Prompt word editing method and device, equipment, storage medium and program product

Abstract

The embodiment of the invention provides a prompt word editing method and device, equipment, a storage medium and a program product. At a client, the method comprises the following steps: in response to a task request sent to server-side equipment, receiving a task execution instruction corresponding to the task request from the server-side equipment for execution; receiving prediction information for the task request from the server-side equipment, wherein the prediction information indicates at least one prediction execution result of the task execution instruction and a prediction response corresponding to the at least one prediction execution result; and after execution of the task execution instruction is completed, providing a response to the task request based on matching between a target execution result of the task execution instruction and the at least one predicted execution result. Therefore, the prompt word editing efficiency can be improved.

Description

Technical Field

[0001] The exemplary embodiments disclosed herein generally relate to the field of computers, and particularly to methods, apparatuses, electronic devices, computer-readable storage media, and computer program products for editing prompt words. Background Technology

[0002] With the development of information technology, various terminal devices can provide people with a variety of services in work and life. For example, terminal devices can be equipped with applications that provide different services, as well as digital assistants. Digital assistants are provided to assist users in handling various tasks in different applications and scenarios. Digital assistants typically have intelligent dialogue and task processing capabilities. Generally, digital assistants can support users to input questions in natural language and perform tasks and provide responses based on their understanding of natural language input and logical reasoning abilities. Summary of the Invention

[0003] In a first aspect of this disclosure, a method for editing prompt words is provided. The method is implemented at a client device and includes: in response to sending a task request to a server device, receiving from the server device a task execution instruction corresponding to the task request for execution; receiving from the server device prediction information for the task request, the prediction information indicating at least one predicted execution result of the task execution instruction and a prediction response corresponding to each of the at least one predicted execution result; and after the execution of the task execution instruction is completed, providing a response to the task request based on the matching between the target execution result of the task execution instruction and the at least one predicted execution result.

[0004] In a second aspect of this disclosure, an apparatus for prompt word editing is provided. The apparatus is implemented at a client device and includes: a task request sending module configured to receive, in response to sending a task request to a server device, a task execution instruction corresponding to the task request from the server device for execution; a prediction information receiving module configured to receive prediction information for the task request from the server device, the prediction information indicating at least one predicted execution result of the task execution instruction and a prediction response corresponding to each of the at least one predicted execution result; and a response providing module configured to provide a response to the task request after the execution of the task execution instruction is completed, based on the matching between the target execution result of the task execution instruction and at least one predicted execution result.

[0005] In a third aspect of this 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 this disclosure, a computer-readable storage medium is provided. The medium stores a computer program that, when executed by a processor, implements the method of the first aspect.

[0007] In a fifth aspect of this disclosure, a computer program product is provided. The product includes a computer program, wherein when executed by a processor, the computer program implements the method according to a first aspect of this disclosure.

[0008] It should be understood that the content described in this content section is not intended to limit the key or essential features of the embodiments of this disclosure, nor is it intended to restrict the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0009] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. In the drawings, the same or similar reference numerals denote the same or similar elements, wherein:

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

[0011] Figure 2A and Figure 2B Example interfaces according to some embodiments of this disclosure are shown;

[0012] Figures 3A to 3E An example of an editing interface for creating prompt words for a prompt word library, according to some embodiments of the present disclosure, is shown;

[0013] Figure 4A and Figure 4B An example of a configuration area for receiving prompt words is shown according to some embodiments of the present disclosure;

[0014] Figures 5A to 5D Examples of editing interfaces for target functions according to some embodiments of this disclosure are shown;

[0015] Figure 6A Examples of highlighting certain prompts in an editing interface according to some embodiments of the present disclosure are shown;

[0016] Figures 6B to 6H Example interfaces related to the creation and application of prompt words in a prompt word library according to other embodiments of this disclosure are shown;

[0017] Figures 7A to 7E A schematic diagram of an example interface for a comment function on prompt words according to some embodiments of the present disclosure is shown;

[0018] Figure 8 A flowchart of a method for editing prompt words according to some embodiments of the present disclosure is shown;

[0019] Figure 9 A schematic structural block diagram of an apparatus for prompt word editing according to some embodiments of the present disclosure is shown; and

[0020] Figure 10 A block diagram of an electronic device in which one or more embodiments of the present disclosure may be implemented is shown. Detailed Implementation

[0021] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0022] In the description of embodiments of this disclosure, the term "comprising" and similar terms should be understood as open-ended inclusion, i.e., "including but not limited to". The term "based on" should be understood as "at least partially based 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.

[0023] In this document, unless explicitly stated otherwise, performing a step in response to A does not mean that the step is performed immediately after A, but may include one or more intermediate steps.

[0024] It is understood 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 related provisions.

[0025] It is understood that before using the technical solutions disclosed in the various embodiments of this disclosure, relevant users should be informed of the type, scope of use, and usage scenarios of the information involved in this disclosure through appropriate means in accordance with relevant laws and regulations, and authorization should be obtained from the relevant users. Among them, relevant users may include any type of rights holder, such as individuals, enterprises, and groups.

[0026] For example, in response to receiving an active request from a user, a prompt message is sent to the relevant user to clearly inform the user that the requested operation will require obtaining and using the user's information, thereby enabling the relevant user to choose whether to provide information to the software or hardware such as the electronic device, application, server, or storage medium that performs the operation of the technical solution disclosed herein based on the prompt message.

[0027] As an optional but non-restrictive implementation, in response to a user's active request, a prompt message can be sent to the user, such as a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose "agree" or "disagree" to provide information to the electronic device.

[0028] It is understood that the above notification and user authorization process are merely illustrative and do not constitute a limitation on the implementation of this disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of this disclosure.

[0029] As used in this paper, the term "model" refers to a model that learns the relationship between inputs and outputs from training data, enabling it to generate corresponding outputs for a given input after training. Model generation can be based on machine learning techniques. Deep learning is a machine learning algorithm that processes inputs and provides corresponding outputs using multiple layers of processing units. A neural network model is an example of a deep learning-based model. In this paper, "model" may also be referred to as a "machine learning model," "learning model," "machine learning network," or "learning network," and these terms are used interchangeably.

[0030] Digital assistants can serve as effective tools for people's work, study, and daily life. Typically, the development of digital assistants is similar to that of general applications, requiring developers with programming skills to define the various capabilities of the digital assistant by writing complex code, and then deploying the digital assistant on an appropriate operating platform so that users can download, install, and use it.

[0031] With the diversification of application scenarios and the increasing availability of machine learning technology, there is a growing demand for developing more digital assistants with different capabilities to support task processing in various niche areas or to meet the personalized needs of different users. Users can create different prompts and provide them to machine learning models to determine the appropriate digital assistant. Users can also adjust the digital assistant by modifying the prompts. Traditionally, to achieve prompt sharing among multiple users, the user who created the prompt often needs to copy their own prompt and then send the copied prompt to other users. This affects the efficiency of prompt sharing among multiple users and the efficiency of other users editing the prompt.

[0032] According to embodiments of this disclosure, an improved scheme for editing prompt words is provided. According to this scheme, an editing interface for editing prompt words is presented, wherein the edited prompt words are input into a machine learning model for the model to determine its output. In response to triggering an edit block function, an edit block is configured at a selected location in the editing interface, wherein content can be filled into the edit block and the filled content is editable. In response to confirmation of the editing of the prompt words, the content filled into the edit block is determined as part of the prompt words.

[0033] Therefore, editable blocks can be configured within the prompts, allowing content to be filled in and edited. This enables users to easily fill in and modify the content within the edit blocks to obtain the desired prompts. This helps improve the efficiency of prompt editing.

[0034] Figure 1 A schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented is shown. Environment 100 relates to an assistant creation platform 110 and an assistant application platform 130.

[0035] like Figure 1 As shown, the assistant creation platform 110 can provide users 105 with an environment for creating and publishing digital assistants. In some embodiments, the assistant creation platform 110 can be a low-code platform that provides a suite of tools for creating digital assistants. The assistant creation platform 110 can support visual development of digital assistants, allowing developers to skip the manual coding process and accelerate application development cycles and reduce costs. The assistant creation platform 110 can support any suitable platform for users to develop digital assistants and other types of applications, such as platforms based on Application Platform as a Service (aPaaS). Such platforms enable users to efficiently develop applications, enabling operations such as application creation and application function adjustments.

[0036] The assistant creation platform 110 can be deployed locally on the user 105's terminal device and / or supported by a remote server. For example, the user 105's terminal device can run a client of the assistant creation platform 110, which can support interaction between the user and the assistant creation platform 110. When the assistant creation platform 110 runs locally on the user's terminal device, the user 105 can directly interact with the local assistant creation platform 110 using the client. When the assistant creation platform 110 runs on a server device, the server device can provide services to the client running on the terminal device based on the communication connection with the terminal device. The assistant creation platform 110 can present a corresponding interface 122 to the user 105 based on the user 105's operations, to output and / or receive information from the user 105.

