WO2023115738A1 - Service interface configuration method and device combining rpa and ai - Google Patents

Abstract

The present application discloses a service interface configuration method and device combining RPA and AI. The configuration method comprises: an RPA system obtaining AI service requirements of an AI service interface to be configured; the RPA system splitting the AI service requirements to generate a plurality of sub-AI service requirements of a single type; the RPA system identifying an association relationship between the sub-AI service requirements; and the RPA system configuring an AI service interface on the basis of a sub-AI service interface corresponding to each sub-AI service requirement and the association relationship. Therefore, the RPA system can automatically configure an AI service interface on the basis of the association relationship between the sub-AI service requirements, is suitable for an application scenario of an AI service interface having multiple types of AI service requirements, is good in extensibility, and improves the development efficiency of an AI service interface.

Description

Method and device for configuring service interface combining RPA and AI

Cross References to Related Applications

This application is based on a Chinese patent application with application number 202111592699.1 and a filing date of December 23, 2021, 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

This application relates to the technical fields of Robotic Process Automation (RPA) and Artificial Intelligence (AI), in particular to a configuration method, device, device and medium for a service interface combining RPA and AI.

Background technique

Robotic Process Automation (RPA) uses specific "robot software" to simulate human operations on computers and automatically execute process tasks according to rules.

Artificial Intelligence (AI) is a technical science that studies and develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence.

At present, RPA and AI technologies have the advantages of high degree of automation, high precision, and low cost, and have been widely used.

In related technologies, due to the variety of business requirements, business data formats, and storage methods, it is often necessary to develop multiple AI service interfaces. For example, developers need to develop an AI service interface according to each business requirement, resulting in repetitive development. Many, large development workload and other issues.

Contents of the invention

The present application aims to solve one of the technical problems in the above-mentioned technologies at least to a certain extent.

For this reason, the first purpose of this application is to propose a method for configuring service interfaces combining RPA and AI, which can automatically configure AI service interfaces based on the association relationship between sub-AI service requirements, and is suitable for multi-category AI services The application scenario of the required AI service interface has good scalability, which improves the development efficiency of the AI service interface.

The second purpose of this application is to propose a method for invoking a service interface combining RPA and AI.

The third purpose of the present application is to propose a device for configuring a service interface combining RPA and AI.

The fourth purpose of the present application is to propose a device for invoking a service interface combining RPA and AI.

The fifth object of the present application is to provide an electronic device.

The sixth object of the present application is to provide a computer-readable storage medium.

In order to achieve the above purpose, the embodiment of the first aspect of the present application proposes a method for configuring a service interface combining RPA and AI, including: the RPA system obtains the AI service requirements of the AI service interface to be configured; The AI service requirements are split to generate multiple sub-AI service requirements of a single category; the RPA system identifies the association relationship between the sub-AI service requirements, wherein the association relationship includes a parallel relationship and a series relationship. At least one: the RPA system configures the AI service interface based on the sub-AI service interface corresponding to each sub-AI service requirement and the association relationship.

According to the configuration method of the service interface combining RPA and AI in the embodiment of the present application, the AI service requirements of the AI service interface to be configured can be split to generate multiple sub-AI service requirements of a single category, and the AI service requirements can be realized. Automatically split and identify the association relationship between sub-AI service requirements, and configure the AI service interface based on the sub-AI service interface and association relationship corresponding to each sub-AI service requirement. As a result, the AI service interface can be automatically configured based on the correlation between the sub-AI service requirements, which is suitable for the application scenario of the AI service interface for multiple types of AI service requirements, and has good scalability and improves the development efficiency of the AI service interface. .

In an embodiment of the present application, configuring the AI service interface based on the sub-AI service interface corresponding to each sub-AI service requirement and the association relationship includes: obtaining the sub-AI by the RPA system The first configuration information of the service interface; the RPA system generates the second configuration information of the AI service interface based on the first configuration information of each sub-AI service interface and the association relationship; the RPA system Configure the AI service interface based on the second configuration information.

In an embodiment of the present application, the second configuration information of the AI service interface is generated based on the first configuration information of each sub-AI service interface and the association relationship, including: the RPA The system recognizes that the association relationship is the first sub-AI service interface of the parallel relationship; the RPA system obtains multiple fields of the AI service interface; the RPA system constructs the first sub-AI service interface of the first sub-AI service interface. A mapping relationship between configuration information and the fields, generating the second configuration information based on the mapping relationship.

In an embodiment of the present application, the second configuration information of the AI service interface is generated based on the first configuration information of each sub-AI service interface and the association relationship, including: the RPA The system recognizes that the association relationship is the second sub-AI service interface of a series relationship; the RPA system sorts the sub-AI service requirements corresponding to the second sub-AI service interface according to the call time from early to late, and generates the The first ordering of the sub-AI service requirements corresponding to the second sub-AI service interface; the RPA system generates the first ordering of the sub-AI service requirements corresponding to the second sub-AI service interface. The second sorting of the first configuration information of the second sub-AI service interface; the RPA system splices the first configuration information of the second sub-AI service interface according to the second sorting to generate the the second configuration information.

In an embodiment of the present application, the second configuration information of the AI service interface is generated based on the first configuration information of each sub-AI service interface and the association relationship, including: the RPA The system identifies that the association relationship includes a third sub-AI service interface with a parallel relationship and a serial relationship; for the third sub-AI service interface whose association relationship is a parallel relationship, the RPA system acquires multiple fields of the AI service interface The RPA system constructs the mapping relationship between the first configuration information of the third sub-AI service interface and the field, and generates the first candidate configuration information based on the mapping relationship; for those whose association relationship is a serial relationship For the third sub-AI service interface, the RPA system sorts the sub-AI service requirements corresponding to the third sub-AI service interface according to the call time from early to late, and generates the third sub-AI service interface corresponding The first ranking of the sub-AI service requirements; the RPA system generates the third sub-AI service interface based on the first ranking of the sub-AI service requirements corresponding to the third sub-AI service interface The second sorting of the first configuration information; the RPA system splices the first configuration information of the third sub-AI service interface according to the second sorting to generate second candidate configuration information; wherein, the The second configuration information includes the first candidate configuration information and the second candidate configuration information.

In one embodiment of the present application, the configuration information includes a Schema file and a Resolver based on the GraphQL query language.

In one embodiment of the present application, the splitting the AI service requirements to generate multiple sub-AI service requirements of a single category includes: the RPA system identifies the AI service requirements involved in the AI service requirements based on natural language processing (NLP) multiple single categories; for any identified single category, the RPA system extracts the sub-AI service requirements of any single category from the AI service requirements.

In an embodiment of the present application, the sub-AI service requirements include at least one of NLP, optical character recognition (OCR), speech synthesis, speech recognition, and image annotation.

In order to achieve the above purpose, the embodiment of the second aspect of the present application proposes a method for invoking a service interface combining RPA and AI, including: obtaining a GraphQL query language for invoking the AI service interface; converting the GraphQL query language, Acquiring a Resolver of the AI service interface; calling the AI service interface based on the resolver.

According to the call method of the service interface combining RPA and AI in the embodiment of the present application, after obtaining the GraphQL query language used to call the AI service interface, the GraphQL query language can be converted to obtain the resolver Resolver of the AI service interface, based on the resolver , call the AI service interface. As a result, the AI service interface can be automatically converted into a front-end operation interface based on the GraphQL query language, so as to realize the connection between the AI service interface and the low-code platform, and improve the development efficiency of the AI service interface.

