Application configuration method and device, equipment and storage medium

Through the interactive configuration interface, the input parameters of the target operation are determined and added, which solves the problem of machine learning model understanding caused by API complexity, improves the accuracy of the model and the controllability of operation execution, and simplifies the application development process.

CN119088437AActive Publication Date: 2024-12-06BEIJING ZITIAO NETWORK TECH CO LTD
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
CN202411133021.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-18
Publication Date
2024-12-06
Estimated Expiration
2044-08-18

AI Technical Summary

Technical Problem

The existing API design is complex, making it difficult for machine learning models to accurately understand and call, especially when dealing with inaccurate naming of multi-layer nested parameters and parameter names, which affects the judgment and operational execution of the model.

Method used

Provide an application configuration method. By presenting predetermined input parameter information of target operations, the user can interactively determine the input parameter configuration information and add the target operation to the application, simplifying API calls and exposing only necessary parameters to the machine learning model.

Benefits of technology

It improves the accuracy and inference ability of machine learning models to understand API operations, reduces the difficulty of model inference, enhances the determinism and controllability of operation execution, and simplifies the application creation and development process.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119088437A_ABST
    Figure CN119088437A_ABST
Patent Text Reader

Abstract

The embodiment of the invention provides an application configuration method and device, equipment and a storage medium. The method comprises the steps that in response to an instruction of adding a target operation to a target application, information related to one or more preset input parameters of the target operation is presented, and the one or more input parameters correspond to one or more fields in a calling request of the target operation respectively; determining configuration information of one or more input parameters; and adding the target operation to the target application based on the configuration information of the one or more input parameters. As a result, a creator of the application may set only one or more necessary parameters. In this way, an application creator can be helped to efficiently build an application. Accordingly, in the process of calling each operation by the machine learning model, only the exposed necessary parameters need to be understood, so that the inference accuracy can be improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] Example embodiments of the present disclosure generally relate to the field of computers, and more particularly, to application configuration methods, apparatuses, devices, and computer-readable storage media. Background Art

[0002] With the development of information technology, various terminal devices can provide various services to people in work and life. Applications that provide services can be deployed in terminal devices. Terminal devices present corresponding content and interact with users through the user interface of the application to meet various needs of users. In some cases, users may need to add some operations to the application. Therefore, how to improve the efficiency of adding some operations to the application is a problem of concern. Summary of the invention

[0003] In a first aspect of the present disclosure, an application configuration method is provided. The method includes: in response to an instruction to add a target operation to a target application, presenting information related to one or more predetermined input parameters of the target operation, the one or more input parameters respectively corresponding to one or more fields in a call request of the target operation; determining configuration information of the one or more input parameters; and adding the target operation to the target application based on the configuration information of the one or more input parameters.

[0004] In a second aspect of the present disclosure, an information processing method is provided. The method includes: determining corresponding parameter values ​​of one or more input parameters based on user input and configuration information of one or more input parameters for a target operation; based on the corresponding parameter values ​​of the one or more input parameters, invoking the target operation to obtain an operation result of the target operation according to a correspondence between the one or more input parameters and one or more fields in a call request of the target operation; and generating a response to the user input based on the operation result.

[0005] In a third aspect of the present disclosure, a device for application configuration is provided, comprising: a configuration interface presentation module, configured to present information related to one or more predetermined input parameters of the target operation in response to an instruction to add a target operation to a target application, the one or more input parameters respectively corresponding to one or more fields in a call request of the target operation; a configuration information determination module, configured to determine configuration information of the one or more input parameters; and an operation adding module, configured to add the target operation to the target application based on the configuration information of the one or more input parameters.

[0006] In a fourth aspect of the present disclosure, an information processing device is provided, comprising: a parameter value determination module, configured as a first user input receiving module, configured to determine corresponding parameter values ​​of one or more input parameters based on the user input and configuration information of the one or more input parameters for the target operation; an operation result acquisition module, configured to call the target operation to obtain an operation result of the target operation based on the corresponding parameter values ​​of the one or more input parameters and according to the correspondence between the one or more input parameters and one or more fields in the call request of the target operation; and a response generation module, configured to generate a response to the user input based on the operation result.

[0007] In a fifth aspect of the present disclosure, an electronic device is provided. The device includes at least one processing unit; and at least one memory, the at least one memory is coupled to the at least one processing unit and stores instructions for execution by the at least one processing unit. When the instructions are executed by the at least one processing unit, the electronic device executes the method of the first aspect and / or the second aspect.

[0008] In a sixth aspect of the present disclosure, a computer-readable storage medium is provided, wherein a computer program is stored on the medium, and when the computer program is executed by a processor, the method of the first aspect and / or the second aspect is implemented.

[0009] It should be understood that the content described in this section is not intended to limit the key features or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein:

[0011] Figure 1 A schematic diagram showing an example environment in which embodiments of the present disclosure can be implemented;

[0012] FIG. 2A to FIG. 2E A schematic diagram showing an example interface for application configuration according to some embodiments of the present disclosure;

[0013] Figure 3A A flowchart showing a process of application configuration according to some embodiments of the present disclosure;

[0014] Figure 3B A flowchart showing a process of information processing according to some embodiments of the present disclosure;

[0015] Figure 4AA schematic structural block diagram of an application configuration device according to some embodiments of the present disclosure is shown;

[0016] Figure 4B A schematic structural block diagram of an information processing device according to some embodiments of the present disclosure is shown; and

[0017] Figure 5 A block diagram of an electronic device in which one or more embodiments of the present disclosure may be implemented is shown. DETAILED DESCRIPTION

[0018] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0019] In the description of the embodiments of the present disclosure, the term "including" and similar terms should be understood as open inclusion, that is, "including but not limited to". The term "based on" should be understood as "based at least in part on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The term "some embodiments" should be understood as "at least some embodiments". Other explicit and implicit definitions may also be included below.

[0020] Herein, unless explicitly stated, executing a step “in response to A” does not mean executing the step immediately after “A” but may include one or more intermediate steps.

[0021] It is understandable that the data involved in this technical solution (including but not limited to the data itself, the acquisition, use, storage or deletion of the data) shall comply with the requirements of relevant laws, regulations and relevant provisions.

