CN114416049B

CN114416049B - Configuration method and device of service interface combining RPA and AI

Info

Publication number: CN114416049B
Application number: CN202111592699.1A
Authority: CN
Inventors: 谭繁华; 汪冠春; 胡一川; 褚瑞; 李玮
Original assignee: Beijing Laiye Network Technology Co Ltd; Laiye Technology Beijing Co Ltd
Current assignee: Beijing Laiye Network Technology Co Ltd; Laiye Technology Beijing Co Ltd
Priority date: 2021-12-23
Filing date: 2021-12-23
Publication date: 2023-03-14
Anticipated expiration: 2041-12-23
Also published as: WO2023115738A1; CN114416049A

Abstract

The application discloses a configuration method and device of a service interface combining RPA and AI. The configuration method comprises the following steps: the RPA system acquires an AI service requirement of an AI service interface to be configured; the RPA system splits the AI service requirements to generate a plurality of sub-AI service requirements of a single category; the RPA system identifies the incidence relation among the AI service requirements; and the RPA system configures the AI service interface based on the sub-AI service interface and the association relation corresponding to each sub-AI service requirement. Therefore, the RPA system can automatically configure the AI service interface based on the incidence relation among the sub-AI service requirements, is suitable for the application scene of the AI service interface with multi-class AI service requirements, has good expansibility and improves the development efficiency of the AI service interface.

Description

Configuration method and device of service interface combining RPA and AI

Technical Field

The present disclosure relates to the technical field of Robot Process Automation (RPA) and Artificial Intelligence (AI), and in particular, to a method, an apparatus, a device, and a medium for configuring a service interface that combines an RPA and an AI.

Background

Robot Process Automation (RPA) is a Process task that simulates human operations on a computer by specific "robot software" and executes automatically according to rules.

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

At present, the RPA and AI technologies have the advantages of high automation degree, high accuracy and low cost, and are widely applied.

In the related art, since the types of service requirements, the formats of service data, and the storage modes are many, a plurality of AI service interfaces are often required to be developed, for example, a developer needs to develop one AI service interface according to each service requirement, and problems of many repetitive developments, large development workload, and the like exist.

Disclosure of Invention

The present application aims to solve at least to some extent one of the technical problems in the above-mentioned technology.

Therefore, a first objective of the present application is to provide a method for configuring a service interface combining RPA and AI, which can automatically configure an AI service interface based on an association relationship between sub-AI service requirements, and is suitable for an application scenario of an AI service interface with multi-class AI service requirements, and has a better extensibility, thereby improving the development efficiency of the AI service interface.

A second object of the present application is to provide a method for invoking a service interface in conjunction with RPA and AI.

A third object of the present application is to provide a configuration device for service interface combining RPA and AI.

A fourth object of the present application is to provide a calling device for service interface combining RPA and AI.

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

A sixth object of the present application is to propose a computer-readable storage medium.

In order to achieve the above object, an embodiment of the first aspect of the present application provides a method for configuring a service interface in combination with an RPA and an AI, including: the RPA system acquires an AI service requirement of an AI service interface to be configured; the RPA system splits the AI service requirements to generate a plurality of sub-AI service requirements of a single category; the RPA system identifies an incidence relation among the sub-AI service requirements, wherein the incidence relation comprises a parallel relation and/or a series relation; and 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 relation.

According to the configuration method of the service interface combining the RPA and the AI, the AI service requirement of the AI service interface to be configured can be split to generate a plurality of sub-AI service requirements of a single category, the automatic splitting of the AI service requirement can be realized, the incidence relation among the sub-AI service requirements is identified, and the AI service interface is configured based on the sub-AI service interface and the incidence relation corresponding to each sub-AI service requirement. Therefore, the AI service interface can be automatically configured based on the association relation between the sub-AI service requirements, the method is suitable for the application scene of the AI service interface with multi-class AI service requirements, the expansibility is good, and the development efficiency of the AI service interface is improved.

In addition, the configuration method of the service interface combining the RPA and the AI proposed according to the above embodiment of the present application may further have the following additional technical features:

in an embodiment of the application, 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 acquires 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 and the incidence relation of each sub-AI service interface; and the RPA system configures the AI service interface based on the second configuration information.

In an embodiment of the application, the generating second configuration information of the AI service interface based on the first configuration information and the association relationship of each of the sub-AI service interfaces includes: the RPA system identifies a first sub AI service interface of which the association relationship is a parallel relationship; the RPA system acquires a plurality of fields of the AI service interface; the RPA system constructs a mapping relation between the first configuration information of the first sub-AI service interface and the field, and generates the second configuration information based on the mapping relation.

In an embodiment of the application, the generating second configuration information of the AI service interface based on the first configuration information and the association relationship of each of the sub-AI service interfaces includes: the RPA system identifies a second sub AI service interface of which the association relationship is a series relationship; the RPA system sorts the sub-AI service requirements corresponding to the second sub-AI service interface from morning to evening according to calling time to generate a first sequence of the sub-AI service requirements corresponding to the second sub-AI service interface; the RPA system generating a second ordering of the first configuration information of the second sub-AI service interface based on the first ordering of the sub-AI service requirements corresponding to the second sub-AI service interface; and the RPA system splices the first configuration information of the second sub-AI service interface according to the second sequence to generate second configuration information.

In an embodiment of the application, the generating second configuration information of the AI service interface based on the first configuration information and the association relationship of each of the sub-AI service interfaces includes: the RPA system identifies a third sub AI service interface of which the incidence relation comprises a parallel relation and a serial relation; aiming at the third sub-service interface with the incidence relation of parallel connection, the RPA system acquires a plurality of fields of the AI service interface; the RPA system constructs a mapping relation between the first configuration information of the third sub-AI service interface and the field, and generates first candidate configuration information based on the mapping relation; aiming at the third sub-service interface with the incidence relation of series connection, the RPA system sorts the sub-AI service requirements corresponding to the third sub-AI service interface from morning to evening according to the calling time, and generates a first sequence of the sub-AI service requirements corresponding to the third sub-AI service interface; the RPA system generating a second ranking of the first configuration information of 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 RPA system splices the first configuration information of the third sub-AI service interface according to the second sequence to generate second candidate configuration information; wherein the second configuration information comprises the first candidate configuration information and the second candidate configuration information.

In an embodiment of the present application, the configuration information includes Schema files and parser Resolver based on GraphQL query language.

In an embodiment of the present application, the splitting the AI service requirement to generate a plurality of sub-AI service requirements of a single category includes: the RPA system identifying a plurality of single categories to which the AI service requirements relate based on Natural Language Processing (NLP); and the RPA system extracts the sub AI service requirement of any single category from the AI service requirement aiming at any single category identified.