In order to achieve the above purpose, the embodiment of the third aspect of the present application proposes a configuration device for a service interface combining RPA and AI, including: an acquisition module for acquiring the AI service requirements of the AI service interface to be configured; a split module, It is used to split the AI service requirements to generate multiple sub-AI service requirements of a single category; the identification module is used to identify the association relationship between the sub-AI service requirements, wherein the association relationship includes parallel relationship and At least one of the serial relationships; a configuration module configured to configure the AI service interface based on the sub-AI service interface corresponding to each sub-AI service requirement and the association relationship.

The configuration device of the service interface combining RPA and AI in the embodiment of the present application can split the AI service requirements of the AI service interface to be configured to generate multiple sub-AI service requirements of a single category, which can realize automatic AI service requirements Split and identify the relationship between the sub-AI service requirements, and configure the AI service interface based on the sub-AI service interface and the relationship corresponding to each sub-AI service requirement. As a result, the AI service interface can be automatically configured based on the correlation between the sub-AI service requirements, which is suitable for the application scenario of the AI service interface for multiple types of AI service requirements, and has good scalability and improves the development efficiency of the AI service interface. .

In an embodiment of the present application, the configuration module is further configured to: obtain the first configuration information of the sub-AI service interface; based on the first configuration information and the Association relationship, generating second configuration information of the AI service interface; configuring the AI service interface based on the second configuration information.

In an embodiment of the present application, the configuration module is further configured to: identify that the association relationship is a first sub-AI service interface of a parallel relationship; obtain multiple fields of the AI service interface; construct the first sub-AI service interface; The second configuration information is generated based on the mapping relationship between the first configuration information of the sub-AI service interface and the fields.

In an embodiment of the present application, the configuration module is further configured to: identify the second sub-AI service interface in which the association relationship is a series relationship; configure the sub-AI service interface corresponding to the second sub-AI service interface The requirements are sorted from early to late according to the calling time, and the first sorting of the sub-AI service requirements corresponding to the second sub-AI service interface is generated; based on the sub-AI service requirements corresponding to the second sub-AI service interface the first sorting of the first sub-AI service interface to generate a second sorting of the first configuration information of the second sub-AI service interface; and the first configuration information of the second sub-AI service interface according to the second sorting Splicing is performed to generate the second configuration information.

In an embodiment of the present application, the configuration module is further configured to: identify the third sub-AI service interface whose association relationship includes a parallel relationship and a serial relationship; A service interface, acquiring multiple fields of the AI service interface; constructing a mapping relationship between the first configuration information of the third sub-AI service interface and the fields, and generating a first candidate configuration based on the mapping relationship Information; for the third sub-AI service interface whose association relationship is a series relationship, sort the sub-AI service requirements corresponding to the third sub-AI service interface according to the call time from early to late, and generate the third sub-AI service interface. A first ranking of the sub-AI service requirements corresponding to the sub-AI service interface; generating the third sub-AI service interface based on the first ranking of the sub-AI service requirements corresponding to the third sub-AI service interface the second sorting of the first configuration information; splicing the first configuration information of the third sub-AI service interface according to the second sorting to generate second candidate configuration information; wherein, the second The configuration information includes the first candidate configuration information and the second candidate configuration information.

In one embodiment of the present application, the configuration information includes a Schema file and a Resolver based on the GraphQL query language.

In one embodiment of the present application, the splitting module is further configured to: identify multiple single categories involved in the AI service requirements based on natural language processing NLP; for any identified single category, from the The sub-AI service requirements of any single category are extracted from the AI service requirements.

In an embodiment of the present application, the sub-AI service requirements include at least one of NLP, optical character recognition (OCR), speech synthesis, speech recognition, and image annotation.

In order to achieve the above-mentioned purpose, the embodiment of the fourth aspect of the present application proposes a service interface calling device combining RPA and AI, including: an acquisition module for acquiring the GraphQL query language used to call the AI service interface; a conversion module for using Converting the GraphQL query language to obtain a Resolver of the AI service interface; a calling module, configured to call the AI service interface based on the resolver.

The configuration device of the service interface combining RPA and AI in the embodiment of the present application can split the AI service requirements of the AI service interface to be configured to generate multiple sub-AI service requirements of a single category, which can realize automatic AI service requirements Split and identify the relationship between the sub-AI service requirements, and configure the AI service interface based on the sub-AI service interface and the relationship corresponding to each sub-AI service requirement. As a result, the AI service interface can be automatically configured based on the correlation between the sub-AI service requirements, which is suitable for the application scenario of the AI service interface for multiple types of AI service requirements, and has good scalability and improves the development efficiency of the AI service interface. .

To achieve the above purpose, the embodiment of the fifth aspect of the present application proposes an electronic device, including: at least one processor; and a memory connected to the at least one processor in communication; wherein, the memory stores information that can be used by the Instructions executed by at least one processor, the instructions are executed by the at least one processor, so that the at least one processor can execute the configuration of the service interface combining RPA and AI as described in the embodiment of the first aspect of the present application method, or execute the calling method of the service interface combining RPA and AI as described in the embodiment of the second aspect of the present application.

The electronic device in the embodiment of the present application can split the AI service requirements of the AI service interface to be configured through the processor to execute the instructions stored in the memory, so as to generate multiple sub-AI service requirements of a single category, and realize the AI service. The requirements are automatically split, and the association relationship between the sub-AI service requirements is identified, and the AI service interface is configured based on the sub-AI service interface and the association relationship corresponding to each sub-AI service requirement. As a result, the AI service interface can be automatically configured based on the correlation between the sub-AI service requirements, which is suitable for the application scenario of the AI service interface for multiple types of AI service requirements, and has good scalability and improves the development efficiency of the AI service interface. .

In order to achieve the above purpose, the embodiment of the sixth aspect of the present application proposes a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the combined RPA as described in the embodiment of the first aspect of the application is realized. A configuration method of a service interface with AI, or a method of invoking a service interface combining RPA and AI as described in the embodiment of the second aspect of the present application.

The computer-readable storage medium of the embodiment of the present application can split the AI service requirements of the AI service interface to be configured by storing the computer program and executing it by the processor, so as to generate multiple sub-AI service requirements of a single category, which can realize Automatically split AI service requirements, identify the relationship between sub-AI service requirements, and configure AI service interfaces based on the sub-AI service interface and association relationship corresponding to each sub-AI service requirement. As a result, the AI service interface can be automatically configured based on the correlation between the sub-AI service requirements, which is suitable for the application scenario of the AI service interface for multiple types of AI service requirements, and has good scalability and improves the development efficiency of the AI service interface. .

Description of drawings

The above and/or additional aspects and advantages of the present application will become apparent and easy to understand from the following description of the embodiments in conjunction with the accompanying drawings, wherein:

FIG. 1 is a schematic flowchart of a method for configuring a service interface combining RPA and AI according to an embodiment of the present application.

FIG. 2 is a schematic flowchart of configuring an AI service interface in a method for configuring a service interface combining RPA and AI according to an embodiment of the present application.

FIG. 3 is a schematic flowchart of generating second configuration information of an AI service interface in a method for configuring a service interface combining RPA and AI according to an embodiment of the present application.

FIG. 4 is a schematic flowchart of generating second configuration information of an AI service interface in a method for configuring a service interface combining RPA and AI according to another embodiment of the present application.

FIG. 5 is a schematic flowchart of generating second configuration information of an AI service interface in a method for configuring a service interface combining RPA and AI according to another embodiment of the present application.

FIG. 6 is a schematic flowchart of a method for invoking a service interface combining RPA and AI according to an embodiment of the present application.