[0022] It is understandable that before using the technical solutions disclosed in the various embodiments of the present disclosure, the types, scopes of use, usage scenarios, etc. of the information involved in the present disclosure should be informed to relevant users and their authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations. The relevant users may include any type of right holders, such as individuals, enterprises, and groups.

[0023] For example, in response to receiving an active request from a user, a prompt message is sent to the relevant user to clearly prompt the relevant user that the operation requested to be performed will require obtaining and using the information of the relevant user, so that the relevant user can independently choose whether to provide information to software or hardware such as an electronic device, application, server or storage medium that executes the operation of the technical solution of the present disclosure based on the prompt message.

[0024] As an optional but non-limiting implementation, in response to receiving an active request from a relevant user, a prompt message is sent to the relevant user, for example, in the form of a pop-up window, in which the prompt message may be presented in text form. In addition, the pop-up window may also carry a selection control for the user to select "agree" or "disagree" to provide information to the electronic device.

[0025] It is understandable that the above notification and the process of obtaining user authorization are only illustrative and do not limit the implementation of the present disclosure. Other methods that meet relevant laws and regulations may also be applied to the implementation of the present disclosure. The activation of the digital assistant related functions, the acquired data, the processing and storage of the data, etc. in the embodiment of the present disclosure shall obtain the prior authorization of the user and other rights holders associated with the user, and shall comply with the relevant laws and regulations and the agreement rules between the rights holders.

[0026] As used herein, the term "model" can learn the association between the corresponding input and output from the training data, so that after the training is completed, the corresponding output can be generated for a given input. The generation of the model can be based on machine learning technology. Deep learning is a machine learning algorithm that processes inputs and provides corresponding outputs by using multi-layer processing units. A neural network model is an example of a model based on deep learning. In this article, "model" may also be referred to as "machine learning model", "learning model", "machine learning network" or "learning network", and these terms are used interchangeably in this article.

[0027] Figure 1 A schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented is shown. Environment 100 involves an application management platform 110, which can support the creation of applications and / or the running of applications. In some embodiments, the portion of the application management platform 110 that supports the creation of applications can also be referred to as an application creation portion. In some embodiments, the portion of the application management platform 110 that supports the running of applications can also be referred to as an application running portion.

[0028] As shown in the figure, the application creation part can provide a user 105 with an environment for creating and publishing applications. User 105 can be referred to as an application creation user or creator. In some embodiments, the application creation part can be a low-code platform that provides a collection of tools for application creation. The application creation part can support visual development of various types of applications, so that developers can skip the process of manual coding and speed up the development cycle and cost of applications. The application creation part can support any appropriate platform for users to develop one or more types of applications, for example, it can include a platform based on application platform as a service (aPaaS). Such a platform can support users to efficiently develop applications and realize operations such as application creation and application function adjustment.

[0029] The application creation part can be deployed locally on the terminal device of user 105, and / or can be supported by a server-side device. For example, the terminal device of user 105 can run a client of the application creation part, which can support the interaction between the user and the application creation part provided by the server. In the case where the application creation part runs locally on the user's terminal device, the user 105 can directly interact with the local application creation part using the terminal device. In the case where the application creation part runs on the server-side device, the server-side device can, based on the communication connection with the terminal device, implement service provision for the client running in the terminal device. The application creation part can present a corresponding page 130 to the user 105 based on the operation of the user 105, so as to output to the user 105 and / or receive from the user 105 information related to application creation.

[0030] In some embodiments, the application creation part can be associated with a corresponding database, which stores data or information required for the application creation process supported by the application creation part. For example, the database can store the code and description information corresponding to each functional module that constitutes the application. The application creation part can also perform operations such as calling, adding, deleting, and updating the functional modules in the database. The database can also store operations that can be performed on different functional blocks. Exemplarily, in a scenario where an application is to be created, the application creation part can call the corresponding functional blocks from the database to build the application.

[0031] In an embodiment of the present disclosure, a user 105 can create a target application 120 as needed on the application creation part and publish the target application 120. The target application 120 can be published to any appropriate application running part, as long as the application running part can support the operation of the target application 120. After publishing, the target application 120 can be used to be operated by one or more terminal users 145. The terminal user 145 can operate the target application 120 through an associated terminal device 146, and then interact with the application management platform 110. The terminal user 145 can be referred to as the terminal user of the target application 120. In some embodiments, the target application 120 may include or be implemented as a digital assistant 122.

[0032] The digital assistant 122 can be configured to have the ability of intelligent dialogue. In the example shown in the figure, the digital assistant 122 can be integrated into the target application 120, as part of the target application 120 to assist in the task processing within the target application 120. In other examples, the digital assistant 122 can be configured as an independently running application, such as a web application or other types of applications. In such an example, the digital assistant 122 and the target application 120 can be regarded as the same application. The digital assistant 122 is provided to assist users in various task processing requirements in different applications and scenarios. In the interaction process with the digital assistant 122, the user inputs an interactive message, and the digital assistant 122 provides a reply message in response to the user input. Typically, the digital assistant 122 can support users to input questions in a natural language, and perform tasks and provide replies based on the understanding of natural language input and logical reasoning ability.

[0033] In some embodiments, digital assistant 122 can interact with end user 145 as a contact of end user 145. For example, digital assistant 122 can be implemented in an instant messaging (IM) application. Digital assistant 122 can interact with end user 145 in a single chat session with end user 145. In some embodiments, digital assistant 122 can interact with multiple users in a group chat session including multiple users.

[0034] For each terminal user 145, the client of the application running part can present an interactive window 142 of the target application 120 or the digital assistant 122 in the client interface, such as a conversation window with the digital assistant 122. The terminal user 145 can enter a conversation message in the conversation window, and the target application 120 can determine the reply message of the digital assistant 122 based on the created configuration information and present it to the user in the interactive window 142. In some embodiments, depending on the configuration of the target application 120, the interactive message with the target application 120 may include a message in a multimodal form, such as a text message (e.g., a natural language text), a voice message, an image message, a video message, and the like.

[0035] Similar to the application creation part, the application running part can be deployed locally on the terminal device of each terminal user 145, and / or can be supported by the server device. For example, the terminal device of the terminal user 145 can run a client with the application running part, and the client can support the interaction between the user and the application running part provided by the server. In the case where the application running part runs locally on the user's terminal device, the terminal user 145 can directly use the terminal device to interact with the local application running part. In the case where the application running part runs on the server device, the server device can realize the service supply to the client running in the terminal device based on the communication connection with the terminal device. The application running part can present the corresponding application page to the terminal user 145 based on the operation of the terminal user 145, so as to output and / or receive information related to the use of the application to the terminal user 145.

