting, closing, and querying the workflow template.

That is to say, in the embodiment of the present disclosure, after the workflow template is obtained from the workflow template warehouse according to the storage location information, the workflow management service module of the workflow development platform can start, close, and Query and other operations to obtain the corresponding workflow to be rendered, there is no limit to this.

S208: Generate a target workflow according to the workflow to be rendered.

In this embodiment, because the workflow template is obtained from the workflow template warehouse according to the storage location information in response to the workflow management request, the corresponding workflow template can be quickly captured from the workflow template warehouse based on the storage location information , so that the workflow template can be described according to the node meta-information, the workflow to be rendered can be obtained, and when the target workflow is generated according to the workflow to be rendered, it can effectively assist in improving the generation efficiency of the target workflow. In addition, because it is based on the node element The information describes and processes the workflow template to obtain the target workflow, so that the generation effect of the target workflow can be effectively improved.

In some embodiments, according to the workflow to be rendered, generating the target workflow can determine whether the workflow to be rendered meets the user's requirements, and when the workflow to be rendered meets the user's requirements, directly use the workflow to be rendered as the target workflow.

Optionally, in some embodiments, a target workflow is generated according to the workflow to be rendered. It may be that the workflow to be rendered is provided to the workflow user's terminal, and the rendering operation information fed back by the terminal is received, wherein the rendering operation information is obtained by analyzing the rendering operation instruction in response to the rendering operation instruction, and according to the rendering operation The information is rendered to the workflow to be rendered to obtain the target workflow. Since the rendering operation information is obtained through the interaction between the user and the front-end page, the rendering operation information fed back by the terminal is used to render the workflow to be rendered, so that the rendering can be obtained. The target workflow can be more adapted to the needs of the user's actual business scenario, and thus can effectively improve the generation effect of the workflow.

The terminal of the workflow user may specifically be, for example, a computer device or a processor on the workflow user side, which is not limited.

Wherein, the instruction for triggering the rendering operation processing of the workflow to be rendered may be referred to as a rendering operation instruction.

Wherein, the information used to perform rendering operation processing on the workflow to be rendered may be referred to as rendering operation information, and the rendering operation information may specifically include, for example: actual application scene information of the workflow, usage information of the workflow, etc., or, The rendering operation information can also be the terminal of the workflow user. According to the use requirements of the artificial intelligence AI model corresponding to the workflow to be rendered, the defined artificial intelligence AI model interface information, interface call relationship information, and artificial intelligence AI model input and/or output data type information, etc., without limitation.

Among them, the rendering process refers to the front-end page of the workflow development platform, according to the rendering operation information of the workflow (artificial intelligence AI model interface information, interface call relationship information, artificial intelligence AI model input and/or output data type information, etc. ) renders an interactive page that can be operated by the user, and then the user can interact with the workflow to be rendered on the interactive interface obtained by the aforementioned rendering process to obtain the target workflow.

That is to say, in the embodiment of the present disclosure, after providing the workflow to be rendered to the terminal of the workflow user and receiving the rendering operation information fed back by the terminal of the workflow user, the terminal of the workflow user The use requirements of the artificial intelligence AI model corresponding to the rendering workflow, the rendering operation information such as the defined artificial intelligence AI model interface information, interface call relationship information, artificial intelligence AI model input and output data type information, etc. to get the target workflow.

In other embodiments, after obtaining the workflow to be rendered, the workflow to be rendered and the rendering operation instruction can be provided to the terminal of the workflow user together, and the terminal of the workflow user will receive the rendering operation instruction , get the corresponding rendering operation information from the rendering operation instruction, and feed back the rendering operation information to the workflow producer. The workflow producer can treat the rendering work according to the rendering operation information on the front-end page of the workflow development platform. The flow is rendered to obtain the user-operated interactive interface corresponding to the workflow to be rendered, and then the user can interact with the workflow to be rendered on the interactive interface obtained by the aforementioned rendering processing to obtain the target workflow .