Fig. 7 is a block diagram of an AI service system according to an embodiment of the present application.

FIG. 8 is a block diagram of an AI service system in the related art.

FIG. 9 is a block diagram of an apparatus for configuring a service interface combining RPA and AI according to an embodiment of the present application.

Fig. 10 is a block diagram of a device for invoking a service interface combining RPA and AI according to an embodiment of the present application.

FIG. 11 is a block diagram of an electronic device according to an embodiment of the present application.

Detailed ways

Embodiments of the present application are described in detail below, examples of which are shown in the drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the figures are exemplary, and are intended to explain the present application, and should not be construed as limiting the present application.

For ease of understanding, terms involved in this application are firstly introduced.

In the description of the present application, the term "plurality" means two or more.

In the description of this application, the term "AI service interface" refers to the AI service interface to be configured.

In the description of this application, the term "AI service requirements" refers to the AI service requirements and/or AI capabilities corresponding to the AI service interface to be configured, and there are multiple corresponding service categories. For example, AI service requirements include but are not limited to natural language Processing (Natural Language Processing, NLP), Optical Character Recognition (Optical Character Recognition, OCR), speech synthesis, speech recognition, image annotation, etc.

In the description of this application, the term "sub-AI service requirements" refers to the sub-AI service requirements after the AI service requirements are split, and there is one corresponding service category.

In the description of this application, the term "sub-AI service interface" refers to the sub-AI service interface corresponding to the sub-AI service requirements.

In the description of this application, the term "association relationship" refers to the relationship between sub-AI service requirements, including at least one of a parallel relationship and a serial relationship.

In the description of this application, the term "configuration information" refers to the configuration information used to configure the service interface, including the first configuration information and the second configuration information, and the first configuration information refers to the configuration information used to configure the sub-AI service interface , the second configuration information refers to configuration information used to configure the AI service interface.

In the description of this application, the term "call time" refers to the call time of the sub-AI service interface. The invocation time of sub-AI service interfaces with a parallel relationship is the same, and the invocation time of sub-AI service interfaces with a serial relationship is different.

In the description of this application, the term "GraphQL query language" refers to the query language Query Language with better query performance on graph data Graph.

In the description of this application, the term "Schema file" refers to a file used to define the operations supported by the service interface, including input parameters and returned fields.

In the description of this application, the term "Resolver" refers to a resolver for obtaining each returned field in a Schema file, including a resolver function.

In the description of this application, the term "low-code platform" refers to a development platform that can quickly generate applications without coding or with a small amount of code. The method of developing applications through visualization allows developers to use graphical user interfaces. Create web pages and applications using drag-and-drop components and model-driven logic.

The configuration method, calling method, device, electronic device, and computer-readable storage medium of the AI service interface of the embodiments of the present application are described below with reference to the accompanying drawings.

FIG. 1 is a schematic flowchart of a method for configuring a service interface combining RPA and AI according to an embodiment of the present application.

As shown in Figure 1, the configuration method of the service interface combining RPA and AI in the embodiment of the present application includes:

S101. The RPA system obtains the AI service requirements of the AI service interface to be configured.

It should be noted that the execution subject of the configuration method of the service interface combining RPA and AI in the embodiment of the present application may be a robotic process automation (Robotic Process Automation, RPA) system, and may also be the combination of RPA and AI in the embodiment of the present application. The device for configuring the service interface, the above-mentioned RPA system and/or the device for configuring the service interface combining RPA and AI can be configured in any electronic device to implement the method for configuring the service interface combining RPA and AI according to the embodiment of the present application. Optionally, the above RPA system may include an RPA robot.

In the embodiment of the present application, the RPA system can obtain the AI service requirements of the artificial intelligence (Artificial Intelligence, AI) service interface to be configured.

It should be noted that the AI service interface refers to the interface used to connect to the AI server, where the AI server includes but is not limited to AI algorithms, models, and so on.

It should be noted that there are multiple service categories for AI service requirements, and the service categories for AI service requirements are not too limited. For example, AI service requirements include but are not limited to natural language processing (Natural Language Processing, NLP), optical character Recognition (Optical Character Recognition, OCR), speech synthesis, speech recognition, image annotation, etc.

In one embodiment, obtaining the AI service requirements of the AI service interface to be configured may include the RPA system receiving a configuration request from the user, and the configuration request carries the AI service requirements of the AI service interface to be configured. For example, a user can issue a configuration request on a low-code platform. Correspondingly, the RPA system can receive the user's configuration request and extract the AI service requirements of the AI service interface to be configured from the configuration request.

In one embodiment, the RPA system can open the low-code platform, log in to the low-code platform with a preset account, and obtain the AI service requirements of the AI service interface to be configured from the list to be configured on the low-code platform. Among them, the default account is the login account for the RPA system to log in to the low-code platform, which can be set according to the actual situation, and there are no too many restrictions here. Therefore, in this method, the RPA system can automatically open and log in to the low-code platform, and automatically obtain the AI service requirements of the AI service interface to be configured from the to-be-configured list of the low-code platform, which can realize the automatic acquisition of AI service requirements.

S102. The RPA system splits the AI service requirements to generate multiple sub-AI service requirements of a single category.

In the embodiment of this application, the RPA system can split the AI service requirements to generate multiple sub-AI service requirements of a single category, that is, each sub-AI service requirement after splitting has one service category.

For example, the AI service requirements of the AI service interface A to be configured include text recognition and form recognition, the above AI service requirements can be split, and the generated sub-AI service requirements include text recognition and form recognition.

For example, the AI service requirements of the AI service interface B to be configured include optical character recognition and natural language processing, the above AI service requirements can be split, and the generated sub-AI service requirements include optical character recognition and natural language processing.

For example, the AI service requirements of the AI service interface C to be configured include voice recognition and voice interaction, the above AI service requirements can be split, and the generated sub-AI service requirements include voice recognition and voice interaction.

In one embodiment, splitting the AI service requirements to generate multiple sub-AI service requirements of a single category may include the RPA system identifying multiple single categories involved in the AI service requirements based on NLP, and the RPA system for any identified sub-categories A single category, extract any single category of sub-AI service requirements from AI service requirements. Therefore, the RPA system can realize the automatic splitting of AI service requirements based on NLP.

For example, the AI service requirement of the AI service interface I to be configured is intelligent document processing. The document includes pictures, and the pictures carry text and tables. The RPA system can identify multiple single categories involved in the above AI service requirements based on NLP, and identify The multiple single categories include text recognition and form recognition, and for the recognized text recognition, extract the sub-AI service requirements for text recognition from the above AI service requirements, and extract the sub AI service requirements for the recognized form recognition from the above AI service requirements Sub-AI service requirements identified by the table.

S103. The RPA system identifies an association relationship between sub-AI service requirements, wherein the association relationship includes at least one of a parallel relationship and a serial relationship.

In the embodiment of the present application, sub-AI service requirements have an association relationship, wherein the association relationship includes at least one of a parallel relationship and a serial relationship.

In one embodiment, the association relationship between sub-AI service requirements only includes parallel relationship. For example, sub-AI service requirements include text recognition and form recognition, and the relationship between text recognition and form recognition is a parallel relationship.

In an implementation manner, the association relationship between sub-AI service requirements only includes a series relationship. For example, sub-AI service requirements include optical character recognition and natural language processing. The correlation between optical character recognition and natural language processing is a serial relationship, and the processing time of optical character recognition is earlier than that of natural language processing.