[0037] In some embodiments, the assistant creation platform 110 can be associated with a corresponding database, which stores the data or information required for the digital assistant creation process supported by the assistant creation platform 110. For example, the database can store the code and description information corresponding to the various functional modules that make up the digital assistant. The assistant creation platform 110 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. For example, in a scenario where a digital assistant needs to be created, the assistant creation platform 110 can call the corresponding functional blocks from the database to build the digital assistant. These modules may include, but are not limited to, plugins for implementing specific functions, workflows (workflows may consist of a series of workflow nodes with sequential execution order and dependencies), knowledge bases, etc.

[0038] In embodiments of this disclosure, user 105 can create and publish a digital assistant 120 on assistant creation platform 110 as needed. Digital assistant 120 can be published to any suitable assistant application platform 130, as long as the assistant application platform 130 supports the operation of digital assistant 120. After publication, digital assistant 120 can be used for conversational interaction with user 135. The client of assistant application platform 130 can present an interaction window 132 of digital assistant 120, such as a conversation window, in the client interface. Digital assistant 120, as an intelligent assistant, has intelligent dialogue and information processing capabilities. User 135 can input conversational messages in the conversation window, and digital assistant 120 can determine the reply message based on the created configuration information and present it to the user in interaction window 132. In some embodiments, depending on the configuration of digital assistant 120, interaction messages with digital assistant 120 can include multimodal messages, such as text messages (e.g., natural language text), voice messages, image messages, video messages, etc.

[0039] The assistant creation platform 110 and / or assistant application platform 130 can run on suitable electronic devices. These electronic devices can be any type of computing-capable device, including terminal devices or server devices. Terminal devices 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 system (PCS) devices, personal navigation devices, personal digital assistants (PDAs), audio / video players, digital cameras / camcorders, positioning devices, television receivers, radio receivers, e-book devices, gaming devices, or any combination of the foregoing, including accessories and peripherals of these devices or any combination thereof. Server devices can include, for example, computing systems / servers, such as mainframes, edge computing nodes, computing devices in cloud environments, and so on. In some embodiments, the assistant creation platform 110 and / or assistant application platform 130 can be implemented based on cloud services.

[0040] It should be understood that the structure and function of environment 100 are described for illustrative purposes only and do not imply any limitation on the scope of this disclosure. For example, although Figure 1 The illustration shows a single user interacting with the assistant creation platform 110 and a single user interacting with the assistant application platform 130, but in reality, multiple users can access the assistant creation platform 110 to create their own digital assistants, and each digital assistant can be used to interact with multiple users.

[0041] The following description will detail some exemplary embodiments of this disclosure with reference to the accompanying drawings. It should be understood that the pages / interfaces shown in the drawings are merely examples, and various page designs / interfaces may actually exist. The various graphic elements in the page / interface may have different arrangements and different visual representations, one or more elements may be omitted or replaced, and one or more other elements may also be present. The embodiments of this disclosure are not limited in this respect.

[0042] The prompt word editing process described in the embodiments of this disclosure can be implemented on an assistant creation platform, a terminal device with the assistant creation platform installed, and / or a server corresponding to the assistant creation platform. In the examples below, for the sake of discussion, the description is from the perspective of the assistant creation platform, for example... Figure 1 The assistant creation platform 110 is shown. The interface presented by the assistant creation platform 110 can be displayed via the terminal device of user 105, and user input can be received via the terminal device of user 105. In this document, the user 105 who creates the digital assistant is sometimes also referred to as the assistant creator, assistant developer, etc.

[0043] In some embodiments, the assistant creation platform 110 may also provide a resource library interface for digital assistants. For example... Figure 2A Example 200A, as shown, illustrates an example of a resource library interface. Example 200A includes a resource selection control 210. The assistant creation platform 110 can, in response to a trigger on the resource selection control 210, present a resource list. The resource list includes at least one option corresponding to at least one resource. The at least one resource includes at least one prompt word, and the at least one option includes at least one option corresponding to the prompt word. It is understood that the at least one resource may also include other resources, such as workflows, image streams, plugins, knowledge bases, message cards, etc. The assistant creation platform 110 can, in response to receiving a selection of the option corresponding to the prompt word, determine the resource creation request that received the prompt word and present, as shown... Figure 2B Example 200B is shown. Example 200B includes a prompt word editing interface 220.

[0044] Interface 220 includes a region 222 for editing the prompt name, a region 224 for editing the prompt description, and a region 226 for editing the prompt content. The prompt description may, for example, describe the scenarios in which the prompt can be used, such as whether it is suitable for a role-playing digital assistant or a productivity tool digital assistant. The prompt description may also additionally or alternatively describe the functions that the prompt can perform. For example, the description may indicate that a machine learning model can call certain plugins, workflows, databases, knowledge bases, etc., based on the prompt. However, this is merely exemplary and is not intended to limit the scope of the disclosure. The prompt content may include the full text of the prompt. Interface 220 may also include a confirmation control 228, which the assistant creation platform 110 can use to edit the prompt based on the content in regions 222, 224, and 226 in response to receiving a trigger on the confirmation control 228.

[0045] Edited prompts may include, for example, system prompts. In some examples, for a machine learning-based digital assistant interacting with user A, if the assistant receives input from user A, it can determine the prompt to be input to the machine learning model associated with the digital assistant based on user A's input and the system prompt. The machine learning model can then determine its output based on the input prompt, which will be used to determine a response to user A.

[0046] Edited prompts will be stored in the prompt library. This prompt library can be a user's personal prompt library or a prompt library created by multiple users (e.g., a team prompt library). If the prompt library is a team prompt library, the prompts in the prompt library can be created by any user in the team, and each user in the team can use prompts created by other users in the team and stored in the prompt library.

[0047] In some embodiments, permission to apply, edit, or delete at least one of the prompts in the prompt library is based on the user's role. It is understood that, depending on the user's role, prompts in the prompt library can be copied or directly used in a digital assistant or workflow node. Correspondingly, depending on the user's role, prompts in the prompt library can also be edited, deleted, etc. For example, the creator of the prompt (e.g., user 105) can edit, delete, etc., prompts in the prompt library. Other users belonging to the same organization / team / workspace as user 105 can access, apply, and copy prompts in the prompt library. In some embodiments, the creator of the prompt can configure which users have the ability to access, apply, and / or copy the prompt, or the ability of users to access, apply, and / or copy individual prompts can be configured based on a default policy. The following describes in more detail how prompts are added to the prompt library and how prompts in the prompt library are applied.

[0048] It should be noted that, in addition to the editing interface 220 described above, the assistant creation platform 110 may also provide other areas or interfaces that can be used to edit prompts. For example, the assistant creation platform 110 may also provide an editing interface / area for prompts in workflow nodes, a configuration area in the user interface for creating the digital assistant 120 for receiving prompts input in natural language, and so on. This disclosure does not limit the area or interface used for editing prompts, nor does it limit the specific way in which such area or interface is presented.

[0049] The editing interface 220 here can be viewed as an editing interface for creating prompts for the prompt word library. The configuration area for receiving prompts in the user interface for creating the digital assistant 120, as well as the editing interface / area for prompts in workflow nodes, can all be viewed as editing interfaces for the target function. The target function may include the digital assistant or workflow nodes, and the target function runs based on a machine learning model (e.g., a target machine learning model). The editing interface for the target function may, for example, include the user interface for creating the digital assistant 120.

[0050] When creating a digital assistant, the digital assistant's responses to the user are generated based on a machine learning model specified by the creator. During workflow editing, one or more workflow nodes can be selected as machine learning model-based workflow nodes, configured to utilize the machine learning model to process the workflow node's inputs to obtain the workflow node's output. It should be understood that other types of machine learning model-based functions may exist besides digital assistants or workflow nodes. The embodiments of this disclosure also apply to those functions. According to some embodiments of this disclosure, the assistant creation platform 110 can, in response to confirmation of the creation of a target function, confirm the content filled in the edit block as part of a prompt for the machine learning model.

[0051] In some embodiments, prompts may include a defined persona, describing the role or responsibilities of the digital assistant, its response style, etc., guiding the machine learning model to process the input according to the defined persona. Prompts may also include functions and workflows, such as describing the functions and workflows of the digital assistant and specifying how the digital assistant should answer user questions in different scenarios. This guides the machine learning model to process the input according to the functions and workflows. Prompts may also include constraints and limitations, restricting the scope of the digital assistant's responses, such as defining what the digital assistant should and should not answer. Additionally, prompts may include specifying a response format for the digital assistant, so that the digital assistant responds to user input according to that format.

[0052] In some embodiments, the prompt words may indicate the definition of the response style of the digital assistant to be created. By setting the response style, the responses of the created digital assistant can be differentiated and able to reveal a specific personality to the user. Alternatively or additionally, in some embodiments, the prompt words may indicate a description of the functionality supported by the digital assistant to be created. Alternatively or additionally, in some embodiments, the prompt words may indicate at least one response format of the digital assistant to be created. The response format may, for example, include Markdown (a lightweight markup language).