In this embodiment, by receiving the workflow generation request, and according to the description information, determine the workflow node, and then process the workflow node to form a workflow template, and obtain the workflow metadata according to the workflow template, so that the work can be effectively improved. The comprehensiveness and referenceability of the flow element information can also directly call the corresponding workflow template from the workflow template warehouse based on the workflow element information during the execution of the subsequent workflow generation method, so as to effectively It can greatly improve the reusability of workflow templates, and can also effectively save the time to generate workflow templates by splicing workflow nodes, thereby effectively assisting in improving the efficiency of workflow template acquisition, and then feeding back workflow meta-information To the workflow producer, because the workflow meta information is fed back to the workflow producer, it can effectively facilitate the workflow producer to obtain the workflow meta information, so that the work producer can quickly grasp the workflow meta information Based on the workflow meta-information, it effectively assists in improving the workflow production efficiency of the workflow producer, and then responds to the workflow management request, obtains the workflow template from the workflow template warehouse according to the storage location information, and based on the node meta-information The information describes the workflow template, obtains the workflow to be rendered, and then generates the target workflow according to the workflow to be rendered, so as to effectively meet the workflow customization needs of different users, and effectively improve the flexibility and applicability of the workflow generation method .

Fig. 4 is a flowchart of a workflow generation method according to an embodiment of the present disclosure.

As shown in Figure 4, the workflow generation method includes:

S401: Receive a workflow description request, where the workflow description request carries scene information.

Wherein, the request for triggering the description of the workflow to obtain the description information of the workflow may be referred to as a workflow description request.

Among them, in the workflow description request, the information used to describe the business scenario for workflow adaptation can be called scenario information, and the scenario information can be specifically, for example, the identification information of the scenario, the attribute information of the scenario, etc., for This is not limited.

In the embodiment of the present disclosure, receiving the workflow description request may be that the terminal of the workflow user provides a corresponding Hyper Text Transfer Protocol (Hyper Text Transfer Protocol, HTTP) interface in advance, and receives the workflow description request via the HTTP interface, or, It is also possible to pre-configure the corresponding monitoring device for the terminal of the workflow user, and request the user's workflow description via the monitoring device. Of course, any other possible way can also be used to receive the workflow description request. Do limit.

S402: Determine the description information of the workflow matching the scenario information.

In the embodiments of the present disclosure, in different business scenarios, they can be respectively adapted to different workflows. Correspondingly, the scenario information for different business scenarios can correspond to the description information of different workflows, so that when determining the scenario After the information is obtained, the description information of the workflow matching the scene information can be determined.

In some embodiments, determining the description information of the workflow matching the scenario information may be parsing and processing the scenario information to determine the workflow matching the scenario information, and adding the description of the workflow corresponding to the workflow The information is used as the description information of the workflow matched with the scene information.

In the embodiment of the present disclosure, the description information of the workflow may include scenario information corresponding to a scenario adapted to the workflow.

Therefore, determining the description information of the workflow that matches the scene information can also be to compare the scene information with the description information of multiple workflows, for example, it is possible to determine multiple similarities between the scene information and the description information of the workflow degrees, and use the description information of the workflow corresponding to the maximum similarity among the multiple similarities as the description information of the workflow matching the scene information, or, any other possible way can also be used to determine the workflow matching scene information Descriptive information, without limitation.

S403: Generate a workflow generation request according to the description information of the workflow.

In the embodiment of the present disclosure, after the description information of the workflow matching the scene information is determined, the description information of the workflow may be packaged, and the description information obtained through the packaging process may be converted into a corresponding workflow generation request.

In some embodiments, a workflow generation request is generated according to the description information of the workflow, or the description information of the workflow can be provided to the terminal of the workflow user, and the terminal of the workflow user combines its own requirements for the workflow and workflow description information to generate a workflow generation request, or any other possible manner may be used to generate a workflow generation request according to the workflow description information, which is not limited.