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

In order to achieve the above object, an embodiment of a second aspect of the present application provides a method for invoking a service interface in combination with an RPA and an AI, including: acquiring GraphQL query language for calling an AI service interface; converting the GraphQL query language to obtain a Resolver of the AI service interface; based on the resolver, calling the AI service interface.

According to the calling method of the service interface combining the RPA and the AI, after the GraphQL query language for calling the AI service interface is obtained, the GraphQL query language can be converted, the Resolver of the AI service interface is obtained, and the AI service interface is called based on the Resolver. Therefore, the AI service interface can be automatically converted into a front-end operation interface based on the GraphQL query language, so that the interface between the AI service interface and the low-code platform is realized, and the development efficiency of the AI service interface is improved.

In order to achieve the above object, a third embodiment of the present application provides a device for configuring a service interface combining an RPA and an AI, including: the acquisition module is used for acquiring the AI service requirement of the AI service interface to be configured; the splitting module is used for splitting the AI service requirements to generate a plurality of sub-AI service requirements of a single category; the identification module is used for identifying the incidence relation among the sub AI service demands, wherein the incidence relation comprises a parallel relation and/or a serial relation; and the configuration module is used for configuring the AI service interface based on the sub-AI service interface corresponding to each sub-AI service requirement and the association relation.

The configuration device of the service interface combining the RPA and the AI according to the embodiment of the application can split the AI service requirement of the AI service interface to be configured to generate a plurality of sub-AI service requirements of a single category, can realize automatic splitting of the AI service requirement, identify the association relationship between the sub-AI service requirements, and configure the AI service interface based on the sub-AI service interface and the association relationship corresponding to each sub-AI service requirement. Therefore, the AI service interface can be automatically configured based on the incidence relation among the sub-AI service requirements, the method is suitable for the application scene of the AI service interface with multi-class AI service requirements, the expansibility is good, and the development efficiency of the AI service interface is improved.

In addition, the configuration device of the service interface combining the RPA and the AI proposed according to the above embodiment of the present application may also have the following additional technical features:

in an embodiment of the application, the configuration module is further configured to: acquiring first configuration information of the sub AI service interface; generating second configuration information of the AI service interface based on the first configuration information and the association relationship of each sub-AI service interface; configuring the AI service interface based on the second configuration information.

In an embodiment of the application, the configuration module is further configured to: identifying a first sub AI service interface with the incidence relation of parallel connection; acquiring a plurality of fields of the AI service interface; and constructing a mapping relation between the first configuration information of the first sub-AI service interface and the field, and generating the second configuration information based on the mapping relation.

In an embodiment of the application, the configuration module is further configured to: identifying a second sub AI service interface of which the incidence relation is a series relation; sorting the sub-AI service requirements corresponding to the second sub-AI service interface from morning to evening according to calling time, and generating a first order of the sub-AI service requirements corresponding to the second sub-AI service interface; generating a second ordering of the first configuration information of the second sub-AI service interface based on the first ordering of the sub-AI service requirements corresponding to the second sub-AI service interface; and splicing the first configuration information of the second sub-AI service interface according to the second sequence to generate second configuration information.

In an embodiment of the application, the configuration module is further configured to: identifying a third sub AI service interface of which the incidence relation comprises a parallel relation and a serial relation; aiming at the third sub-service interface with the incidence relation of parallel connection, acquiring a plurality of fields of the AI service interface; constructing a mapping relation between the first configuration information of the third sub-AI service interface and the field, and generating first candidate configuration information based on the mapping relation; for the third sub-service interface with the incidence relation of the serial relation, sequencing the sub-AI service requirements corresponding to the third sub-AI service interface from morning to evening according to calling time, and generating a first sequence of the sub-AI service requirements corresponding to the third sub-AI service interface; generating a second ordering of the first configuration information of the third sub-AI service interface based on the first ordering of the sub-AI service requirements corresponding to the third sub-AI service interface; splicing the first configuration information of the third sub-AI service interface according to the second sequence to generate second candidate configuration information; wherein the second configuration information comprises the first candidate configuration information and the second candidate configuration information.

In an embodiment of the application, the splitting module is further configured to: identifying a plurality of single categories to which the AI service requirements relate based on Natural Language Processing (NLP); and aiming at any single category identified, extracting the child AI service requirement of any single category from the AI service requirements.

In order to achieve the above object, a fourth aspect of the present application provides a device for invoking a service interface in combination with an RPA and an AI, including: the acquisition module is used for acquiring GraphQL query language for calling an AI service interface; the conversion module is used for converting the GraphQL query language to obtain a Resolver of the AI service interface; and the calling module is used for calling the AI service interface based on the resolver.

The configuration device of the service interface combining the RPA and the AI in the embodiment of the application can split the AI service requirement of the AI service interface to be configured to generate a plurality of sub-AI service requirements of a single category, can realize automatic splitting of the AI service requirements, identifies the incidence relation among the sub-AI service requirements, and configures the AI service interface based on the sub-AI service interface and the incidence relation corresponding to each sub-AI service requirement. Therefore, the AI service interface can be automatically configured based on the incidence relation among the sub-AI service requirements, the method is suitable for the application scene of the AI service interface with multi-class AI service requirements, the expansibility is good, and the development efficiency of the AI service interface is improved.

To achieve the above object, a fifth embodiment of the present application provides an electronic device, including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute a method for configuring a service interface combining an RPA and an AI according to an embodiment of the first aspect of the present application, or to execute a method for invoking a service interface combining an RPA and an AI according to an embodiment of the second aspect of the present application.

According to the electronic device, the processor executes the instruction stored in the memory, the AI service requirement of the AI service interface to be configured can be split, so that a plurality of sub-AI service requirements of a single category can be generated, the automatic splitting of the AI service requirement can be realized, the incidence relation among the sub-AI service requirements can be identified, and the AI service interface is configured based on the sub-AI service interface and the incidence relation corresponding to each sub-AI service requirement. Therefore, the AI service interface can be automatically configured based on the incidence relation among the sub-AI service requirements, the method is suitable for the application scene of the AI service interface with multi-class AI service requirements, the expansibility is good, and the development efficiency of the AI service interface is improved.

In order to achieve the above object, a sixth aspect of the present application provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements a method for configuring a service interface combining an RPA and an AI according to an embodiment of the first aspect of the present application, or implements a method for invoking a service interface combining an RPA and an AI according to an embodiment of the second aspect of the present application.