In an implementation manner, the association relationship between sub-AI service requirements includes a parallel relationship and a serial relationship. For example, sub-AI service requirements include text recognition, form recognition, and natural language processing. Among them, the association between text recognition and form recognition is a parallel relationship, and the association between natural language processing, text recognition, and form recognition is serial relationship, and the processing time of natural language processing is later than that of text recognition and form recognition.

In one embodiment, a mapping relationship or a mapping table between sub-AI service requirements and association relationships can be established in advance, and after the sub-AI service requirements are obtained, the mapping relationship or mapping table can be queried to obtain the corresponding association relationship. It should be noted that the above mapping relationship or mapping table can be set according to actual conditions, and there is no excessive limitation here.

S104. The RPA system configures the AI service interface based on the sub-AI service interface and the association relationship corresponding to each sub-AI service requirement.

In one embodiment, configuring the AI service interface based on the sub-AI service interface and the association relationship corresponding to each sub-AI service requirement may include that the RPA system constructs the sub-AI service interface based on the association relationship between the sub-AI service requirements. The above association relationship is used to configure the AI service interface.

For example, the sub-AI service requirements corresponding to the AI service requirements of AI service interface A to be configured include text recognition and form recognition, the association between text recognition and form recognition is a parallel relationship, and the sub-AI services corresponding to text recognition and form recognition The interfaces are sub-AI service interfaces D and E, and the RPA system can build a parallel relationship between sub-AI service interfaces D and E to configure AI service interface A.

For example, the sub-AI service requirements corresponding to the AI service requirements of AI service interface B to be configured include optical character recognition and natural language processing. The association relationship between optical character recognition and natural language processing is a serial relationship, optical character recognition and natural language The corresponding sub-AI service interfaces are respectively sub-AI service interfaces F and G, and the RPA system can build a serial relationship between sub-AI service interfaces F and G to configure AI service interface B.

For example, the sub-AI service requirements corresponding to the AI service requirements of the AI service interface H to be configured include text recognition, form recognition, and natural language processing. The association between text recognition and form recognition is a parallel relationship, and natural language processing is respectively The association relationship with text recognition and form recognition is a serial relationship. The sub-AI service interfaces corresponding to text recognition, form recognition and natural language processing are respectively sub-AI service interfaces D, E, and G. The RPA system can build sub-AI service interfaces The parallel relationship between D and E, the serial relationship between sub-AI service interfaces D and G, and the serial relationship between sub-AI service interfaces E and G are constructed to configure AI service interface H.

To sum up, according to the configuration method of the AI service interface of the embodiment of the present application, the RPA system can split the AI service requirements of the AI service interface to be configured to generate multiple sub-AI service requirements of a single category, which can realize the AI service requirements Automatic splitting of sub-AI service requirements, identifying the relationship between sub-AI service requirements, and configuring AI service interfaces based on the sub-AI service interface and association relationship corresponding to each sub-AI service requirement. Therefore, the RPA system can automatically configure the AI service interface based on the correlation between the sub-AI service requirements, which is suitable for the application scenarios of the AI service interface for multi-category AI service requirements. It has good scalability and improves the AI service interface. Development efficiency.

On the basis of any of the above embodiments, as shown in FIG. 2, in step S103, configuring the AI service interface based on the sub-AI service interface and the association relationship corresponding to each sub-AI service requirement may include:

S201. The RPA system acquires first configuration information of a sub-AI service interface.

In the embodiment of the present application, the RPA system can acquire the first configuration information of the sub-AI service interface. It should be noted that the first configuration information refers to the configuration information used to configure the sub-AI service interface, and the type of configuration information is not limited too much. For example, the configuration information may include Schema files based on the GraphQL query language, parser Resolver.

In one embodiment, the RPA system can pre-establish the mapping relationship or mapping table between the sub-AI service interface and the first configuration information. After obtaining the sub-AI service interface, query the mapping relationship or mapping table to obtain the corresponding The first configuration information. It should be noted that the above mapping relationship or mapping table can be set according to actual conditions, and there is no excessive limitation here.

S202. The RPA system generates second configuration information of the AI service interface based on the first configuration information and the association relationship of each sub-AI service interface.

In one embodiment, generating the second configuration information of the AI service interface based on the first configuration information and the association relationship of each sub-AI service interface may include the RPA system performing the first configuration information of each sub-service interface according to the association relationship combined to generate the second configuration information of the AI service interface.

For example, the RPA system may combine the first configuration information of sub-service interfaces whose association relationship is a parallel relationship according to a parallel relationship, and/or combine the first configuration information of sub-service interfaces whose association relationship is a serial relationship according to a series relationship, Generate second configuration information of the AI service interface.

For example, the sub-AI service requirements corresponding to the AI service requirements of the AI service interface H to be configured include text recognition, form recognition, and natural language processing. The association between text recognition and form recognition is a parallel relationship, and natural language processing is respectively The association relationship with text recognition and form recognition is a series relationship. The sub-AI service interfaces corresponding to text recognition, form recognition and natural language processing are sub-AI service interfaces D, E, and G respectively. The RPA system can use sub-AI service interfaces Combine the first configuration information of D and E according to the parallel relationship, combine the first configuration information of the sub-AI service interfaces D and G according to the serial relationship, and combine the first configuration information of the sub-AI service interfaces E and G according to the serial relationship Combine them to generate the second configuration information of the AI service interface H.

S203. The RPA system configures the AI service interface based on the second configuration information.

In one embodiment, configuring the AI service interface based on the second configuration information may include the RPA system storing the second configuration information in a target storage space in the low-code platform, and the target storage space is used to store the configuration of the AI service interface information. It should be noted that the target storage space is not limited too much.

In one embodiment, the RPA system can also generate a front-end operation interface of the AI service interface. It should be noted that the front-end operation interface refers to the interface used to respond to user operations, and there are no excessive restrictions on the types of front-end operation interfaces. For example, front-end operation interfaces include but are not limited to front-end operation interfaces based on query languages, such as based on GraphQL's front-end operation interface.

Therefore, in this method, the RPA system can generate the second configuration information of the AI service interface based on the first configuration information and the association relationship of each sub-AI service interface, and configure the AI service interface based on the second configuration information to realize the AI service Automatic configuration of interfaces.

On the basis of any of the above embodiments, as shown in FIG. 3, in step S202, based on the first configuration information and association relationship of each sub-AI service interface, the second configuration information of the AI service interface is generated, which may include:

S301. The RPA system identifies that the association relationship is the first sub-AI service interface of the parallel relationship.

For example, the sub-AI service requirements corresponding to the AI service requirements of AI service interface A to be configured include text recognition and form recognition, the association between text recognition and form recognition is a parallel relationship, and the sub-AI services corresponding to text recognition and form recognition The interfaces are respectively sub-AI service interfaces D and E, and the first sub-AI service interface for which the RPA system recognizes that the association relationship is a parallel relationship includes sub-AI service interfaces D and E.

S302. The RPA system acquires multiple fields of the AI service interface.

In the embodiment of the present application, multiple fields of the AI service interface to be configured can be obtained. It should be noted that the fields refer to the fields fed back by the AI service interface, and the fields are not limited too much. For example, fields include, but are not limited to, name, address, title, title, introduction, outline, and the like.

S303. The RPA system constructs a mapping relationship between the first configuration information and fields of the first sub-AI service interface, and generates second configuration information based on the mapping relationship.

In one embodiment, the RPA system can construct the mapping relationship between the data extraction DataFetcher configuration information of the first sub-AI service interface and the fields in the Schema file, and generate the second configuration information based on the mapping relationship. It should be noted that the data fetching configuration information is used to define an interface for fetching data.