[0053] In some embodiments, alternatively or additionally, the prompts may also indicate at least one workflow to be executed by the digital assistant 120 to be created. Each workflow may correspond to various operations performed by the digital assistant 120 when performing a specific function. That is, the user 105 may be allowed to describe in natural language how the digital assistant 120 should perform a certain function. Understandably, functions based on machine learning models (e.g., workflow nodes in the digital assistant or workflow) can be enhanced with their inherent features. For example, the digital assistant or workflow node may have the ability to call plugins, knowledge bases, databases, triggers, workflows, etc. Accordingly, the use cases and descriptions of these functions can be explained in the prompts corresponding to the digital assistant or workflow node.

[0054] It should be understood that users can actually freely try different prompts to create a digital assistant that meets their expectations in terms of response. For example, in the prompts, users 105 can input requirements for the language of the response to the digital assistant 120, as well as constraints on the content of the response from the digital assistant 120 (e.g., the number of characters for different types of responses, the type of response content, etc.).

[0055] The machine learning model can run locally on the assistant creation platform 110 or on a remote server. In some embodiments, the machine learning model can be based on a language model (LM). Language models, by learning from large corpora, are capable of question-and-answering. The machine learning model can also be based on other suitable models. During the function creation process, a specific configuration area is provided for users to provide prompts, and the configuration of prompts can be done using natural language. This allows users to easily constrain the model's output and configure diverse digital assistants. In some embodiments, the machine learning model can also be based on any suitable model architecture, including but not limited to Transformer models, convolutional neural networks (CNNs), recurrent neural networks (RNNs), deep neural networks (DNNs), and so on.

[0056] In embodiments of this disclosure, the assistant creation platform 110 can present an editing interface for editing prompts. As mentioned above, the edited prompts are input into a machine learning model to determine the model output, and the digital assistant determines a response for the user based on this model output. The assistant creation platform 110 can configure an editing block at a selected location in the editing interface in response to a triggering of the edit block function. Content can be filled into the editing block, and the filled content is editable. Specifically, the editing block can be configured within the prompt content. One or more editing blocks can be configured within the prompt as needed. Configuring editing blocks allows the prompts to exhibit a structured characteristic, making them easier for developer users to understand and share among multiple developer users. In some embodiments, only the content within the editing blocks of the prompt can be edited, while the content outside the editing blocks is not editable. In other embodiments, both the content within the editing blocks and the content outside the editing blocks of the prompt can be edited, and the editing methods for both can be the same or different.

[0057] If a prompt contains an edit block, the user can create new prompt content within the provided edit block when the prompt is reused or edited. During the editing of a digital assistant or workflow node, the user can edit the prompt content corresponding to that digital assistant or workflow node within the edit block. In some embodiments, where an edit block exists for a prompt resource, the user 105 can edit the content contained in the prompt. Alternatively, the user can edit the content contained in the edit block within the prompt. In some examples, the content contained in the edit block can be provided to the user (e.g., a developer) using the prompt resource in the form of a form to be filled out.

[0058] The assistant creation platform 110 can detect the triggering of the edit block function in any suitable manner. In some embodiments, the assistant creation platform 110 can determine that a triggering of the edit block function has been detected in response to the detection of a selection of a predetermined control. The predetermined control here can be, for example, an add control or edit control for the edit block in the editing interface. Alternatively or additionally, in some embodiments, the assistant creation platform 110 can also determine that a triggering of the edit block function has been detected in response to the detection of input of a predetermined symbol in the editing interface. The predetermined symbol here can be any suitable symbol, and this disclosure does not limit the specific symbol. Alternatively or additionally, in some embodiments, the assistant creation platform 110 can be deployed on any suitable electronic device, which may include physical controls. The assistant creation platform 110 can determine that a triggering of the edit block function has been detected in response to receiving a trigger of an indication physical control (e.g., a shortcut key). It is understood that the assistant creation platform 110 can also detect the triggering of the edit block function in response to receiving any other means such as a right-click or hover operation, and this disclosure does not limit the specific means.

[0059] In some embodiments, to facilitate intuitive user identification of edit blocks, the assistant creation platform 110 can present edit blocks or their content, as well as non-edit block content in prompts, using different visual styles. (See reference) Figure 3A , Figure 3A Example 300 of an editing interface for creating prompts for a prompt word library, according to some embodiments of the present disclosure, is shown. Example 300 includes a region 310 for editing prompt word content, which can display the prompt word content. It should be noted that this example description only assumes that the prompt words (including editable and non-editable blocks) consist only of text. In actual applications, prompt words can include any suitable type of content such as images and code. Different content can correspond to different types of editable blocks. For example, text content can correspond to a text editable block, image content can correspond to an image editable block, application programming interface (API) descriptions can correspond to an API editable block, and so on. The triggering methods, creation methods, etc., of different types of editable blocks can be the same or different.

[0060] Specifically, area 310 can display content with at least one editable block (e.g., editable blocks 311, 312, 313, 314, and 315) and non-editable blocks (e.g., the text "You will play a task role," the text "The following are detailed settings for this role; please construct your answer based on this information," the text "Basic task information," the text "Role background and context," etc., as shown in the figure). The assistant creation platform 110 can display the non-editable block content in a regular text visual style, and can display the editable blocks in visual styles such as bolding, italics, using different colors, different fonts, and / or adding borders. It is understood that the visual styles of the editable blocks shown in the figure are merely examples, and the visual styles to be used can be selected according to actual needs.

[0061] In some embodiments, the assistant creation platform 110 may, in response to detecting a triggering of the text editing block function when at least a portion of the prompt word's text is not selected, insert a text editing block (which may, for example, be referred to as a second text editing block) at the input cursor position in the editing interface. Continue to refer to Figure 3A The assistant creation platform 110 can display an input cursor 320 and an add control 301 for text editing blocks in area 310. If no selection of at least part of the text of the prompt word is received, the assistant creation platform 110 can determine that a trigger for the text editing block function has been detected in response to receiving a trigger for the add control 301. The assistant creation platform 110 can display... Figure 3B The editing interface shown.

[0062] exist Figure 3B In this configuration, the assistant creation platform 110 can display the inserted text editing block 330 at the input cursor 320. In some embodiments, the assistant creation platform 110 can also display fill guide text associated with the text editing block 330 (e.g., the text "Please enter the prompt text when the editing block content is empty" shown in the figure).

[0063] In some embodiments, the assistant creation platform 110 may also present a text input interface 340 for the text editing block 330 in association with the text editing block 330. The text input interface 340 includes at least one of an input area 342 (which may be referred to, for example, as a second input area corresponding to the second text editing block) and an input area 344 (which may be referred to, for example, as a first input area corresponding to the second text editing block).

[0064] In some embodiments, the assistant creation platform 110 may also provide fill guide text in a given text editing block in response to receiving fill guide text for that text editing block in input area 342, when no fill text is provided in the given text editing block. In some embodiments, the assistant creation platform 110 may replace the fill text in a given text editing block with specified text in response to receiving specified text in input area 344. That is, if no specified text input by the user is received via input area 344, the assistant creation platform 110 may present the guide text in input area 342 in text editing block 330; if specified text input by the user is received via input area 344, the assistant creation platform 110 preferentially presents the specified text in text editing block 330.

[0065] In some embodiments, when a text input interface 340 is presented in association with the text editing block 330, it can be determined that the text editing block 330 is in a text editing state; when the text input interface 340 is not presented, it can be determined that the text editing block 330 is not in a text editing state. The assistant creation platform 110 can present the text editing block 330 in a text editing state and the text editing block 330 not in a text editing state in different visual styles. As an example, also refer to... Figure 3C The assistant can create platform 110. Figure 3B Neutralization Figure 3C The text editing block 330 is presented in different visual styles.

[0066] In some embodiments, the assistant creation platform 110 may also, in response to detecting a triggering of the text editing block function when at least a portion of the text of the prompt word is selected, configure a text editing block (which may be referred to as a first text editing block, for example) based on at least a portion of the text at the location of the selected at least a portion of the text, wherein the text editing block may be filled with at least a portion of the text.

[0067] refer to Figure 3D In some embodiments of the editing interface shown, the assistant creation platform 110 may directly present a window 360 including at least one operation control in response to the selection of the text "This Role" (a non-editable block in the prompt). In other embodiments, 110 may present a window 360 including at least one operation control in response to the selection of the text "This Role" (a non-editable block in the prompt) and receipt of a trigger operation (e.g., a right-click operation) for the text "This Role". At least one control in window 360 includes at least an editing control 362. The assistant creation platform 110 may configure a text editing block 350 based on the text "This Role" in response to the triggering of the editing control 362. The text editing block 350 is filled with the text "This Role".

[0068] In some embodiments, the assistant creation platform 110 may also present a text input interface 370 for the text editing block 350 in association with the text editing block 350. The text input interface 370 includes at least one of an input area 372 (which may be referred to, for example, as a second input area corresponding to the first text editing block) and an input area 374 (which may be referred to, for example, as a first input area corresponding to the first text editing block).

[0069] Similarly, the assistant creation platform 110 can also respond to receiving fill guide text for a given text editing block in input area 372, where the fill guide text is displayed when no text is filled in the given text editing block. The assistant creation platform 110 can also respond to receiving specified text in input area 374, replacing the already filled text in the given text editing block with the specified text. That is, the assistant creation platform 110 can respond to receiving specified text in input area 374, replacing the text "this role" in the given text editing block with the specified text.