The computer-readable storage medium of the embodiment of the application, which stores a computer program and is executed by a processor, can split an AI service requirement of an AI service interface to be configured to generate a plurality of sub-AI service requirements of a single category, can realize automatic splitting of the AI service requirements, identify an association relationship between the sub-AI service requirements, and configure the AI service interface based on the sub-AI service interface and the association relationship corresponding to each sub-AI service requirement. Therefore, the AI service interface can be automatically configured based on the incidence relation among the sub-AI service requirements, the method is suitable for the application scene of the AI service interface with multi-class AI service requirements, the expansibility is good, and the development efficiency of the AI service interface is improved.

Drawings

The foregoing and/or additional aspects and advantages of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:

fig. 1 is a flow chart illustrating a method for configuring a service interface in conjunction with an RPA and an AI according to an embodiment of the present application;

fig. 2 is a schematic flowchart illustrating a configuration of an AI service interface in a configuration method of a service interface combining an RPA and an AI according to an embodiment of the present application;

fig. 3 is a schematic flowchart illustrating a process of generating second configuration information of an AI service interface in a method for configuring a service interface in combination with an RPA and an AI according to an embodiment of the present application;

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

fig. 5 is a schematic flowchart illustrating a process of generating second configuration information of an AI service interface in a method for configuring a service interface in combination with an RPA and an AI according to another embodiment of the present application;

FIG. 6 is a flowchart illustrating a method for invoking a service interface in conjunction with RPA and AI according to an embodiment of the present application;

FIG. 7 is a block diagram of an AI service system in accordance with one embodiment of the subject application;

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

FIG. 9 is a block diagram of a configuration device for a service interface incorporating RPA and AI according to one embodiment of the present application;

FIG. 10 is a block diagram of a calling device for a service interface incorporating RPA and AI according to one embodiment of the present application;

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

Detailed Description

Reference will now be made in detail to embodiments of the present application, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative and intended to explain the present application and should not be construed as limiting the present application.

For ease of understanding, terms referred to in the present application will be first introduced.

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

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

In the description of the present application, the term "AI service requirement" refers to an AI service requirement and/or an AI capability corresponding to an AI service interface to be configured, and the corresponding service category is multiple, for example, the AI service requirement includes, but is not limited to, natural Language Processing (NLP), optical Character Recognition (OCR), speech synthesis, speech Recognition, image annotation, and the like.

In the description of the present application, the term "child AI service requirement" refers to a child AI service requirement after an AI service requirement is split, and the corresponding service class is one.

In the description of the present application, the term "sub AI service interface" refers to a sub AI service interface corresponding to a sub AI service requirement.

In the description of the present application, the term "association" refers to an association between child AI service requirements, including a parallel relationship and/or a series relationship.

In the description of the present application, the term "configuration information" refers to configuration information for configuring a service interface, including first configuration information referring to configuration information for configuring a sub AI service interface and second configuration information referring to configuration information for configuring an AI service interface.

In the description of the present application, the term "call time" refers to the call time of the child AI service interface. The calling time of the sub AI service interfaces with the incidence relation of parallel connection is the same, and the calling time of the sub AI service interfaces with the incidence relation of serial connection is different.

In the description of the present application, the term "Graph ql Query Language" refers to a Query Language that is better in Query performance for Graph-like data Graph.

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

In the description of the present application, the term "parser" refers to a parser, including a parser function, for retrieving each returned field in the Schema file.

In the description of the present application, the term "low-code platform" refers to a development platform that can generate an application program quickly without coding or with a small amount of code, and a method for developing an application program through visualization enables a developer to create a web page and an application program through a graphical user interface using a drag component and model-driven logic.

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

Fig. 1 is a flowchart illustrating a configuration method of a service interface combining RPA and AI according to an embodiment of the present application.

As shown in fig. 1, a method for configuring a service interface in combination with an RPA and an AI according to an embodiment of the present application includes:

s101, the RPA system acquires an AI service requirement of an AI service interface to be configured.

It should be noted that the execution subject of the configuration method of the service interface combining the RPA and the AI according to the embodiment of the present application may be a Robot Process Automation (RPA) system, and may also be a configuration device of the service interface combining the RPA and the AI according to the embodiment of the present application, and the RPA system and/or the configuration device of the service interface combining the RPA and the AI may be configured in any electronic device to execute the configuration method of the service interface combining the RPA and the AI according to the embodiment of the present application. Optionally, the RPA system may include an RPA robot.

In an embodiment of the present application, an RPA system may obtain an Artificial Intelligence (AI) service requirement of an AI service interface to be configured.

It should be noted that the AI service interface refers to an interface for connecting an AI service end, where the AI service end includes, but is not limited to, an AI algorithm, a model, and the like.

It should be noted that the service types of the AI service demand are multiple, and the service types of the AI service demand are not limited too much, for example, the AI service demand includes, but is not limited to, natural Language Processing (NLP), optical Character Recognition (OCR), speech synthesis, speech Recognition, image tagging, and the like.

In an embodiment, obtaining the AI service requirement of the AI service interface to be configured may include receiving, by the RPA system, a configuration request of a user, where the configuration request carries the AI service requirement of the AI service interface to be configured. For example, the user may issue a configuration request on the low code platform, and accordingly, the RPA system may receive the configuration request of the user, and extract an AI service requirement of the AI service interface to be configured from the configuration request.

In one embodiment, the RPA system may open the low code platform, log in the low code platform using a preset account, and obtain an AI service requirement of the AI service interface to be configured from a list to be configured on the low code platform. The preset account is a login account for logging in the low-code platform by the RPA system, and can be set according to actual conditions without excessive limitation. Therefore, in the method, the RPA system can automatically open and log in the low-code platform, and automatically acquire the AI service requirement of the AI service interface to be configured from the list to be configured of the low-code platform, thereby realizing the automatic acquisition of the AI service requirement.

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

In the embodiment of the application, the RPA system may split the AI service requirements to generate a plurality of sub-AI service requirements of a single category, that is, the service category of each split sub-AI service requirement is 1.

For example, the AI service requirement of the AI service interface a to be configured includes character recognition and table recognition, the AI service requirement may be split, and the generated sub-AI service requirement includes character recognition and table recognition.

For example, the AI service requirement of the AI service interface B to be configured includes optical character recognition and natural language processing, the AI service requirement may be split, and the generated sub-AI service requirement includes optical character recognition and natural language processing.

For example, the AI service requirement of the AI service interface C to be configured includes voice recognition and voice interaction, the AI service requirement may be split, and the generated sub-AI service requirement includes voice recognition and voice interaction.

In an embodiment, splitting the AI service requirement to generate a plurality of sub-AI service requirements of a single category may include that the RPA system identifies a plurality of single categories to which the AI service requirement relates based on the NLP, and the RPA system extracts the sub-AI service requirement of any single category from the AI service requirement for any identified single category. Thus, the RPA system can implement 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 a picture, the picture carries characters and a table, the RPA system can identify a plurality of single categories related to the AI service requirement based on NLP, the identified single categories include character identification and table identification, and extract sub-AI service requirements of the character identification from the AI service requirement for the identified character identification, and extract sub-AI service requirements of the table identification from the AI service requirement for the identified table identification.