[0036] In some embodiments, the implementation of at least part of the functions of the target application 120 and / or the implementation of at least part of the functions of the digital assistant 122 in the target application 120 can be implemented based on the model. During the creation or operation of the target application 120, one or more models 155, such as the capabilities of the model 155, can be called. In the target application 120, the digital assistant 122 can use the model 155 to understand the user input and provide a reply to the user based on the output of the model 155.

[0037] During the creation process, the application management platform 110 needs to use the model 155 to determine whether the operation result of the target application 120 meets expectations when testing the target application 120. During the operation process, in response to different operation requests of the user of the target application 120, the application operation part may need to use the model 155 to determine the response result to the user.

[0038] Although shown as being independent of the application management platform 110, one or more models 155 may run on the application management platform 110, or other remote servers. In some embodiments, the model 155 may be a machine learning model, a deep learning model, a learning model, a neural network, etc. In some embodiments, the model may be based on a language model (LM). The language model can have question-answering capabilities by learning from a large amount of corpus. The model 155 may also be based on other appropriate models.

[0039] The application management platform 110 can run on appropriate electronic devices. The electronic devices here can be any type of device with computing capabilities, including terminal devices or server devices. The terminal device can be any type of mobile terminal, fixed terminal or portable terminal, including mobile phones, desktop computers, laptop computers, notebook computers, netbook computers, tablet computers, media computers, multimedia tablets, personal communication systems (PCS) devices, personal navigation devices, personal digital assistants (PDAs), audio / video players, digital cameras / camcorders, positioning devices, television receivers, radio broadcast receivers, e-book devices, gaming devices, or any combination of the foregoing, including accessories and peripherals of these devices or any combination thereof. The server device can include, for example, a computing system / server, such as a mainframe, an edge computing node, a computing device in a cloud environment, and the like. In some embodiments, the management platform 110 can be implemented based on cloud services.

[0040] It should be understood that the structure and functionality of the environment 100 are described for exemplary purposes only and do not imply any limitation on the scope of the present disclosure. For example, although a single user interacting with the application creation portion and a single user interacting with the application execution portion are shown, in reality multiple users can access the application management platform 110 to each create a digital assistant, and each digital assistant can be used to interact with multiple users.

[0041] Currently, the design of application programming interfaces (APIs) is complex. Accordingly, if the API in an event is directly converted into a function and given to a machine learning model, the machine learning model cannot make accurate judgments and understandings due to the large number of API input parameters, inaccurate parameter naming, or the need for calculations.

[0042] An example scenario is as follows: using the digital assistant of the online document, a text content is generated and written into the specified online document. Because the input parameter structure of the creation block interface is too complex, and in the scenario of appending a text to the end of the document, it is necessary to nest multiple layers in the interface input parameter, for example, 6 layers. Accordingly, for documents in the personal document library, it is impossible to directly get the document token from the uniform resource locator (URL). That is, it is necessary to first call the knowledge base to obtain the knowledge space node information, and the token in the output parameter is the real document token.

[0043] In view of this, an embodiment of the present disclosure provides an improved solution for application configuration. In this solution, if an instruction to add a target operation to a target application is received, a configuration interface for the target operation is presented, which at least indicates one or more predetermined input parameters of the target operation, and the one or more input parameters correspond to one or more fields in the call request of the target operation. Based on the interaction with the configuration interface, the configuration information of one or more input parameters is determined. Then, based on the configuration information of the one or more input parameters, the target operation is added to the target application. In an embodiment of the present disclosure, complex APIs in the real world are encapsulated into better understood functions, operations, etc. The creator of the application does not need to know all the parameters required to call the target operation, but can only set one or more necessary parameters. In this way, it can help application creators to build applications efficiently. Accordingly, in the process of calling each operation, the machine learning model only needs to understand the necessary parameters exposed, without understanding the complex API structure, so that the required operation can be selected more accurately and the incoming parameters required for this operation can be inferred more accurately. Thus, the accuracy of the machine learning model inference can be improved.

[0044] Some example embodiments of the present disclosure will be described in detail below with reference to the examples of the accompanying drawings. It should be understood that the pages shown in the accompanying drawings are only examples, and various page designs may actually exist. The various graphical elements in the page may have different arrangements and different visual representations, one or more of which may be omitted or replaced, and one or more other elements may also exist. The embodiments of the present disclosure are not limited in this respect.

[0045] The task management process described in the embodiments of the present disclosure may be implemented on an application management platform, a terminal device on which the application management platform is installed, and / or a server corresponding to the application management platform. In the following examples, for the sake of discussion, the description is from the perspective of the application management platform, for example Figure 1 The application management platform 110 shown. The user interface presented by the application management platform 110 can be presented via the terminal device of the user 145, and the application management platform 110 can receive user input via the terminal device of the user 145. In some embodiments of the present disclosure, the user 145 is the terminal user of the target application 120. It should be understood that the user interface presented by the application management platform 110 can also be presented via the terminal device of the user 105, and the application management platform 110 can also receive user input via the terminal device of the user 105. In some embodiments of the present disclosure, the user 105 is the creator, manager or maintainer of the target application 120.

[0046] For ease of understanding, please refer to FIG. 2A to FIG. 2E The process of the user 105 configuring the target application 120 is described. FIG. 2A to FIG. 2ESchematic diagrams showing example interfaces 200A to 200E of application configurations according to some embodiments of the present disclosure. The task processing process may be implemented on the application management platform 110 .

[0047] In some embodiments, if the application management platform 110 detects an indication to add a target operation to the target application, information related to one or more predetermined input parameters of the target operation is presented. The one or more input parameters correspond to one or more fields in the call request of the target operation, respectively. The presented information may include, for example, the parameter name of the parameter, the type of parameter value, prompts on how to configure the parameter, and the like. In the following embodiment, in response to detecting the indication, a configuration interface for the target operation may be presented. The configuration interface at least indicates the above-mentioned one or more input parameters. The following will mainly refer to the configuration interface to describe the example embodiments, but this is only exemplary and not intended to be limiting.