S404: Provide the workflow generation request to the workflow producer, so as to trigger the workflow producer to generate the target workflow according to the workflow generation request.

In the embodiments of the present disclosure, after a workflow generation request is generated according to workflow description information, the workflow generation request may be provided to a workflow producer, so as to trigger the workflow producer to generate a target workflow according to the workflow generation request.

In this embodiment, by receiving the workflow description request, wherein the workflow description request carries scene information, and determining the description information of the workflow matching the scene information, and then generating the workflow generation request according to the description information of the workflow , and provide the workflow generation request to the workflow producer to trigger the workflow producer to generate the target workflow according to the workflow generation request, since the workflow generation request is generated according to the description information of the workflow matching the scene information, The workflow generation request can accurately represent the scene information, so that when the workflow generation request is provided to the workflow producer, it can be based on the workflow generation request and accurately trigger the generation of the user's actual business scenario. The target workflow enables the target workflow to effectively meet the individual needs in actual workflow application scenarios.

Fig. 5 is a flowchart of a workflow generation method according to an embodiment of the present disclosure.

As shown in Figure 5, the workflow generation method includes:

S501: Receive a workflow description request, where the workflow description request carries scene information.

S502: Determine the description information of the workflow matching the scenario information.

S503: Generate a workflow generation request according to the description information of the workflow.

S504: Provide the workflow generation request to the workflow producer, so as to trigger the workflow producer to generate the target workflow according to the workflow generation request.

For descriptions of S501-S504, reference may be made to the above-mentioned embodiments, and details are not repeated here.

S505: Obtain the workflow to be rendered provided by the workflow producer.

Wherein, the workflow currently to be rendered provided by the workflow producer may be referred to as a workflow to be rendered.

In the embodiment of the present disclosure, after the workflow generation request is provided to the workflow producer to trigger the workflow producer to generate the target workflow according to the workflow generation request, the workflow to be rendered provided by the workflow producer can be obtained, and then based on To render the workflow, execute the subsequent workflow generation method, for details, refer to the subsequent embodiments.

S506: In response to the rendering operation instruction, parse the rendering operation instruction to obtain rendering operation information, where the rendering operation information is used to perform rendering processing on the workflow to be rendered.

Wherein, the instruction used to trigger the rendering operation of the workflow to be rendered can be called a rendering operation instruction. The rendering operation instruction can specifically, for example, pre-configure a corresponding instruction interface for the workflow development platform, and based on the instruction interface Receive rendering operation instructions.

In the embodiment of the present disclosure, after receiving the rendering operation instruction sent by the workflow generator, the terminal of the workflow user can parse and process the rendering operation instruction to obtain the corresponding rendering operation information, and then based on the rendering operation information Trigger next steps.

S507: Provide the rendering operation information to the workflow producer.

In the embodiment of the present disclosure, after the terminal of the workflow user parses the rendering operation instruction to obtain the rendering operation information, it can provide the rendering operation information to the workflow producer, and then the workflow producer can convert the rendering operation The front-end page provided to the workflow development platform is used to trigger the front-end page to render the workflow to be rendered according to the rendering operation information, so as to generate the target workflow.

In this embodiment, because the workflow to be rendered provided by the workflow producer is obtained, and in response to the rendering operation instruction, the rendering operation instruction is analyzed to obtain the rendering operation information, so that the rendering operation information obtained by the analysis can be accurately adapted to For the workflow to be rendered, it effectively guarantees the referenceability of the rendering operation information, so that when the rendering operation information is provided to the workflow producer, the workflow producer can effectively ensure the smoothness of the rendering operation logic based on the rendering operation information Execution, so as to effectively improve the rendering effect of the workflow to be rendered, and then effectively assist in improving the generation effect of the target workflow.

