Interaction method and apparatus, electronic device, storage medium and program product

Abstract

Provided are an interaction method and apparatus, an electronic device, a storage medium and a program product, relating to the technical field of artificial intelligence. The interaction method comprises: in response to a user triggering an instruction creation function, displaying an instruction creation interface (S102); on the basis of information input by the user on the instruction creation interface and used for creating a target instruction, determining prompt information corresponding to the target instruction (S104), wherein the target instruction is used for representing demand information of the user for an interaction function of an agent; and, on the basis of the prompt information, generating and displaying an operation control of the target instruction (S106).

Description

Interaction methods, devices, electronic devices, storage media, and program products Technical Field

[0001] This disclosure relates to the field of artificial intelligence technology, and in particular to an interaction method, apparatus, electronic device, storage medium, and program product. Background Technology

[0002] With the development of artificial intelligence (AI) technology, intelligent agents have gradually come into people's view and are being used more and more widely in various fields. Intelligent agents can be used to interact with users, for example, by providing interactive services such as chat and question answering.

[0003] Summary of the Invention

[0004] This summary section is provided to briefly introduce the concepts, which will be described in detail in the detailed description section below. This summary section is not intended to identify key or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0005] According to some embodiments of this disclosure, an interaction method is provided, including: displaying an instruction creation interface in response to a user's triggering of an instruction creation function; determining prompt information corresponding to the target instruction based on information input by the user on the instruction creation interface for creating a target instruction, wherein the target instruction is used to represent the user's demand information for the interactive function of the intelligent agent; and generating and displaying operation controls for the target instruction based on the prompt information.

[0006] According to some other embodiments of this disclosure, an interactive device is provided, including: a first display module configured to display an instruction creation interface in response to a user's triggering of an instruction creation function; a determination module configured to determine prompt information corresponding to a target instruction based on information input by the user for creating a target instruction, wherein the target instruction is used to represent the user's demand information for the interactive function of the intelligent agent; and a second display module configured to generate and display operation controls for the target instruction based on the prompt information.

[0007] According to further embodiments of the present disclosure, an electronic device is provided, including: a processor; and a memory coupled to the processor for storing instructions that, when executed by the processor, cause the processor to perform an interactive method of any embodiment of the present disclosure.

[0008] According to further embodiments of the present disclosure, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, performs the interactive method of any embodiment of the present disclosure.

[0009] According to further embodiments of the present disclosure, a computer program product is provided, comprising: instructions that, when executed by a processor, implement the interaction method of any embodiment of the present disclosure.

[0010] According to further embodiments of the present disclosure, a computer program is provided, comprising: instructions that, when executed by a processor, implement the interactive method of any embodiment of the present disclosure.

[0011] Other features, aspects, and advantages of this disclosure will become clear from the following detailed description of exemplary embodiments with reference to the accompanying drawings. Attached Figure Description

[0012] Preferred embodiments of the present disclosure are described below with reference to the accompanying drawings. The accompanying drawings, which are included to provide a further understanding of the present disclosure, and which, together with the following detailed description, are incorporated in and form a part of this specification and are used to explain the present disclosure. It should be understood that the drawings described below only relate to some embodiments of the present disclosure and are not intended to limit the present disclosure. In the drawings:

[0013] Figure 1 shows a flowchart illustrating the interaction methods of some embodiments of this disclosure;

[0014] Figures 2A to 4C show schematic diagrams of interactive interfaces of some embodiments of this disclosure;

[0015] Figure 5 shows a schematic diagram of the structure of an interactive device according to some embodiments of the present disclosure;

[0016] Figure 6 shows a schematic diagram of the structure of an electronic device according to some embodiments of the present disclosure;

[0017] Figure 7 shows a schematic diagram of the structure of a computer system according to some embodiments of the present disclosure.

[0018] It should be understood that, for ease of description, the dimensions of the various parts shown in the accompanying drawings are not necessarily drawn to actual scale. The same or similar reference numerals are used in the various drawings to denote the same or similar parts. Therefore, once an item is defined in one drawing, it may not be discussed further in subsequent drawings. Detailed Implementation

[0019] The technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. However, it is obvious that the described embodiments are only some embodiments of this disclosure, and not all embodiments. The following description of the embodiments is merely illustrative and is in no way intended to limit this disclosure or its application or use. 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.

[0020] It should be understood that the various steps described in the method embodiments of this disclosure may be performed in different orders and / or in parallel. Furthermore, method embodiments may include additional steps and / or omit the steps shown. The scope of this disclosure is not limited in this respect. Unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of components and steps set forth in these embodiments should be interpreted as merely exemplary and do not limit the scope of this disclosure.

[0021] As used in this disclosure, the term "comprising" and its variations are open-ended terms that include at least the following elements / features but do not exclude other elements / features, i.e., "including but not limited to". Furthermore, as used in this disclosure, the term "including" and its variations are open-ended terms that include at least the following elements / features but do not exclude other elements / features, i.e., "including but not limited to". Therefore, "comprising" and "including" are synonymous. The term "based on" means "at least partially based on".

[0022] Throughout this specification, the terms "one embodiment," "some embodiments," or "embodiment" mean that a specific feature, structure, or characteristic described in connection with an embodiment is included in at least one embodiment of the invention. For example, the term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; and the term "some embodiments" means "at least some embodiments." Furthermore, the appearance of the phrases "in one embodiment," "in some embodiments," or "in an embodiment" in various places throughout the specification does not necessarily refer to the same embodiment, but may refer to the same embodiment.

[0023] It should be noted that the concepts of "first," "second," etc., used in this disclosure are used only to distinguish different devices, modules, or units, and are not intended to define the order of functions performed by these devices, modules, or units or their interdependencies. Unless otherwise specified, the concepts of "first," "second," etc., are not intended to imply that the objects described herein must be in a given temporal, spatial, rank, or any other given order.

[0024] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0025] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0026] The embodiments of this disclosure are described in detail below with reference to the accompanying drawings; however, this disclosure is not limited to these specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. Furthermore, in one or more embodiments, specific features, structures, or characteristics can be combined in any suitable manner that will be apparent to those skilled in the art from this disclosure.

[0027] During interactions with an intelligent agent, users often have specific needs regarding the agent's interactive functions, hoping that the agent can output specific types of responses. For example, a user might want the agent to tell a story, and expect the story's general content, word count, and other details to meet specific requirements.

[0028] If a user wants to control an agent to perform specific interactive functions to meet specific needs, they need to input detailed requirements so that the agent can output a specific type of response. If the user uses a particular interactive function frequently, they need to repeatedly input detailed requirements, which reduces interaction efficiency and user experience.

[0029] To address the aforementioned issues, this disclosure provides an interaction method, which is described below with reference to Figures 1-4C.

