Methods, apparatuses, devices, and storage media for function call

Abstract

Embodiments of the present disclosure provide a method, device, equipment and storage medium for function invocation. The method comprises: in response to triggering invocation of a target function, determining at least one invocation parameter of the target function based on configuration information of the target function; obtaining a parameter value of the at least one invocation parameter based on a triggering mode of the invocation, the triggering mode being one of a plurality of predetermined modes for triggering invocation of the target function; and invoking the target function based on the parameter value of the at least one invocation parameter. In this way, the function can support being invoked through different triggering modes, thereby meeting different use requirements. This is conducive to expanding the application scenarios of the function.

Description

Technical Field

[0001] Example embodiments of the present disclosure generally relate to the field of computers, and more particularly, to a method, apparatus, device, and computer-readable storage medium for function calling. Background Art

[0002] With the development of information technology, various terminal devices can provide people with a variety of services in work and life. Applications that provide these services can be deployed on these devices. These applications present content and interact with users through their user interfaces, meeting their needs. In some cases, users may initiate function calls within applications. Therefore, improving the efficiency of function calls is a key concern. Summary of the Invention

[0003] In a first aspect of the present disclosure, a method for function invocation is provided. The method comprises: in response to triggering a call to a target function, determining at least one call parameter of the target function based on configuration information of the target function; obtaining a parameter value of the at least one call parameter based on a trigger mode of the call, where the trigger mode is one of a plurality of predetermined modes for triggering the call of the target function; and invoking the target function based on the parameter value of the at least one call parameter.

[0004] In a second aspect of the present disclosure, a device for function invocation is provided. The device includes: a determination module configured to, in response to triggering a call to a target function, determine at least one call parameter of the target function based on configuration information of the target function; an acquisition module configured to acquire a parameter value of the at least one call parameter based on a trigger mode of the call, where the trigger mode is one of multiple predetermined modes for triggering the call of the target function; and a call module configured to call the target function based on the parameter value of the at least one call parameter.

[0005] In a third aspect of the present disclosure, an electronic device is provided. The device includes at least one processing unit; and at least one memory coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit. When executed by the at least one processing unit, the instructions cause the electronic device to perform the method of the first aspect.

[0006] In a fourth 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 is implemented.

[0007] According to a fifth aspect of the present disclosure, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, the method according to the first aspect of the present disclosure is implemented.

[0008] It is to be understood that the details set forth herein are by way of illustration only and not intended as limitations of the embodiments of the present disclosure. Other features of the present disclosure will become apparent with reference to the following detailed description and drawings. BRIEF DESCRIPTION OF DRAWINGS

[0009] The above and other features, aspects and advantages of certain embodiments of the present disclosure will become more apparent with reference to the following detailed description and accompanying drawings. In the drawings, like reference numerals are used to represent like elements and aspects of the disclosure, wherein:

[0010] Figure 1 A schematic diagram illustrating an example environment in which embodiments of the present disclosure can be implemented is shown;

[0011] Figure 2 A flow diagram illustrating a process for function invocation according to some embodiments of the present disclosure is shown;

[0012] Figure 3 A schematic diagram illustrating an example of a configuration interface according to some embodiments of the present disclosure is shown;

[0013] Figure 4A And Figure 4B Flow diagrams illustrating signaling flows for function invocation according to some embodiments of the present disclosure are shown, respectively;

[0014] Figure 5 A schematic diagram illustrating an example of a call relationship building interface according to some embodiments of the present disclosure is shown;

[0015] Figure 6 A flow diagram illustrating a signaling flow for function invocation according to some embodiments of the present disclosure is shown;

[0016] Figure 7 A schematic block diagram of an apparatus for function invocation according to some embodiments of the present disclosure is shown; and

[0017] Figure 8 A block diagram of an electronic device that can implement one or more embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0018] Embodiments of the present disclosure will be described hereinafter with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it is understood that the present disclosure can be embodied in various forms and should not be construed as being limited to the embodiments set forth herein, but rather, the embodiments are provided so that the present disclosure will be more thoroughly and completely understood. It is understood that the drawings and embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of the present disclosure.

[0019] In the description of embodiments of the disclosure, the term "comprising" and similar terms thereof are understood to be inclusive, i.e., "including but not limited to". The term "based on" is understood to mean "based at least in part on". The term "one embodiment" or "the embodiment" is understood to mean "at least one embodiment". The term "some embodiments" is understood to mean "at least some embodiments". Other explicit and implicit definitions can also be included below.

[0020] In this article, unless specifically stated, performing a step "in response to A" does not mean performing the step immediately after "A", but can include one or more intermediate steps.

[0021] It can be understood that the data involved in the technical solutions of the present application (including but not limited to the data itself, the acquisition, use, storage or deletion of the data) should comply with the requirements of the relevant laws and regulations and the relevant provisions.

[0022] It can be understood that before using the technical solutions disclosed in the embodiments of the present disclosure, the type of information involved in the present disclosure, the scope of use, the use scenario, etc. should be informed to the relevant user and the authorization of the relevant user should be obtained by appropriate means, wherein the relevant user can include any type of right subject, such as individual, enterprise, group.

[0023] For example, in response to receiving the active request of the user, a prompt information is sent to the relevant user to explicitly prompt the relevant user that the operation requested to be performed will require the information of the relevant user to be obtained and used, so that the relevant user can voluntarily choose whether to provide the information to the software or hardware such as electronic device, application program, server or storage medium performing the operation of the technical solutions of the present disclosure according to the prompt information.

[0024] As an optional but not limited implementation manner, in response to receiving the active request of the relevant user, the prompt information can be sent to the relevant user in the form of a pop-up window, and the prompt information can be presented in the form of text in the pop-up window. In addition, the pop-up window can also carry selection controls for the user to select "agree" or "disagree" to provide information to the electronic device.

[0025] It can be understood that the above notification and user authorization process is only illustrative and does not limit the implementation of the present disclosure. Other ways that meet the relevant laws and regulations can also be applied to the implementation of the present disclosure. The enabling of the digital assistant related functions of the embodiments of the present disclosure, the data obtained, the processing and storage manner of the data, etc. should be authorized in advance by the user and other right subjects associated with the user, and should comply with the relevant laws and regulations and the agreement rules between the right subjects.