[0070] Similarly, if no specified text is received from the user via the input area 374, the assistant creation platform 110 may present the guiding text in the input area 372 in the text editing block 350. If the specified text is received from the user via the input area 374, the assistant creation platform 110 will prioritize presenting the specified text in the text editing block 350.

[0071] Similarly, when the text input interface 370 is presented in association with the text editing block 350, it can be determined that the text editing block 350 is in a text editing state; when the text input interface 370 is not presented, it can be determined that the text editing block 350 is not in a text editing state. The assistant creation platform 110 can present the text editing block 350 in a text editing state and the text editing block 350 not in a text editing state with different visual styles. As an example, see also... Figure 3E The assistant can create platform 110. Figure 3D Neutralization Figure 3E The text editing block 350 is presented in different visual styles.

[0072] The assistant creation platform 110 can, in response to confirmation of editing of the prompt word, determine the content filled in the edit block as part of the prompt word. For example, refer to Figures 3A to 3E The example 300 shown may include a confirmation control for the prompt word. The assistant creation platform 110, for example, can respond to receiving a trigger on the confirmation control, determine that confirmation of editing the prompt word has been received, and then determine that the content filled in the edit block is part of the prompt word.

[0073] refer to Figure 4A and Figure 4B , Figure 4A and Figure 4B Example 400 of a configuration area for receiving prompt words according to some embodiments of the present disclosure is shown. This configuration area can be a configuration area in a user interface for creating a digital assistant 120 for receiving prompt words input in natural language. The prompt words are presented in area 410 of example 400. The assistant creation platform 110 can also, in response to detecting a triggering of a text editing block function when at least a portion of the text of the prompt word is selected, configure a text editing block based on the selected at least a portion of the text, wherein the text editing block can be filled with at least a portion of the text.

[0074] refer to Figure 4A In some embodiments of the editing interface shown, the assistant creation platform 110 may directly present a window 420 including at least one operation control in response to the selection of the text "XXXXXXXX" (a non-editable block in the prompt word). In other embodiments, 110 may present a window 420 including at least one operation control in response to the selection of the text "XXXXXXXX" (a non-editable block in the prompt word) and receipt of a trigger operation (e.g., a right-click operation) on that text. The at least one control in window 420 includes at least an editing control 422. The assistant creation platform 110 may configure a text editing block 412 based on the selected text, the text editing block 412 being filled with the selected text "XXXXXXXX", in response to the triggering of the editing control 422.

[0075] In some embodiments, the assistant creation platform 110 may also present a text input interface 430 for the text editing block 4120 in association with the text editing block 4120. Figure 4A In the example, the text input interface 430 includes at least one of an input area 432 (which may be referred to as a second input area corresponding to the text editing block 412) and an input area 434 (which may be referred to as a first input area corresponding to the text editing block 412). The input area 434 may display the text "XXXXXXXX" 412 selected from the current prompt by default.

[0076] Similarly, when the text input interface 430 is presented in association with the text editing block 412, it can be determined that the text editing block 412 is in a text editing state; when the text input interface 430 is not presented, it can be determined that the text editing block 412 is not in a text editing state. The assistant creation platform 110 can present the text editing block 412 in a text editing state and the text editing block 412 not in a text editing state in different visual styles. As an example, the assistant creation platform 110 can... Figure 4A Neutralization Figure 4BThe text editing block 412 is presented in different visual styles.

[0077] In some embodiments, the assistant creation platform 110 may, in response to detecting a trigger on the application programming interface (API) edit block function, insert an API edit block (which may be referred to as a first API edit block) at a selected location of the prompt word. This API edit block can be filled with identification information for a predefined API. The API identification information may include any appropriate information such as the API's name, image identifier, and brief description. APIs that can be associated with a specific function may include plugins, knowledge bases, workflows, image streams, etc. During the operation of a function, one or more tasks or operations to be performed may require calling an associated API to complete the task.

[0078] refer to Figures 5A to 5D , Figures 5A to 5D Example 500 of an editing interface for a target function according to some embodiments of the present disclosure is shown. Reference Figure 5A Example 500 includes at least a configuration area 510 for receiving prompts input in natural language and an area 520 for API (e.g., plugin) configuration. In Example 500, the assistant creation platform 110 may, for example, determine that a trigger for API edit block functionality has been detected in response to receiving a predetermined symbol 530 (e.g., curly braces {}) input by the user in the configuration area 510. In this case, the assistant creation platform 110 may determine that a trigger for API edit block functionality has been detected and insert an API edit block at the predetermined symbol 530. It is understood that the assistant creation platform 110 may also determine that a trigger for API edit block functionality has been detected in response to any other suitable triggering method. For example, the assistant creation platform 110 may determine that a trigger for API edit block functionality has been detected in response to receiving a right-click operation.

[0079] The assistant creation platform 110 can display at least one populated API, which is associated with a target function. As an example, area 520 of example 500 can display at least one API associated with a target function; for instance, if plugin A is associated with the target function, area 520 can display an identifier for plugin A. The assistant creation platform 110 can also display a window 540 at a predetermined symbol 530, which can display identification information for plugin A and add controls for plugin A.

[0080] The assistant creation platform 110 can, in response to detecting a selection of a first API among at least one APIs, populate the identification information of the first API into the first API edit block. For example, the assistant creation platform 110 can, in response to receiving a trigger for adding a control for plugin A in window 540, determine that a selection of plugin A has been received, and populate the identification information of plugin A into the first API edit block. The assistant creation platform 110 can then present... Figure 5B Example 500 is shown. Figure 5B The example 500 shown presents an API edit block 550, which is filled with the identification information of plugin A.

[0081] In some embodiments, the prompts presented in the editing interface of the target function may be prompts determined from a prompt word library. Therefore, there may be cases where the prompts include an API editing block (which may be referred to as a second API editing block) filled with the identification information of a second API, and the second API is not associated with the target function. In this case, the assistant creation platform 110 may, in response to the second API not being associated with the target function, present the identification information of the second API in a visual style corresponding to the disabled state. The visual style corresponding to the disabled state may be, for example, grayed out, but this is merely exemplary and is not limited thereto. For example, refer to Figure 5C The prompt includes API editing block 560. Since the second API (i.e., plugin 123) is not associated with the target function, the assistant creation platform 110 can overlay strikethrough on the API editing block to present the identification information of plugin 123 in a visual style corresponding to the disabled state.

[0082] The assistant creation platform 110 can, in response to detecting a trigger on the API edit block 560, present a populateable second API, and, in response to detecting a selection of the second API, present the identification information of plugin 123 in a visual style corresponding to its enabled state. (Continue to refer to...) Figure 5C The assistant creation platform 110 can respond to a trigger on the API edit block 560 by presenting a window 562. The window 562 displays a populateable plugin 123 and an add control for the plugin 123. The assistant creation platform 110 can respond to receiving a trigger on the add control for the plugin 123, determine that a selection of the plugin 123 has been received, and then present... Figure 5D Example 500 is shown. At this time, the assistant creation platform 110 associates plugin 123 with the target function, and the assistant creation platform 110 can display plugin 123 in area 520. Plugin 123, which is associated with the target function, is now switched to the enabled state. The assistant creation platform 110 can also display the identification information of plugin 123 in a visual style corresponding to the enabled state by canceling the strikethrough.

[0083] In some embodiments, the assistant creation platform 110 may also, in response to determining that a portion of the input content in the editing interface is marked as annotation content, present the annotation content in a first visual style. This annotation content will not be input into the machine learning model. The assistant creation platform 110 may determine that it has received annotation content in response to receiving specified symbols, specified text, etc. The assistant creation platform 110 may also, in response to determining that a portion of the input content in the editing interface is computer language code, present at least a portion of the predetermined symbols in the code in a second visual style. The computer language may include any suitable computer language such as Jinja, Markdown, etc. Which parts of the code should be highlighted in the second visual style can be pre-configured. The first visual style and the second visual style can be different visual styles or the same visual style.

[0084] refer to Figure 6A , Figure 6A Example 600 of an editing interface according to some embodiments of the present disclosure is shown. Example 600 includes a region 610 for receiving prompts input in natural language. In example 600, the assistant creation platform 110 may, in response to determining that content 601 is identified as annotation content, present the annotation content in region 601 with a visual style such as italic text and gray font. The assistant creation platform 110 may also, in response to determining that content 602 is code in computer language, present the symbol “%” in content 602 and the word “set” in the code with a bold visual style.

[0085] The above briefly mentions adding prompts to specific functions or newly created prompts to the prompt library. Editable blocks can be applied to prompts during the addition process. The following section will discuss in more detail how to add prompts to the prompt library and how to apply prompts from the library.

[0086] In some embodiments, the assistant creation platform 110 can present Figure 6B Example 600B of the project development interface is shown. Example 600B includes a debug control 603 for debugging a created digital assistant. The assistant creation platform 110 can, in response to a trigger on the debug control 603, present an editing interface for the target function. As mentioned earlier, the target function includes a digital assistant, workflow nodes, etc. If the target function includes a digital assistant, the editing interface for the target function can include a creation interface for the digital assistant. User 105 can, for example, initiate a creation request to the assistant creation platform 110 as needed. In response to receiving the creation request, the assistant creation platform 110 presents a user interface for creating a digital assistant.