In this embodiment, by receiving the workflow description request, determine the description information of the workflow matching the scene information, and generate a workflow generation request according to the description information of the workflow, and then provide the workflow generation request to the workflow production to trigger the workflow producer to generate the target workflow according to the workflow generation request. Since the workflow generation request is generated according to the description information of the workflow matching the scene information, the workflow generation request can accurately match the scene information. To perform characterization, so that when the workflow generation request is provided to the workflow producer, it can be based on the workflow generation request and accurately trigger the generation of a target workflow that is adapted to the user's actual business scenario. The workflow to be rendered, and in response to the rendering operation instruction, parse the rendering operation instruction to obtain the rendering operation information, so that the rendering operation information obtained by parsing can be accurately adapted to the workflow to be rendered, effectively ensuring the integrity of the rendering operation information Reference, so that when the rendering operation information is provided to the workflow producer, the workflow producer can effectively ensure the smooth execution of the rendering operation logic based on the rendering operation information, thereby effectively improving the rendering of the workflow to be rendered Effect, and then effectively assist in improving the generation effect of the target workflow.

Fig. 6 is a block diagram of a workflow generating device according to an embodiment of the present disclosure.

As shown in Figure 6, the workflow generating device 60 includes:

The first receiving module 601 is configured to receive a workflow generation request, wherein the workflow generation request carries workflow description information;

The first determining module 602 is configured to determine the workflow node according to the description information;

The first processing module 603 is configured to process workflow nodes, and obtain workflow meta-information based on the processing results; and

The first generation module 604 is configured to generate a target workflow according to workflow meta-information.

In some embodiments of the present disclosure, as shown in FIG. 7, FIG. 7 is a block diagram of a workflow generating device according to an embodiment of the present disclosure. The workflow generating device 70 includes: a first receiving module 701, a first determining module 702. The first processing module 703, the first generating module 704, wherein the first processing module 703 includes:

The processing sub-module 7031 is used to process workflow nodes to form a workflow template;

The first acquiring sub-module 7032 is configured to acquire workflow meta-information according to the workflow template.

In some embodiments of the present disclosure, the first obtaining submodule 7032 is also used to:

Store workflow templates in the workflow template repository;

determine the storage location information of the workflow template in the workflow template repository; and

Store location information as workflow meta information.

In some embodiments of the present disclosure, the number of workflow nodes is multiple;

Wherein, the processing sub-module 7031 is also used for:

Determine the node meta information corresponding to each workflow node;

According to the node meta-information, multiple workflow nodes are spliced to form a workflow template;

Among them, the first acquisition sub-module 7032 is also used for:

Use node meta information as workflow meta information.

In some embodiments of the present disclosure, the workflow generation device 70 further includes:

The feedback module 705 is configured to feed back the workflow meta-information to the workflow producer, wherein the workflow generation request is triggered by the workflow producer.

In some embodiments of the present disclosure, the first generating module 704 includes:

The second obtaining sub-module 7041 is configured to obtain the workflow template from the workflow template warehouse according to the storage location information in response to the workflow management request;

The management sub-module 7042 is used to describe the workflow template according to the node meta-information, and obtain the workflow to be rendered; and

The generating sub-module 7043 is configured to generate a target workflow according to the workflow to be rendered.

In some embodiments of the present disclosure, the generating submodule 7043 is also used to:

Provide the workflow to be rendered to the terminal of the workflow consumer;

receiving rendering operation information fed back by the terminal, wherein the rendering operation information is obtained by the terminal parsing the rendering operation instruction in response to the rendering operation instruction; and

Perform rendering processing on the workflow to be rendered according to the rendering operation information to obtain the target workflow.

It can be understood that the workflow generation device 70 in Fig. 7 of this embodiment is the same as the workflow generation device 60 in the above embodiment, the first receiving module 701 and the first receiving module 601 in the above embodiment, the first determination The module 702 and the first determination module 602 in the above embodiment, the first processing module 703 and the first processing module 603 in the above embodiment, and the first generation module 704 and the first generation module 604 in the above embodiment may have Same function and structure.

It should be noted that the foregoing explanations of the workflow generation method are also applicable to the workflow generation device of this embodiment.