[0030] Figure 1 is a flowchart of some embodiments of the interactive method of this disclosure. As shown in Figure 1, the method of this embodiment includes steps S102 to S106.

[0031] In step S102, in response to the user's triggering of the instruction creation function, the instruction creation interface is displayed.

[0032] Users can trigger the command creation function in any way, such as through controls, voice, or preset actions; there are no restrictions. Users can trigger the command creation function in various distribution scenarios.

[0033] In step S104, the prompt information corresponding to the target instruction is determined based on the information entered by the user on the instruction creation interface for creating the target instruction.

[0034] Users can input information for creating target instructions in various forms, such as text and voice, without restriction. This information can directly serve as the corresponding prompt. However, in practice, user-inputted information often fails to adequately control the agent's output, requiring repeated modifications and adjustments to ensure the agent's output meets requirements. Therefore, prompts can be automatically generated based on the information used to create the target instructions. Prompts are easier for the agent's machine learning model to understand than the initial instruction information, leading to more tailored output and improved operational efficiency.

[0035] Intelligent agents can be implemented based on machine learning models and can interact with users. The content of these interactions can include various forms of content such as text, voice, and images, without limitation. Machine learning models can be, for example, LLM (Large Language Model), but are not limited to the examples given. Prompt information is used as input to the machine learning model corresponding to the intelligent agent, enabling the model to output specific types of responses based on the prompts.

[0036] Target instructions are used to represent the user's desired interactive functions for the intelligent agent. For example, a target instruction might indicate that the user wants the intelligent agent to perform Chinese-French translation, or that the user wants it to write a document. The information used to create target instructions can be descriptive, such as the desired word count and expression in the output French during the Chinese-French translation process.

[0037] In step S106, the operation controls for the target instruction are generated and displayed according to the prompt information.

[0038] For example, displaying a prompt message and generating an operation control for the target instruction in response to the user's confirmation of the prompt message. The operation control for the target instruction can be displayed in one or more distribution scenarios. For example, the operation control for the target instruction is used to send the target instruction to the corresponding agent in response to a user trigger, thereby enabling the agent to generate a response message based on the target instruction.

[0039] The above embodiments provide a method for users to create instructions. In response to a user's triggering of the instruction creation function, an instruction creation interface is displayed. The user can input information for creating a target instruction on the interface, and the system automatically determines the corresponding prompt information. Based on the prompt information, the system generates and displays the operation controls for the target instruction. Based on the method described above, users can customize personalized instructions, and the instruction creation process is simple and convenient, allowing for rapid instruction creation. Because the operation controls for the target instruction are generated, when a user wants to use the interactive function corresponding to the target instruction, they only need to trigger the operation controls to call the corresponding interactive function for interaction. Especially when the operation controls for the target instruction are used frequently, this greatly improves the convenience and efficiency of the operation, enhances the interaction efficiency between the user and the intelligent agent, and improves the user experience.

[0040] Users can trigger the command creation function through various means to display the command creation interface, which is described below with reference to some examples.

[0041] In some embodiments, the operation controls for the instruction creation function are displayed; in response to the user's triggering of the operation controls for the instruction creation function, the instruction creation interface is displayed.

[0042] The control panel for creating commands can be displayed on one or more pages. For example, it can be displayed on a user interaction page with the agent; or it can be displayed on the application's homepage, and so on.

[0043] In some embodiments, an interaction page between the user and the intelligent agent is displayed, and a command viewing control is displayed on the interaction page. In response to the user's triggering of the command viewing control, a command display interface is displayed, which shows the operation controls for the command creation function. The command display interface may also include one or more commands that have already been created.

[0044] Figure 2A shows the interaction page between the user and the intelligent agent a. The interaction page can be divided into a display area 201, which is used to display the interaction information between the user and the intelligent agent a. The interaction page may also include an input area 202, where the user can input information, such as text or voice. A "command" control 203 can be displayed in the display area 201, or it can be displayed in the input area. The "command" control 203 can be a command viewing control or an operation control for command creation. When the "command" control 203 is a command viewing control, the command display interface shown in Figure 2B or 2C can be displayed in response to the user's triggering of the "command" control 203.

[0045] As shown in Figure 2A, one or more candidate instructions (controls 204) can also be displayed on the interactive page, such as "travel outfit matching" or "fitness plan". These candidate instructions can be instructions created by the user or recommended instructions. Recommended instructions can be created by other users or provided by the application.

[0046] As shown in Figure 2B, the command display interface can be a half-screen page, a full-screen page, a window, a floating layer, or any other form; no restrictions are placed here. The command display interface may include a first tab page, for example, the "My" tab. The "My" tab can display the operation control "Create My Command" 211 for the command creation function, and can also display already created commands 212. The command display interface may also include a second tab page, for example, the "Recommended" tab. The "Recommended" tab can display one or more recommended commands. These recommended commands can be created by other users or provided by the application, and can be selected as recommended commands based on metrics such as the number of times commands are used, their frequency of use, and their popularity (e.g., ratings).

[0047] As shown in Figure 2C, if the user has not created any commands, the command creation function operation control "Create" 221 can be directly displayed on the command display interface. The corresponding guidance information can be displayed to guide the user to customize commands or save frequently used dialogues as commands.

[0048] In response to a user's triggering of the "Create My Command" or "Create" control, the command creation interface shown in Figure 2D can be displayed. Alternatively, if the "Command" control 203 is an operation control for the command creation function, in response to a user's triggering of the "Command" control 203, the command creation interface shown in Figure 2D can be displayed.

[0049] In some embodiments, the instruction creation interface includes a title input area and an instruction content input area. Alternatively, the instruction creation interface may include only one area for inputting information used to create the target instruction. As shown in Figure 2D, the instruction creation interface includes a title input area 231 and an instruction content input area 232. When the title input area is inactive, first guidance information is displayed. For example, the first guidance information includes an example title, as shown in Figure 2D, where the first guidance information is "For example, summarize website information." When the instruction content input area is inactive, second guidance information is displayed. For example, the second guidance information includes an example prompt, as shown in Figure 2D, where the first guidance information is "For example, you will analyze and summarize the website content…." The first and second guidance information can be used to guide the user to input the title and instruction content, improving the ease of user operation.

[0050] Information for creating a target instruction can be entered in the title input area and the instruction content input area via text or voice. In some embodiments, the information for creating a target instruction includes at least one of the title and content of the target instruction; in response to the information for creating a target instruction including the title of the target instruction, the title of the target instruction is displayed in the operation control of the target instruction; in response to the information for creating a target instruction not including the title of the target instruction, a title generated based on the prompt information is displayed in the operation control of the target instruction.