[0087] Figure 6CExample 600C illustrates an example of a user interface for creating a digital assistant. User 105 can configure the digital assistant to be created (assuming it is...) in Example 600C. Figure 1 The digital assistant 120 shown is configured. Unlike creating a digital assistant by writing code, in embodiments of this disclosure, the interface for creating a digital assistant is designed to include at least one configuration area for receiving configuration information for the digital assistant, each configuration area being defined to receive a type of configuration information required to build the digital assistant.

[0088] The user interface for creating a digital assistant includes at least a configuration area 610 for receiving prompts input in natural language, comprising an input box for receiving prompts (also referred to as prompt input) entered by the user in natural language. The prompt input is provided to a machine learning model, and the digital assistant 120's response to the user is determined based on the output of this machine learning model. In other words, the digital assistant 120 to be created will use a machine learning model to determine the user's needs corresponding to the user's input and provide responses to the user based on the output of the machine learning model.

[0089] In some embodiments, configuration area 610 may include area 612 and area 614. Area 612 may be used to display received prompt words. Area 614 may be used to display identifiers of prompt words previously created or acquired by the user. The assistant creation platform 110 may, in response to receiving a user's selection of an identifier for a prompt word in area 614, determine the prompt word corresponding to that identifier as a prompt word for the machine learning model and display that prompt word in area 612. Area 614 may include an entry point 616 for the prompt word library. The assistant creation platform 110 may, in response to receiving a user's trigger on the entry point 616 for the prompt word library, determine to display the interface corresponding to the prompt word library.

[0090] In some embodiments, the assistant creation platform 110 may also display the details page corresponding to the workflow node in response to detecting that the user 105 clicks on the workflow node in the workflow corresponding to the machine learning model. Figure 6D Example 600D shows an example of a details page. Details page 600D includes an entry 604 for a suggestion dictionary. The assistant creation platform 110 can respond to a trigger on entry 604, determine if a trigger for the suggestion dictionary has been received, and then present the interface corresponding to the suggestion dictionary.

[0091] refer to Figure 6E , Figure 6EExample 600E shows an interface 660 corresponding to a prompt word library. Interface 660 can display multiple prompt words available to the user. These prompt words can include those created by the user in the past, or those created by other users and shared with the user (e.g., prompt words within a team). The assistant creation platform 110 can also display prompt words included in the prompt word library, such as AA prompt word 664, BB prompt word, CC prompt word, etc., in interface 660. In some examples, the assistant creation platform 110 can also display the creator's identification information, creation time, etc., of at least one prompt word.

[0092] In some examples, the assistant creation platform 110 may present at least one prompt word in list form on the left side of the prompt word library presentation interface 660. However, this is merely exemplary and is not a limitation of this disclosure. Furthermore, if the assistant creation platform 110 detects that user 105 clicks on prompt word AA 664, it may present the content of prompt word AA 664 on the right side of the prompt word library presentation interface 660 for user 105 to preview.

[0093] In some embodiments, the assistant creation platform 110 may present at least one prompt if it detects a trigger on the prompt word library. Each prompt word is categorized into at least one of multiple types. In some examples, the assistant creation platform 110 may display at least one prompt word according to different types. The types of prompt words can be configured according to various criteria; for example, some prompt words may be divided into recommended prompt words and other prompt words. For example, the assistant creation platform 110 may present at least one prompt word recommended by the user, and may also present at least one prompt word created by the developer and / or the developer's team. In some examples, the assistant recommendation platform 110 may present at least one prompt word recommended by the user 105 based on information about the digital assistant / workflow node that the user 105 is currently creating (e.g., the name of the digital assistant / workflow node). In some embodiments, the types of prompt words may also be categorized based on the scenario in which the prompt word is used and / or the function it targets. For example, prompt words for the "character avatar" category may be applicable to digital assistants or workflow nodes that generate character avatars, and prompt words for efficiency tools may be applied to digital assistants or workflow nodes that are efficiency tools. In addition, different prompt word types can be categorized for the functions being created (e.g., plugins, workflows, databases, knowledge bases, etc.).

[0094] In some embodiments, the assistant creation platform 110 can display at least one prompt word included in the prompt word library according to different types. In some examples, the assistant creation platform 110 can categorize the prompt words in the prompt word library according to their source (e.g., from a recommendation or from the team to which user 105 belongs). In some examples, the assistant creation platform 110 can also divide the prompt words in the prompt word library into several categories based on their identification information. Such categorization and display methods facilitate users in quickly locating the desired prompt word.

[0095] In some embodiments, if the assistant creation platform 110 receives a request to apply a first prompt among at least one prompt words, it can insert the first prompt word into the area of ​​the editing interface corresponding to the prompt word editing. For example, in Example 600E, the assistant creation platform 110 can insert the AA prompt word 664 into the area 666 of the interface 660 corresponding to the prompt word editing in response to detecting a user 105's selection of the AA prompt word 664 and a selection of the "Use" control 668.

[0096] Subsequently, the assistant creation platform 110 creates a first function based at least on the first prompt word or the edited first prompt word. In some examples, the assistant creation platform 110 creates a digital assistant 120 or a workflow node based at least on the AA prompt word 664. In other examples, the assistant creation platform 110 can also create a digital assistant 120 or a workflow node based at least on the edited AA prompt word 664. It is understood that after selecting to insert the AA prompt word 664, the user 105 can also write the AA prompt word 664 based on the AA prompt word 664.

[0097] In some embodiments, the first prompt word or an edited first prompt word can be input into a first machine learning model associated with a first function, and the output of the first function is determined based on the output of the first machine learning model. It is understood that the AA prompt word 664 or the edited AA prompt word 664 can be associated with a function based on the first machine learning model (e.g., digital assistant 120 or workflow node). In this way, the digital assistant 120 or workflow node can use the first machine learning model to process the input of the function and provide the output of the function based on the output of the first machine learning model. For example, for a machine learning model-based digital assistant, the first machine learning model can determine the user's needs corresponding to the user input based on the AA prompt word 664 or the edited AA prompt word 262, and output an output that will be used to determine a response to the user.

[0098] Interface 660 includes a creation control 662 for prompt words. The assistant creation platform 110 can respond to a user's trigger on the creation control 662, displaying... Figure 6FExample 600F is shown. Example 600F includes an editing interface 670 (also referred to as a prompt creation interface) for creating prompts for a prompt word library. Interface 670 includes an area 671 for editing prompt names, an area 672 for editing prompt descriptions, and an area 673 for editing prompt content. The prompt description can indicate the prompt's function, purpose, etc., and the prompt content can include the full text of the prompt. Area 673 may also include an import control 674. In response to receiving a trigger on the import control 674, the assistant creation platform 110 can present the prompts in area 612 of the configuration area 610 in area 673. Interface 670 may also include a confirmation control 675. In response to receiving a trigger on the confirmation control 675, the assistant creation platform 110 can create prompts based on the content presented in areas 671, 672, and 673.

[0099] Return to reference Figure 6C In some embodiments, the user interface for creating the digital assistant 120 may further include a second configuration area for receiving configurations of at least one processing component. The configuration of the processing component indicates at least one processing component that the digital assistant 120 can use when processing user requests. In some embodiments, after the configuration of the processing component is provided, when the created digital assistant 120 interacts with a user, the configuration of the processing component can be provided to a model so that the model can determine which / which processing components need to be used to process user input, thereby determining the response for the user.

[0100] Each processing component can be understood as a tool that the digital assistant 120 can invoke when processing user requests, and each processing component can perform corresponding functions or services. The types of processing components can be very diverse. Users 105 can select, configure, or modify existing processing components, or users 105 can customize one or more processing components.

[0101] In some embodiments, the second configuration area may include an area for API (e.g., plugin) configuration, such as Figure 6C The area 620 is shown. In this area, the user can select or customize at least one plugin used by the digital assistant 120. Each plugin is configured to perform a corresponding function. For example, a search plugin can perform data search; a browser plugin can provide web browsing; a music plugin can provide music search and playback, and so on.

[0102] Plugins can be considered atomic capabilities of the digital assistant 110. The digital assistant 120 can invoke one or more plugins to handle user requests. In some embodiments, the assistant creation platform 110 can provide a plugin library from which the user 105 can select developed plugins. In some embodiments, alternatively or additionally, the assistant creation platform 110 can provide a plugin definition interface for the user 105 to define plugins with specific functions as needed.

[0103] Area 620 may include an add control 621 for plugins. The assistant creation platform 110 can respond to a trigger on the add control 621 by presenting... Figure 6G Example 600G is shown. Example 600G includes a plugin library interface 680. Interface 680 can display all plugins in the plugin library (e.g., it can include plugins A, B, C, D, etc.). To facilitate users quickly finding the desired plugin, interface 680 can also include a search box 681. The assistant creation platform 110 can receive user input via the search box 681 and search for the corresponding plugin from the plugin library based on the user input. Interface 681 can also include an add control corresponding to each plugin, such as add control 682 for plugin A, add control 683 for plugin B, add control 684 for plugin C, add control 685 for plugin D, and so on.