S103, the RPA system identifies an incidence relation among the AI service demands, wherein the incidence relation comprises a parallel relation and/or a series relation.

In the embodiment of the application, the sub-AI service requirements have an association relationship therebetween, wherein the association relationship includes a parallel relationship and/or a series relationship.

In one embodiment, the association between child AI service requirements includes only a parallel relationship. For example, the sub AI service requirement includes character recognition and table recognition, and the association relationship between the character recognition and the table recognition is a parallel relationship.

In one embodiment, the association between child AI service requirements includes only a concatenation relationship. For example, the sub AI service requirement includes optical character recognition and natural language processing, the association relationship between the optical character recognition and the natural language processing is a series relationship, and the processing time of the optical character recognition is earlier than that of the natural language processing.

In one embodiment, the association between sub-AI service requirements includes a parallel relationship and a series relationship. For example, the sub-AI service requirements include character recognition, table recognition and natural language processing, wherein the association relationship between the character recognition and the table recognition is a parallel connection relationship, the association relationship between the natural language processing and the character recognition and the table recognition is a serial connection relationship, and the processing time of the natural language processing is later than that of the character recognition and the table recognition.

In an embodiment, a mapping relationship or a mapping table between the sub AI service requirement and the association relationship may be established in advance, and after the sub AI service requirement is obtained, the mapping relationship or the mapping table is queried, so that the corresponding association relationship can be obtained. It should be noted that the mapping relationship or the mapping table may be set according to actual situations, and is not limited herein.

And S104, configuring an AI service interface by the RPA system based on the sub-AI service interface and the association relation corresponding to each sub-AI service requirement.

In an embodiment, configuring the AI service interfaces based on the sub-AI service interfaces and the association relationship corresponding to each sub-AI service requirement may include constructing, by the RPA system, the association relationship between the sub-AI service interfaces based on the association relationship between the sub-AI service requirements, where the association relationship is used to configure the AI service interfaces.

For example, the sub-AI service requirements corresponding to the AI service requirements of the AI service interface a to be configured include character recognition and table recognition, the association between the character recognition and the table recognition is a parallel relationship, the sub-AI service interfaces corresponding to the character recognition and the table recognition are respectively sub-AI service interfaces D, E, and the RPA system can construct a parallel relationship between sub-AI service interfaces D, E to configure the AI service interface a.

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 association relationship between the optical character recognition and the natural language processing is a series relationship, the sub-AI service interfaces corresponding to the optical character recognition and the natural language processing are respectively sub-AI service interfaces F, G, and the RPA system can construct the series relationship between the sub-AI service interfaces F, G to configure the 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 character recognition, table recognition and natural language processing, where an association relationship between the character recognition and the table recognition is a parallel relationship, an association relationship between the natural language processing and the character recognition and the table recognition is a serial relationship, sub-AI service interfaces corresponding to the character recognition, the table recognition and the natural language processing are sub-AI service interfaces D, E, G, respectively, the RPA system may construct a parallel relationship between sub-AI service interfaces D, E, construct a serial relationship between sub-AI service interfaces D, G, and construct a serial relationship between sub-AI service interfaces E, G, so as to configure the AI service interface H.

To sum up, according to the configuration method of the AI service interface in the embodiment of the present application, the RPA system can split the AI service requirement of the AI service interface to be configured to generate a plurality of sub-AI service requirements of a single category, can realize automatic splitting of the AI service requirements, identify an association relationship between the sub-AI service requirements, and configure the AI service interface based on the sub-AI service interface and the association relationship corresponding to each sub-AI service requirement. Therefore, the RPA system can automatically configure the AI service interface based on the incidence relation among the sub-AI service requirements, is suitable for the application scene of the AI service interface with multi-class AI service requirements, has good expansibility and improves the development efficiency of the AI service interface.

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

s201, the RPA system acquires first configuration information of the sub AI service interface.

In an embodiment of the application, the RPA system may obtain first configuration information of the sub AI service interface. It should be noted that the first configuration information refers to configuration information for configuring the sub AI service interface, and the category of the configuration information is not limited too much, for example, the configuration information may include Schema file and parser Resolver based on GraphQL query language.

In an embodiment, the RPA system may pre-establish a mapping relationship or a mapping table between the sub AI service interface and the first configuration information, and after acquiring the sub AI service interface, query the mapping relationship or the mapping table to acquire the corresponding first configuration information. It should be noted that the mapping relationship or the mapping table may be set according to actual situations, and is not limited herein.

S202, the RPA system generates second configuration information of the AI service interface based on the first configuration information and the incidence relation 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 combining the first configuration information of each sub-AI service interface according to the association relationship to generate the second configuration information of the AI service interface.

For example, the RPA system may combine the first configuration information of the sub-service interfaces associated with the parallel relationship according to the parallel relationship, and/or combine the first configuration information of the sub-service interfaces associated with the serial relationship according to the serial relationship, to generate the 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 character recognition, table recognition and natural language processing, where an association relationship between the character recognition and the table recognition is a parallel relationship, an association relationship between the natural language processing and the character recognition and the table recognition is a serial relationship, sub-AI service interfaces corresponding to the character recognition, the table recognition and the natural language processing are sub-AI service interfaces D, E, G, respectively, the RPA system may combine the first configuration information of the sub-AI service interface D, E according to the parallel relationship, combine the first configuration information of the sub-AI service interface D, G according to the serial relationship, and combine the first configuration information of the sub-AI service interface E, G according to the serial relationship, so as to generate the second configuration information of the AI service interface H.

And S203, the RPA system configures an 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 into a target storage space in the low code platform, the target storage space for storing the configuration information of the AI service interface. It should be noted that, the target storage space is not limited too much,

in one embodiment, the RPA system may also generate a front-end operational interface for the AI service interface. It should be noted that the front-end operation interface refers to an interface for responding to a user operation, and the category of the front-end operation interface is not limited too much, for example, the front-end operation interface includes, but is not limited to, a front-end operation interface based on a query language, such as a front-end operation interface based on GraphQL.

Therefore, in the method, the RPA system can generate second configuration information of the AI service interface based on the first configuration information and the association relation of each sub-AI service interface, and configure the AI service interface based on the second configuration information, thereby realizing automatic configuration of the AI service interface.

Based on any of the above embodiments, as shown in fig. 3, the generating, in step S202, 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:

s301, the RPA system identifies a first sub-AI service interface with the association relationship of parallel connection.