[0051] Users can enter either the title or the content of the target instruction. The title of the target instruction can be displayed in the operation controls; for example, "Fitness Plan" is the title shown in Figure 2A, making it easy for users to view and quickly select the instruction. If the user does not enter a title, it can be generated based on the corresponding prompt information. For example, a machine learning model can be used to summarize the prompt information and generate the title of the target instruction.

[0052] In the above embodiments, users can directly trigger the display of the instruction creation interface by using the control that triggers the instruction creation function, and then input the information used to create the target instruction, which improves the convenience and efficiency of user operation.

[0053] Users can also create target instructions using previously entered information. In some embodiments, in response to user input of first interactive information, the first interactive information is displayed; in response to user triggering of the instruction creation function for the first interactive information, an instruction creation interface is displayed, and the first interactive information is displayed in the instruction creation interface as information for creating the target instruction.

[0054] The user-inputted first interaction information is displayed in the user-agent interaction interface. For example, as shown in Figures 2A and 3A, the first interaction information is "tell a bedtime story". For example, in response to the user's preset operation on the first interaction information, an information operation interface is displayed, in which a save command control is displayed. In response to the user's triggering of the save command control (i.e., triggering the command creation function for the first interaction information), a command creation interface is displayed, and the first interaction information is displayed in the command creation interface as information used to create the target command.

[0055] As shown in Figure 3A, users can trigger the display of the information operation interface 301 through preset operations such as long press and double-click. The information operation interface can be displayed in the form of a floating layer, window, etc., and is not limited to the example in the figure. While displaying the information operation interface, the first interactive information can be highlighted. A mask can also be added to the interactive interface to prevent the displayed content from affecting each other. The information operation interface can display a save command control 302 for "Save as Command". In response to the user's triggering of the save command control 302, the command creation interface is displayed. The information operation interface can also display other controls, such as a "Create New Dialogue" control used to send the first interactive information to other interactive objects to create a new dialogue, a "Copy" control used to copy the first exchanged information, a "Modify" control used to modify the first interactive information that has been sent, and a "Select Text" control used to select part or all of the text in the first interactive information.

[0056] As shown in Figure 3B, in response to the user's triggering of the save instruction control 302, the first interactive information can be displayed in the instruction content input area of ​​the instruction creation interface. The user can continue to edit the first interactive information and input information for creating the target instruction.

[0057] Users can also trigger the command creation function based on the first interactive information through voice or other operations, not limited to the examples given. Users can also trigger the command creation function through voice, preset actions, and other methods, which will not be elaborated here.

[0058] The following describes, with reference to some embodiments, how to determine the prompt information corresponding to the target instruction based on the information entered by the user in the instruction creation interface for creating the target instruction.

[0059] In some embodiments, structured prompt information corresponding to the target instruction is generated based on the information entered by the user in the instruction creation interface for creating the target instruction.

[0060] Structured prompts can make the prompts more standardized, clear, and specific, enabling machine learning models to better understand the context and constraints of the task and output more accurate and relevant responses.

[0061] In some embodiments, the information used to create the target instruction is parsed to determine the content of at least one of the tasks and outputs included in the information used to create the target instruction; the content of at least one of the tasks and outputs is expanded to generate task description information and output description information in the prompt information; and a structured prompt information corresponding to the target instruction is generated based on the task description information and output description information.

[0062] In many cases, the information users input to create target instructions is too simple or lacks a standardized structure, making it difficult for machine learning models to understand. This results in the agent's interactive functions not meeting requirements, meaning the output information is unsuitable. Therefore, the information used to create target instructions can be expanded and improved to allow the machine learning model to better understand it and output more accurate and relevant responses.

[0063] Machine learning models can be used to parse the information used to create target instructions, yielding at least one of the following: a task and an output. For example, the task might be "to analyze and summarize information from a website," where the task defines the task or role the machine learning model is to perform. The output might be "to output summary information," which can include format and style. The information used to create target instructions can also include constraints, rules that the machine learning model must follow when performing the task; these constraints can also apply to the output. Furthermore, the information can include examples, such as output samples. The more detailed the information used to create target instructions, the more accurate the generated prompts, the better the machine learning model understands them, and the more the final output meets the user's needs.

[0064] Even when the user only inputs a task or output, a machine learning model can be used to expand the information, generating task descriptions and output descriptions. These output descriptions are more detailed than the task and output information used to create the target instruction, resulting in more accurate prompts. Furthermore, if the information used to create the target instruction also includes constraints, these constraints can be further expanded.

[0065] If the information used to create the target instruction only includes the title of the target instruction, at least one of the tasks and outputs in the title can be identified. For example, if the title is "Chinese-French Translation," then "Chinese-French Translation" can be used as the task. Even if the user only enters the title, the system can automatically expand the information to obtain the corresponding prompts for the target instruction.

[0066] In some embodiments, the content of at least one of the tasks and outputs is expanded based on the content of at least one of the tasks and outputs and sample hint information, wherein the sample hint information includes sample task description information and sample output description information.

[0067] The example task description and example output description in the example prompts are in a more accurate and standardized format. Based on these prompts, machine learning models can better understand where to expand upon the content, thus obtaining more accurate prompts. For example, when the output is "output summary information," expanding the output could involve increasing the word count requirement or adding other content.

[0068] In some embodiments, a structured prompt message corresponding to the target instruction is generated based on the task description information and output description information in the generated prompt message, as well as the preset structure corresponding to the sample prompt message.

[0069] Sample prompts can be structured into multiple parts, such as task description and sample output description. The sample output description can include format, style, constraints, etc. The specific sample prompts and their structure can be customized according to actual needs. Using sample prompts can make the structured prompts corresponding to the target instructions generated by the machine learning model more accurate.

[0070] In some embodiments, in response to the user's triggering of the information completion control in the instruction creation interface, a structured prompt message corresponding to the target instruction is generated based on the information entered by the user in the instruction creation interface for creating the target instruction.

[0071] As shown in Figure 2D or 3B, the information completion control is displayed in the instruction content input area, i.e. "one-click completion". In response to the user's triggering of the information completion control, the information used to create the target instruction can be expanded and improved, and the prompt information corresponding to the target instruction can be obtained and displayed.

[0072] "One-click completion" corresponds to an information completion command, which can be user-created or application-provided. In response to the user's triggering of the information completion control, an information completion command can be sent to the agent. This allows the machine learning model corresponding to the agent to expand the information used to create the target command, obtaining the corresponding prompt information. Sending information completion commands to the agent can include inputting the prompt information corresponding to the information completion command into the machine learning model. The prompt information corresponding to the information completion command can include the example prompt information mentioned above.