[0048] In some examples, if the application management platform 110 detects an instruction to add an application programming interface (API) and / or a function to the target application 120, a configuration interface for the target operation is presented. For ease of understanding, the following description will be given using the online document writing scenario as an example, but this is merely exemplary and is not limited in the present disclosure. Figure 2A As shown in the example interface 200A, if the application management platform 110 receives an instruction to add an operation for writing text content into an online document to the target application, the application management platform 110 presents a configuration interface 210 for the operation.

[0049] The application management platform 110 may also present predetermined input parameters 211 (e.g., which online document to write to), predetermined input parameters 212 (e.g., what text content to add), etc. for the operation of writing text content into an online document in the configuration interface 210 presented to the user 105. In some examples, the application management platform 110 may also configure a mapping relationship in the development tool provided by it, that is, mapping one or more input parameters to one or more fields in a call request (also referred to as an actual API request).

[0050] like Figures 2A to 2B In the example interfaces 200A to 200B shown, the application management platform 110 places the input parameter 211 into the field 221 in the post office protocol (POST) corresponding to the uniform resource locator (URL). Accordingly, the application management platform 110 places the input parameter 212 into the field 222 included in the request body. In some examples, the mapping relationship provided by the application management platform 110 may also be invisible to the user 105.

[0051] In some embodiments, one or more fields corresponding to one or more input parameters are part of the fields included in the call request. In some examples, one or more input parameters are streamlined input parameters, that is, the user 105 can tailor the input parameter content of the API to provide key information to the machine learning model so that the machine learning model can understand and summarize it.

[0052] In some embodiments, the fields included in the call request can be organized into multiple levels, for example, multiple levels of fields can be nested in the API. In this case, the field levels in the API can be simplified. For example, the fields included in the call request can be organized into a first number of levels, and the one or more exposed input parameters can be organized into a second number of levels, and the second number is less than the first number. For example, in the scenario of writing text content into an online document, five or six levels of parameters need to be nested in the API. Through the present disclosure, the parameters in the API can be simplified to one or two layers to improve the accuracy of the machine learning model's understanding.

[0053] In some embodiments, the application management platform 110 determines the configuration information of one or more input parameters based on the interaction with the configuration interface. Then, the application management platform 110 adds the target operation to the target application based on the configuration information of the one or more input parameters. In some examples, the user 105 can perform certain operations based on the configuration interface 210 to determine the configuration information of the input parameters 211 and 212. Then, the application management platform 110 adds the API and / or function corresponding to the writing of text content into the online document to the target application based on the configuration information of the input parameters 211 and 212.

[0054] In some embodiments, a first input parameter in one or more input parameters corresponds to a first field in one or more fields, a parameter name of the first input parameter is different from a field name of the first field, and the semantics of the parameter name of the first input parameter matches the purpose of the first input parameter. In some examples, a field name in an input parameter in the API that originally had a poor naming convention is configured as a field with more business semantics, thereby facilitating the machine learning model to better infer the parameter value of the input parameter. For example, if a field in an input parameter in the API is called "custom_11111", it has no semantics at all. Therefore, after mapping by the development tool, the field name exposed to the machine learning model can be modified to "document_id" to represent the document identity identifier (ID) to be written.

[0055] In some embodiments, the target operation added to the target application may include multiple operations assembled in sequence to implement a predetermined process, and these operations assembled in sequence are called as a whole. That is, these operations are exposed to the caller as one operation. It can be understood that for APIs with deterministic calling processes, the application management platform 110 can encapsulate multiple APIs into one API, that is, one execution action, to avoid the machine learning model from calling each API in sequence. In some embodiments, the application management platform 110 encapsulates multiple APIs into one execution action, which is invisible to the user 105. In this way, the machine learning model does not need to perceive the multiple encapsulated operations, nor does it need to infer the calling order of these operations. This reduces the difficulty of inference of the machine learning model on the one hand, and enhances the certainty and controllability of operation execution on the other hand.

[0056] In some embodiments, user 105 (e.g., developer) can first configure the target operation in other tools. It is understandable that user 105 only inputs the request type and request address for calling the target operation (e.g., encapsulated API) in the configuration interface to call the target operation.

[0057] In some embodiments, the application management platform 110 receives the request type and request address for calling the target operation via the configuration interface. Figure 2C and Figure 2D In the example interfaces 200C and 200D shown, when creating a new management schedule, the following three APIs must be called in series: operation 232 (eg, obtaining the primary calendar ID), operation 233 (eg, creating a new management schedule), and operation 234 (eg, adding schedule participants).

[0058] At this point, the developer can first encapsulate the three APIs as a target operation 236, and add a URL trigger 231 and a synchronous callback 235, so that the machine learning model calls the target operation 236 through the request type and request address. After the developer pre-configures the target operation 236, the user 105 enters the request type 242 (e.g., request method) and request address 243 (e.g., https: / / open.xxxxxxxx) of the target operation 236 in the configuration interface.

[0059] When calling an API or function, there may also be format issues with parameter values ​​or field values. A typical example can be time. For example, the time included in the API needs to be converted into a timestamp. In this case, the input parameters of the interface for creating a schedule management (for example, setting the start and end time of a schedule) require the second-level timestamps of the start and end times to be passed in, and the interface for creating a task management (for example, setting the deadline of a task) requires the millisecond-level timestamp of the task deadline to be passed in. Since the machine learning model can only read strings of hours, minutes, and seconds but cannot calculate timestamps, the machine learning model cannot accurately understand and cannot infer the corresponding input parameters of the API accordingly.

[0060] To this end, in some embodiments, the creator may be supported to set the format of the field value required for the target operation. Accordingly, the format processed by the machine learning model may be different, that is, the machine learning model can still process the format it is good at.

[0061] In some embodiments, a second input parameter in the one or more input parameters corresponds to a second field in the one or more fields. The application management platform 110 may receive a selection of a format for the second input parameter via a configuration interface to determine configuration information for the second input parameter. In some embodiments, for the second input parameter, the selected format matches the format of the second field.