[0026] As used herein, the term “model” can learn the relationship 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 techniques. Deep learning is a machine learning algorithm that processes input and provides a corresponding output by using multiple layers of processing units. The neural network model is an example of a model based on deep learning. In this document, “model” can also be referred to as “machine learning model”, “learning model”, “machine learning network” or “learning network”, which are used interchangeably herein.

[0027] The term “function” used herein should be understood to refer to a functional module having a specific capability, capable of performing a specific task and / or capable of providing a specific service. For example, a “function” can have the capability of invoking a model to generate specific content, or a “function” can also have the capability of performing a specific task alone.

[0028] Figure 1 A schematic diagram showing an example environment 100 in which embodiments of the present disclosure can be implemented. The environment 100 involves a server end 110, terminal devices 120, 150, and a target model 140.

[0029] As Figure 1 shown, the server end 110 is deployed with a function management platform 111, which can include a function creation part and a function application part, and the function creation part can provide a user 160 with a creation, publication and management environment of functions. In some embodiments, the function management platform 111 can be a low-code platform, which provides a toolset for function creation. The function management platform 110 can support visual development of functions. The function management platform 111 can support any suitable platform for users to develop functions.

[0030] The function management platform 111 can be deployed at the server end 110, can be deployed locally at the terminal device 120 of the user 130, and / or can be supported by a remote server. For example, the terminal device 120 of the user 130 can run a client of the function management platform 111, which can support the interaction of the user 130 with the function management platform 111. In the case where the function management platform is run locally at the terminal device 120 of the user 130, the user 130 can directly interact with the local function management platform using the client. In the case where the function management platform 111 is run at the server end 110, the server end 110 can implement the provision of services to the client running at the terminal device 120 based on the communication connection between the terminal device 120.

[0031] The terminal device 120 may be deployed with a digital assistant 121, and the user 130 may interact with the digital assistant 121 through the terminal device 120 or an attached device of the terminal device 120. The digital assistant 121 is provided to assist the user 130 in various task processing needs in different applications and scenarios. The digital assistant 121 generally has intelligent dialogue and task processing capabilities. During the interaction with the digital assistant 121, the user 130 inputs interactive messages (such as text, voice, image, video or other modal dialogue content), and the digital assistant 121 provides reply messages in response to the user input. Generally, the digital assistant 121 can support the user 130 to input questions in natural language, and perform tasks and provide replies based on the understanding of natural language input and logical reasoning ability. The digital assistant 121 can also be configured to call a matching interface to provide reply messages based on user input, thereby improving the processing capabilities of the digital assistant 121.

[0032] In an embodiment of the present disclosure, the user 160 can create functions as needed on the function creation part of the function management platform 111 and publish the functions. The functions can be published to any appropriate function application part, as long as the function application part can support the call of the function by the digital assistant 121. The function application part can be deployed on the server 110, or it can be deployed on the terminal device 120 of the user 130. After the function is published, the digital assistant 121 can call the function to provide services to the user 130. For example, the user 130 can enter a conversation message in the conversation window of the digital assistant 121, and the digital assistant 121 can request the function management platform 111 to assist in calling the function, obtain feedback information from the function, determine the reply message based on the feedback information, and present it to the user in the conversation window.

[0033] In some embodiments, digital assistant 121 can utilize goal models 140 to support interactions with user 130. For example, digital assistant 121 can utilize one or more goal models to provide question-and-answer services to user 130.

[0034] In some embodiments, one or more target models 140 can be built based on a language model (LM). The machine learning model used is a content generative model, which is capable of generating a corresponding output based on a model input. In some embodiments, the language model based machine learning model is capable of processing a model input in a text modality (e.g., natural language and / or machine language) and / or a non-text modality (e.g., image, voice, video, etc.), and is capable of generating a desired output according to the model input and a prompt word. The prompt word here is used to guide the machine learning model to generate an output that can address a user demand indicated by the model input. In an application scenario for supporting user conversation, a user input can be provided as at least a part of the model input (other parts can include the prompt word) to the machine learning model. The user input is considered as a question. Based on the model output, a corresponding answer can be generated to be provided to the user 130.

[0035] The function management platform 111 can be running on a suitable electronic device. The electronic device here can be any type of device with computing capability, including a terminal device or a server device. The terminal device can be any type of mobile terminal, fixed terminal, or portable terminal including a mobile phone, a desktop computer, a laptop computer, a notebook computer, a netbook computer, a tablet computer, a media computer, a multimedia tablet, a personal communication system (PCS) device, a personal navigation device, a personal digital assistant (PDA), an audio / video player, a digital camera / camcorder, a positioning device, a television receiver, a radio broadcast receiver, an electronic book device, a game device, or any combination of the foregoing, including accessories and peripherals of these devices or any combination thereof. The server 110 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 function management platform 111 can be implemented based on a cloud service.

[0036] It should be understood that the structure and function of the various elements in the environment 100 are described for illustrative purposes only, without implying any limitation on the scope of the present disclosure.

[0037] As mentioned before, an application or digital assistant providing a service can be deployed in a terminal device, and a call for a function can be initiated through the application or digital assistant. With the development of information technology, the application of functions is also increasingly diversified. In order to meet the use requirements of the same function in different application scenarios, it is desirable to be able to call the same function using multiple calling manners. However, the calling logic and the way of obtaining calling parameters of different calling manners are usually different. Traditionally, a function is usually built for a specific calling manner, and it is usually difficult to meet the use requirements of calling using multiple calling manners.

[0038] In view of this, embodiments of the present disclosure provide an improved solution for function invocation. In this solution, in response to triggering a call to a target function, at least one call parameter of the target function is determined based on the configuration information of the target function. A parameter value of the at least one call parameter is obtained based on a trigger mode in which the target function is invoked, where the trigger mode is one of multiple predetermined modes for triggering the call of the target function. Based on the parameter value of the at least one call parameter, the target function is invoked.

[0039] In an embodiment of the present disclosure, at least one call parameter required to invoke a function is specified in the configuration information. During use, the value of the at least one call parameter is obtained based on the specific trigger mode used to trigger the function call. This enables the function to support different trigger modes for triggering calls, facilitating the expansion of the function's application scenarios.

[0040] Some example embodiments of the present disclosure will be described in detail below with reference to examples in the accompanying drawings.