[0104] The assistant creation platform 110 can respond to a trigger on adding a control and associate the plugin corresponding to that control with the digital assistant. For example, the assistant creation platform 110 can respond to a trigger on adding control 682 and associate plugin A with the digital assistant. This process can be viewed as associating an API with a target function. The assistant creation platform 110 can, for example, respond to plugin A being associated with the digital assistant and present... Figure 6H Example 600H is shown. In area 620 of example 600H, an identifier corresponding to plugin A can be displayed to indicate that plugin A is associated with the digital assistant.

[0105] Return to reference Figure 6C In some embodiments, the second configuration area may include an area for workflow configuration, such as Figure 6C The area shown is 622. In this area, the user can select or customize at least one workflow to be executed by the digital assistant 120. Workflows can be entered not only through prompts in natural language, but also by providing workflow entry points for the user 105 to select existing workflows or define workflows through a dedicated interface.

[0106] In some embodiments, the second configuration area may include an area for workflow configuration, such as Figure 6CThe area shown is 624. In this area, the user can select at least one dataset, which the digital assistant 120 uses to determine a response to the user. Here, "dataset" can also be referred to as a "knowledge base". When determining a response to the user, the digital assistant 120 can retrieve relevant knowledge from the configured dataset for response determination. In some embodiments, the assistant creation platform 110 can allow the user 105 to configure the dataset of the digital assistant 120 by selecting from existing datasets, uploading local datasets, or specifying online datasets, etc.

[0107] It is understood that the second configuration area may also include other areas, such as areas for workflow configuration, areas for configuring persistent storage information, areas for configuring tasks, and so on. This disclosure does not limit this. Example 600C may also present control 626. The assistant creation platform 110 may, for example, respond to a trigger operation received on control 626 and present more second configuration areas.

[0108] As mentioned earlier, the digital assistant 120 can use a machine learning model to understand user requests and determine responses to the user. In some embodiments, the machine learning model used by the digital assistant 120 can be a default model, requiring no configuration from the creator. In some embodiments, during the creation of the digital assistant 120, the creator can be allowed to select the machine learning model to use. A fourth configuration area can be provided in the user interface used to create the digital assistant for receiving the selection of the machine learning model. The selected machine learning model is invoked to determine the digital assistant 120's response to the user. Figure 6C As shown, Example 600C also includes a region 630 for configuring machine learning models, in which user 105 can select the machine learning model to use.

[0109] The above discussion covered the configurable processing components during the creation of a digital assistant. In specific applications, the assistant creation platform can provide configurations of more, fewer, or different processing components for the digital assistant creator to choose or configure as needed.

[0110] In some embodiments, to allow the user 105 who creates the digital assistant to conveniently test the performance of the created digital assistant 120 during the creation process, a debugging area for the digital assistant can also be provided in the user interface, such as... Figure 6CThe debug area 640 is shown. This debug area 640 includes an input area 642 for receiving debug requests for the digital assistant 120, and a presentation area 644 for providing debug results for the debug request (and providing the received debug request). The debug area 640 can be configured as an interactive window, simulating the interactive interface seen by the user of the digital assistant 120.

[0111] During debugging, the debugging results presented in the debugging area 640 can be determined based on the received debugging request and the current configuration information for the digital assistant 120 in the user interface. The user 105 can use the debugging results to determine whether the actual operating results of the digital assistant 120 meet expectations, whether to continue modifying the configuration information, or whether to release the digital assistant. In some embodiments, for each debugging session, in addition to providing the debugging results, the underlying operating process through which the digital assistant 120 determined the debugging results can also be provided, such as calls to the machine learning model, the processing procedures of the machine learning model, one or more plugins used, etc. This allows the user 105 to more quickly determine whether the currently configured digital assistant meets expectations.

[0112] By leveraging machine learning models and configuration information to understand user needs and using processing components to execute those needs, the digital assistant 120 will be able to interact with users and respond to their requests. The user interface for creating the digital assistant is templated to provide various configuration areas for receiving configuration information from the digital assistant 120, allowing the user 105 to customize the digital assistant 120 through complex configuration and coding.

[0113] In some embodiments, the assistant creation platform 110 may provide an entry point for creating a digital assistant in any suitable user interface. A user can access the user interface for creating a digital assistant by triggering this entry point. Based on the input of user 105 on the user interface for creating a digital assistant, configuration information received in the user interface can be obtained. The configuration information includes at least the prompts received in the configuration area 610. After configuration is complete, user 105 is also allowed to publish the created digital assistant. In response to receiving a publishing request, the assistant creation platform 110 publishes the digital assistant 120 for interaction with the user based on the configuration information received in the user interface. Figure 6C As shown, the user interface displays a publishing control 650. In response to detecting a trigger on the publishing control 650, the assistant creation platform 110 receives the user's publishing request and publishes the digital assistant 120 based on the configuration information received in the user interface.

[0114] In some embodiments, the created digital assistant 120 can be published to a default platform for operation. In some embodiments, candidate platforms can be provided for user selection. In response to receiving a publication request, the assistant creation platform 110 can provide at least one candidate platform, each of the at least one candidate platform supporting the operation of the digital assistant 120. In response to receiving confirmation of a target platform among the at least one candidate platform, the digital assistant 120 is published to the target platform, for example... Figure 1 The assistant application platform 130 in the middle.

[0115] The foregoing describes the creation process of digital assistants and the editing process of prompt words in some embodiments of this disclosure. In the embodiments of this disclosure, the assistant creation platform provides full support for the construction of digital assistants, thereby enabling users to conveniently, quickly, flexibly, and freely create prompt words and digital assistants.

[0116] In some embodiments, for the editing interface of a prompt-based function, a commenting function for the prompts can also be provided in the prompt area. For example, this commenting function can be provided in the editing interface for prompts from a prompt library, or in the editing interface for a specific function (e.g., a digital assistant or workflow node). This is because different users may develop and maintain the same function, and providing a commenting function helps these users share their opinions on the prompts, provide annotations, and help users better understand the function of the prompts. The following will refer to... Figures 7A to 7E Let's discuss the comment function for prompt words.

[0117] Figures 7A to 7E An example interface 700 for commenting on prompt words is shown according to some embodiments of this disclosure. The commenting function here is sometimes also referred to as a annotation function. Figures 7A to 7E The diagram illustrates the provision of a comment function for prompts in the prompt input area for digital assistants. It should be understood that the comment function can be provided during the editing of prompts for other functions (e.g., workflow nodes), the addition of new prompts to the prompt library, or the viewing of prompts in the prompt library.

[0118] In some embodiments, in response to a comment trigger on at least a portion of the prompt word, the assistant creation platform 110 presents a user interface for comment input. In some embodiments, in response to at least a portion of the prompt word being selected, a comment control is presented, and in response to a trigger on the comment control, a user interface for comment input is presented. The user interface for comment input includes input controls. The input controls for comment input may include input boxes, or may also include one or more other input controls that support voice input, image input, file import, etc. Comments on at least a portion of the selected content can be received via the input controls, such as input boxes.

[0119] like Figure 7A As shown, in the prompt input area of ​​the digital assistant, in response to the selection of a portion 712 in the prompt, a panel of operable controls can be presented, including at least a comment control 712. In response to detecting a trigger on the comment control 710, a user interface 720 for comment input is presented, including an input box 722. The user can enter comment content regarding the portion 712 in the input box 722. In response to detecting confirmation of the comment content, such as... Figure 7A The "Submit" control 724 in the middle (or confirmation triggered by other means) can associate the received comment content with the selected part of the content 712.

[0120] In some embodiments, the comment control used to trigger the comment function can be presented in association with the unit content of the prompt word; for example, the comment control can be presented in association with each paragraph or each line of prompt word content. Figure 7B As shown, a comment control 710 is presented at each paragraph of the prompt. This comment control can be fixed in place or can be presented after a hover operation on that section is detected (e.g., the mouse hovers over the section). Figure 7B Similar to the example, by triggering the comment control, a user interface for comment input can be presented for the user to enter their comment content.

[0121] In some embodiments, the commenting functionality for prompts can be determined based on the user's role. For example, a digital assistant, workflow node, or the creator of prompts in a prompt library can add comments to prompts, and the scope of users who can comment on corresponding prompts can be configured.

[0122] In some embodiments, comments associated with at least a portion of the prompt words may be presented to the user. In some embodiments, comments associated with at least a portion of the prompt words may be permanently displayed in a specific comment display area. In some embodiments, comments associated with at least a portion of the prompt words may be collapsed and expanded to be presented to the user upon detecting a trigger to view the comments. Figure 7C As shown, a comment panel 730 can be displayed by clicking the comment control 710 or by hovering over the comment control 710, where comments on the associated prompt content are presented. In some embodiments, if multiple comments exist on at least part of the prompt content, the comments can also be displayed in a collapsed state and can be presented to the user upon being triggered. Figure 7D As shown, after triggering the comment control 710, multiple comments can be displayed in the comment panel 730. In some embodiments, the comment panel may also provide similar comment controls or other comment input triggering methods to trigger the display of comments. Figure 7C As shown, while displaying other comments, the comment input box 722 can also be displayed so that the current user can enter the comment content.