For example, the sub-AI service requirements corresponding to the AI service requirements of the AI service interface a to be configured include character recognition and table recognition, the association between the character recognition and the table recognition is a parallel relationship, the sub-AI service interfaces corresponding to the character recognition and the table recognition are respectively sub-AI service interfaces D, E, and the first sub-AI service interface whose association is recognized by the RPA system as a parallel relationship includes a sub-AI service interface D, E.

S302, the RPA system acquires a plurality of fields of the AI service interface.

In an embodiment of the application, a plurality of fields of an AI service interface to be configured may be obtained. It should be noted that the field refers to a field fed back by the AI service interface, and the field is not limited too much. For example, fields include, but are not limited to, name, address, name, title, profile, outline, and the like.

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

In one embodiment, the RPA system may construct a mapping relationship between the Data fetch Data Fetcher configuration information of the first sub-AI service interface and a field in the Schema file, and generate the second configuration information based on the mapping relationship. It should be noted that the data fetch 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 character recognition and table recognition, the sub-AI service interfaces corresponding to the character recognition and the table recognition are respectively sub-AI service interfaces D, E, the first sub-AI service interface with the parallel association relationship includes a sub-AI service interface D, E, fields in the Schema file of the AI service interface a include a name, a title, a summary, a table row number, and a table column number, the RPA system can construct a mapping relationship between the data fetch configuration information of the sub-AI service interface D and the name, the title, and the summary, construct a mapping relationship between the data fetch configuration information of the sub-AI service interface E and the table row number and the table column number, and generate the second configuration information of the AI service interface a based on the mapping relationship.

In one embodiment, the RPA system may construct a mapping relationship between a Resolver of the first sub-service interface and a field in the Schema file, and generate the second configuration information based on the mapping relationship. It should be noted that, for the relevant content of constructing the mapping relationship between the parser and the field, reference may be made to the above embodiments, and details are not described here.

Therefore, in the method, the RPA system can acquire a plurality of fields of the AI service interface aiming at the first sub-AI service interface with the association relation of parallel connection, construct the mapping relation between the first configuration information of the first sub-AI service interface and the fields, generate the second configuration information based on the mapping relation, and realize the parallel connection calling of the plurality of first sub-AI service interfaces.

Based on any of the above embodiments, as shown in fig. 4, the generating, in step S202, 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:

s401, the RPA system identifies a second sub-AI service interface with the association relationship of a series connection relationship.

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 association relationship between the optical character recognition and the natural language processing is a serial relationship, the sub-AI service interfaces corresponding to the optical character recognition and the natural language processing are sub-AI service interfaces F, G, respectively, and the second sub-AI service interface whose association relationship is identified by the RPA system as a serial relationship includes a sub-AI service interface F, G.

S402, the RPA system sorts the sub-AI service requirements corresponding to the second sub-AI service interface from morning to evening according to the calling time, and generates a first sort of the sub-AI service requirements corresponding to the second sub-AI service interface.

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

In an embodiment of the present application, the RPA system may sort the sub-AI service requirements corresponding to the second sub-AI service interface from morning to evening according to the invocation time, and generate a first sort of the sub-AI service requirements corresponding to the second sub-AI service interface, where the sub-AI service requirements with the earlier invocation time are sorted in front of the sub-AI service requirements with the later invocation time, and the sub-AI service requirements with the later invocation time are sorted in back of the sub-AI service requirements with the earlier invocation time. For example, the second sub-AI service interface identifying the association relationship as the series relationship includes sub-AI service interface F, G, and if the call time of the sub-AI service requirement (optical character recognition) corresponding to sub-AI service interface F is earlier than the call time of the sub-AI service requirement (natural language processing) corresponding to sub-AI service interface G, the first ordering of the sub-AI service requirements corresponding to second sub-AI service interface F, G is optical character recognition and natural language processing.

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

In an embodiment of the application, the RPA system may generate a second ordering of the first configuration information of the second sub-AI service interface based on the first ordering of the sub-AI service requirements corresponding to the second sub-AI service interface, that is, the ordering of the first configuration information corresponding to the sub-AI service requirement with the earlier invocation time is earlier, and the ordering of the first configuration information corresponding to the sub-AI service requirement with the later invocation time is later.

For example, the first ordering of the sub-AI service requirements corresponding to the second sub-AI service interface F, G is optical character recognition and natural language processing, and the second ordering of the first configuration information of the second sub-AI service interface F, G is 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 a second sequence to generate second configuration information.

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

In an embodiment, the RPA system may splice a last field of a first Schema file with a first field of a second Schema file, where the first Schema file and the second Schema file are Schema files ordered adjacently, and the first Schema file is ordered before 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, an association relationship between the optical character recognition and the natural language processing is a serial relationship, the sub-AI service interfaces corresponding to the optical character recognition and the natural language processing are respectively sub-AI service interfaces F, G, the second sub-AI service interface including a sub-AI service interface F, G, a second order of Schema files of the second sub-AI service interface F, G is Schema file of the second sub-AI service interface F and Schema file of the second sub-AI service interface G, and the RPA system may splice the Schema file of the second sub-AI service interface F and the Schema file of the second sub-AI service interface G according to the second order, so as to generate second configuration information of the AI service interface B. For example, the RPA system may 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 the method, aiming at a second sub-AI service interface with the association relation of series connection, the RPA system can sort the sub-AI service requirements corresponding to the second sub-AI service interface from morning to evening according to the calling time to obtain a first sort, generate a second sort of first configuration information of the second sub-AI service interface based on the first sort, splice the first configuration information of the second sub-AI service interface according to the second sort to generate second configuration information, and realize the series calling of a plurality of second sub-AI service interfaces.

Based on any of the above embodiments, as shown in fig. 5, the generating, in step S202, 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:

s501, the RPA system identifies a third sub-AI service interface of which the association relationship comprises 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 word recognition, table recognition and natural language processing, wherein an association relationship between the word recognition and the table recognition is a parallel relationship, an association relationship between the natural language processing and the word recognition and the table recognition is a serial relationship, sub-AI service interfaces corresponding to the word recognition, the table recognition and the natural language processing are sub-AI service interfaces D, E, G, respectively, a third sub-AI service interface whose association relationship is recognized by the RPA system includes a parallel relationship and a serial relationship includes a sub-AI service interface D, E, G, wherein the third sub-AI service interface whose association relationship is a parallel relationship includes a sub-AI service interface D, E, the third sub-AI service interface whose association relationship is a serial relationship includes a sub-AI service interface D, G, and the third sub-AI service interface whose association is a serial relationship includes a sub-AI service interface E, G.

S502, aiming at a third sub-service interface with the incidence relation of parallel connection, the RPA system acquires a plurality of fields of the AI service interface; and the RPA system constructs a mapping relation between the first configuration information of the third sub-AI service interface and the field, and generates first candidate configuration information based on the mapping relation.