[0041] Figure 2 1 shows a flow chart of a process 200 for function calling according to some embodiments of the present disclosure. The process 200 can be implemented on the server 110, for example, it can be implemented by the function application part of the function management platform 110 deployed on the server 110. Figure 1 To describe Figure 2 Process 200 is shown.

[0042] In block 210, the server 110 determines at least one call parameter of the target function based on the configuration information of the target function in response to triggering the call to the target function. The functions herein may include functional modules with different capabilities, and the target function may include but is not limited to content generation functions using language models, data analysis functions, data processing functions, and the like. The tasks performed, capabilities possessed, or services provided by the functions are not limited here. The at least one call parameter may include one or more parameters required to perform the call operation to the target function. The at least one call parameter may include one call parameter or multiple call parameters.

[0043] It is understood that the at least one call parameter corresponds to a function. For different functions, the specific parameters included in the at least one call parameter may vary. For example, if the target function is used to generate online promotional content, the at least one call parameter of the target function may include a title and promotion channel, etc. For another example, if the target function is used to query the weather, the at least one call parameter of the target function may include time and location, etc.

[0044] During the creation of the target function, at least one calling parameter of the target function can be configured, which can be saved as at least part of the configuration information in the data storage unit of the server 110, for example. In some embodiments, the server 110 can present a configuration interface of the target function in response to a configuration request of the target function. Then, the server 110 can receive attribute information of the at least one calling parameter through the configuration interface. The attribute information herein is used to describe the basic attributes of the calling parameter, and the attribute information can include but is not limited to the parameter name, type, description, etc. of the calling parameter.

[0045] Reference Figure 3 An example is described. Figure 3 A schematic diagram of an example 300 of a configuration interface according to some embodiments of the present disclosure is shown. The example 300 shows a configuration interface of an “ABCD function”, which can be used to generate marketing materials for a specified commodity distribution “channel”. The example 300 includes a calling parameter input entry 310, which can include at least one set of input boxes corresponding to the at least one calling parameter. Specifically, the at least one calling parameter can include the “title” of the marketing materials and the distribution “channel” to which the marketing materials are directed. At this time, the at least one set of input boxes can include a set of input boxes 311 corresponding to the “title” and a set of input boxes 312 corresponding to the “channel”. The set of input boxes 311 and the set of input boxes 312 respectively include input boxes for inputting the parameter name, type and description. The user can input the attribute information of the at least one calling parameter to the calling parameter input entry 310. Of course, the above-mentioned configuration interface is only an example, and in actual application, the interface elements and interface layout contained in the configuration interface can be selected according to actual needs.

[0046] In some embodiments, the server 110 can further include a data storage unit for saving the metadata of the function. After determining the called target function, the function management platform 111 can send an information acquisition request to the data storage unit based on the function identifier of the target function. The function metadata storage unit can feed back the configuration information of the target function to the function management platform in response to the information acquisition request, which can include at least one calling parameter of the target function. The at least one calling parameter is used to perform a calling operation on the target function.

[0047] At block 220, the server 110 obtains a parameter value for at least one call parameter based on the trigger mode of the call. The target function can be configured to be triggered by multiple predetermined modes, where a trigger mode is one of multiple predetermined modes for triggering the call of the target function. Alternatively or additionally, the multiple predetermined modes can have corresponding parameter value acquisition methods. Upon determining the trigger mode of the call, the parameter value for the at least one call parameter can be obtained using the corresponding acquisition method.

[0048] The following will use some specific trigger modes to exemplify the process of the server 110 obtaining parameter values ​​under different trigger modes, but it should not be understood that the target function is limited to the trigger modes shown below, nor should it be understood that the parameter values ​​of the call parameters are obtained only through the acquisition method shown below under each trigger mode shown below.

[0049] In some embodiments, the target function can be configured to be triggered through a session trigger mode. Specifically, the server 110 can determine a function that matches the user input from at least one function in response to receiving user input. If it is determined that the function matches the user input, the trigger mode is determined to be a session trigger mode, and the call to the target function is triggered based on the session trigger mode. Afterwards, the server 110 can obtain the configuration information of the target function in response to the call to the target function being triggered through the session mode. Based on the configuration information, a clarification mode of the at least one call parameter is determined, and a parameter value of the at least one call parameter is obtained based on the clarification mode. Alternatively or additionally, the clarification mode may include but is not limited to a dialogue mode, a form mode, and the like. The dialogue mode and the form mode will be described in detail later in conjunction with specific examples and will not be elaborated on here.

[0050] During the process of creating the target function, a clarification mode of at least one call parameter of the target function may be configured. In some embodiments, the server 110 may receive a selection of a clarification mode for at least one call parameter through a configuration interface, where the clarification mode indicates a method for obtaining the at least one call parameter.

[0051] For example, Figure 3 As shown, the configuration interface shown in example 300 may also include a mode selection entry 320. Mode selection entry 320 may include one or more option boxes corresponding to one or more predetermined clarification modes. In example 300, option box 321 corresponding to the dialogue mode and option box 322 corresponding to the form mode are respectively provided. In response to the user's selection operation for the form mode, the server 110 may switch option box 322 to a selected state (e.g., switching the line of the option box to a thick line) and switch option box 321 to a non-selected state (e.g., switching the line of the option box to a thin line).

[0052] Furthermore, the configuration interface shown in example 300 may also include a structural information input entry 330, which is used to receive structural information of the form. The structural information of the form includes but is not limited to the form title, call parameters, etc. The server 110 can present the structural information input entry 330 on the configuration interface in response to the selection operation of the option box 322 corresponding to the form mode. The structural information input entry 330 may include a form title input entry 331 and a call parameter configuration entry 332. The user (for example, the creator of the function) can input a title for the form into the form title input entry. The call parameter configuration entry 332 may include multiple input boxes, such as an input box for inputting the parameter name of the call parameter, an input box for inputting the parameter value, and an element for characterizing the mapping relationship between the parameter name and the parameter value, etc. The user can configure the call parameters that need to be clarified through the call parameter configuration entry 332.

[0053] In some embodiments, the server 110 may present a parameter input interface including a form in response to the configuration information indicating that the clarification mode of at least one call parameter is a form mode, based on the structural information of the form, and the form may include a parameter value input entry for at least one call parameter. The server 110 may receive a parameter value for at least one call parameter through the parameter input entry. The parameter value input entry here may be pre-filled with a parameter value for user confirmation, or may be set to an empty value and wait for user input. Exemplarily, the server 110 may present a form similar to the structural information input entry 330 in Example 300, which may include, for example, a title, a parameter name, an input box for entering a parameter value, and elements for characterizing the mapping relationship between a parameter name and a parameter value, etc.