[0073] The generated prompt information, after being expanded and improved based on the information used to create the target instruction, will be displayed. Users can modify the prompt information to obtain the final prompt information corresponding to the target instruction. In some embodiments, the prompt information is displayed; in response to user modification operations, the prompt information is updated according to the modification operations.

[0074] The method in the above embodiments automatically expands and improves the information used to create the target instruction, thereby obtaining the prompt information corresponding to the target instruction. This improves the convenience and efficiency of user operation, and the generated prompt information is more accurate, thus improving the accuracy of generating the target instruction.

[0075] Users can also choose not to expand or improve the information used to create the target instruction, and directly determine that the information used to create the target instruction will be used as the prompt information corresponding to the target instruction.

[0076] After generating the prompt information corresponding to the target instruction, the operation controls for the target instruction can be automatically generated and displayed based on the prompt information. In some embodiments, in response to the user's confirmation operation of the prompt information, the operation controls for the target instruction are generated, the prompt information corresponding to the target instruction and the operation controls for the target instruction are associated, and the operation controls for the target instruction are displayed.

[0077] In some embodiments, in response to the user's operation control of the target instruction, the prompt information corresponding to the target instruction is input into the machine learning model corresponding to the agent to generate the interactive function corresponding to the target instruction, and the agent interacts with the user based on the interactive function.

[0078] Sending a target instruction to an agent can be done by sending a prompt message to the agent, which is then input into a machine learning model. After understanding the prompt message, the machine learning model can output a corresponding response based on the needs expressed in the prompt message, thus providing the interactive function corresponding to the target instruction. The target instruction can consist of two parts: a title and a prompt message. A unique identifier can also be set. The title is used to display in the corresponding control or other location for easy user identification, while the prompt message is used to control the agent to generate a specific type of response.

[0079] In some embodiments, in response to the user's confirmation operation of the prompt information, an interactive function corresponding to the target instruction and an operation control of the target instruction associated with the interactive function are generated according to the prompt information; the operation control of the target instruction is then displayed.

[0080] For example, a user can trigger the generation of operation controls for the target instruction by clicking the "Create" control in Figure 2D or 3B. After the user confirms the prompt, the interactive function corresponding to the target instruction can be directly generated. This interactive function can be the interactive function of a new intelligent agent, that is, creating a new intelligent agent with this interactive function. For example, creating an intelligent agent that plays a certain role. The operation controls for the target instruction can be controls that call the new intelligent agent. In response to the user's triggering of the operation controls for the target instruction, the new intelligent agent is called to interact with the user.

[0081] The method described in the above embodiments automatically generates operation controls for the target instruction based on the prompt information corresponding to the target instruction, which improves the convenience and efficiency of user operation and facilitates the user's subsequent application of the target instruction, thereby enhancing the user experience.

[0082] Once the operation controls for the target instruction are generated, they can be distributed in different scenarios. In some embodiments, in response to the user's setting of the distribution scenario or based on the target instruction, the distribution scenario of the target instruction's controls is determined; and the operation controls for the target instruction are displayed in the distribution scenario.

[0083] For example, when there are multiple agents, the user can set the agent corresponding to the target command, and display the operation controls of the target command in the interactive interface of the agent corresponding to the target command according to the user's settings. As another example, the user can set one or more pages to display the target command, and display the operation controls of the target command in one or more pages according to the user's settings. Yet another example is that, based on the prompt information corresponding to the target command, the agent or page associated with the target command can be determined, and the operation controls of the target command can be displayed in the interactive interface of the agent associated with the target command or in the page associated with the target command.

[0084] By flexibly setting the distribution scenarios of the target instruction's operation controls, users can more easily operate the target instruction's operation controls, improving interaction efficiency.

[0085] The following describes, with reference to some embodiments, how the operation controls of the target instruction are applied.

[0086] In some embodiments, in response to the user's operation control of the target instruction, information corresponding to the target instruction sent to the agent is displayed, and the response information generated by the agent based on the target instruction is output.

[0087] As shown in Figure 4A, the operation control of the target instruction is, for example, the "bedtime story" control. In response to the user triggering "bedtime story", it can send the message "tell a bedtime story" to the agent. The message can be displayed with a preset effect. Then the agent will generate and display a bedtime story.

[0088] In some embodiments, in response to the user's operation of the control for the target instruction, guidance information for enabling interaction based on the target instruction is displayed; in response to the user inputting second interaction information, response information generated by the agent based on the target instruction and the second interaction information is output.

[0089] Some target commands have interactive functions that generate a response without requiring further user input, while others require specific user input to generate a response. Therefore, different types of target commands will have different display and interactive effects.

[0090] As shown in Figure 4B, the operation control for the target instruction is, for example, a control for "Chinese-French translation." In response to the user triggering "Chinese-French translation," the input area can display "Chinese-French translation" guidance information in a preset manner, or it can display guidance information such as "Start Chinese-French translation now" in the interactive information display area, not limited to the example given. In response to the user inputting and sending the second interactive information "existentialism," the second interactive information is displayed in the interactive information display area, and it can be displayed in a specific way, for example, displaying "Chinese-French translation" and "existentialism" together, along with an identifier, etc.

[0091] The method described in the above embodiments allows users to directly trigger target commands through operation controls.

[0092] In some embodiments, in response to a third interactive information input by the user matching a target instruction, guidance information for enabling the target instruction is displayed; in response to the user's confirmation operation, information for sending the target instruction to the agent is displayed; and response information generated by the agent based on the target instruction is output.

[0093] Not only can the interactive function corresponding to a target command be activated by the user triggering the operation control of the target command, but it can also be activated by recognizing whether the input third-party interactive information matches the target command. For example, if a user inputs "tell a bedtime story," "tell a bedtime story" can be displayed with preset effects (e.g., highlighting, specific font, color, adding identifiers, etc.) as guidance information to prompt the user that "tell a bedtime story" corresponds to a command. After the user confirms, a bedtime story can be generated directly according to the target command. Of course, after the user inputs the third-party interactive information, the guidance information for activating the target command can be hidden, and instead, the guidance information for activating the target command can be displayed in the interactive information display area after the user confirms sending the third-party interactive information.

[0094] In some embodiments, in response to a user input of fourth interaction information that matches a target instruction, guidance information for enabling interaction based on the target instruction is displayed; and in response to a user input of fourth interaction information, response information generated by the agent based on the target instruction and the fourth interaction information is output.

[0095] For example, in response to the user's input of the fourth interactive information "Chinese-French translation", the input area can display the guidance information "Chinese-French translation" with a preset effect, or the interactive information display area can display guidance information such as "Start Chinese-French translation now", etc., without being limited to the examples given. In response to the user inputting and sending the fourth interactive information "existentialism", the fourth interactive information can be displayed in the interactive information display area, and can be displayed in a specific way, for example, displaying "Chinese-French translation" and "existentialism" together, and displaying an identifier, etc.