[0123] In some embodiments, when the comment is collapsed, a summary of a portion of the prompt can be provided. This summary may indicate the number of comments, the identifier of at least some of the users who posted the comment, a portion of the comment's content, etc. This allows users to know that a portion of the prompt contains a comment, and also to obtain at least some information about the comment, without expanding the comment details. Figure 7E As shown, a comment viewing control 740 is provided in the comment-related prompt word section. By triggering the comment viewing control 740, a comment panel 730 can be displayed, showing comments on the related prompt word content.

[0124] In some embodiments, the presentation of comments can also be determined based on the user's role. For example, a user who can access the prompt can be configured to access comments related to the prompt. In some embodiments, editing of existing comments in the prompt can also be supported, including modifying or deleting the comment content. The comment editing functionality can also be determined based on the user's role. For example, a user who has the ability to edit the prompt can also be configured to edit comments.

[0125] In some embodiments, during the prompt editing process, the annotations and comments associated with the prompts are not used to build the prompts input into the machine learning model. In some embodiments, when creating a digital assistant or workflow, adding annotations / comments can help other developers of the digital assistant or workflow quickly understand the logic of the prompt, thereby improving development efficiency. Furthermore, after the prompts with added annotations / comments are saved in the prompt library, other developers can also quickly understand the logic of the prompt when reusing it.

[0126] It should be noted that the visual styles mentioned above can include any appropriate visual style such as highlighting, bolding, italics, and underlining. The visual styles for different content in different states can be preset. This disclosure does not limit the specific visual styles.

[0127] In summary, according to the embodiments of this disclosure, an editable block can be presented within the prompt, and this editable block can be filled with content. This allows users to easily edit the editable block to modify the prompt, thus improving the efficiency of prompt editing.

[0128] Figure 8 A flowchart of a prompt word editing method 800 according to some embodiments of the present disclosure is shown. Method 800 can be implemented at the assistant creation platform 110. Reference is made below. Figure 1 Description method 800.

[0129] In box 810, the assistant creation platform 110 presents an editing interface for editing prompt words, where the edited prompt words are input into the machine learning model to determine the model output.

[0130] In box 820, the assistant creation platform 110, in response to the triggering of the edit block function, configures an edit block at a selected location in the editing interface, wherein content can be filled in the edit block and the filled content is editable.

[0131] In box 830, the assistant creation platform 110, in response to confirmation of the editing of the prompt word, identifies the content filled in the edit block as part of the prompt word.

[0132] In some embodiments, the visual style of an edit block or the content within an edit block differs from the visual style of the content in a non-edit block within a prompt.

[0133] In some embodiments, configuring an edit block at a selected location of a prompt word includes: in response to detecting a triggering of a text edit block function when at least a portion of the text of the prompt word is selected, configuring a first text edit block at the location of the selected at least a portion of the text based on the at least a portion of the text, wherein the first text edit block is filled with at least a portion of the text.

[0134] In some embodiments, configuring an edit block at a selected location of a prompt word includes: in response to detecting a trigger of the text edit block function when at least a portion of the text of the prompt word is not selected, inserting a second text edit block at the input cursor of the editing interface, wherein fill guide text is displayed in association with the second text edit block.

[0135] In some embodiments, method 800 further includes: for a given text editing block in a first text editing block or a second text editing block, presenting a text input interface for the given text editing block, the text input interface including at least one of a first input area and a second input area; in response to receiving specified text in the first input area, replacing the text already filled in the given text editing block with the specified text; and receiving fill guide text for the given text editing block in the second input area, the fill guide text being displayed when there is no text filled in the given text editing block.

[0136] In some embodiments, configuring an edit block at a selected location of a prompt word includes: in response to detecting a trigger of an application programming interface (API) edit block function, inserting a first API edit block at the selected location of the prompt word, wherein the first API edit block can be filled with identification information for a predefined API.

[0137] In some embodiments, the editing interface includes an editing interface for a target function that operates based on a target machine learning model, and the method 800 further includes: in response to detecting a trigger on a first API editing block, presenting at least one populated API, wherein the at least one API is associated with the target function; and in response to detecting a selection of a first API among the at least one API, populating the first API's identification information into the first API editing block.

[0138] In some embodiments, the editing interface includes an editing interface for a target function that operates based on a target machine learning model, and wherein the prompt includes a second API editing block populated with identification information of a second API. The method 800 further includes: in response to the second API not being associated with the target function, presenting the identification information of the second API in a visual style corresponding to a disabled state; in response to detecting a trigger on the second API editing block, presenting a populated second API; and in response to detecting a selection of the second API, presenting the identification information of the second API in a visual style corresponding to an enabled state.

[0139] In some embodiments, method 800 further includes: determining that a trigger of an edit block function has been detected in response to detecting a selection of a predetermined control; or determining that a trigger of an edit block function has been detected in response to detecting input of a predetermined symbol in the editing interface.

[0140] In some embodiments, the editing interface includes an editing interface for a target function that operates based on a target machine learning model, and wherein confirming the content filled in the editing block as part of a prompt word includes: confirming the content filled in the editing block as part of a prompt word in response to confirmation of the creation of the target function.

[0141] In some embodiments, the editing interface includes an editing interface for creating prompt words for a prompt word library, and method 800 further includes: adding the edited prompt word to the prompt word library in response to confirmation of editing of the prompt word.

[0142] In some embodiments, method 800 further includes: in response to determining that a portion of the input in the editing interface is labeled as annotation content, presenting the annotation content in a first visual style, wherein the annotation content is not input into the machine learning model; and in response to determining that a portion of the input in the editing interface is code in computer language, presenting at least a portion of predetermined symbols in the code in a second visual style.

[0143] Embodiments of this disclosure also provide corresponding apparatus for implementing the above methods or processes. Figure 9 A schematic structural block diagram of a device 900 for prompt word editing according to some embodiments of the present disclosure is shown. The device 900 may be implemented in or included in an assistant creation platform 110, for example. The various modules / components in the device 900 may be implemented by hardware, software, firmware, or any combination thereof.

[0144] As shown in the figure, device 900 includes an editing interface presentation module 910, configured to present an editing interface for editing prompts, wherein the edited prompts are input into a machine learning model to determine the model output. Device 900 also includes an editing block configuration module 920, configured to configure an editing block at a selected location in the editing interface in response to triggering the editing block function, wherein content can be filled into the editing block and the filled content is editable. Device 900 also includes a prompt determination module 930, configured to determine the content filled in the editing block as part of the prompt in response to confirmation of the editing of the prompt.

[0145] In some embodiments, the visual style of an edit block or the content within an edit block differs from the visual style of the content in a non-edit block within a prompt.

[0146] In some embodiments, the edit block configuration module 920 is further configured to: in response to detecting a triggering of the text edit block function when at least a portion of the text of the prompt word is selected, configure a first text edit block based on at least a portion of the text at the location of the selected at least a portion of the text, wherein the first text edit block is filled with at least a portion of the text.

[0147] In some embodiments, the edit block configuration module 920 is further configured to: in response to detecting a trigger of the text edit block function when at least a portion of the text of the prompt word is not selected, insert a second text edit block at the input cursor position of the editing interface, wherein fill guide text is displayed in association with the second text edit block.

[0148] In some embodiments, the apparatus 900 further includes: a text input interface presentation module configured to present a text input interface for a given text editing block for a given text editing block in either a first text editing block or a second text editing block, the text input interface including at least one of a first input area and a second input area; a replacement module configured to replace the text already filled in the given text editing block with the specified text in response to receiving the specified text in the first input area; and a guide text receiving module configured to receive a fill guide text for the given text editing block in the second input area, the fill guide text being displayed when there is no fill text in the given text editing block.

[0149] In some embodiments, the edit block configuration module 920 is further configured to: in response to detecting a trigger of the application programming interface (API) edit block function, insert a first API edit block at a selected position of a prompt word, wherein the first API edit block can be filled with identification information of a predefined API.

[0150] In some embodiments, the editing interface includes an editing interface for a target function that operates based on a target machine learning model, and the apparatus 900 further includes: a first presentation module configured to present at least one populated API in response to detecting a trigger on a first API editing block, wherein the at least one API is associated with the target function; and an identification information filling module configured to fill identification information of the first API into the first API editing block in response to detecting a selection of the first API among the at least one API.

[0151] In some embodiments, the editing interface includes an editing interface for a target function, the target function running based on a target machine learning model, and wherein the prompt includes a second API editing block, the second API editing block being filled with identification information of a second API. The device 900 further includes: a first style presentation module configured to present the identification information of the second API in a visual style corresponding to a disabled state in response to the second API not being associated with the target function; a second presentation module configured to present a fillable second API in response to detecting a trigger on the second API editing block; and a second style presentation module configured to present the identification information of the second API in a visual style corresponding to an enabled state in response to detecting a selection of the second API.

[0152] In some embodiments, the apparatus 900 further includes: a first trigger detection module configured to determine that a trigger of an edit block function has been detected in response to detecting a selection of a predetermined control; or a second trigger detection module configured to determine that a trigger of an edit block function has been detected in response to detecting input of a predetermined symbol in the editing interface.