In an 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 character recognition, table recognition, and natural language processing, where an association relationship between the character recognition and the table recognition is a parallel relationship, an association relationship between the natural language processing and the character recognition and the table recognition is a serial relationship, sub-AI service interfaces corresponding to the character recognition, the table recognition, and the natural language processing are sub-AI service interfaces D, E, G, respectively, and a third sub-AI service interface whose association relationship identified by the RPA system includes a parallel relationship and a serial relationship includes a sub-AI service interface D, E, G.

The third sub-AI service interface with the parallel relationship comprises a sub-AI service interface D, E, the RPA system can acquire a plurality of fields of the AI service interface H aiming at the sub-AI service interface D, E with the parallel relationship, a mapping relationship between first configuration information of the sub-AI service interface D, E and the fields is constructed, and first candidate configuration information is generated based on the mapping relationship.

It should be noted that, the relevant content of step S502 can be referred to the above embodiments, and is not described herein again.

S503, aiming at a third sub-AI service interface with the association relation of series connection, the RPA system sorts the sub-AI service requirements corresponding to the third sub-AI service interface from morning to evening according to the calling time, and generates a first sorting of the sub-AI service requirements corresponding to the third sub-AI service interface; the RPA system generates a second sequence of the first configuration information of the third sub-AI service interface based on the first sequence of the sub-AI service requirements corresponding to the third sub-AI service interface; and the RPA system splices the first configuration information of the third sub-AI service interface according to a second sequence to generate second candidate configuration information.

In an 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 character recognition, table recognition and natural language processing, where an association relationship between the character recognition and the table recognition is a parallel relationship, an association relationship between the natural language processing and the character recognition and the table recognition is a serial relationship, sub-AI service interfaces corresponding to the character recognition, the table recognition and the natural language processing are sub-AI service interfaces D, E, G, respectively, and a third sub-AI service interface where the RPA system recognizes the association relationship includes a parallel relationship and a serial relationship includes a sub-AI service interface D, E, G.

The third sub-AI service interface with the relation of series connection comprises a sub-AI service interface D, G, and the third sub-AI service interface with the relation of series connection comprises a sub-AI service interface E, G.

Aiming at the sub-AI service interfaces D, G with the association relation of series connection, the RPA system can sort the sub-AI service requirements corresponding to the sub-AI service interfaces D, G from the morning to the evening according to the calling time, and generate a first order of the sub-AI service requirements corresponding to the sub-AI service interfaces D, G; the RPA system generates a second sequence of the first configuration information of the sub-AI service interface D, G based on the first sequence of the sub-AI service requirements corresponding to the sub-AI service interface D, G; and splicing the first configuration information of the sub AI service interface D, G according to the second sequence to generate second candidate configuration information.

Aiming at the sub-AI service interfaces E, G with the association relation of series connection, the RPA system can sort the sub-AI service requirements corresponding to the sub-AI service interfaces E, G from morning to evening according to the calling time, and generate a first order of the sub-AI service requirements corresponding to the sub-AI service interfaces E, G; the RPA system generates a second sequence of the first configuration information of the sub-AI service interface E, G based on the first sequence of the sub-AI service requirements corresponding to the sub-AI service interface E, G; and splicing the first configuration information of the sub AI service interface E, G according to the second sequence to generate second candidate configuration information.

It should be noted that, the relevant content of step S503 can refer to the foregoing embodiment, and is not described herein again.

Therefore, in the method, for a third sub-AI service interface with an association relationship including a parallel relationship and a serial relationship, the RPA system may generate first candidate configuration information based on the first configuration information of the third sub-AI service interface with the association relationship being the parallel relationship, and generate second candidate configuration information based on the first configuration information of the third sub-AI service interface with the association relationship being the serial relationship, where the second configuration information includes the first candidate configuration information and the second candidate configuration information, and may implement parallel call and serial call of multiple third sub-AI service interfaces.

Fig. 6 is a flowchart illustrating a method for invoking a service interface in conjunction with RPA and AI according to an embodiment of the present application.

As shown in fig. 6, the method for calling a service interface in combination with an RPA and an AI according to the embodiment of the present application includes:

s601, the RPA system obtains GraphQL query language for calling the AI service interface.

It should be noted that the execution subject of the method for calling the service interface combining the RPA and the AI according to the embodiment of the present application may be a Robot Process Automation (RPA) system, and may also be a device for calling the service interface combining the RPA and the AI according to the embodiment of the present application, and the RPA system and/or the device for calling the service interface combining the RPA and the AI may be configured in any electronic device to execute the method for calling the service interface combining the RPA and the AI according to the embodiment of the present application. Optionally, the RPA system may include an RPA robot.

In one embodiment, the user may input the GraphQL query language for invoking the AI service interface on the low-code platform, and accordingly, the RPA system may obtain the GraphQL query language.

And S602, the RPA system converts the GraphQL query language to obtain an analyzer Resolver of the AI service interface.

In one embodiment, as shown in fig. 7, the AI service system can include a business base, an auto-translation layer, and a low code platform. The service base comprises a plurality of sub-AI service ends and a plurality of sub-AI service interfaces, wherein each sub-AI service end corresponds to one sub-AI service interface. After the RPA system acquires the GraphQL query language for calling the AI service interface, the GraphQL query language can be sent to the automatic conversion layer, the automatic conversion layer converts the GraphQL query language, a parser of the AI service interface is acquired, and the parser fed back by the automatic conversion layer is received.

In the related art, as shown in fig. 8, the AI service system includes a service base and a low code platform. In order to realize the docking between the AI service interface and the low-code platform, the docking development between the AI service interface and the low-code platform needs to be performed.

And S603, calling an AI service interface by the RPA system based on the resolver.

In one embodiment, as shown in fig. 7, the RPA system may invoke at least one child AI service interface on the service chassis based on the parser. It should be noted that the invoking manner is not limited too much, for example, the invoking manner includes parallel invoking and/or serial invoking.

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

To sum up, according to the method for calling the AI service interface in the embodiment of the present application, after the RPA system obtains the GraphQL query language for calling the AI service interface, the RPA system may convert the GraphQL query language to obtain the Resolver of the AI service interface, and call the AI service interface based on the Resolver. Therefore, 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 butt joint 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 a configuration device of a service interface in conjunction with RPA and AI according to one embodiment of the present application.

As shown in fig. 9, a configuration apparatus 100 for a service interface combining RPA and AI according to an embodiment of the present application includes: an acquisition module 110, a splitting module 120, a recognition module 130, and a configuration module 140.