For example, the sub-AI service requirements corresponding to the AI service requirements of the AI service interface A to be configured include text recognition and form recognition, and the sub-AI service interfaces corresponding to text recognition and form recognition are sub-AI service interfaces D and E respectively, identifying association relationships The first sub-AI service interface of the parallel relationship includes sub-AI service interfaces D and E. The fields in the Schema file of AI service interface A include name, title, introduction, number of table rows, and number of table columns. The RPA system can build sub-AIs The mapping relationship between the data extraction configuration information of service interface D and the name, title, and introduction, as well as the mapping relationship between the data extraction configuration information of the sub-AI service interface E and the number of table rows and table columns, are generated based on the mapping relationship The second configuration information of AI service interface A.

In an implementation manner, the RPA system may construct a mapping relationship between the Resolver of the first sub-service interface and fields in the Schema file, and generate the second configuration information based on the mapping relationship. It should be noted that, for the related content of constructing the mapping relationship between the parser and the fields, refer to the above-mentioned embodiments, and details are not repeated here.

Therefore, in this method, the RPA system can obtain multiple fields of the AI service interface for the first sub-AI service interface whose association relationship is a parallel relationship, and construct a mapping between the first configuration information and the fields of the first sub-AI service interface The second configuration information is generated based on the mapping relationship, which can realize the parallel invocation of multiple first sub-AI service interfaces.

On the basis of any of the above embodiments, as shown in FIG. 4, in step S202, based on the first configuration information and association relationship of each sub-AI service interface, the second configuration information of the AI service interface is generated, which may include:

S401. The RPA system identifies the second sub-AI service interface whose association relationship is a serial relationship.

For example, the sub-AI service requirements corresponding to the AI service requirements of AI service interface B to be configured include optical character recognition and natural language processing. The association relationship between optical character recognition and natural language processing is a serial relationship, optical character recognition and natural language The sub-AI service interfaces corresponding to the processing are respectively sub-AI service interfaces F and G, and the second sub-AI service interface that the RPA system recognizes as a serial relationship includes sub-AI service interfaces F and G.

S402. The RPA system sorts the sub-AI service requirements corresponding to the second sub-AI service interface from early to late according to the invocation time, and generates a first ranking of the sub-AI service requirements corresponding to the second sub-AI service interface.

It can be understood that the invocation time of sub-AI service requirements corresponding to different second sub-AI service interfaces is different. For example, the second sub-AI service interface that identifies the association relationship as a series relationship includes sub-AI service interfaces F and G, and the invocation time of the sub-AI service requirement (optical character recognition) corresponding to sub-AI service interface F is earlier than that of sub-AI service interface G The invocation time of the corresponding sub-AI service requirement (natural language processing).

In the embodiment of this application, the RPA system can sort the sub-AI service requirements corresponding to the second sub-AI service interface according to the call time from early to late, and generate the first sub-AI service requirements corresponding to the second sub-AI service interface. Sorting, that is, the sub-AI service requirements with the earliest calling time are sorted first, and the sub-AI service requirements with the late calling time are sorted at the bottom. For example, the second sub-AI service interface that identifies the association relationship as a series relationship includes sub-AI service interfaces F and G, and the invocation time of the sub-AI service requirement (optical character recognition) corresponding to sub-AI service interface F is earlier than that of sub-AI service interface G For the invocation time of the corresponding sub-AI service requirement (natural language processing), the first ranking of the sub-AI service requirements corresponding to the second sub-AI service interfaces F and G is optical character recognition and natural language processing.

S403. The RPA system generates a second ranking of first configuration information of the second sub-AI service interface based on the first ranking of sub-AI service requirements corresponding to the second sub-AI service interface.

In the embodiment of this application, the RPA system can generate the second ranking of the first configuration information of the second sub-AI service interface based on the first ranking of the sub-AI service requirements corresponding to the second sub-AI service interface, that is, the one with the earliest call time The ranking of the first configuration information corresponding to the sub-AI service requirements is higher, and the ranking of the first configuration information corresponding to the sub-AI service requirements with a later call time is lower.

For example, the first ranking of the sub-AI service requirements corresponding to the second sub-AI service interfaces F and G is optical character recognition and natural language processing, and the second ranking of the first configuration information of the second sub-AI service interfaces F and G is No. The first configuration information of the second sub-AI service interface F, and the first configuration information of the second sub-AI service interface G.

S404. The RPA system splices the first configuration information of the second sub-AI service interface according to the second order to generate second configuration information.

In one embodiment, the RPA system can splice the Schema files of the second sub-AI service interface according to the second order to generate the second configuration information.

In one embodiment, the RPA system can splice the last field of the first Schema file with the first field of the second Schema file, wherein the first Schema file and the second Schema file are adjacently sorted Schema files , and the sorting of the first Schema file is higher than that of the second Schema file.

For example, the sub-AI service requirements corresponding to the AI service requirements of the AI service interface B to be configured include optical character recognition and natural language processing. The corresponding sub-AI service interfaces are respectively sub-AI service interfaces F and G, and the second sub-AI service interface that identifies the association relationship as a series relationship includes sub-AI service interfaces F and G, and the Schema of the second sub-AI service interfaces F and G The second sorting of the files is the Schema file of the second sub-AI service interface F, the Schema file of the second sub-AI service interface G, and the RPA system can combine the Schema file of the second sub-AI service interface F, the second sub-AI service interface G The Schema files are spliced according to the above-mentioned second sorting to generate the second configuration information of the AI service interface B. For example, the RPA system can splice the last field of the Schema file of the second sub-AI service interface F with the first field of the Schema file of the second sub-AI service interface G to generate the second configuration information of the AI service interface B .

Therefore, in this method, the RPA system can sort the sub-AI service requirements corresponding to the second sub-AI service interface according to the call time from early to late for the second sub-AI service interface whose association relationship is a series relationship, and obtain the first ranking Based on the first sorting, the second sorting of the first configuration information of the second sub-AI service interface is generated, and the first configuration information of the second sub-AI service interface is spliced according to the second sorting to generate the second configuration information, which can realize multiple A serial call of the second sub-AI service interface.

On the basis of any of the above embodiments, as shown in FIG. 5, in step S202, based on the first configuration information and association relationship of each sub-AI service interface, the second configuration information of the AI service interface is generated, which may include:

S501. The RPA system identifies a third sub-AI service interface whose association relationship includes a parallel relationship and a serial relationship.

For example, the sub-AI service requirements corresponding to the AI service requirements of the AI service interface H to be configured include text recognition, form recognition, and natural language processing. The association between text recognition and form recognition is a parallel relationship, and natural language processing is respectively The association relationship with text recognition and form recognition is a series relationship. The sub-AI service interfaces corresponding to text recognition, form recognition, and natural language processing are sub-AI service interfaces D, E, and G respectively. The RPA system identification association relationship includes a parallel relationship The third sub-AI service interface of the serial relationship includes sub-AI service interfaces D, E, G, wherein the third sub-AI service interface with a parallel relationship includes sub-AI service interfaces D and E, and the associated relationship is a serial relationship The third sub-AI service interface includes sub-AI service interfaces D and G, and the third sub-AI service interface with a serial relationship includes sub-AI service interfaces E and G.

S502, for the third sub-AI service interface whose association relationship is a parallel relationship, the RPA system acquires multiple fields of the AI service interface; the RPA system constructs a mapping relationship between the first configuration information and the fields of the third sub-AI service interface, based on The mapping relationship generates first candidate configuration information.