[0096] In the method described in the above embodiments, the interactive information input by the user can be directly matched with the target instruction, and the target instruction can be invoked to interact with the intelligent agent, which is convenient for users and improves the efficiency and convenience of operation.

[0097] Users can perform various operations on the created instructions, which are described below with reference to some examples.

[0098] In some embodiments, in response to a user triggering the instruction viewing function, one or more created instructions are displayed; in response to a user editing operation on a first instruction among the one or more instructions, the title and prompt information corresponding to the first instruction are displayed; in response to a user modifying at least one of the titles and prompt information corresponding to the first instruction, the title and prompt information corresponding to the first instruction are updated and displayed; in response to a user confirming the updated title and prompt information corresponding to the first instruction, the operation controls of the updated first instruction are displayed.

[0099] In some embodiments, in response to a user's triggering of the instruction viewing function, one or more created instructions are displayed; in response to a user's deletion operation on a second instruction among the one or more instructions, the operation control of the second instruction is deleted.

[0100] For example, as shown in Figure 2B or 4C, in response to the user's activation of the instruction viewing control, the instruction display interface is displayed, showing the created instructions in the first tab. As shown in Figure 4C, each created instruction can correspond to an operation control 401. In response to the user's activation of the operation control for the first instruction, an operation window (or interface) is displayed. The operation window includes an edit control and a delete control. The user can modify the title and / or prompt information of the first instruction by triggering the edit control, and the user can delete the second instruction by triggering the delete control.

[0101] The method described in the above embodiments allows users to edit and delete created instructions, flexibly manage created instructions, and improve user experience.

[0102] This disclosure also provides an interactive device, which will be described below with reference to Figure 5.

[0103] Figure 5 is a structural diagram of some embodiments of the interactive device of this disclosure. As shown in Figure 5, the interactive device 50 of this embodiment includes: a first display module 510, a determination module 520, and a second display module 530.

[0104] The first display module 510 is configured to display the command creation interface in response to a user's triggering of the command creation function.

[0105] The determination module 520 is configured to determine the prompt information corresponding to the target instruction based on the information input by the user for creating the target instruction, wherein the target instruction is used to represent the user's demand information for the interactive functions of the intelligent agent.

[0106] The second display module 530 is configured to generate and display operation controls for the target instruction based on the prompt information.

[0107] In some embodiments, the second display module 530 is configured to determine the distribution scenario of the target instruction's control in response to the user's setting of the distribution scenario or according to the target instruction; and to display the operation control of the target instruction in the distribution scenario.

[0108] In some embodiments, the determining module 520 is configured to generate structured prompt information corresponding to the target instruction based on the information entered by the user in the instruction creation interface for creating the target instruction.

[0109] In some embodiments, the determining module 520 is configured to parse the information used to create the target instruction, determine the content of at least one of the tasks and outputs included in the information used to create the target instruction; expand the content of at least one of the tasks and outputs to generate task description information and output description information in the prompt information; and generate structured prompt information corresponding to the target instruction based on the task description information and output description information.

[0110] In some embodiments, the determining module 520 is configured to expand the content of at least one of the tasks and outputs based on the content of at least one of the tasks and outputs and sample prompt information, wherein the sample prompt information includes sample task description information and sample output description information.

[0111] In some embodiments, the determining module 520 is configured to generate structured prompt information corresponding to the target instruction based on the task description information and output description information in the generated prompt information, as well as the preset structure corresponding to the sample prompt information.

[0112] In some embodiments, the determining module 520 is configured to, in response to the user's triggering of the information completion control in the instruction creation interface, generate structured prompt information corresponding to the target instruction based on the information entered by the user in the instruction creation interface for creating the target instruction.

[0113] In some embodiments, the instruction creation interface includes a title input area and an instruction content input area; the information for creating the target instruction includes at least one of the title and content of the target instruction; the second display module 530 is configured to display the title of the target instruction in the operation control of the target instruction in response to the information for creating the target instruction including the title of the target instruction; and to display the title generated according to the prompt information in the operation control of the target instruction in response to the information for creating the target instruction not including the title of the target instruction.

[0114] In some embodiments, the second display module 530 is configured to, in response to a user's confirmation operation of a prompt message, generate an interactive function corresponding to the target instruction and an operation control associated with the interactive function for the target instruction based on the prompt message; and display the operation control of the target instruction.

[0115] In some embodiments, the first display module 510 is configured to display the operation controls for the instruction creation function; in response to the user's triggering of the operation controls for the instruction creation function, the instruction creation interface is displayed.

[0116] In some embodiments, the first display module 510 is configured to display the first interactive information in response to user input of the first interactive information; to display the instruction creation function for the first interactive information in response to user triggering; and to display the instruction creation interface and display the first interactive information as information for creating the target instruction in the instruction creation interface.

[0117] In some embodiments, the interactive device 50 further includes: a third display module 540 configured to display prompt information; and to update the prompt information in response to a user's modification operation on the prompt information.

[0118] In some embodiments, the interaction device 50 further includes: an interaction module 550, configured to, in response to the user's operation control of the target instruction, display information corresponding to the target instruction sent to the agent, and output response information generated by the agent based on the target instruction; or, in response to the user's operation control of the target instruction, display guidance information to enable interaction based on the target instruction, and in response to the user inputting second interaction information, output response information generated by the agent based on the target instruction and the second interaction information.

[0119] In some embodiments, the interaction module 550 is configured to, in response to a third interaction message input by the user matching a target instruction, display guidance information to enable the target instruction; in response to a user's confirmation operation, display information corresponding to the target instruction sent to the agent and output response information generated by the agent based on the target instruction; or, in response to a fourth interaction message input by the user matching a target instruction, display guidance information to enable interaction based on the target instruction; and in response to a fourth interaction message input by the user, output response information generated by the agent based on the target instruction and the fourth interaction message.

[0120] In some embodiments, the interactive device 50 further includes: an editing module 560, configured to display one or more created instructions in response to a user's triggering of the instruction viewing function; display the title and prompt information corresponding to the first instruction in response to a user's editing operation on the first instruction among the one or more instructions; update and display the title and prompt information corresponding to the first instruction in response to a user's modification operation on at least one of the title and prompt information corresponding to the first instruction; and display the operation controls of the updated first instruction in response to a user's confirmation operation on the updated title and prompt information corresponding to the first instruction.

[0121] In some embodiments, the interactive device 50 further includes: a deletion module 570, configured to display one or more created instructions in response to a user's triggering of the instruction viewing function; and to delete the operation controls of the second instruction in response to a user's deletion operation of the second instruction among the one or more instructions.