[0054] It should also be noted that the parameter input interface is not limited to obtaining the parameter value of the at least one call parameter through the form data structure, but can also obtain the parameter value of the at least one call parameter through other data structures, as long as the parameter input interface includes the parameter value input entrance of the at least one call parameter and the parameter value of the at least one call parameter can be received through the parameter value input entrance.

[0055] In some embodiments, the server 110 may generate prompt information for the target model 140 based on the user input and the at least one call parameter, and the server 110 may provide the prompt information to the target model 140 to obtain an output of the target model 140. Thereafter, the server 110 may determine parameter values ​​for at least some of the at least one call parameter based on the output of the target model 140.

[0056] Exemplarily, the server 110 can further include a flow manager, a flow engine and a business engine. The function management platform 111 of the server 110 can generate prompt information of the target model 140 based on the user input and the at least one calling parameter. The function management platform 111 sends the prompt information to the flow manager, the flow manager sends the prompt information to the flow engine, and the flow engine sends the prompt information to the business engine. Then, the business engine can provide the prompt information to the target model 140 in response to receiving the prompt information. The business engine can also receive the output of the target model 140 and send the output of the target model 140 to the function management platform 111 through the flow engine and the flow manager. The function management platform 111 can determine the parameter value of the at least part of the calling parameter based on the output of the target model 140.

[0057] It can be understood that the user input can include the parameter values of all calling parameters, or can only include the parameter values of part of the calling parameters. In response to the target model 140 determining the parameter values of part of the calling parameters from the user input, and in the case that part of the calling parameters lack parameter values, in some embodiments, the server 110 can present structured content for the at least one calling parameter in response to determining that part of the at least one calling parameter lacks parameter values. The structured content includes the parameter values determined based on the output of the target model 140 and parameter value input entries of the part of the calling parameters. The parameter values of the part of the calling parameters are received through the parameter value input entries of the part of the calling parameters.

[0058] Exemplarily, the server 110 can present a form similar to the structure information input entry 330 in the example 300, which can include, for example, a title, a parameter name, an input box for inputting a parameter value, and an element for representing the mapping relationship between the parameter name and the parameter value, etc. The server 110 can fill the parameter values determined based on the output of the target model 140 into the corresponding parameter input entries in the form. For the calling parameters whose parameter values are not determined, the corresponding input boxes can be set to be empty, or the corresponding input boxes can also present, for example, “please enter”. It should be noted that although the above examples take the form as an example of the structured content, it should not be understood that the structured content is limited to the form. The structured content here can include various data contents with predetermined data formats.

[0059] In some embodiments, the server 110 can perform a dialogue operation with the terminal device 120 by means of the target model 140 to obtain the parameter values of the at least one calling parameter in response to the configuration information indicating that the clarification mode of the at least one calling parameter is the dialogue mode.

[0060] In some embodiments, the service end 110 provides prompt information generated based on the user input and the at least one calling parameter to the target model 140 to obtain an output of the target model 140. The service end 110 can obtain a clarification question for the at least one calling parameter based on the output of the target model 140. The service end 110 can provide prompt information generated based on the clarification answer to the target model 140 to obtain an output of the target model 140 in response to receiving the clarification answer of the user to the clarification question. Then, the service end 110 can determine the parameter value of the at least one calling parameter based on the output of the target model 140.

[0061] Exemplarily, the service end 110 can send the clarification question to the terminal device 120, and the terminal device 120 can present the clarification question. The user can input the clarification answer to the clarification question through the terminal device 120 or an attached device of the terminal device 120. The terminal device 120 can feed back the clarification answer to the service end 110 in response to receiving the clarification answer. The service end 110 can provide prompt information generated based on the clarification answer to the target model 140 to extract the parameter value of the at least one calling parameter from the clarification answer by the target model. In this way, the generation of the clarification question and the extraction of the parameter value are realized by utilizing the dialogue capability and the parameter extraction capability of the target model, which is beneficial to simplify the processing logic.

[0062] In some embodiments, the service end 110 can obtain a first clarification question for a first calling parameter in the at least one calling parameter based on the output of the target model 140. The service end 110 can provide prompt information based on the first clarification answer to the target model 140 to obtain an output of the target model 140 in response to receiving the first clarification answer of the user to the first clarification question. The parameter value of the first calling parameter is determined based on the output of the target model 140. Here, the first calling parameter can include all or part of the at least one calling parameter.

[0063] To illustrate the triggering of the target function by the session triggering mode, the process of triggering the target function by the session triggering mode will be exemplarily described in combination with Figure 4A The process of triggering the target function by the session triggering mode will be exemplarily described. Figure 4A A flowchart of a signaling flow 400A for a function call according to some embodiments of the present disclosure is shown. The signaling flow 400A involves the terminal device 120, the service end 110, and the target model 140, and the service end 110 includes the target interface 112, the dialogue manager 113, and the function management platform 111. The function management platform 111 can pre-create at least one function.

[0064] As shown in signaling flow 400A, user 130 may input user input to terminal device 120 through terminal device 120 or an attached device of terminal device 120. In response to receiving the user input, terminal device 120 sends (401) the user input to dialogue manager 113. Alternatively or additionally, the user input may include multimodal content such as text, voice, image, video, etc. The dialogue manager 113 receives (402) the user input from terminal device 120. In response to receiving the user input, the dialogue manager 113 determines (403) a target function that matches the user input from at least one pre-created function.

[0065] Regarding how the dialog manager 113 determines the target function that matches the user input, in one example, the dialog manager 113 may generate prompt information based on the user input and the description information of the at least one function, and provide the prompt information to the target model 140 or other models to obtain the output of the target model 140. The dialog manager 113 may determine the function that matches the user input based on the output of the target model 140. Of course, the dialog manager 113 is not limited to using the target model 140 to determine the function that matches the user input. The dialog manager 113 may also determine the function that matches the user input based on, for example, semantic recognition or other methods.