[0153] In some embodiments, the editing interface includes an editing interface for a target function that operates based on a target machine learning model, and the prompt word determination module 930 is further configured to: in response to confirmation of the creation of the target function, confirm the content filled in the editing block as part of the prompt word.

[0154] In some embodiments, the editing interface includes an editing interface for creating prompts for a prompt word library, and the device 900 further includes a prompt word adding module configured to add the edited prompt word to the prompt word library in response to confirmation of the editing of the prompt word.

[0155] In some embodiments, the apparatus 900 further includes: an annotation content presentation module configured to present the annotation content in a first visual style in response to determining that a portion of the content entered in the editing interface is marked as annotation content, wherein the annotation content is not input into the machine learning model; and a code presentation module configured to present at least a portion of the predetermined symbols in the code in a second visual style in response to determining that a portion of the content entered in the editing interface is computer language code.

[0156] The modules included in device 900 can be implemented in various ways, including software, hardware, firmware, or any combination thereof. In some embodiments, one or more modules may 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 modules in device 900 may be implemented at least partially by one or more hardware logic components. By way of example, and not limitation, exemplary types of hardware logic components that may be used include field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-chips (SoCs), complex programmable logic devices (CPLDs), and so on.

[0157] Figure 10 A block diagram of an electronic device 1000 in which one or more embodiments of the present disclosure may be implemented is shown. It should be understood that... Figure 10 The electronic device 1000 shown is merely exemplary and should not be construed as limiting the functionality and scope of the embodiments described herein. Figure 10 The illustrated electronic device 1000 may include or be implemented as Figure 1 The assistant creates platform 110, or Figure 9 Device 900.

[0158] like Figure 10 As shown, electronic device 1000 is in the form of a general-purpose electronic device. Components of electronic device 1000 may include, but are not limited to, one or more processors or processing units 1010, memory 1020, storage device 1030, one or more communication units 1040, one or more input devices 1050, and one or more output devices 1060. Processing unit 1010 may be a physical or virtual processor and is capable of performing various processes according to programs stored in memory 1020. In a multiprocessor system, multiple processing units execute computer-executable instructions in parallel to improve the parallel processing capability of electronic device 1000.

[0159] Electronic device 1000 typically includes multiple computer storage media. Such media can be any accessible media that is accessible to electronic device 1000, including but not limited to volatile and non-volatile media, removable and non-removable media. Memory 1020 can be volatile memory (e.g., registers, cache, random access memory (RAM)), non-volatile memory (e.g., read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. Storage device 1030 can be removable or non-removable media and may include machine-readable media, such as flash drives, disks, or any other media that can be used to store information and / or data and can be accessed within electronic device 1000.

[0160] Electronic device 1000 may further include additional removable / non-removable, volatile / non-volatile storage media. Although not explicitly stated... Figure 10 As shown, disk drives for reading from or writing to removable, non-volatile disks (e.g., "floppy disks") and optical disk drives for reading from or writing to removable, non-volatile optical disks can be provided. In these cases, each drive can be connected to a bus (not shown) via one or more data media interfaces. Memory 1020 may include computer program product 1025 having one or more program modules configured to perform various methods or actions of various embodiments of this disclosure.

[0161] The communication unit 1040 enables communication with other electronic devices via a communication medium. Additionally, the functionality of the components of the electronic device 1000 can be implemented using a single computing cluster or multiple computing machines capable of communicating via communication connections. Therefore, the electronic device 1000 can operate in a networked environment using logical connections to one or more other servers, network personal computers (PCs), or another network node.

[0162] Input device 1050 can be one or more input devices, such as a mouse, keyboard, trackball, etc. Output device 1060 can be one or more output devices, such as a monitor, speaker, printer, etc. Electronic device 1000 can also communicate with one or more external devices (not shown) via communication unit 1040 as needed. These external devices include storage devices, display devices, etc., and can communicate with one or more devices that enable user interaction with electronic device 1000, or with any device that enables electronic device 1000 to communicate with one or more other electronic devices (e.g., network card, modem, etc.). Such communication can be performed via input / output (I / O) interface (not shown).

[0163] According to an exemplary implementation of this disclosure, a computer-readable storage medium is provided that stores computer-executable instructions thereon, wherein the computer-executable instructions are executed by a processor to implement the methods described above. According to an exemplary implementation of this disclosure, a computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, which are executed by a processor to implement the methods described above.

[0164] Various aspects of this disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatuses, devices, and computer program products implemented according to this disclosure. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0165] 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 apparatus to produce a machine such that, when executed by the processing unit of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0166] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions that execute on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0167] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction, which contains one or more executable instructions for implementing the specified logical function. In some, as newer, implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0168] Various implementations of this disclosure have been described above. These descriptions are exemplary and not exhaustive, nor are they 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 chosen to best explain the principles, practical applications, or improvements to technology in the market, or to enable others skilled in the art to understand the various implementations disclosed herein.

Claims

1. A method for editing prompt words, comprising: An editing interface is presented for editing prompts, wherein the edited prompts are input into a machine learning model to determine the model output; In response to the triggering of the edit block function, an edit block is configured at a selected location in the editing interface, wherein content can be filled into the edit block and the filled content is editable; and In response to confirmation of the editing of the prompt word, the content filled in the edit block is determined to be part of the prompt word.

2. The method according to claim 1, wherein the visual style of the edit block or the content in the edit block is different from the visual style of the content of the non-edit block in the prompt word.

3. The method according to claim 1, wherein configuring an edit block at the selected position of the prompt word includes: In response to detecting a triggering of a text editing block function when at least a portion of the text of the prompt word is selected, a first text editing block is configured at the location of the selected at least a portion of the text, wherein the first text editing block is filled with the at least a portion of the text.

4. The method of claim 1, wherein configuring an edit block at the selected position of the prompt word comprises: In response to a triggering of the text editing block function being detected when at least a portion of the text of the prompt word is not selected, a second text editing block is inserted at the input cursor position in the editing interface, wherein fill guide text is displayed in association with the second text editing block.

5. The method according to claim 3 or 4, further comprising: For a given text editing block in the first text editing block or the second text editing block A text input interface is presented for the given text editing block, the text input interface including at least one of a first input area and a second input area; In response to receiving specified text in the first input area, the text already filled in the given text editing block is replaced with the specified text; as well as The second input area receives fill guide text for the given text editing block, which is displayed when there is no fill text in the given text editing block.

6. The method of claim 1, wherein configuring the edit block at the selected position of the prompt word comprises: In response to the detection of a trigger on the application programming interface (API) edit block function, a first API edit block is inserted at the selected position of the prompt word, wherein the first API edit block can be filled with identification information for a predefined API.

7. The method of claim 6, wherein the editing interface includes an editing interface for a target function, the target function operating based on a target machine learning model, and the method further comprises: In response to detecting a trigger on the first API edit block, at least one populated API is presented, wherein the at least one API is associated with the target function; as well as In response to detecting the selection of a first API among the at least one API, the identification information of the first API is populated into the first API edit block.

8. The method of claim 1, wherein the editing interface includes an editing interface for a target function, the target function running based on a target machine learning model, and wherein the prompt word includes a second API editing block filled with identification information of a second API, the method further comprising: In response to the second API not being associated with the target function, the identification information of the second API is presented in a visual style corresponding to the disabled state; In response to the detection of a trigger on the second API edit block, the populateable second API is presented; as well as In response to detecting a selection of the second API, the identification information of the second API is presented in a visual style corresponding to the enabled state.

9. The method according to claim 1, further comprising: In response to detecting a selection of a predetermined control, it is determined that a triggering of the edit block function has been detected; or In response to the detection of input of a predetermined symbol in the editing interface, it is determined that a trigger of the editing block function has been detected.

10. The method of claim 1, wherein the editing interface includes an editing interface for a target function, the target function operating based on a target machine learning model, and wherein confirming the content filled in the editing block as part of the prompt word includes: In response to confirmation of the creation of the target function, the content filled in the edit block is confirmed as part of the prompt word.

11. The method of claim 1, wherein the editing interface includes an editing interface for creating prompt words for a prompt word library, the method further comprising: In response to confirmation of the edit of the prompt word, the edited prompt word is added to the prompt word library.

12. The method according to claim 1, further comprising: In response to determining that a portion of the content entered in the editing interface is marked as annotation content, the annotation content is presented in a first visual style, wherein the annotation content is not input into the machine learning model; as well as In response to determining that a portion of the input in the editing interface is computer language code, at least a portion of the predetermined symbols in the code are presented in a second visual style.

13. An apparatus for editing prompt words, comprising: The editing interface presentation module is configured to present an editing interface for editing prompt words, wherein the edited prompt words are input into a machine learning model for the machine learning model to determine the model output; An edit block configuration module is configured to configure an edit block at a selected location in the editing interface in response to the triggering of the edit block function, wherein content can be filled into the edit block and the filled content is editable; as well as The prompt word determination module is configured to determine the content filled in the edit block as part of the prompt word in response to confirmation of editing of the prompt word.

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, the computer program being executable 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, when executed by a processor, implements the method according to any one of claims 1 to 12.

Images