[0122] It should be noted that the above-described units (modules) are logical modules divided according to their specific functions, and are not intended to limit the specific implementation method. For example, they can be implemented in software, hardware, or a combination of both. In actual implementation, the above-described units can be implemented as independent physical entities, or they can be implemented by a single entity (e.g., a processor (CPU or DSP, etc.), integrated circuit, etc.). Furthermore, the units shown in the accompanying drawings with dashed lines indicate that these units may not actually exist, and the operations / functions they perform can be implemented by the processing circuitry itself.

[0123] In addition, although not shown, the device may also include a memory that can store various information generated by the device and its constituent units during operation, programs and data used for operation, data to be transmitted by the communication unit, etc. The memory can be volatile memory and / or non-volatile memory. For example, the memory may include, but is not limited to, random access memory (RAM), dynamic random access memory (DRAM), static random access memory (SRAM), read-only memory (ROM), and flash memory. Of course, the memory may also be located outside the device. Optionally, although not shown, the device may also include a communication unit that can be used to communicate with other devices. In one example, the communication unit can be implemented in a manner known in the art, such as including communication components such as antenna arrays and / or radio frequency links, various types of interfaces, communication units, etc. These will not be described in detail here. Furthermore, the device may also include other components not shown, such as radio frequency links, baseband processing units, network interfaces, processors, controllers, etc. These will not be described in detail here.

[0124] Some embodiments of this disclosure also provide an electronic device. Figure 6 shows a block diagram of some embodiments of the electronic device of this disclosure. For example, in some embodiments, the electronic device 60 can be various types of devices, such as mobile terminals including, but not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs, desktop computers, etc. For example, the electronic device 60 may include a display panel for displaying data and / or execution results utilized in the scheme according to this disclosure. For example, the display panel can be of various shapes, such as a rectangular panel, an elliptical panel, or a polygonal panel. In addition, the display panel can be not only a planar panel, but also a curved panel, or even a spherical panel.

[0125] As shown in FIG6, the electronic device 60 of this embodiment includes a memory 61 and a processor 62 coupled to the memory 61. It should be noted that the components of the electronic device 60 shown in FIG6 are merely exemplary and not limiting; the electronic device 60 may also have other components depending on the actual application requirements. The processor 62 can control other components in the electronic device 60 to perform desired functions.

[0126] In some embodiments, memory 61 is used to store one or more computer-readable instructions. When processor 62 executes the computer-readable instructions, the computer-readable instructions are executed by processor 62 to implement the interaction method according to any of the above embodiments. For specific implementations and related explanations of the various steps of the method, please refer to the above embodiments; repeated details will not be elaborated here.

[0127] For example, processor 62 and memory 61 can communicate with each other directly or indirectly. For example, processor 62 and memory 61 can communicate via a network. The network can include wireless networks, wired networks, and / or any combination of wireless and wired networks. Processor 62 and memory 61 can also communicate with each other via a system bus, which is not limited in this disclosure.

[0128] For example, processor 62 can be embodied in various suitable processors, processing devices, such as central processing unit (CPU), graphics processing unit (GPU), network processor (NP), etc.; it can also be digital signal processor (DSP), application-specific integrated circuit (ASIC), field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The central processing unit (CPU) can be an x86 or ARM architecture, etc. For example, memory 61 can include any combination of various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. Memory 61 can include, for example, system memory, which stores, for example, the operating system, application programs, boot loader, database, and other programs. Various application programs and various data can also be stored in the storage medium.

[0129] Furthermore, according to some embodiments of this disclosure, various operations / processes according to this disclosure, implemented via software and / or firmware, can install programs constituting the software from a storage medium or network onto a computer system with a dedicated hardware architecture, such as the computer system (or electronic device) 70 shown in FIG. 7. When various programs are installed, the computer system is capable of performing various functions, including functions such as those described above. FIG. 7 is a block diagram illustrating an example structure of a computer system that may be employed in an embodiment of this disclosure.

[0130] In Figure 7, the Central Processing Unit (CPU) 701 performs various processes according to a program stored in the Read-Only Memory (ROM) 702 or a program loaded from the storage portion 708 into the Random Access Memory (RAM) 703. The RAM 703 also stores data required as needed when the CPU 701 performs various processes. The CPU is merely exemplary and can be other types of processors, such as the various processors described above. The ROM 702, RAM 703, and storage portion 708 can be various forms of computer-readable storage media, as described below. It should be noted that although the ROM 702, RAM 703, and storage device 708 are shown separately in Figure 7, one or more of them can be combined or located in the same or different memories or storage modules.

[0131] CPU 701, ROM 702 and RAM 703 are interconnected via bus 704. Input / output interface 705 is also connected to bus 704.

[0132] The following components are connected to the input / output interface 705: input section 706, such as a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output section 707, including displays such as cathode ray tube (CRT), liquid crystal display (LCD), speakers, vibrators, etc.; storage section 708, including hard disk, magnetic tape, etc.; and communication section 709, including network interface cards such as LAN cards, modems, etc. The communication section 709 allows communication processing to be performed via a network such as the Internet. It is readily understood that although the various devices or modules in the computer system 70 shown in Figure 7 communicate via bus 704, they can also communicate via a network or other means, wherein the network can include wireless networks, wired networks, and / or any combination of wireless and wired networks.

[0133] As needed, drive 710 is also connected to input / output interface 705. Removable media 711, such as disks, optical disks, magneto-optical disks, semiconductor memories, etc., are installed on drive 710 as needed, so that computer programs read from them can be installed into storage section 708 as needed.

[0134] When the above series of processes are implemented through software, the program constituting the software can be installed from a network such as the Internet or from a storage medium such as removable media 711.

[0135] According to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 709, or installed from a storage device 708, or installed from a ROM 702. When the computer program is executed by the CPU 701, it performs the functions defined in the interactive methods of embodiments of this disclosure.

[0136] It should be noted that, in the context of this disclosure, a computer-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to, an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, capable of transmitting, propagating, or transmitting a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0137] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0138] In some embodiments, a computer program is also provided, comprising: instructions that, when executed by a processor, cause the processor to perform the interactive method of any of the above embodiments. For example, the instructions may be embodied in computer program code.

[0139] In embodiments of this disclosure, computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof. These programming languages ​​include, but are not limited to, object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network (including a local area network (LAN) or a wide area network (WAN)), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0140] 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 code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated 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, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0141] The modules, components, or units described in the embodiments of this disclosure can be implemented in software or hardware. The names of the modules, components, or units do not necessarily constitute a limitation on the module, component, or unit itself.

[0142] The functions described above in this document can be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary hardware logic components that can be used include: field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), and so on.