[0066] As shown in signaling flow 400A, the dialog manager 113 may trigger (404) a call to the target function to the function management platform 111. The function management platform 111 may respond (405) to the call to the target function, obtain (406) configuration information, and determine at least one call parameter for the target function based on the configuration information. The function management platform 111 generates prompt information 407 based on the user input and the at least one call parameter. The function management platform 111 may then provide (408) the prompt information 407 to the target model 140 through, for example, a flow manager, a flow engine, and a business engine. In response to receiving (409) the prompt information 407, the target model 140 generates an output 411 of the target model. The target model 140 may feed back (410) the output 411 to the function management platform 111 through, for example, a flow manager, a flow engine, and a business engine. In response to receiving (412) the output 411, the function management platform 111 obtains a clarification question 414 based on the output 411. The function management platform 111 may send ( 415 ) the clarification question 414 to the dialogue manager 113 , and the dialogue manager 113 may send ( 417 ) the clarification question 414 to the terminal device 120 in response to receiving ( 416 ) the clarification question 414 .

[0067] As shown in signaling flow 400A, terminal device 120 can present the clarifying question 414 in response to receiving the clarifying question 414. The user can input a clarifying answer 420 to the clarifying question 414. Terminal device 120 sends (419) the clarifying answer 420 to dialogue manager 113 in response to receiving the clarifying answer 420. Dialogue manager 113 sends (422) the clarifying answer 420 to function management platform 111 in response to receiving (421) the clarifying answer 420. Function management platform 111 generates prompt information 425 based on the clarifying answer 420 in response to receiving (423) the clarifying answer 420. Function management platform 111 provides (425) the prompt information 425 to target model 140, and target model 140 receives (426) the prompt information 425 and generates output 428 based on the prompt information 425. Then, target model 140 can feed back (427) the output 428 to function management platform 111, and function management platform 111 determines (430) the parameter value of the at least one calling parameter in response to receiving (429) the output 428.

[0068] Due to the randomness of the user dialogue, it is possible to obtain all parameter values of the at least one calling parameter based on the first clarifying answer, and it is also possible to obtain part of the parameter values of the at least one calling parameter. On this basis, the server 110 can also determine whether there is a calling parameter with a missing parameter value in the at least one calling parameter. If it is determined that there is a second calling parameter with a missing parameter value in the at least one calling parameter, the server 110 can generate prompt information based on the second calling parameter and provide the prompt information to the target model 140 to obtain the output of the target model 140. Based on the output of the target model 140, a second clarifying question for the second calling parameter is determined. The server 110 can provide prompt information generated based on the second clarifying answer to the target model 140 to obtain the output of the target model 140 in response to receiving the second clarifying answer of the user to the second clarifying question. Then, the parameter value of the second calling parameter is determined based on the output of the target model 140.

[0069] Exemplarily, as shown in FIG. 4B, the server 110 can determine the parameter value of the at least one calling parameter based on the output of the target model 140. The server 110 can determine the parameter value of the at least one calling parameter based on the output of the target model 140 in response to receiving the output of the target model 140. The server 110 can determine the parameter value of the at least one calling parameter based on the output of the target model 140 in response to receiving the output of the target model 140 in response to receiving the output of the target model 140. Figure 4B Figure 4B A flowchart of a signaling flow 400B for a function call according to some embodiments of the present disclosure is shown. The signaling flow 400B involves terminal device 120, server 110, and target model 140, and server 110 includes target interface 112, dialogue manager 113, and function management platform 111. Function management platform 111 can pre-create at least one function. The signaling flow 400B occurs after the signaling flow 400A, and the signaling flow 400A and the signaling flow 400B together constitute a complete signaling flow.

[0070] ​As shown in signaling flow 400B, the function management platform 111 can determine (431) whether there is a call parameter with a missing parameter value in the at least one call parameter. If it is determined that there is a call parameter with a missing parameter value, prompt information 433 can be generated based on the call parameter with the missing parameter value. Afterwards, a process similar to that of boxes 408 to 430 in signaling flow 400A can be performed. Since the process of boxes 408 to 430 has been explained in signaling flow 400A, it will not be elaborated here. Please refer to the aforementioned explanation. In box 455, the function management platform 111 extracts the parameter value again based on the output 453 of the target model 140. Afterwards, the signaling flow 400B can return to box 431 again to determine whether there is a call parameter with a missing parameter value in the at least one call parameter. If it is determined that all parameter values ​​of the at least one call parameter have been obtained, it is determined that the operation of obtaining the parameter value is completed.

[0071] In some embodiments, the target function can also be configured to be triggered using a task trigger mode. If the server 110 receives a call request for the target function from the target interface, the server 110 can determine that the call trigger mode is a task trigger mode in response to the call request, and trigger the call to the target function based on the task trigger mode. The tasks here may include but are not limited to tasks executed by the application, tasks triggered by links, tasks triggered by processing flows, and so on. That is, during the application execution of the task, a call request can be sent to the target interface of the server 110 to trigger the call of the target function. Alternatively, when the link is triggered, a call request can also be sent to the target interface of the server 110. Alternatively, during the execution of the processing flow, the operation of sending a call request to the target interface can be triggered in response to the processing result of the previous processing node. Of course, the above tasks are only exemplary. In actual applications, the task of sending a call request to the target interface can be configured according to actual needs.

[0072] In some embodiments, a call relationship between a task and a target function can be pre-built, and a call to the target function can be triggered based on the call relationship in response to the execution of the task. Figure 5 As shown, Figure 5A schematic diagram of an example 500 of a call relationship construction interface according to some embodiments of the present disclosure is shown. The call relationship construction interface shown in example 500 is used to construct a call relationship between a processing node of a target application (e.g., XXX application) and a target function (e.g., ABCD function). Example 500 includes an application input box 501, an operation input box 502, and a function input box 503. An application identifier (e.g., an application name “XXX application”) of the target application can be input through the application input box 501, a function identifier (e.g., a function name “ABCD function” of the target function) of the target function can be input through the function input box 503, and a call relationship (e.g., a call function) between the target application and the target function can be input through the operation input box 502. In this way, if the processing node corresponding to example 500 is triggered during the execution of the target application, a call request will be sent to the target interface, triggering the call to the target function. Further, example 500 can also include a parameter passing configuration entry 504, which is used to configure the call parameters and parameter values required by the target application to call the target function. The parameter passing configuration entry 504 can include multiple input boxes, such as input boxes for inputting parameter names, types, and parameter values. A user (e.g., a developer) can input the parameter names, types, and the like of the call parameters into the parameter passing configuration entry 504.