[0062] In some embodiments, when the second input parameter includes time, the format of the second input parameter may include a timestamp. It is understandable that user 105 can configure the input parameter including time as follows: convert the timestamp format required by the interface into a string format such as "YYYY-MM-DDHH:MM:SS" so that the machine learning model can accurately infer and understand it. In some embodiments, the format of the input parameter may include an address under a certain protocol. For example, the address format under protocol A required by the interface is converted to the address format under protocol B. The format of the input parameter can be in various formats, which is not limited in the present disclosure. For ease of understanding, the following reference will be made to Figure 2E Description, the user 105 can configure the format of the input parameters via the configuration interface 200E.

[0063] like Figure 2EIn the example interface 200E shown, if the application management platform 110 detects that the user 105 clicks on the control 250 for configuring the type of the "start time" field, the application management platform 110 presents a selection panel 251 for selecting the type. Next, if the application management platform 110 detects that the user 105 clicks on the control 252 for "date time type" in the selection panel, the application management platform 110 presents a selection panel 253 for selecting the format of the "start time" field. The user 105 can select the format of the "start time" field as "YYYY-MM-DDHH:MM:SS" format 254.

[0064] In some embodiments, the configuration information of one or more input parameters may also include a mode for obtaining parameter values ​​of one or more input parameters. In some embodiments, the application management platform 110 may use a machine learning model to infer parameter values ​​of one or more input parameters. The application management platform 110 may also determine the parameter values ​​of one or more input parameters based on a predetermined value. Figure 2A In the example interface 200A shown, the user 105 can click on the selection control 213 in the configuration interface 210 to select a mode for obtaining parameter values ​​of one or more input parameters.

[0065] In some embodiments, if user 105 configures the acquisition mode of the parameter value of a certain input parameter to be inferred by the machine learning model, then when user 145 uses it, the application management platform 110 fills the field corresponding to the input parameter with the parameter value inferred by the machine learning model. If user 105 configures the acquisition mode of the parameter value of a certain input parameter to be a predetermined value, then when user 145 uses it, the application management platform 110 fills the field corresponding to the input parameter with the predetermined value. The following will describe in detail the fields corresponding to the input parameters filled by the application management platform 110 when user 145 uses it.

[0066] Thus, through the present disclosure, a complex target operation can be configured as a function that is better understood by a machine learning model. The following will further describe the process in which after the user 105 configures the application, the user 105 can publish the application, and after the application is published, the user 145 uses the application.

[0067] In some embodiments, the application management platform 110 determines corresponding parameter values ​​of one or more input parameters based on the user input and the configuration information of the one or more input parameters for the target operation. In some examples, the application management platform 110 receives the user input of the user 145 (e.g., help me write a text content) based on the terminal device 146 of the user 145. Subsequently, the application management platform 110 determines corresponding parameter values ​​of the one or more input parameters based on the user input of the user 145 and the configuration information of the one or more input parameters for the target operation of the user 105.

[0068] In some embodiments, if the configuration information indicates that the acquisition mode of the parameter value of the third parameter in the one or more input parameters includes inference by the machine learning model based on the description information of the target operation and the description information of the third parameter, the application management platform 110 generates prompt information for the machine learning model. Accordingly, the application management platform 110 provides the prompt information to the machine learning model to obtain the model output of the machine learning model. Then, the application management platform 110 determines the parameter value of the third input parameter according to the model output.

[0069] In some examples, if the user 105 configures the acquisition mode of the parameter value of a certain input parameter to be inferred by the machine learning model, then when the user 145 uses it, the application management platform 110 generates prompt information according to the description information of the target operation and the description information of the parameter value of the input parameter. Then, the machine learning model extracts the parameter value of the input parameter according to the prompt information.

[0070] In some examples, when calling a machine learning model, the application management platform 110 may provide the machine learning model with relevant information about the target operation (also referred to as a function list). In some embodiments, the function list includes the name and description of each function, as well as the input parameters of the function, the field name of each input parameter, and the description of the input parameter. In some embodiments, the developer may also provide a more precise text content as a prompt for the machine learning model.

[0071] In some embodiments, the application management platform 110 calls the target operation to obtain the operation result of the target operation based on the corresponding parameter values ​​of the one or more input parameters and the corresponding relationship between the one or more input parameters and the one or more fields in the call request of the target operation. Then, the application management platform 110 generates a response to the user input according to the operation result.

[0072] In some examples, the application management platform 110 calls the target operation based on the parameter value of a certain input parameter and the mapping relationship between the input parameter and the field in the call request. According to the parameter value of a certain input parameter, the parameter value is filled into the field corresponding to the input parameter in the call request. Then, the target operation is called based on the request to obtain the operation result of the target operation. Accordingly, based on the operation result, a response to the user input of the user 145 (for example, help me write a text content) is generated. For example, the text content that meets the needs of the user 145 is written into an online document.

[0073] In some embodiments, the application management platform 110 uses the corresponding parameter values ​​of the one or more input parameters to fill one or more fields in the call request, wherein the remaining fields except the one or more fields in the call request are filled with predetermined values. Then, the application management platform 110 calls the target operation according to the filled call request.

[0074] In some examples, since one or more input parameters are simplified input parameters, the application management platform 110 uses the parameter values ​​corresponding to the one or more input parameters that have been determined to fill in one or more fields included in the call request corresponding to the one or more input parameters. Further, corresponding predetermined values ​​are pre-set for other fields in the call request except for the one or more fields, so the other fields are filled with the predetermined values.

[0075] In some embodiments, the application management platform 110 determines the format selected for the second input parameter of the one or more input parameters based on the configuration information. In some embodiments, the second input parameter corresponds to the second field of the one or more fields. The application management platform 110 converts the parameter value of the second input parameter into a value of the selected format. Accordingly, the application management platform 110 fills the second field in the call request with the value of the selected format. Then, the application management platform 110 calls the target operation based on the filled call request. In some examples, the developer needs to declare the time of the format of the input parameters required by the interface. When the interface is actually called, the management application platform 110 will convert the time once to the format actually required by the API.

[0076] In some examples, the application management platform 110 may determine, based on the configuration information, that a field in the input parameter including time needs to convert the timestamp format to the selected format, for example, the string format of "YYYY-MM-DDHH:MM:SS". Then, the application management platform 110 converts the field in the timestamp format into a value in the string format of "YYYY-MM-DDHH:MM:SS" to fill the field, and then, the application management platform 110 calls the target operation according to the filled call request.