[0143] According to some embodiments of this disclosure, an interaction method is provided, including: displaying an instruction creation interface in response to a user's triggering of an instruction creation function; determining prompt information corresponding to the target instruction based on information input by the user on the instruction creation interface for creating a target instruction, wherein the target instruction is used to represent the user's demand information for the interactive function of the intelligent agent; and generating and displaying operation controls for the target instruction based on the prompt information.

[0144] In some embodiments, the operation control for displaying the target instruction includes: determining the distribution scenario of the control for the target instruction in response to the user's setting of the distribution scenario or according to the target instruction;

[0145] In some embodiments, determining the prompt information corresponding to the target instruction based on the information entered by the user on the instruction creation interface for creating the target instruction includes: generating structured prompt information corresponding to the target instruction based on the information entered by the user on the instruction creation interface for creating the target instruction.

[0146] In some embodiments, generating structured prompt information corresponding to a target instruction based on information input by the user on the instruction creation interface includes: parsing the information used to create the target instruction to determine the content of at least one of the tasks and outputs included in the information used to create the target instruction; expanding the content of at least one of the tasks and outputs to generate task description information and output description information in the prompt information; and generating structured prompt information corresponding to the target instruction based on the task description information and output description information.

[0147] In some embodiments, expanding the content of at least one of the tasks and outputs includes: expanding the content of at least one of the tasks and outputs based on the content of at least one of the tasks and outputs and sample prompt information, wherein the sample prompt information includes sample task description information and sample output description information.

[0148] In some embodiments, the sample prompt information is a structured prompt information generated by combining the sample task description information and the sample output description information according to a preset structure. Generating the structured prompt information corresponding to the target instruction includes: generating the structured prompt information corresponding to the target instruction based on the task description information and output description information in the generated prompt information and the preset structure corresponding to the sample prompt information.

[0149] In some embodiments, generating structured prompt information corresponding to the target instruction based on the information entered by the user in the instruction creation interface for creating the target instruction includes: responding to the user's triggering of the information completion control in the instruction creation interface, generating structured prompt information corresponding to the target instruction based on the information entered by the user in the instruction creation interface for creating the target instruction.

[0150] In some embodiments, the instruction creation interface includes a title input area and an instruction content input area; the information used to create the target instruction includes at least one of the title and content of the target instruction; in response to the information used to create the target instruction including the title of the target instruction, the title of the target instruction is displayed in the operation control of the target instruction; in response to the information used to create the target instruction not including the title of the target instruction, the title generated according to the prompt information is displayed in the operation control of the target instruction.

[0151] In some embodiments, the operation controls for generating and displaying the target instruction based on the prompt information include: in response to the user's confirmation operation on the prompt information, generating an interactive function corresponding to the target instruction and an operation control for the target instruction associated with the interactive function based on the prompt information; and displaying the operation control for the target instruction.

[0152] In some embodiments, displaying the instruction creation interface in response to a user's triggering of the instruction creation function includes: displaying operation controls for the instruction creation function; and displaying the instruction creation interface in response to a user's triggering of the operation controls for the instruction creation function.

[0153] In some embodiments, in response to a user triggering the instruction creation function, displaying the instruction creation interface includes: in response to a user inputting first interactive information, displaying the first interactive information; in response to a user triggering the instruction creation function for the first interactive information; displaying the instruction creation interface, and displaying the first interactive information as information for creating the target instruction in the instruction creation interface.

[0154] In some embodiments, the interaction method further includes: displaying a prompt message; and updating the prompt message in response to a user's modification operation on the prompt message.

[0155] In some embodiments, the interaction method further includes: in response to the user's operation control of the target instruction, displaying information corresponding to the target instruction sent to the agent, and outputting response information generated by the agent based on the target instruction; or in response to the user's operation control of the target instruction, displaying guidance information to enable interaction based on the target instruction, and in response to the user inputting second interaction information, outputting response information generated by the agent based on the target instruction and the second interaction information.

[0156] In some embodiments, the interaction method further includes: displaying guidance information to enable the target instruction in response to a third interaction message input by the user matching the target instruction; displaying information corresponding to the target instruction sent to the agent in response to a user's confirmation operation; and outputting response information generated by the agent based on the target instruction in response to a user's confirmation operation; or displaying guidance information to enable interaction based on the target instruction in response to a fourth interaction message input by the user matching the target instruction; and outputting response information generated by the agent based on the target instruction and the fourth interaction message in response to a user's fourth interaction message.

[0157] In some embodiments, the interaction method further includes: displaying one or more created instructions in response to a user's triggering of the instruction viewing function; displaying the title and prompt information corresponding to the first instruction in response to a user's editing operation on the first instruction among the one or more instructions; updating and displaying the title and prompt information corresponding to the first instruction in response to a user's modification operation on at least one of the title and prompt information corresponding to the first instruction; and displaying the operation controls of the updated first instruction in response to a user's confirmation operation on the updated title and prompt information corresponding to the first instruction.

[0158] In some embodiments, the interaction method further includes: displaying one or more created instructions in response to a user's triggering of the instruction viewing function; and deleting the operation control of the second instruction in response to a user's deletion operation of the second instruction among the one or more instructions.

[0159] According to some other embodiments of this disclosure, an interactive device is provided, comprising: a first display module configured to display an instruction creation interface in response to a user's triggering of an instruction creation function; a determination module configured to determine prompt information corresponding to a target instruction based on information input by the user for creating a target instruction, wherein the target instruction is used to represent the user's demand information for the interactive function of the intelligent agent; and a second display module configured to generate and display operation controls for the target instruction based on the prompt information.

[0160] According to further embodiments of the present disclosure, an electronic device is provided, including: a processor; and a memory coupled to the processor for storing instructions that, when executed by the processor, cause the processor to perform an interactive method of any embodiment of the present disclosure.

[0161] According to further embodiments of the present disclosure, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, performs the interactive method of any embodiment of the present disclosure.

[0162] According to some further embodiments of the present disclosure, a computer program product is provided, comprising: instructions that, when executed by a processor, implement the interaction method of any embodiment of the present disclosure.

[0163] According to further embodiments of the present disclosure, a computer program is provided, comprising: instructions that, when executed by a processor, implement the interactive method of any embodiment of the present disclosure.

[0164] The above description is merely an embodiment of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features disclosed in this disclosure that have similar functions.

[0165] Many specific details are set forth in the description provided herein. However, it is understood that embodiments of the invention may be practiced without these specific details. In other instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of the description.

[0166] Furthermore, while the operations are described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or in a sequential order. In certain environments, multitasking and parallel processing may be advantageous. Similarly, while several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of this disclosure. Certain features described in the context of individual embodiments may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented individually or in any suitable sub-combination in multiple embodiments.