[0073] To illustrate the triggering of a target function using a task trigger mode, an example 700 of a signaling flow for a function call according to some embodiments of the present disclosure is shown. Figure 6 An example process of triggering a target function using a task trigger mode is described. Figure 6 A flowchart of a signaling flow 600 for a function call according to some embodiments of the present disclosure is shown, which involves a terminal device 120 and a server 110. The server 110 includes a target interface 112, a session manager 113, and a function management platform 111.

[0074] As shown in signaling flow 600, the terminal device 120 can send (601) a call request for a target function to the target interface 112 of the server 110, and the target interface 112 receives the call request for the target function from the terminal device 120. For example, the terminal device 120 can run a target application, and the terminal device 120 can send a call request for a target function to the target interface in response to the target application triggering a predetermined processing node. Also for example, the terminal device 120 can present an application interface, and the application interface can include a function trigger control. The terminal device 120 can send a call request for a target function to the target interface in response to receiving a trigger operation on the function trigger control.

[0075] As shown in the signaling flow 600, the target interface 112 sends (603) the invocation request to the function management platform 111, and the function management platform 111 receives (604) the invocation request from the target interface. Then, the function management platform 111 can determine (605) the target function corresponding to the invocation request. For example, the function management platform 111 can determine the corresponding target function based on the interface number of the target interface 112. For another example, the invocation request can carry a function identifier (e.g., a number for identifying a function) for identifying the target function, and the function management platform 111 can determine the corresponding target function based on the function identifier.

[0076] As shown in the signaling flow 600, the function management platform 111 can obtain (606) the configuration information of the target function. For example, the function management platform 111 can send an information obtaining request to the data storage unit based on the function identifier, and receive the configuration information of the target function from the data storage unit. The function management platform 111 can determine at least one invocation parameter of the target function based on the configuration information.

[0077] Since the parameter values of the invocation parameters required for the target function to be invoked by the task have been pre-configured, the invocation request sent by the terminal device 120 can have carried the parameter values of the invocation parameters. On this basis, the function management platform 111 can obtain (607) the parameter values of the at least one invocation parameter from the invocation request. If the function management platform 111 cannot obtain all the parameter values of the at least one invocation parameter from the invocation request, the function management platform 111 can send notification information to the terminal device to notify the terminal device 120 of the failure of the target function invocation.

[0078] At block 230, the server 110 invokes the target function based on the parameter values of the at least one invocation parameter. It can be understood that the invocation manner of the function management platform 111 to the target function based on the parameter values of the at least one invocation parameter can not be the same in different cases where the target function has different capabilities, performs different operations, or provides different services.

[0079] For example, in the case where the target function needs to use the capability of the target model 140, the function management platform 111 can generate prompt information based on the at least one invocation parameter, provide the prompt information to the target model 140, and obtain the output of the target model 140. Based on the output of the target model 140, the execution result of the target function is determined.

[0080] For example, the configuration information of the target function can further include an invocation address of the target function. The function management platform 111 can invoke the target function based on the invocation address and the at least one invocation parameter. For example, the function management platform 111 can obtain weather information through an invocation interface.

[0081] In some embodiments, the server 110 may also determine feedback information based on the triggering mode of the target function. Figure 4B As shown, when the trigger mode is the session trigger mode, the function management platform 111 can call (456) the target function and obtain the execution result of the target function. The function management platform 111 can determine a response to the user input based on the execution result of the target function. For example, the function management platform 111 can provide the execution result of the target function to the target model 140 again, and generate a response to the user input through the target model 140. The function management platform 111 can send (457) the response to the dialogue manager 113, and the dialogue manager 113 can send (459) the response to the terminal device 120 in response to receiving (458) the response. The terminal device 120 can present the response in response to receiving (460) the response.

[0082] For example, Figure 6 As shown, when the trigger mode is the task trigger mode, the function management platform can send (609) the execution result of the target function to the target interface 112. In response to receiving (610) the execution result of the target function, the target interface 112 can feedback (611) the execution result to the terminal device 120. After receiving (612) the execution result, the terminal device 120 can present the execution result or trigger another processing node.

[0083] To sum up, according to the embodiments of the present disclosure, by specifying at least one calling parameter required for calling the function in the configuration information, and obtaining the parameter value of the at least one calling parameter according to the trigger mode that specifically triggers the call to the function, the function can support the use requirements of triggering the call using different trigger modes, which is conducive to expanding the application scenarios of the function.

[0084] The embodiments of the present disclosure also provide corresponding devices for implementing the above methods or processes. Figure 7 1 shows a schematic structural block diagram of an apparatus 700 for function invocation according to some embodiments of the present disclosure. The apparatus 700 may be implemented in or included in the server 110. Each module / component in the apparatus 700 may be implemented by hardware, software, firmware, or any combination thereof.

[0085] As shown, the apparatus 700 includes a determining module 710, an obtaining module 720, and a calling module 730. The determining module 710 is configured to determine at least one calling parameter of a target function based on configuration information of the target function in response to triggering a call of the target function. The obtaining module 720 is configured to obtain a parameter value of the at least one calling parameter based on a triggering mode of the call, the triggering mode being one of a plurality of predetermined modes for triggering the call of the target function. The calling module 730 is configured to call the target function based on the parameter value of the at least one calling parameter.

[0086] In some embodiments, the determining module 710 is configured to determine the triggering mode by: determining a function matching the user input from the at least one function in response to receiving the user input; and determining the triggering mode as the conversation triggering mode in response to determining that the target function matches the user input.

[0087] In some embodiments, the obtaining module 720 is further configured to: present a parameter input interface including a parameter value input entry of the at least one calling parameter based on the triggering mode of the call being the conversation triggering mode; and receive the parameter value of the at least one calling parameter through the parameter value input entry.

[0088] In some embodiments, the configuration information indicates that the clarification mode of the at least one calling parameter includes a form, and the configuration information includes structure information of the form; the obtaining module 720 is further configured to: present a parameter input interface including the form based on the structure information of the form, the form including a parameter value input entry of the at least one calling parameter.