In the embodiment of the present application, the second configuration information includes first candidate configuration information.

For example, the sub-AI service requirements corresponding to the AI service requirements of the AI service interface H to be configured include text recognition, form recognition, and natural language processing. The association between text recognition and form recognition is a parallel relationship, and natural language processing is respectively The association relationship with text recognition and form recognition is a series relationship. The sub-AI service interfaces corresponding to text recognition, form recognition, and natural language processing are sub-AI service interfaces D, E, and G respectively. The RPA system identification association relationship includes a parallel relationship The third sub-AI service interface in series relationship includes sub-AI service interfaces D, E, and G.

Among them, the third sub-AI service interface whose association relationship is a parallel relationship includes sub-AI service interfaces D and E, and for the sub-AI service interfaces D and E whose association relationship is a parallel relationship, the RPA system can obtain multiple fields of the AI service interface H , constructing a mapping relationship between the first configuration information and fields of the sub-AI service interfaces D and E, and generating first candidate configuration information based on the mapping relationship.

It should be noted that, relevant content of step S502 may refer to the above-mentioned embodiments, and details are not repeated here.

S503, for the third sub-AI service interface whose association relationship is a serial relationship, the RPA system sorts the sub-AI service requirements corresponding to the third sub-AI service interface according to the calling time from early to late, and generates the corresponding sub-AI service requirements of the third sub-AI service interface The first sorting of the sub-AI service requirements; the RPA system generates the second sorting of the first configuration information of the third sub-AI service interface based on the first sorting of the sub-AI service requirements corresponding to the third sub-AI service interface; The first configuration information of the three sub-AI service interfaces is spliced according to the second ranking to generate second candidate configuration information.

In the embodiment of the present application, the second configuration information further includes second candidate configuration information.

For example, the sub-AI service requirements corresponding to the AI service requirements of the AI service interface H to be configured include text recognition, form recognition, and natural language processing. The association between text recognition and form recognition is a parallel relationship, and natural language processing is respectively The association relationship with text recognition and form recognition is a series relationship. The sub-AI service interfaces corresponding to text recognition, form recognition, and natural language processing are sub-AI service interfaces D, E, and G respectively. The RPA system identification association relationship includes a parallel relationship The third sub-AI service interface in series relationship includes sub-AI service interfaces D, E, and G.

Wherein, the third sub-AI service interface whose association relationship is a serial relationship includes sub-AI service interfaces D and G, and the third sub-AI service interface whose association relationship is a serial relationship includes sub-AI service interfaces E and G.

For sub-AI service interfaces D and G whose association relationship is in series, the RPA system can sort the sub-AI service requirements corresponding to sub-AI service interfaces D and G according to the call time from early to late, and generate sub-AI service interfaces D and G The first ordering of the corresponding sub-AI service requirements; the RPA system generates the second ordering of the first configuration information of the sub-AI service interfaces D and G based on the first ordering of the sub-AI service requirements corresponding to the sub-AI service interfaces D and G; The first configuration information of the sub-AI service interfaces D and G are spliced according to the second ranking to generate second candidate configuration information.

For the sub-AI service interfaces E and G whose relationship is in series, the RPA system can sort the sub-AI service requirements corresponding to the sub-AI service interfaces E and G according to the call time from early to late, and generate sub-AI service interfaces E and G The first ordering of the corresponding sub-AI service requirements; the RPA system generates the second ordering of the first configuration information of the sub-AI service interfaces E and G based on the first ordering of the sub-AI service requirements corresponding to the sub-AI service interfaces E and G; The first configuration information of the sub-AI service interfaces E and G are spliced according to the second ranking to generate second candidate configuration information.

It should be noted that, relevant content of step S503 may refer to the above-mentioned embodiments, and details are not repeated here.

Therefore, in this method, for the third sub-AI service interface whose association relationship includes a parallel relationship and a serial relationship, the RPA system can generate first candidate configuration information for the first configuration information of the third sub-AI service interface with a parallel relationship based on the association relationship , generate second candidate configuration information for the first configuration information of the third sub-AI service interface in a series relationship based on the association relationship, the second configuration information includes the first candidate configuration information and the second candidate configuration information, and multiple third sub-AI service interfaces can be implemented. Parallel call and serial call of AI service interface.

FIG. 6 is a schematic flowchart of a method for invoking a service interface combining RPA and AI according to an embodiment of the present application.

As shown in Figure 6, the calling method of the service interface combining RPA and AI in the embodiment of the present application includes:

S601. The RPA system obtains the GraphQL query language used to call the AI service interface.

It should be noted that the execution subject of the invocation method of the service interface combining RPA and AI in the embodiment of the present application may be a robotic process automation (Robotic Process Automation, RPA) system, and may also be the combination of RPA and AI in the embodiment of the present application. The device for invoking the service interface, the RPA system and/or the device for invoking the service interface combining RPA and AI can be configured in any electronic device to execute the method for invoking the service interface combining RPA and AI according to the embodiment of the present application. Optionally, the above RPA system may include an RPA robot.

In one embodiment, the user can input the GraphQL query language used to call the AI service interface on the low-code platform, and correspondingly, the RPA system can obtain the above-mentioned GraphQL query language.

S602. The RPA system converts the GraphQL query language to obtain a Resolver for the AI service interface.

In one implementation, as shown in Figure 7, the AI service system may include a business base, an automatic conversion layer, and a low-code platform. Wherein, the business base includes multiple sub-AI service terminals and multiple sub-AI service interfaces, and each sub-AI server corresponds to a sub-AI service interface. After the RPA system obtains the GraphQL query language used to call the AI service interface, it can send the GraphQL query language to the automatic conversion layer, and the automatic conversion layer converts the GraphQL query language, obtains the parser of the AI service interface, and receives the automatic conversion layer The parser for feedback.

In related technologies, as shown in Figure 8, the AI service system includes a business base and a low-code platform. In order to realize the connection between the AI service interface and the low-code platform, it is necessary to carry out the development of the connection between the AI service interface and the low-code platform.

S603, the RPA system calls the AI service interface based on the parser.

In one implementation manner, as shown in FIG. 7 , the RPA system can call at least one sub-AI service interface on the business base based on the parser. It should be noted that there are no too many restrictions on the calling method, for example, the calling method includes at least one of parallel calling and serial calling.

In one embodiment, after invoking the AI service interface, the RPA system may establish a connection between the low-code platform and the AI server based on the AI service interface. For example, the low-code platform can receive data fed back by the AI server through the AI service interface.

In summary, according to the calling method of the AI service interface in the embodiment of the present application, after the RPA system obtains the GraphQL query language used to call the AI service interface, it can convert the GraphQL query language to obtain the resolver Resolver of the AI service interface, based on the analysis server to call the AI service interface. As a result, the RPA system can automatically convert the AI service interface into a front-end operation interface based on the GraphQL query language, so as to realize the connection between the AI service interface and the low-code platform, and improve the development efficiency of the AI service interface.

FIG. 9 is a block diagram of an apparatus for configuring a service interface combining RPA and AI according to an embodiment of the present application.

As shown in FIG. 9 , the configuration device 100 of the service interface combining RPA and AI in the embodiment of the present application includes: an acquisition module 110 , a splitting module 120 , an identification module 130 and a configuration module 140 .

The obtaining module 110 is used to obtain the AI service requirements of the AI service interface to be configured.

The splitting module 120 is configured to split the AI service requirement to generate multiple sub-AI service requirements of a single category.

The identification module 130 is configured to identify the association relationship between the sub-AI service requirements, wherein the association relationship includes at least one of a parallel relationship and a serial relationship.