The obtaining module 110 is configured to obtain an AI service requirement of an AI service interface to be configured;

the splitting module 120 is configured to split the AI service requirement to generate a plurality of sub-AI service requirements of a single category;

the identifying module 130 is configured to identify an association relationship between the sub-AI service demands, where the association relationship includes a parallel relationship and/or 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: acquiring first configuration information of the sub AI service interface; generating second configuration information of the AI service interface based on the first configuration information and the association relationship of each sub-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: identifying a first sub AI service interface with the incidence relation of parallel connection; acquiring a plurality of fields of the AI service interface; and constructing a mapping relation between the first configuration information of the first sub-AI service interface and the field, and generating the second configuration information based on the mapping relation.

In an embodiment of the present application, the configuration module 140 is further configured to: identifying a second sub AI service interface of which the association relationship is a series relationship; sorting the sub-AI service requirements corresponding to the second sub-AI service interface from morning to evening according to calling time, and generating a first order of the sub-AI service requirements corresponding to the second sub-AI service interface; generating a second ordering of the first configuration information of the second sub-AI service interface based on the first ordering of the sub-AI service requirements corresponding to the second sub-AI service interface; and splicing the first configuration information of the second sub-AI service interface according to the second sequence to generate second configuration information.

In an embodiment of the present application, the configuration module 140 is further configured to: identifying a third sub AI service interface of which the incidence relation comprises a parallel relation and a serial relation; aiming at the third sub-service interface with the incidence relation of parallel connection, acquiring a plurality of fields of the AI service interface; constructing a mapping relation between the first configuration information of the third sub-AI service interface and the field, and generating first candidate configuration information based on the mapping relation; for the third sub-service interface with the incidence relation of the serial relation, sequencing the sub-AI service requirements corresponding to the third sub-AI service interface from morning to evening according to calling time, and generating a first sequence of the sub-AI service requirements corresponding to the third sub-AI service interface; generating a second ordering of the first configuration information for the third sub-AI service interface based on the first ordering of the sub-AI service requirements corresponding to the third sub-AI service interface; splicing the first configuration information of the third sub-AI service interface according to the second sequence to generate second candidate configuration information; wherein the second configuration information comprises the first candidate configuration information and the second candidate configuration information.

In an embodiment of the present application, the splitting module 120 is further configured to: identifying a plurality of single categories to which the AI service requirements relate based on Natural Language Processing (NLP); and aiming at any single category identified, extracting the child AI service requirement of any single category from the AI service requirements.

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

It should be noted that, for details that are not disclosed in the configuration apparatus of the service interface combining RPA and AI in the embodiment of the present application, please refer to details disclosed in the configuration method of the AI service interface in the above embodiment of the present application, and details are not described here again.

To sum up, the configuration device of the service interface combining the RPA and the AI according to the embodiment of the present application can split the AI service requirement of the AI service interface to be configured to generate a plurality of sub-AI service requirements of a single category, can realize automatic splitting of the AI service requirements, identify an association relationship between the sub-AI service requirements, and configure the AI service interface based on the sub-AI service interface and the association relationship corresponding to each sub-AI service requirement. Therefore, the AI service interface can be automatically configured based on the incidence relation among the sub-AI service requirements, the method is suitable for the application scene of the AI service interface with multi-class AI service requirements, the expansibility is good, and the development efficiency of the AI service interface is improved.

Fig. 10 is a block diagram of a calling device for a service interface incorporating RPA and AI according to one embodiment of the present application.

As shown in fig. 10, the invoking device 200 for service interface combining RPA and AI according to the embodiment of the present application includes: an acquisition module 210, a translation module 220, and a calling module 230.

The obtaining module 210 is configured to obtain a GraphQL query language for calling an AI service interface;

the conversion module 220 is configured to convert the GraphQL query language to obtain an Resolver of the AI service interface;

the calling module 230 is configured to call the AI service interface based on the parser.

It should be noted that details that are not disclosed in the invoking device of the service interface combining the RPA and the AI in the embodiment of the present application refer to details disclosed in the invoking method of the service interface combining the RPA and the AI in the above embodiment of the present application, and are not described herein again.

To sum up, after acquiring the GraphQL query language for calling the AI service interface, the RPA and AI combined calling device according to the embodiment of the present application may convert the GraphQL query language to acquire the Resolver of the AI service interface, and call the AI service interface based on the Resolver. Therefore, the AI service interface can be automatically converted into a front-end operation interface based on the GraphQL query language, so that the interface between the AI service interface and the low-code platform is realized, and the development efficiency of the AI service interface is improved.

To implement the above embodiments, as shown in fig. 11, the present application further proposes an electronic device 300, which includes at least one processor 310; and a memory 320 communicatively coupled to the at least one processor 310; the memory 320 stores instructions executable by the at least one processor 310, and the instructions are executed by the at least one processor 310, so that the at least one processor 310 can perform a configuration method of the AI service interface or perform a calling method of the AI service interface.

According to the electronic device, the processor executes the instruction stored in the memory, the AI service requirement of the AI service interface to be configured can be split, so that a plurality of sub-AI service requirements of a single category can be generated, the automatic splitting of the AI service requirement can be realized, the incidence relation among the sub-AI service requirements can be identified, and the AI service interface is configured based on the sub-AI service interface and the incidence relation corresponding to each sub-AI service requirement. Therefore, the AI service interface can be automatically configured based on the association relation between the sub-AI service requirements, the method is suitable for the application scene of the AI service interface with multi-class AI service requirements, the expansibility is good, and the development efficiency of the AI service interface is improved.

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

In various embodiments of the present application, it should be understood that the size of the serial number of each process described above does not mean that the execution sequence is necessarily sequential, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

In the embodiments provided herein, it should be understood that "B corresponding to a" means that B is associated with a from which B can be determined. It should also be understood that determining B from a does not mean determining B from a alone, but may also be determined from a and/or other information.

In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.

The integrated units, if implemented as software functional units and sold or used as a stand-alone product, may be stored in a computer accessible memory. Based on such understanding, the technical solution of the present application, which is a part of or contributes to the prior art in essence, or all or part of the technical solution, may be embodied in the form of a software product, stored in a memory, including several requests for causing a computer device (which may be a personal computer, a server, a network device, or the like, and may specifically be a processor in the computer device) to execute part or all of the steps of the above-described method of the embodiments of the present application.

It will be understood by those skilled in the art that all or part of the steps of the methods of the embodiments described above may be implemented by associated hardware instructed by a program, which may be stored in a computer-readable storage medium, including Read-Only Memory (ROM), random Access Memory (RAM), programmable Read-Only Memory (PROM), erasable Programmable Read-Only Memory (EPROM), one-time Programmable Read-Only Memory (OTPROM), electrically Erasable Programmable Read-Only Memory (EEPROM), a Compact Disc-Read-Only Memory (CD-ROM) or other Memory capable of storing data, a magnetic tape, or any other computer-readable medium capable of storing data.