[0089] In some embodiments, the obtaining module 720 is further configured to: provide prompt information generated based on the user input and the at least one calling parameter to a target model to obtain an output of the target model; and determine a parameter value of at least part of the at least one calling parameter based on the output of the target model.

[0090] In some embodiments, the obtaining module 720 is further configured to: present structured content for the at least one calling parameter in response to determining that part of the at least one calling parameter lacks a parameter value, the structured content including a parameter value determined based on the output of the target model and a parameter value input entry of the part of the at least one calling parameter; and receive the parameter value of the part of the at least one calling parameter through the parameter value input entry of the part of the at least one calling parameter.

[0091] In some embodiments, the configuration information indicates that the clarification mode of the at least one calling parameter includes a dialogue mode.

[0092] In some embodiments, the obtaining module 720 is further configured to: provide prompt information generated based on the user input and the at least one invocation parameter to the target model to obtain an output of the target model; obtain a clarification question for the at least one invocation parameter based on the output of the target model; in response to receiving a clarification reply of the user to the clarification question, provide prompt information generated based on the clarification reply to the target model to obtain an output of the target model; and determine a parameter value of the at least one invocation parameter based on the output of the target model.

[0093] In some embodiments, the obtaining module 720 is further configured to: obtain a first clarification question for a first invocation parameter in the at least one invocation parameter based on the output of the target model; in response to receiving a first clarification reply of the user to the first clarification question, provide prompt information generated based on the first clarification reply to the target model to obtain an output of the target model; and determine a parameter value of the first invocation parameter based on the output of the target model.

[0094] In some embodiments, the obtaining module 720 is further configured to: in response to determining that a second invocation parameter in the at least one invocation parameter has a missing parameter value, provide prompt information generated based on the second invocation parameter to the target model to obtain an output of the target model; determine a second clarification question for the second invocation parameter based on the output of the target model; in response to receiving a second clarification reply of the user to the second clarification question, provide prompt information generated based on the second clarification reply to the target model to obtain an output of the target model; and determine a parameter value of the second invocation parameter based on the output of the target model.

[0095] In some embodiments, the determining module 710 determines the trigger mode by: receiving a request for invoking the target function from the target interface; and in response to the request for invoking, determining that the trigger mode of the invocation is the task trigger mode.

[0096] In some embodiments, the obtaining module 720 is further configured to: obtain the parameter value of the at least one invocation parameter from the request for invoking.

[0097] In some embodiments, the apparatus 700 further comprises: a presenting module configured to present a configuration interface of the target function in response to a request for configuring the target function; and receive attribute information of the at least one invocation parameter through the configuration interface.

[0098] In some embodiments, the apparatus 700 further comprises: a receiving module configured to receive a selection of a clarification mode of the at least one invocation parameter through the configuration interface, the clarification mode indicating an obtaining manner of the at least one invocation parameter.

[0099] The units and / or modules included in the device 700 can be implemented in various ways, including software, hardware, firmware, or any combination thereof. In some embodiments, one or more units and / or modules can be implemented using software and / or firmware, such as machine executable instructions stored on a storage medium. In addition to or as an alternative to machine executable instructions, some or all of the units and / or modules in the device 700 can be implemented at least in part by one or more hardware logic components. By way of example and not limitation, exemplary types of hardware logic components that can be used include field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chip (SOCs), complex programmable logic devices (CPLDs), and the like.

[0100] Figure 8 8 shows a block diagram of an electronic device 800 in which one or more embodiments of the present disclosure may be implemented. Figure 8 The illustrated electronic device 800 is merely exemplary and should not be construed as limiting the functionality and scope of the embodiments described herein. Figure 8 The electronic device 800 shown may include or be implemented as Figure 1 Server 110, or Figure 7 device 700.

[0101] like Figure 8 As shown, electronic device 800 is in the form of a general electronic device. Components of electronic device 800 may include, but are not limited to, one or more processors or processing units 810, memory 820, storage device 830, one or more communication units 840, one or more input devices 850, and one or more output devices 860. Processing unit 810 may be a real or virtual processor and is capable of performing various processes according to programs stored in memory 820. In a multi-processor system, multiple processing units execute computer-executable instructions in parallel to increase the parallel processing capabilities of electronic device 800.

[0102] The electronic device 800 typically includes a plurality of computer storage media. Such media can be any accessible media that can be obtained by the electronic device 800, including but not limited to volatile and non-volatile media, removable and non-removable media. The memory 820 can be a volatile memory (e.g., registers, cache, random access memory (RAM)), a non-volatile memory (e.g., read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. The storage device 830 can be a removable or non-removable medium and can include a machine-readable medium, such as a flash drive, a disk, or any other medium that can be used to store information and / or data and can be accessed within the electronic device 800.

[0103] The electronic device 800 may further include additional removable / non-removable, volatile / non-volatile storage media. Figure 8 As shown in FIG, a magnetic disk drive for reading from or writing to a removable, non-volatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, non-volatile optical disk may be provided. In these cases, each drive may be connected to a bus (not shown) by one or more data media interfaces. The memory 820 may include a computer program product 825 having one or more program modules configured to perform the various methods or actions of various embodiments of the present disclosure.

[0104] The communication unit 840 enables communication with other electronic devices via a communication medium. Additionally, the functions of the components of the electronic device 800 can be implemented in a single computing cluster or multiple computing machines that can communicate via a communication connection. Thus, the electronic device 800 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.

[0105] The input device 850 may be one or more input devices, such as a mouse, keyboard, or trackball. The output device 860 may be one or more output devices, such as a display, a speaker, or a printer. The electronic device 800 may also communicate with one or more external devices (not shown) via the communication unit 840 as needed, such as a storage device, a display device, or the like, with one or more devices that allow a user to interact with the electronic device 800, or with any device that allows the electronic device 800 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).

[0106] 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.

[0107] Various aspects of the present disclosure are described herein with reference to flowcharts and / or block diagrams of methods, apparatuses, devices, and computer program products implemented according to the present disclosure. It should be understood that each block of the flowcharts and / or block diagrams, and combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer-readable program instructions.

[0108] 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, such that when these instructions are executed by the processing unit of the computer or other programmable data processing device, a device is generated that implements the functions / actions specified in one or more blocks in the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium, where these instructions cause the computer, programmable data processing device, and / or other device to operate in a specific manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing various aspects of the functions / actions specified in one or more blocks in the flowchart and / or block diagram.