[0077] For example, if the original response time of the interface for creating a schedule is a timestamp in seconds, the application management platform 110 converts the timestamp in seconds into a string of year, month, day, hour, minute, and second according to the developer's configuration of the interface for creating a schedule. In this way, it can be ensured that during the interaction between the user 145 and the application, the machine learning model can accurately infer the start time and end time of the schedule.

[0078] In summary, the present disclosure can configure a complex target operation into a function that is better understood by a machine learning model. During the function recall process, the machine learning model can more accurately select which operation to use and more accurately infer the parameters that need to be passed in to the operation.

[0079] Figure 3A FIG. 3 is a flow chart showing a process 300A for application configuration according to some embodiments of the present disclosure. The process 300A may be implemented at the application management platform 110. Figure 1 Process 300A is described.

[0080] In block 310 , the application management platform 110 presents information related to one or more predetermined input parameters of the target operation in response to an instruction to add the target operation to the target application, where the one or more input parameters respectively correspond to one or more fields in a call request of the target operation.

[0081] At block 320 , the application management platform 110 determines configuration information for one or more input parameters.

[0082] In block 330 , the application management platform 110 adds a target operation to the target application based on the configuration information of the one or more input parameters.

[0083] In some embodiments, one or more fields corresponding to the one or more input parameters are part of the fields included by the call request.

[0084] In some embodiments, a first input parameter of the one or more input parameters corresponds to a first field of the one or more fields, a parameter name of the first input parameter is different from a field name of the first field, and the semantics of the parameter name of the first input parameter matches the purpose of the first input parameter.

[0085] In some embodiments, the target operation includes a plurality of operations assembled in sequence to implement a predetermined process, and the plurality of operations assembled in sequence are called as a whole.

[0086] In some embodiments, determining configuration information of one or more input parameters includes receiving a request type and a request address for invoking a target operation.

[0087] In some embodiments, a second input parameter of the one or more input parameters corresponds to a second field of the one or more fields, and determining configuration information for the one or more input parameters includes receiving a selection of a format for the second input parameter, the selected format matching a format of the second field.

[0088] In some embodiments, the second input parameter comprises a time, and the selected format comprises a timestamp.

[0089] In some embodiments, the configuration information of one or more input parameters includes an acquisition mode of parameter values ​​of the one or more input parameters, and the acquisition mode includes at least one of the following: inference by a machine learning model, or a predetermined value.

[0090] In some embodiments, the fields included in the call request are organized into a first number of levels, and the one or more input parameters are organized into a second number of levels, and the second number is smaller than the first number.

[0091] Figure 3B FIG. 3 is a flowchart of a process 300B of information processing according to some embodiments of the present disclosure. The process 300B may be implemented at the application management platform 110. Figure 1 Process 300B is described.

[0092] In block 340 , the application management platform 110 determines corresponding parameter values ​​for the one or more input parameters based on the user input and the configuration information for the one or more input parameters of the target operation.

[0093] In block 350 , the application management platform 110 calls the target operation to obtain an operation result of the target operation based on corresponding parameter values ​​of the one or more input parameters and according to a correspondence between the one or more input parameters and one or more fields in the call request of the target operation.

[0094] In block 360 , the application management platform 110 generates a response to the user input based on the operation result.

[0095] In some embodiments, one or more fields corresponding to one or more input parameters are part of the fields included in the call request, and calling the target operation includes: filling one or more fields in the call request using the corresponding parameter values ​​of the one or more input parameters, wherein the remaining fields in the call request except the one or more fields are filled with predetermined values; and calling the target operation based on the filled call request.

[0096] In some embodiments, a first input parameter of the one or more input parameters corresponds to a first field of the one or more fields, and a parameter name of the first input parameter is different from a field name of the first field and has semantics matching those of the first input parameter.

[0097] In some embodiments, a second input parameter among the one or more input parameters corresponds to a second field among the one or more fields, and calling the target operation includes: determining a format selected for the second input parameter based on configuration information; converting a parameter value of the second input parameter into a value of the selected format; filling the second field in the call request with the value of the selected format; and calling the target operation based on the filled call request.

[0098] In some embodiments, the second input parameter comprises a time, and the selected format comprises a timestamp.

[0099] In some embodiments, the configuration information of one or more input parameters includes an acquisition mode of parameter values ​​of the one or more input parameters, and the acquisition mode includes at least one of the following: inference by a machine learning model, or a predetermined value.

[0100] In some embodiments, determining the corresponding parameter values ​​of one or more input parameters includes: in response to the configuration information indicating that the acquisition mode of the parameter value of a third input parameter among the one or more input parameters includes inference by the machine learning model, generating prompt information for the machine learning model based on the description information of the target operation and the description information of the third input parameter; providing the prompt information to the machine learning model to obtain a model output of the machine learning model; and determining the parameter value of the third input parameter based on the model output.

[0101] Figure 4A A schematic structural block diagram of an apparatus 400A for application configuration according to some embodiments of the present disclosure is shown. The apparatus 400A may be implemented in or included in the application management platform 110, for example. Each module / component in the apparatus 400A may be implemented by hardware, software, firmware, or any combination thereof.

[0102] As shown in the figure, the device 400A includes a configuration interface presentation module 410, which is configured to present information related to one or more predetermined input parameters of the target operation in response to an instruction to add a target operation to the target application, and the one or more input parameters correspond to one or more fields in the call request of the target operation. The device 400A also includes a configuration information determination module 420, which is configured to determine the configuration information of the one or more input parameters. The device 400A also includes an operation addition module 430, which is configured to add the target operation to the target application based on the configuration information of the one or more input parameters.

[0103] In some embodiments, one or more fields corresponding to the one or more input parameters are part of the fields included by the call request.

[0104] In some embodiments, a first input parameter of the one or more input parameters corresponds to a first field of the one or more fields, a parameter name of the first input parameter is different from a field name of the first field, and the semantics of the parameter name of the first input parameter matches the purpose of the first input parameter.

[0105] In some embodiments, the target operation includes a plurality of sub-operations assembled in sequence to implement a predetermined process, and the plurality of operations assembled in sequence are called as a whole.

[0106] In some embodiments, the configuration information determination module 420 is configured to receive a request type and a request address for invoking a target operation.

[0107] In some embodiments, a second input parameter among the one or more input parameters corresponds to a second field among the one or more fields, and the configuration information determination module 420 is also configured to receive a selection of a format for the second input parameter via a configuration interface, and the selected format matches the format of the second field.