Fig. 8 is a block diagram of a workflow generating device according to an embodiment of the present disclosure.

As shown in Figure 8, the workflow generating device 80 includes:

The second receiving module 801 is configured to receive a workflow description request, wherein the workflow description request carries scene information;

The second determination module 802 is configured to determine the description information of the workflow matching the scene information;

The second generation module 803 is configured to generate a workflow generation request according to the description information of the workflow;

The second processing module 804 is configured to provide a workflow generation request to the workflow producer, so as to trigger the workflow producer to generate a target workflow according to the workflow generation request.

In some embodiments of the present disclosure, as shown in FIG. 9, FIG. 9 is a block diagram of a workflow generating device according to an embodiment of the present disclosure. The workflow generating device 90 includes: a second receiving module 901, a second determining module 902, the second generation module 903, the second processing module 904, wherein, the workflow generation device 90 further includes:

An acquisition module 905, configured to acquire the workflow to be rendered provided by the workflow producer after the workflow generation request is provided to the workflow producer;

The parsing module 906 is configured to parse the rendering operation instruction to obtain rendering operation information in response to the rendering operation instruction, wherein the rendering operation information is used to perform rendering processing on the workflow to be rendered;

A providing module 907, configured to provide the rendering operation information to the workflow producer.

It can be understood that the workflow generating device 90 in Fig. 9 of this embodiment is the same as the workflow generating device 80 in the above embodiment, the second receiving module 901 is the same as the second receiving module 801 in the above embodiment, and the second determination The module 902 and the second determination module 802 in the above embodiment, the second generation module 903 and the second generation module 803 in the above embodiment, and the second processing module 904 and the second processing module 804 in the above embodiment may have Same function and structure.

According to the embodiments of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.

Fig. 10 shows a schematic block diagram of an example electronic device for implementing the workflow generation method of the embodiment of the present disclosure. Electronic device is intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other suitable computers. Electronic devices may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are by way of example only, and are not intended to limit implementations of the disclosure described and/or claimed herein.

As shown in FIG. 10 , the device 1000 includes a computing unit 1001 that can be executed according to a computer program stored in a read-only memory (ROM) 1002 or loaded from a storage unit 1008 into a random-access memory (RAM) 1003. Various appropriate actions and treatments. In the RAM 1003, various programs and data necessary for the operation of the device 1000 can also be stored. The computing unit 1001, ROM 1002, and RAM 1003 are connected to each other through a bus 1004. An input/output (I/O) interface 1005 is also connected to the bus 1004 .

Multiple components in the device 1000 are connected to the I/O interface 1005, including: an input unit 1006, such as a keyboard, a mouse, etc.; an output unit 1007, such as various types of displays, speakers, etc.; a storage unit 1008, such as a magnetic disk, an optical disk, etc. ; and a communication unit 1009, such as a network card, a modem, a wireless communication transceiver, and the like. The communication unit 1009 allows the device 1000 to exchange information/data with other devices through a computer network such as the Internet and/or various telecommunication networks.

The computing unit 1001 may be various general-purpose and/or special-purpose processing components having processing and computing capabilities. Some examples of computing units 1001 include, but are not limited to, central processing units (CPUs), graphics processing units (GPUs), various dedicated artificial intelligence (AI) computing chips, various computing units that run machine learning model algorithms, digital signal processing processor (DSP), and any suitable processor, controller, microcontroller, etc. The calculation unit 1001 executes various methods and processes described above, such as a workflow generation method. For example, in some embodiments, the workflow generation method may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as storage unit 1008 . In some embodiments, part or all of the computer program may be loaded and/or installed on the device 1000 via the ROM 1002 and/or the communication unit 1009. When the computer program is loaded into the RAM 1003 and executed by the computing unit 1001, one or more steps of the workflow generation method described above can be performed. Alternatively, in other embodiments, the computing unit 1001 may be configured in any other appropriate way (for example, by means of firmware) to execute the workflow generation method.

Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips Implemented in a system of systems (SOC), load programmable logic device (CPLD), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include being implemented in one or more computer programs executable and/or interpreted on a programmable system including at least one programmable processor, the programmable processor Can be special-purpose or general-purpose programmable processor, can receive data and instruction from storage system, at least one input device, and at least one output device, and transmit data and instruction to this storage system, this at least one input device, and this at least one output device an output device.

Program codes for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special purpose computer, or other programmable data processing devices, so that the program codes, when executed by the processor or controller, make the functions/functions specified in the flow diagrams and/or block diagrams Action is implemented. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media would include one or more wire-based electrical connections, portable computer discs, hard drives, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, compact disk read only memory (CD-ROM), optical storage, magnetic storage, or any suitable combination of the foregoing.

To provide for interaction with the user, the systems and techniques described herein can be implemented on a computer having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user. ); and a keyboard and pointing device (eg, a mouse or a trackball) through which a user can provide input to the computer. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and can be in any form (including Acoustic input, speech input or, tactile input) to receive input from the user.

The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., as a a user computer having a graphical user interface or web browser through which a user can interact with embodiments of the systems and techniques described herein), or including such backend components, middleware components, Or any combination of front-end components in a computing system. The components of the system can be interconnected by any form or medium of digital data communication, eg, a communication network. Examples of communication networks include: local area networks (LANs), wide area networks (WANs), the Internet, and blockchain networks.

A computer system may include clients and servers. Clients and servers are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the problem of traditional physical host and virtual private server (Virtual Private Server, referred to as VPS) services. The management is difficult and the business scalability is weak. The server can also be a server of a distributed system, or a server combined with a blockchain.

It should be understood that steps may be reordered, added or deleted using the various forms of flow shown above. For example, each step described in the present disclosure may be executed in parallel, sequentially, or in a different order, as long as the desired result of the technical solution disclosed in the present disclosure can be achieved, no limitation is imposed herein.

The specific implementation manners described above do not limit the protection scope of the present disclosure. It should be apparent to those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made depending on design requirements and other factors. Any modifications, equivalent replacements and improvements made within the spirit and principles of the present disclosure shall be included within the protection scope of the present disclosure.

Claims

A workflow generation method, the method comprising:

receiving a workflow generation request, wherein the workflow generation request carries workflow description information;

Determine workflow nodes according to the description information;

processing the workflow node, and obtaining workflow meta-information based on the processing result; and

A target workflow is generated according to the workflow meta-information.
The method according to claim 1, wherein said processing said workflow node and acquiring workflow meta-information based on a processing result comprises:

processing said workflow nodes to form a workflow template; and

According to the workflow template, the workflow meta-information is acquired.
The method according to claim 2, wherein said processing said workflow node to form a workflow template comprises:

determining node meta information corresponding to each workflow node in the plurality of workflow nodes; and

The multiple workflow nodes are spliced according to the node meta-information to form the workflow template.
The method according to claim 2 or 3, wherein said acquiring said workflow meta-information according to said workflow template comprises:

storing the workflow template in a workflow template repository;

determining storage location information of the workflow template in the workflow template warehouse; and

using the storage location information as the workflow meta-information;

or

The node meta information is used as the workflow meta information.
The method according to any one of claims 1 to 4, further comprising:

The workflow meta-information is fed back to a workflow producer, wherein the workflow generation request is triggered by the workflow producer.
The method according to claim 4, wherein said generating a target workflow according to said workflow meta-information comprises:

Responding to a workflow management request, acquiring the workflow template from the workflow template warehouse according to the storage location information;

Describe the workflow template according to the node meta information to obtain a workflow to be rendered; and

Generate the target workflow according to the workflow to be rendered.
The method according to claim 6, wherein said generating said target workflow according to said workflow to be rendered comprises:

providing the workflow to be rendered to a terminal of a workflow user;

receiving rendering operation information fed back by the terminal, wherein the rendering operation information is obtained by the terminal parsing the rendering operation instruction in response to the rendering operation instruction; and