The configuration module 140 is configured to configure the AI service interface based on the sub-AI service interface corresponding to each sub-AI service requirement and the association relationship.

In an embodiment of the present application, the configuration module 140 is further configured to: obtain the first configuration information of the sub-AI service interface; based on the first configuration information and the Association relationship, generating second configuration information of the AI service interface; configuring the AI service interface based on the second configuration information.

In an embodiment of the present application, the configuration module 140 is further configured to: identify that the association relationship is a first sub-AI service interface of a parallel relationship; acquire multiple fields of the AI service interface; construct the first sub-AI service interface; The second configuration information is generated based on the mapping relationship between the first configuration information of the sub-AI service interface and the fields.

In an embodiment of the present application, the configuration module 140 is further configured to: identify the second sub-AI service interface in which the association relationship is a serial relationship; configure the sub-AI service interface corresponding to the second sub-AI service interface The requirements are sorted from early to late according to the calling time, and the first sorting of the sub-AI service requirements corresponding to the second sub-AI service interface is generated; based on the sub-AI service requirements corresponding to the second sub-AI service interface the first sorting of the first sub-AI service interface to generate a second sorting of the first configuration information of the second sub-AI service interface; and the first configuration information of the second sub-AI service interface according to the second sorting Splicing is performed to generate the second configuration information.

In an embodiment of the present application, the configuration module 140 is further configured to: identify the third sub-AI service interface whose association relationship includes a parallel relationship and a serial relationship; for the third sub-AI whose association relationship is a parallel relationship A service interface, acquiring multiple fields of the AI service interface; constructing a mapping relationship between the first configuration information of the third sub-AI service interface and the fields, and generating a first candidate configuration based on the mapping relationship Information; for the third sub-AI service interface whose association relationship is a series relationship, sort the sub-AI service requirements corresponding to the third sub-AI service interface according to the call time from early to late, and generate the third sub-AI service interface. A first ranking of the sub-AI service requirements corresponding to the sub-AI service interface; generating the third sub-AI service interface based on the first ranking of the sub-AI service requirements corresponding to the third sub-AI service interface the second sorting of the first configuration information; splicing the first configuration information of the third sub-AI service interface according to the second sorting to generate second candidate configuration information; wherein, the second The configuration information includes the first candidate configuration information and the second candidate configuration information.

In one embodiment of the present application, the configuration information includes a Schema file and a Resolver based on the GraphQL query language.

In one embodiment of the present application, the splitting module 120 is further configured to: identify multiple single categories involved in the AI service requirements based on natural language processing (NLP); The sub-AI service requirements of any single category are extracted from the AI service requirements.

In an embodiment of the present application, the sub-AI service requirements include at least one of natural language processing (NLP), optical character recognition (OCR), speech synthesis, speech recognition, and image annotation.

It should be noted that, for details not disclosed in the configuration device of the service interface combining RPA and AI in the embodiment of the present application, please refer to the details disclosed in the configuration method of the AI service interface in the above-mentioned embodiment of the application, and will not be repeated here. .

To sum up, the configuration device of the service interface combining RPA and AI in the embodiment of the present application can split the AI service requirements of the AI service interface to be configured to generate multiple sub-AI service requirements of a single category, which can realize AI service The requirements are automatically split, and the association relationship between the sub-AI service requirements is identified, and the AI service interface is configured based on the sub-AI service interface and the association relationship corresponding to each sub-AI service requirement. As a result, the AI service interface can be automatically configured based on the correlation between the sub-AI service requirements, which is suitable for the application scenario of the AI service interface for multiple types of AI service requirements, and has good scalability and improves the development efficiency of the AI service interface. .

Fig. 10 is a block diagram of a device for invoking a service interface combining RPA and AI according to an embodiment of the present application.

As shown in FIG. 10 , the invocation device 200 of the service interface combining RPA and AI in the embodiment of the present application includes: an acquisition module 210 , a conversion module 220 and an invocation module 230 .

The obtaining module 210 is used to obtain the GraphQL query language used to call the AI service interface.

The converting module 220 is configured to convert the GraphQL query language, and acquire the Resolver of the AI service interface.

The calling module 230 is used for calling the AI service interface based on the parser.

It should be noted that, for details not disclosed in the calling device of the service interface combining RPA and AI in the embodiment of the present application, please refer to the details disclosed in the calling method of the service interface combining RPA and AI in the above-mentioned embodiments of the application, I won't go into details here.

To sum up, in the embodiment of the present application, the calling device combining RPA and AI service interface, after obtaining the GraphQL query language used to call the AI service interface, can convert the GraphQL query language to obtain the resolver Resolver of the AI service interface, based on The parser calls the AI service interface. As a result, the AI service interface can be automatically converted into a front-end operation interface based on the GraphQL query language, so as to realize the connection between the AI service interface and the low-code platform, and improve the development efficiency of the AI service interface.

In order to realize the above-mentioned embodiment, as shown in FIG. 11 , the present application also proposes an electronic device 300, including at least one processor 310; and a memory 320 communicatively connected to the at least one processor 310; wherein, the memory 320 Instructions that can be executed by the at least one processor 310 are stored, and the instructions are executed by the at least one processor 310, so that the at least one processor 310 can execute the above-mentioned AI service interface configuration method, or execute the above-mentioned The calling method of the AI service interface.

The electronic device in the embodiment of the present application can split the AI service requirements of the AI service interface to be configured through the processor to execute the instructions stored in the memory, so as to generate multiple sub-AI service requirements of a single category, and realize the AI service. The requirements are automatically split, and the association relationship between the sub-AI service requirements is identified, and the AI service interface is configured based on the sub-AI service interface and the association relationship corresponding to each sub-AI service requirement. As a result, the AI service interface can be automatically configured based on the correlation between the sub-AI service requirements, which is suitable for the application scenario of the AI service interface for multiple types of AI service requirements, and has good scalability and improves the development efficiency of the AI service interface. .

In order to realize the above-mentioned embodiments, the present application also proposes a computer-readable storage medium, which stores a computer program, and when the program is executed by a processor, implements the configuration method of the above-mentioned AI service interface, or implements the calling method of the above-mentioned AI service interface.

The computer-readable storage medium of the embodiment of the present application can split the AI service requirements of the AI service interface to be configured by storing the computer program and executing it by the processor, so as to generate multiple sub-AI service requirements of a single category, which can realize Automatically split AI service requirements, identify the relationship between sub-AI service requirements, and configure AI service interfaces based on the sub-AI service interface and association relationship corresponding to each sub-AI service requirement. As a result, the AI service interface can be automatically configured based on the correlation between the sub-AI service requirements, which is suitable for the application scenario of the AI service interface for multiple types of AI service requirements, and has good scalability and improves the development efficiency of the AI service interface. .

In various embodiments of the present application, it should be understood that the sequence numbers of the above-mentioned processes do not necessarily mean the order of execution. The implementation of the examples constitutes no limitation.

In the examples provided in this application, it should be understood that "B corresponding to A" means that B is associated with A, and B can be determined according to A. However, it should also be understood that determining B based on A does not mean determining B only based on A, and B can also be determined based on A and/or other information.

In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, each unit may exist separately physically, or two or more units may be integrated into one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

If the above-mentioned integrated units are realized in the form of software function units and sold or used as independent products, they can be stored in a computer-accessible memory. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a memory , including several requests to make a computer device (which may be a personal computer, server, or network device, etc., specifically, a processor in the computer device) execute some or all of the steps of the above-mentioned methods in various embodiments of the present application.

Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above-mentioned embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, and the storage medium includes read-only Memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), programmable read-only memory (Programmable Read-only Memory, PROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, EPROM), One-time Programmable Read-Only Memory (OTPROM), Electronically Erasable Programmable Read-Only Memory (EEPROM), Compact Disc (Compact Disc Read-Only Memory, CD-ROM) or other optical disk storage, magnetic disk storage, tape storage, or any other computer-readable medium that can be used to carry or store data.

The configuration method, training method, device, equipment and medium of an AI service interface disclosed in the embodiment of the application have been introduced in detail above. In this paper, specific examples are used to illustrate the principle and implementation of the application. The above embodiment The description is only used to help understand the method of the present application and its core idea; at the same time, for those of ordinary skill in the art, according to the idea of the present application, there will be changes in the specific implementation and application scope. In summary, As stated above, the contents of this specification should not be construed as limiting the application.

Claims (15)

A method for configuring a service interface combining robotic process automation RPA and artificial intelligence AI, performed by an RPA system, the method comprising: The RPA system obtains the AI service requirements of the AI service interface to be configured; The RPA system splits the AI service requirements to generate multiple sub-AI service requirements of a single category; The RPA system identifies an association relationship between the sub-AI service requirements, wherein the association relationship includes at least one of a parallel relationship and a serial relationship; The RPA system configures the AI service interface based on the sub-AI service interface corresponding to each sub-AI service requirement and the association relationship. The method according to claim 1, wherein the configuring the AI service interface based on the sub-AI service interface corresponding to each sub-AI service requirement and the association relationship includes: The RPA system obtains the first configuration information of the sub-AI service interface; The RPA system generates second configuration information of the AI service interface based on the first configuration information of each sub-AI service interface and the association relationship; The RPA system configures the AI service interface based on the second configuration information. The method according to claim 2, wherein the generating the second configuration information of the AI service interface based on the first configuration information of each sub-AI service interface and the association relationship includes: The RPA system recognizes that the association relationship is a first sub-AI service interface of a parallel relationship; The RPA system obtains multiple fields of the AI service interface; The RPA system constructs a mapping relationship between the first configuration information of the first sub-AI service interface and the fields, and generates the second configuration information based on the mapping relationship. The method according to claim 2, wherein the generating the second configuration information of the AI service interface based on the first configuration information of each sub-AI service interface and the association relationship includes: The RPA system recognizes that the association relationship is a second sub-AI service interface of a serial relationship; The RPA system sorts the sub-AI service requirements corresponding to the second sub-AI service interface according to the invocation time from early to late, and generates the first sub-AI service requirement corresponding to the second sub-AI service interface. a sort; The RPA system generates a second ranking of the first configuration information of the second sub-AI service interface based on the first ranking of the sub-AI service requirements corresponding to the second sub-AI service interface; The RPA system splices the first configuration information of the second sub-AI service interface according to the second order to generate the second configuration information. The method according to claim 2, wherein the generating the second configuration information of the AI service interface based on the first configuration information of each sub-AI service interface and the association relationship includes: The RPA system identifies that the association relationship includes a third sub-AI service interface of a parallel relationship and a serial relationship; For the third sub-AI service interface whose association relationship is a parallel relationship, the RPA system obtains multiple fields of the AI service interface; the RPA system constructs the third sub-AI service interface of the third sub-AI service interface. A mapping relationship between configuration information and the fields, generating first candidate configuration information based on the mapping relationship; For the third sub-AI service interface whose association relationship is a series relationship, the RPA system sorts the sub-AI service requirements corresponding to the third sub-AI service interface according to the call time from early to late, and generates The first ordering of the sub-AI service requirements corresponding to the third sub-AI service interface; the RPA system generates based on the first ordering of the sub-AI service requirements corresponding to the third sub-AI service interface The second sorting of the first configuration information of the third sub-AI service interface; the RPA system splices the first configuration information of the third sub-AI service interface according to the second sorting to generate second candidate configuration information; Wherein, the second configuration information includes the first candidate configuration information and the second candidate configuration information. The method according to any one of claims 2-5, wherein the configuration information includes a Schema file and a Resolver based on a GraphQL query language. The method according to claims 1-6, wherein said splitting said AI service requirements to generate multiple sub-AI service requirements of a single category comprises: The RPA system recognizes multiple single categories involved in the AI service requirements based on natural language processing NLP; For any identified single category, the RPA system extracts the sub-AI service requirements of any single category from the AI service requirements. The method according to any one of claims 1-7, wherein the sub-AI service requirements include at least one of NLP, optical character recognition (OCR), speech synthesis, speech recognition, and image annotation. A configuration device for a service interface combining RPA and AI, comprising: An acquisition module, configured to acquire the AI service requirements of the AI service interface to be configured; A splitting module, configured to split the AI service requirements to generate multiple sub-AI service requirements of a single category; An identification module, configured to identify an association relationship between the sub-AI service requirements, wherein the association relationship includes at least one of a parallel relationship and a serial relationship; A configuration module configured to configure the AI service interface based on the sub-AI service interface corresponding to each sub-AI service requirement and the association relationship. The device according to claim 9, wherein the configuration module is further configured to: Obtain first configuration information of the sub-AI service interface; generating second configuration information of the AI service interface based on the first configuration information of each sub-AI service interface and the association relationship; Configure the AI service interface based on the second configuration information. The device according to claim 10, wherein the configuration module is further configured to: A first sub-AI service interface that identifies the association relationship as a parallel relationship; Obtain multiple fields of the AI service interface; Constructing a mapping relationship between the first configuration information of the first sub-AI service interface and the fields, and generating the second configuration information based on the mapping relationship. The device according to claim 10, wherein the configuration module is further configured to: A second sub-AI service interface that identifies the association relationship as a serial relationship; sorting the sub-AI service requirements corresponding to the second sub-AI service interface from early to late according to the invocation time, and generating a first ranking of the sub-AI service requirements corresponding to the second sub-AI service interface; generating a second ranking of the first configuration information of the second sub-AI service interface based on the first ranking of the sub-AI service requirements corresponding to the second sub-AI service interface; The first configuration information of the second sub-AI service interface is spliced according to the second order to generate the second configuration information. The device according to claim 10, wherein the configuration module is further configured to: A third sub-AI service interface that identifies that the association relationship includes a parallel relationship and a serial relationship; For the third sub-AI service interface whose association relationship is a parallel relationship, obtain a plurality of fields of the AI service interface; construct a relationship between the first configuration information of the third sub-AI service interface and the fields A mapping relationship among them, generating first candidate configuration information based on the mapping relationship; For the third sub-AI service interface whose association relationship is a series relationship, sort the sub-AI service requirements corresponding to the third sub-AI service interface according to the call time from early to late, and generate the third sub-AI service interface. A first ranking of the sub-AI service requirements corresponding to the sub-AI service interface; generating the third sub-AI service interface based on the first ranking of the sub-AI service requirements corresponding to the third sub-AI service interface a second ordering of the first configuration information; splicing the first configuration information of the third sub-AI service interface according to the second ordering to generate second candidate configuration information; Wherein, the second configuration information includes the first candidate configuration information and the second candidate configuration information. An electronic device comprising: at least one processor; and a memory communicatively coupled to the at least one processor; wherein, The memory stores instructions that can be executed 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 the operation described in any one of claims 1-8. The configuration method of the AI service interface. A computer-readable storage medium, on which a computer program is stored, wherein, when the program is executed by a processor, the method for configuring an AI service interface according to any one of claims 1-8 is implemented.

Images