[0108] In some embodiments, the second input parameter comprises a time, and the selected format comprises a timestamp.

[0109] In some embodiments, the configuration information of one or more input parameters includes an acquisition mode of parameter values ​​of the one or more input parameters, and the acquisition mode includes at least one of the following: inference by a machine learning model, or a predetermined value.

[0110] In some embodiments, the fields included in the call request are organized into a first number of levels, and the one or more input parameters are organized into a second number of levels, and the second number is smaller than the first number.

[0111] Figure 4B A schematic structural block diagram of an information processing apparatus 400B according to some embodiments of the present disclosure is shown. The apparatus 400B may be implemented in or included in the application management platform 110, for example. Each module / component in the apparatus 400B may be implemented by hardware, software, firmware, or any combination thereof.

[0112] As shown in the figure, the device 400B includes a parameter value determination module 440, which is configured to determine the corresponding parameter values ​​of one or more input parameters based on the user input and the configuration information of the one or more input parameters for the target operation. The device 400B also includes an operation result acquisition module 450, which is configured to call the target operation to obtain the operation result of the target operation based on the corresponding parameter values ​​of the one or more input parameters and the corresponding relationship between the one or more input parameters and one or more fields in the call request of the target operation; and the device 400B also includes a response generation module 460, which is configured to generate a response to the user input based on the operation result.

[0113] In some embodiments, one or more fields corresponding to one or more input parameters are part of the fields included in the call request, and the operation result acquisition module 450 is also configured to fill one or more fields in the call request using the corresponding parameter values ​​of the one or more input parameters, wherein the remaining fields in the call request except one or more fields are filled with predetermined values; and based on the filled call request, call the target operation.

[0114] In some embodiments, a first input parameter of the one or more input parameters corresponds to a first field of the one or more fields, and a parameter name of the first input parameter is different from a field name of the first field and has semantics matching those of the first input parameter.

[0115] In some embodiments, a second input parameter among the one or more input parameters corresponds to a second field among the one or more fields, and the operation result acquisition module 450 is also configured to determine the format selected for the second input parameter based on the configuration information; convert the parameter value of the second input parameter into a value of the selected format; fill the second field in the call request with the value of the selected format; and call the target operation based on the filled call request.

[0116] In some embodiments, the second input parameter comprises a time, and the selected format comprises a timestamp.

[0117] In some embodiments, the configuration information of one or more input parameters includes an acquisition mode of parameter values ​​of the one or more input parameters, and the acquisition mode includes at least one of the following: inference by a machine learning model, or a predetermined value.

[0118] In some embodiments, the parameter value determination module 440 is also configured to respond to the configuration information indicating that the acquisition mode of the parameter value of the third input parameter among the one or more input parameters includes inferring by the machine learning model, generating prompt information for the machine learning model based on the description information of the target operation and the description information of the third input parameter; providing the prompt information to the machine learning model to obtain the model output of the machine learning model; and determining the parameter value of the third input parameter based on the model output.

[0119] Figure 5 1 shows a block diagram of an electronic device 500 in which one or more embodiments of the present disclosure may be implemented. It should be understood that Figure 5 The electronic device 500 shown is merely exemplary and should not constitute any limitation on the functionality and scope of the embodiments described herein. Figure 5 The electronic device 500 shown may include or be implemented as Figure 1 application management platform 110, or Figure 4A and / or Figure 4B Device 400A and / or 400B.

[0120] like Figure 5As shown, the electronic device 500 is in the form of a general electronic device. The components of the electronic device 500 may include, but are not limited to, one or more processors or processing units 510, a memory 520, a storage device 530, one or more communication units 540, one or more input devices 550, and one or more output devices 560. The processing unit 510 may be an actual or virtual processor and is capable of performing various processes according to a program stored in the memory 520. In a multi-processor system, multiple processing units execute computer executable instructions in parallel to improve the parallel processing capability of the electronic device 500.

[0121] The electronic device 500 typically includes a plurality of computer storage media. Such media may be any accessible media that is accessible to the electronic device 500, including but not limited to volatile and non-volatile media, removable and non-removable media. The memory 520 may be a volatile memory (e.g., registers, caches, random access memory (RAM)), a non-volatile memory (e.g., a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. The storage device 530 may be a removable or non-removable medium, and may include a machine-readable medium, such as a flash drive, a disk, or any other medium, which may be capable of being used to store information and / or data and may be accessed within the electronic device 500.

[0122] The electronic device 500 may further include additional removable / non-removable, volatile / non-volatile storage media. Figure 5 As shown in , a disk drive for reading or writing from a removable, non-volatile disk (e.g., a "floppy disk") and an optical drive for reading or writing from a removable, non-volatile optical disk may be provided. In these cases, each drive may be connected to the bus (not shown) by one or more data media interfaces. The memory 520 may include a computer program product 525 having one or more program modules that are configured to perform various methods or actions of various embodiments of the present disclosure.

[0123] The communication unit 540 implements communication with other electronic devices through a communication medium. Additionally, the functions of the components of the electronic device 500 can be implemented in a single computing cluster or multiple computing machines that can communicate through a communication connection. Therefore, the electronic device 500 can operate in a networked environment using a logical connection with one or more other servers, a network personal computer (PC), or another network node.

[0124] The input device 550 may be one or more input devices, such as a mouse, a keyboard, a tracking ball, etc. The output device 560 may be one or more output devices, such as a display, a speaker, a printer, etc. The electronic device 500 may also communicate with one or more external devices (not shown) through the communication unit 540 as needed, such as a storage device, a display device, etc., communicate with one or more devices that allow a user to interact with the electronic device 500, or communicate with any device that allows the electronic device 500 to communicate with one or more other electronic devices (e.g., a network card, a modem, etc.). Such communication may be performed via an input / output (I / O) interface (not shown).

[0125] According to an exemplary implementation of the present disclosure, a computer-readable storage medium is provided, on which computer-executable instructions are stored, wherein the computer-executable instructions are executed by a processor to implement the method described above. According to an exemplary implementation of the present disclosure, a computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, and the computer-executable instructions are executed by a processor to implement the method described above.

[0126] Various aspects of the present disclosure are described herein with reference to the flowcharts and / or block diagrams of the methods, devices, equipment, and computer program products implemented according to the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer-readable program instructions.