[0167] While specific embodiments of this disclosure have been described in detail by way of example, those skilled in the art should understand that the examples are for illustrative purposes only and not intended to limit the scope of this disclosure. Those skilled in the art should understand that modifications can be made to the above embodiments without departing from the scope and spirit of this disclosure. The scope of this disclosure is defined by the appended claims.

Claims

1. An interaction method, comprising: In response to the user's triggering of the command creation function, the command creation interface is displayed; Based on the information entered by the user on the instruction creation interface for creating a target instruction, the prompt information corresponding to the target instruction is determined, wherein the target instruction is used to represent the user's demand information for the interactive functions of the intelligent agent; Based on the prompt information, generate and display the operation controls for the target instruction.

2. The interaction method according to claim 1, wherein, The operation control for displaying the target instruction includes: In response to the user's setting of the distribution scenario or according to the target instruction, determine the distribution scenario of the control of the target instruction; The operation controls for the target instruction are displayed in the distribution scenario.

3. The interaction method according to claim 1, wherein, The step of determining the prompt information corresponding to the target instruction based on the information entered by the user on the instruction creation interface includes: Based on the information entered by the user in the instruction creation interface for creating the target instruction, a structured prompt message corresponding to the target instruction is generated.

4. The interaction method according to claim 3, wherein, The step of generating structured prompt information corresponding to the target instruction based on the information entered by the user on the instruction creation interface for creating the target instruction includes: The information used to create the target instruction is parsed to determine at least one of the tasks and outputs included in the information used to create the target instruction. Expand the content of at least one of the task and the output to generate the task description information and output description information in the prompt information; Based on the task description information and output description information, a structured prompt message corresponding to the target instruction is generated.

5. The interaction method according to claim 4, wherein, The expansion of at least one of the tasks and outputs includes: Based on the content of at least one of the tasks and the outputs, and the example prompt information, the content of at least one of the tasks and the outputs is expanded, wherein the example prompt information includes example task description information and example output description information.

6. The interaction method according to claim 5, wherein, The example prompt information is a structured prompt information generated by combining the example task description information and the example output description information according to a preset structure. The generation of the structured prompt information corresponding to the target instruction includes: Based on the task description information and output description information in the generated prompt information, as well as the preset structure corresponding to the sample prompt information, a structured prompt information corresponding to the target instruction is generated.

7. The interaction method according to any one of claims 3-6, wherein, The step of generating structured prompt information corresponding to the target instruction based on the information entered by the user on the instruction creation interface for creating the target instruction includes: In response to the user's activation of the information completion control in the instruction creation interface, a structured prompt message corresponding to the target instruction is generated based on the information entered by the user in the instruction creation interface for creating the target instruction.

8. The interaction method according to any one of claims 1-7, wherein: The instruction creation interface includes a title input area and an instruction content input area; The information used to create the target instruction includes at least one of the target instruction's title and the target instruction's content; In response to the information used to create the target instruction including the title of the target instruction, the title of the target instruction is displayed in the operation control of the target instruction; In response to the fact that the information used to create the target instruction does not include the title of the target instruction, the title generated based on the prompt information is displayed in the operation control of the target instruction.

9. The interaction method according to any one of claims 1-8, wherein, The operation control that generates and displays the target instruction based on the prompt information includes: In response to the user's confirmation of the prompt information, an interactive function corresponding to the target instruction and an operation control of the target instruction associated with the interactive function are generated according to the prompt information. The operation controls that display the target instruction.

10. The interaction method according to any one of claims 1-9, wherein, The step of displaying the instruction creation interface in response to the user's triggering of the instruction creation function includes: The operation controls for displaying the instruction creation function; In response to the user's operation control of the instruction creation function, the instruction creation interface is displayed.

11. The interaction method according to any one of claims 1-10, wherein, The step of displaying the instruction creation interface in response to the user's triggering of the instruction creation function includes: In response to the user inputting first interactive information, the first interactive information is displayed; In response to the user triggering an instruction creation function for the first interactive information; The instruction creation interface is displayed, and the first interactive information is displayed in the instruction creation interface as the information used to create the target instruction.

12. The interaction method according to any one of claims 1-11, further comprising: Display the aforementioned prompt message; In response to the user's modification of the prompt information, the prompt information is updated according to the modification operation.

13. The interaction method according to any one of claims 1-12, further comprising: In response to the user's operation control on the target instruction, the system displays information corresponding to the target instruction sent to the agent and outputs the response information generated by the agent based on the target instruction. or In response to the user's operation control of the target instruction, guidance information for enabling interaction based on the target instruction is displayed; in response to the user inputting second interaction information, response information generated by the agent based on the target instruction and the second interaction information is output.

14. The interaction method according to any one of claims 1-13, further comprising: In response to the user's input of third interactive information matching the target instruction, guidance information for enabling the target instruction is displayed; in response to the user's confirmation operation, information corresponding to the target instruction is sent to the agent, and response information generated by the agent based on the target instruction is output. or In response to the user inputting fourth interaction information matching the target instruction, guidance information for enabling interaction based on the target instruction is displayed; in response to the user inputting fourth interaction information, response information generated by the agent based on the target instruction and the fourth interaction information is output.

15. The interaction method according to any one of claims 1-14, further comprising: In response to the user's triggering of the command viewing function, display one or more commands that have been created; In response to the user's editing operation on the first instruction among the one or more instructions, the title and prompt information corresponding to the first instruction are displayed; In response to the user's modification of at least one of the title and prompt information corresponding to the first instruction, update and display the title and prompt information corresponding to the first instruction; In response to the user's confirmation of the title and prompt information corresponding to the updated first instruction, the operation controls for the updated first instruction are displayed.

16. The interaction method according to any one of claims 1-15, further comprising: In response to the user's triggering of the command viewing function, display one or more commands that have been created; In response to the user's deletion operation on the second instruction among the one or more instructions, the operation control of the second instruction is deleted.

17. An interactive device, comprising: The first display module is configured to display the command creation interface in response to the user's triggering of the command creation function; The determining module is configured to determine the prompt information corresponding to the target instruction based on the information input by the user for creating the target instruction, wherein the target instruction is used to represent the user's demand information for the interactive functions of the intelligent agent; The second display module is configured to generate and display operation controls for the target instruction based on the prompt information.

18. An electronic device comprising: processor; as well as A memory coupled to the processor is used to store instructions that, when executed by the processor, cause the processor to perform the interaction method as described in any one of claims 1-16.

19. A computer-readable storage medium having a computer program stored thereon, wherein, When the program is executed by the processor, it implements the interaction method as described in any one of claims 1-16.

20. A computer program product comprising: Instructions that, when executed by a processor, implement the interaction method as described in any one of claims 1-16.

Images