Perform rendering processing on the workflow to be rendered according to the rendering operation information to obtain the target workflow.
A workflow generation method, the method comprising:

receiving a workflow description request, wherein the workflow description request carries scene information;

Determining the description information of the workflow matching the scenario information;

generating a workflow generation request according to the description information of the workflow; and

The workflow generation request is provided to a workflow producer to trigger the workflow producer to generate a target workflow according to the workflow generation request.
The method according to claim 8, after the workflow generation request is provided to the workflow producer, further comprising:

Obtain the workflow to be rendered provided by the workflow producer;

Responding to a rendering operation instruction, parsing the rendering operation instruction to obtain rendering operation information, wherein the rendering operation information is used to perform rendering processing on the workflow to be rendered; and

The rendering operation information is provided to the workflow producer.
A workflow generation device, the device comprising:

The first receiving module is configured to receive a workflow generation request, wherein the workflow generation request carries workflow description information;

A first determining module, configured to determine a workflow node according to the description information;

A first processing module, configured to process the workflow node, and obtain workflow meta-information based on the processing result; and

The first generating module is configured to generate a target workflow according to the workflow meta-information.
The device according to claim 10, wherein the first processing module comprises:

a processing submodule, configured to process the workflow nodes to form a workflow template; and

The first acquiring submodule is configured to acquire the workflow meta-information according to the workflow template.
The device according to claim 11, wherein the processing submodule is further configured to:

determining node meta information corresponding to each workflow node in the plurality of workflow nodes; and

The multiple workflow nodes are spliced according to the node meta-information to form the workflow template.
The device according to claim 11 or 12, wherein the first acquisition submodule is further configured to:

storing the workflow template in a workflow template repository;

determining storage location information of the workflow template in the workflow template warehouse; and

using the storage location information as the workflow meta-information;

or

The node meta information is used as the workflow meta information.
Apparatus according to any one of claims 10 to 13, further comprising:

A feedback module, configured to feed back the workflow meta-information to a workflow producer, wherein the workflow generation request is triggered by the workflow producer.
The device according to claim 13, wherein the first generating module comprises:

The second acquiring submodule is configured to acquire the workflow template from the workflow template warehouse according to the storage location information in response to the workflow management request;

a management submodule, configured to describe the workflow template according to the node meta information, and obtain a workflow to be rendered; and

The generation sub-module is used to generate the target workflow according to the workflow to be rendered.
The device according to claim 15, wherein the generating submodule is also used for:

providing the workflow to be rendered to a terminal of a workflow user;

receiving rendering operation information fed back by the terminal, wherein the rendering operation information is obtained by the terminal parsing the rendering operation instruction in response to the rendering operation instruction; and

Perform rendering processing on the workflow to be rendered according to the rendering operation information to obtain the target workflow.
A workflow generation device, the device comprising:

The second receiving module is configured to receive a workflow description request, wherein the workflow description request carries scene information;

A second determining module, configured to determine the description information of the workflow matching the scenario information;

A second generation module, configured to generate a workflow generation request according to the description information of the workflow; and

The second processing module is configured to provide the workflow generation request to a workflow producer, so as to trigger the workflow producer to generate a target workflow according to the workflow generation request.
The apparatus of claim 17, further comprising:

An acquisition module, configured to acquire the workflow to be rendered provided by the workflow producer after the workflow generation request is provided to the workflow producer;

A parsing module, configured to, in response to a rendering operation instruction, parse the rendering operation instruction to obtain rendering operation information, wherein the rendering operation information is used to perform rendering processing on the workflow to be rendered; and

A module is provided for providing the rendering operation information to the workflow producer.
An electronic device comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor, so that the at least one processor can perform any one of claims 1-9. Methods.
A non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause the computer to execute the method according to any one of claims 1-9.
A computer program product comprising a computer program which, when executed by a processor, implements the steps of the method according to any one of claims 1-9.