[0127] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processing unit of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0128] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, so that the instructions executed on the computer, other programmable data processing apparatus, or other device implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0129] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to multiple implementations of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and a part of a module, program segment or instruction includes one or more executable instructions for realizing the logical function of the specification. In some implementations as replacements, the function marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be realized by a special hardware-based system that performs the function or action of the specification, or can be realized by a combination of special hardware and computer instructions.

[0130] The above descriptions of various implementations of the present disclosure are exemplary, non-exhaustive, and not limited to the disclosed implementations. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described implementations. The selection of terms used herein is intended to best explain the principles of the implementations, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the various implementations disclosed herein.

Claims

1. An application configuration method, comprising: In response to an instruction to add a target operation to a target application, present information related to one or more predetermined input parameters of the target operation, wherein the one or more input parameters respectively correspond to one or more fields in a call request of the target operation; determining configuration information of the one or more input parameters; as well as The target operation is added to the target application based on the configuration information of the one or more input parameters. 2 . The method according to claim 1 , wherein the one or more fields corresponding to the one or more input parameters are part of the fields included in the call request.

3. The method of claim 1, wherein a first input parameter of the one or more input parameters corresponds to a first field of the one or more fields, a parameter name of the first input parameter is different from a field name of the first field, and the semantics of the parameter name of the first input parameter matches the purpose of the first input parameter. 4 . The method according to claim 1 , wherein the target operation comprises a plurality of operations assembled in sequence for implementing a predetermined process, and the plurality of operations assembled in sequence are called as a whole.

5. The method of claim 4, wherein determining configuration information of the one or more input parameters comprises: A request type and a request address for invoking the target operation are received.

6. The method of claim 1 , wherein a second input parameter of the one or more input parameters corresponds to a second field of the one or more fields, and determining configuration information of the one or more input parameters comprises: A selection of a format for the second input parameter is received, the selected format matching a format of the second field.

7. The method of claim 6, wherein the second input parameter comprises a time and the selected format comprises a timestamp.

8. The method according to claim 1, wherein the configuration information of the one or more input parameters includes an acquisition mode of parameter values ​​of the one or more input parameters, and the acquisition mode includes at least one of the following: inferred by a machine learning model, or Predetermined value. 9 . The method according to claim 1 , wherein the fields included in the call request are organized into a first number of levels, the one or more input parameters are organized into a second number of levels, and the second number is smaller than the first number.

10. An information processing method, comprising: Determining corresponding parameter values ​​of the one or more input parameters based on user input and configuration information for the one or more input parameters of the target operation; Based on corresponding parameter values ​​of the one or more input parameters and according to a correspondence between the one or more input parameters and one or more fields in the call request of the target operation, calling the target operation to obtain an operation result of the target operation; as well as Based on the operation result, a response to the user input is generated.

11. The method of claim 10, wherein the one or more fields corresponding to the one or more input parameters are part of the fields included in the call request, and calling the target operation comprises: filling the one or more fields in the call request using the corresponding parameter values ​​of the one or more input parameters, wherein the remaining fields in the call request except the one or more fields are filled with predetermined values; as well as Based on the populated invocation request, the target operation is invoked.

12. The method of claim 10, wherein a first input parameter of the one or more input parameters corresponds to a first field of the one or more fields, a parameter name of the first input parameter being different from a field name of the first field and having semantics matching those of the first input parameter.

13. The method of claim 10, wherein a second input parameter of the one or more input parameters corresponds to a second field of the one or more fields, and invoking the target operation comprises: Based on the configuration information, determining a format selected for the second input parameter; Converting the parameter value of the second input parameter into a value of the selected format; populating the second field in the call request with the value of the selected format; and Based on the populated invocation request, the target operation is invoked.

14. The method of claim 13, wherein the second input parameter comprises a time and the selected format comprises a timestamp.

15. The method according to claim 10, wherein the configuration information of the one or more input parameters comprises an acquisition mode of parameter values ​​of the one or more input parameters, and the acquisition mode comprises at least one of the following: inferred by a machine learning model, or Predetermined value.

16. The method of claim 15, wherein determining corresponding parameter values ​​of the one or more input parameters comprises: In response to the configuration information indicating that the acquisition mode of the parameter value of the third input parameter among the one or more input parameters includes inference by a machine learning model, based on the description information of the target operation and the description information of the third input parameter, generating prompt information for the machine learning model; Providing the prompt information to the machine learning model to obtain a model output of the machine learning model; and Based on the model output, a parameter value of the third input parameter is determined.

17. An apparatus for application configuration, comprising: a configuration interface presenting module, configured to present information related to one or more predetermined input parameters of the target operation in response to an instruction to add the target operation to the target application, wherein the one or more input parameters respectively correspond to one or more fields in the call request of the target operation; a configuration information determination module, configured to determine configuration information of the one or more input parameters; as well as The operation adding module is configured to add the target operation to the target application based on the configuration information of the one or more input parameters.

18. An apparatus for information processing, comprising: a parameter value determination module configured to determine corresponding parameter values ​​of the one or more input parameters based on user input and configuration information of the one or more input parameters for the target operation; an operation result acquisition module, configured to call the target operation to obtain an operation result of the target operation based on corresponding parameter values ​​of the one or more input parameters and according to a correspondence between the one or more input parameters and one or more fields in a call request of the target operation; as well as The response generation module is configured to generate a response to the user input based on the operation result.

19. An electronic device comprising: at least one processing unit; as well as At least one memory, the at least one memory is coupled to the at least one processing unit and stores instructions for execution by the at least one processing unit, the instructions, when executed by the at least one processing unit, cause the electronic device to perform a method according to any one of claims 1 to 9 and / or claims 10 to 16.

20. A computer-readable storage medium having a computer program stored thereon, the computer program being executable by a processor to implement the method according to any one of claims 1 to 9 and / or claims 10 to 16.

Citation Information

Patent Citations

  • Open domain natural language reasoning question-answering system and method driven by large language model

    CN116932708A

  • Method, device and equipment for intelligently acquiring information and storage medium

    CN117312641A

  • Data processing method and device, electronic equipment and storage medium

    CN117540805A

  • Bidding document generation method and system and computer readable storage medium

    CN117709866A

  • Machine learning for case management information generation

    US20200302393A1