The configuration method, the training method, the device, the equipment and the medium of the AI service interface disclosed in the embodiment of the present application are introduced in detail, a specific example is applied in the text to explain the principle and the implementation of the present application, and the description of the embodiment is only used to help understanding the method and the core idea of the present application; meanwhile, for a person skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.

Claims

1. A method of configuring a service interface incorporating robot process automation, RPA, and artificial intelligence, AI, performed by an RPA system, the method comprising:

the RPA system acquires an AI service requirement of an AI service interface to be configured;

the RPA system splits the AI service requirements to generate a plurality of sub-AI service requirements, wherein each sub-AI service requirement corresponds to a service category;

the RPA system identifies an incidence relation among the sub-AI service requirements, wherein the incidence relation comprises a parallel relation and/or a series relation;

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 relation;

configuring the AI service interface based on the sub-AI service interface corresponding to each sub-AI service requirement and the association relationship, including:

the RPA system acquires first configuration information of the sub-AI service interface, wherein the first configuration information is used for configuring the 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 and the incidence relation of each sub-AI service interface;

the RPA system configures the AI service interface based on the second configuration information;

generating, by the AI service interface, second configuration information based on the first configuration information and the association relationship of each of the child AI service interfaces, including:

the RPA system identifies a third sub AI service interface of which the incidence relation comprises a parallel relation and a serial relation;

aiming at the third sub-service interface of which the association relationship is a parallel relationship, the RPA system acquires a plurality of fields of the AI service interface; the RPA system constructs a mapping relation between the first configuration information of the third sub-AI service interface and the field, and generates first candidate configuration information based on the mapping relation;

for the third sub-service interface with the association relationship being a series relationship, the RPA system sorts the sub-AI service requirements corresponding to the third sub-AI service interface from morning to evening according to call time, and generates a first order of the sub-AI service requirements corresponding to the third sub-AI service interface; the RPA system generating a second ranking of the first configuration information of 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 RPA system splices the first configuration information of the third sub-AI service interface according to the second sequence to generate second candidate configuration information;

wherein the second configuration information comprises the first candidate configuration information and the second candidate configuration information.

2. The method according to claim 1, wherein the generating second configuration information of the AI service interface based on the first configuration information and the association relationship of each of the sub-AI service interfaces comprises:

the RPA system identifies a first sub-AI service interface of which the association relationship is a parallel relationship;

the RPA system acquires a plurality of fields of the AI service interface;

the RPA system constructs a mapping relation between the first configuration information of the first sub-AI service interface and the field, and generates the second configuration information based on the mapping relation.

3. The method of claim 1, wherein the generating second configuration information for the AI service interfaces based on the first configuration information and the association relationship for each of the sub-AI service interfaces comprises:

the RPA system identifies a second sub-AI service interface of which the association relationship is a series relationship;

the RPA system sorts the sub-AI service requirements corresponding to the second sub-AI service interface from morning to evening according to calling time to generate a first sequence of the sub-AI service requirements corresponding to the second sub-AI service interface;

the RPA system generating a second ordering of the first configuration information of the second sub-AI service interface based on the first ordering of the sub-AI service requirements corresponding to the second sub-AI service interface;

and the RPA system splices the first configuration information of the second sub-AI service interface according to the second sequence to generate second configuration information.

4. The method according to any of claims 1-3, wherein the configuration information comprises Schema files and parser Resolver resolvers based on GraphQL query language.

5. The method of claim 1, wherein the splitting the AI service requirement to generate a single category of multiple sub-AI service requirements comprises:

the RPA system identifying a plurality of single categories to which the AI service requirements relate based on Natural Language Processing (NLP);

and the RPA system extracts the sub AI service requirement of any single category from the AI service requirement aiming at any single category identified.

6. The method of any of claims 1-3, wherein the sub-AI service requirements comprise at least one of NLP, OCR, speech synthesis, speech recognition, image annotation.

7. A device for configuring service interfaces in conjunction with RPA and AI, comprising:

the acquisition module is used for acquiring AI service requirements of the AI service interface to be configured;

the splitting module is used for splitting the AI service requirements to generate a plurality of sub-AI service requirements, and each sub-AI service requirement corresponds to one service category;

the identification module is used for identifying the incidence relation among the sub AI service demands, wherein the incidence relation comprises a parallel relation and/or a serial relation;

the configuration module is used for configuring the AI service interface based on the sub-AI service interface corresponding to each sub-AI service requirement and the incidence relation;

acquiring first configuration information of the sub-AI service interface, wherein the first configuration information is used for configuring the sub-AI service interface;

generating second configuration information of the AI service interface based on the first configuration information and the association relationship of each sub-AI service interface;

configuring the AI service interface based on the second configuration information;

the configuration module is further configured to:

identifying a third sub AI service interface of which the incidence relation comprises a parallel relation and a serial relation;

aiming at the third sub-service interface of which the association relationship is a parallel relationship, acquiring a plurality of fields of the AI service interface; constructing a mapping relation between the first configuration information of the third sub-AI service interface and the field, and generating first candidate configuration information based on the mapping relation;

for the third sub-service interface with the association relationship being a series relationship, sorting the sub-AI service requirements corresponding to the third sub-AI service interface from morning to evening according to calling time, and generating a first sorting of the sub-AI service requirements corresponding to the third sub-AI service interface; generating a second ordering of the first configuration information for the third sub-AI service interface based on the first ordering of the sub-AI service requirements corresponding to the third sub-AI service interface; splicing the first configuration information of the third sub-AI service interface according to the second sequence to generate second candidate configuration information;

8. The apparatus of claim 7, wherein the configuration module is further configured to:

identifying a first sub AI service interface with the incidence relation of parallel connection;

acquiring a plurality of fields of the AI service interface;

and constructing a mapping relation between the first configuration information of the first sub-AI service interface and the field, and generating the second configuration information based on the mapping relation.

9. The apparatus of claim 7, wherein the configuration module is further configured to:

identifying a second sub AI service interface of which the incidence relation is a series relation;

sorting the sub-AI service requirements corresponding to the second sub-AI service interface from morning to evening according to calling time, and generating a first order of the sub-AI service requirements corresponding to the second sub-AI service interface;

generating a second ordering of the first configuration information of the second sub-AI service interface based on the first ordering of the sub-AI service requirements corresponding to the second sub-AI service interface;

and splicing the first configuration information of the second sub-AI service interface according to the second sequence to generate second configuration information.

10. An electronic device, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of configuring the AI service interface of any of claims 1-6.

11. A computer-readable storage medium on which a computer program is stored, the program implementing the configuration method of the AI service interface according to any one of claims 1 to 6 when executed by a processor.