[0109] 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, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0110] The flow charts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the systems, methods and computer program products according to multiple implementations of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a part for a module, program segment or instruction, and a part for a module, program segment or instruction comprises one or more executable instructions for realizing the logical function of the specification. In some alternative implementations, the functions marked in the box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the 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.

[0111] While various implementations of the present disclosure have been described above, the foregoing description is intended to be illustrative, not exhaustive, and not limited to the disclosed implementations. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described implementations. The terminology used herein is selected to best explain the principles of the implementations, their practical applications, or improvements to existing technologies, or to enable others skilled in the art to understand the various implementations disclosed herein.

Claims

1. A method for function calling, comprising: In response to triggering a call to a target function, determining at least one call parameter of the target function based on configuration information of the target function, the target function being configured to support triggering through a plurality of predetermined modes, the plurality of predetermined modes having respective corresponding parameter value acquisition methods, the plurality of predetermined modes including at least a session triggering mode and a task triggering mode; Determining a trigger mode for the call, where the trigger mode is a predetermined mode among the plurality of predetermined modes that triggers the call of the target function; Acquire a parameter value of the at least one calling parameter based on an acquisition method corresponding to the trigger mode of the call; as well as Invoking the target function based on a parameter value of the at least one invocation parameter; Wherein, determining the trigger mode of the call includes: Based on receiving user input and determining that at least one pre-created function has the target function that matches the user input, determining that the trigger mode is the session trigger mode; Based on receiving a call request for the target function from a target interface, determining that the trigger mode of the call is the task trigger mode.

2. The method according to claim 1, wherein obtaining the parameter value of the at least one calling parameter comprises: Based on the trigger mode of the call being the session trigger mode, presenting a parameter input interface, the parameter input interface including a parameter value input entry for the at least one call parameter; as well as The parameter value of the at least one calling parameter is received through the parameter value input entry.

3. The method according to claim 2, wherein the configuration information indicates that the clarification mode of the at least one call parameter includes a form, and the configuration information includes structural information of the form; and The parameter input interface includes: Based on the structural information of the form, a parameter input interface including the form is presented, where the form includes a parameter value input entry for the at least one calling parameter.

4. The method according to claim 1, wherein obtaining the parameter value of the at least one calling parameter comprises: providing prompt information generated based on the user input and the at least one calling parameter to a target model to obtain an output of the target model; as well as The parameter values ​​of at least part of the at least one call parameter are determined based on an output of the target model.

5. The method according to claim 4, wherein obtaining the parameter value of the at least one calling parameter further comprises: In response to determining that some of the at least one call parameter lack parameter values, presenting structured content for the at least one call parameter, the structured content including the parameter value determined based on the output of the target model and parameter value input entries for the some of the call parameters; as well as The parameter values ​​of the part of the calling parameters are received through the parameter value input entrance of the part of the calling parameters. The method of claim 1 , wherein the configuration information indicates that the clarification mode of the at least one call parameter comprises a dialog mode.

7. The method according to claim 6, wherein obtaining the parameter value of the at least one calling parameter comprises: providing prompt information generated based on the user input and the at least one calling parameter to a target model to obtain an output of the target model; obtaining a clarification question for the at least one call parameter based on an output of the target model; In response to receiving a clarification answer from the user to the clarification question, providing prompt information generated based on the clarification answer to the target model to obtain an output of the target model; as well as A parameter value of the at least one call parameter is determined based on an output of the target model.

8. The method of claim 7, wherein obtaining a clarification question regarding the at least one call parameter comprises: obtaining a first clarification question for a first calling parameter of the at least one calling parameter based on an output of the target model; and Determining the parameter value of the at least one calling parameter includes: In response to receiving a first clarification answer from the user to the first clarification question, providing prompt information generated based on the first clarification answer to the target model to obtain an output of the target model; as well as Based on the output of the target model, a parameter value of the first calling parameter is determined.

9. The method according to claim 8, wherein obtaining a clarification question for the at least one call parameter further comprises: In response to determining that a second calling parameter in the at least one calling parameter has a missing parameter value, providing prompt information generated based on the second calling parameter to the target model to obtain an output of the target model; determining a second clarification question for the second call parameter based on an output of the target model; In response to receiving a second clarification answer from the user to the second clarification question, providing prompt information generated based on the second clarification answer to the target model to obtain an output of the target model; as well as Based on the output of the target model, a parameter value of the second calling parameter is determined.

10. The method according to claim 1, wherein obtaining the parameter value of the at least one calling parameter comprises: Obtain a parameter value of the at least one calling parameter from the calling request.

11. The method according to claim 1 , further comprising: In response to a configuration request for the target function, presenting a configuration interface for the target function; as well as Receive attribute information of the at least one calling parameter through the configuration interface.

12. The method according to claim 11, further comprising: A selection of a clarification mode for the at least one call parameter is received through the configuration interface, where the clarification mode indicates a method for obtaining the at least one call parameter.

13. A device for function calling, comprising: a determination module configured to, in response to triggering a call to a target function, determine at least one call parameter of the target function based on configuration information of the target function, wherein the target function is configured to support triggering through multiple predetermined modes, and the multiple predetermined modes have respective corresponding parameter value acquisition methods; Determining a trigger mode for the call, where the trigger mode is a predetermined mode among the multiple predetermined modes that triggers the target function, and the multiple predetermined modes include at least a session trigger mode and a task trigger mode; an acquisition module configured to acquire a parameter value of the at least one calling parameter based on an acquisition method corresponding to the trigger mode of the call; as well as a calling module configured to call the target function based on a parameter value of the at least one calling parameter; The determining module is further configured to: Based on receiving user input and determining that at least one pre-created function has the target function that matches the user input, determining that the trigger mode is the session trigger mode; Based on receiving a call request for the target function from a target interface, determining that the trigger mode of the call is the task trigger mode.

14. An electronic device comprising: at least one processing unit; as well as At least one memory coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions causing the electronic device to perform the method according to any one of claims 1 to 12 when executed by the at least one processing unit.

15. A computer-readable storage medium having a computer program stored thereon, wherein the computer program can be executed by a processor to implement the method according to any one of claims 1 to 12.

16. A computer program product comprising a computer program, wherein the computer program implements the method according to any one of claims 1 to 12 when executed by a processor.

Images