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

Abstract

The present disclosure relates to an interaction method and apparatus, an electronic device, a storage medium and a program product, and relates to the technical field of artificial intelligence. The interaction method of the present disclosure comprises: displaying an interaction interface between a user and a first agent; on the basis of interaction information between the user and the first agent, determining one or more interaction functions associated with the interaction information, the one or more interaction functions being used for interacting with the user on the basis of an intent indicated by the interaction information; displaying operation controls of the one or more interaction functions; and in response to the user triggering a target operation control among the operation controls of the one or more interaction functions, invoking the interaction function corresponding to the target operation control to perform interactions with the user.

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 interaction interface between a user and a first intelligent agent; determining one or more interaction functions associated with the interaction information between the user and the first intelligent agent, wherein the one or more interaction functions are used to interact with the user based on the intent reflected in the interaction information; displaying operation controls for the one or more interaction functions; and, in response to the user triggering a target operation control among the operation controls of the one or more interaction functions, calling the interaction function corresponding to the target operation control to interact with the user.

[0006] According to other embodiments of this disclosure, an interactive device is provided, comprising: a first display module configured to display an interactive interface between a user and a first intelligent agent; a determining module configured to determine one or more interactive functions associated with the interaction information between the user and the first intelligent agent; a second display module configured to display operation controls for one or more interactive functions; and an interaction module configured to, in response to a user triggering a target operation control among the operation controls for one or more interactive functions, invoke the interactive function corresponding to the target operation control to interact with the user.

[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] Figure 2 shows a schematic diagram of the interactive interface of some embodiments of this disclosure;

[0015] Figure 3 shows a schematic diagram of the interactive interface of some other embodiments of this disclosure;

[0016] Figure 4 shows a schematic diagram of the interactive interface of some embodiments of this disclosure;

[0017] Figure 5 shows a schematic diagram of the structure of an interactive device according to some embodiments of the present disclosure;

[0018] Figure 6 shows a schematic diagram of the structure of an electronic device according to some embodiments of the present disclosure;

[0019] Figure 7 shows a schematic diagram of the structure of a computer system according to some embodiments of the present disclosure.

[0020] 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

[0021] 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.

[0022] 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.

[0023] 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".

[0024] 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.

[0025] 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.

[0026] 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".

[0027] 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.

[0028] 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.

[0029] Intelligent agents can be implemented based on artificial intelligence technologies such as large-scale models and can interact with users. One or more intelligent agents can be implemented within an application (APP) or client, and each agent can perform one or more interactive functions. For example, different intelligent agents can be created based on different roles, scenarios, domains, functions, etc., and different interactive functions can be used to achieve interaction with users based on different roles, scenarios, tool functions, domains, etc. For example, the same intelligent agent or different intelligent agents can implement various interactive functions such as chat, translation, and knowledge-based Q&A in a specific domain.

[0030] Different interactive functions can engage with users from different perspectives, providing more accurate responses. Users can search for interactive functions and trigger their corresponding controls to interact with them. However, when multiple interactive functions are available, users may struggle to quickly locate the desired function and achieve accurate interaction.

[0031] This disclosure proposes an interaction method that can improve the efficiency and accuracy of user interaction, which is described below with reference to Figures 1-4.

[0032] 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 S108.

[0033] In step S102, the interaction interface between the user and the first intelligent agent is displayed.

[0034] The first agent can interact with the user based on a machine learning model. The content of the interaction can include various forms of content such as text, voice, and images, without limitation. The machine learning model is, for example, an LLM (Large Language Model), but is not limited to the examples given. The first agent can be the basic agent or the default agent in the application. For example, it can display the interaction interface between the user and the first agent in response to the user triggering interactive controls in the application.

[0035] The first intelligent agent can be created based on a specific role, scenario, domain, or function. For example, the first intelligent agent may be an agent that plays a specific role and interacts with the user; or it may be an agent that simulates a specific plot (scenario) and interacts with the user; or it may possess knowledge of a specific domain and interact with the user based on that knowledge; or it may function as a specific tool and interact with the user based on the tool's functions. The first intelligent agent can be created by the user or provided by the application or client itself, and can be created based on actual needs, not limited to the examples given. The first intelligent agent can also implement one or more interactive functions. For example, in response to the user's triggering of an interactive function on the first intelligent agent, an interactive interface between the user and the first intelligent agent can be displayed.

[0036] In step S104, one or more interactive functions associated with the interaction information are determined based on the interaction information between the user and the first intelligent agent.

[0037] Users can input information in the interactive interface using text, voice, or other means, and the first intelligent agent can generate response information. The user's input and response information serve as the interaction information between the user and the first intelligent agent.

[0038] Machine learning models can be used to analyze the interaction information between the user and the first intelligent agent to determine the user's intent, thereby identifying one or more interactive functions associated with the interaction information. For example, the machine learning model could be the one corresponding to the first intelligent agent.

[0039] For example, one or more interactive functions are used to interact with the user based on the intent reflected in the interactive information. For instance, if the interactive information reflects that the user wants to interact with a specific role, then the interactive function corresponding to that specific role is determined to be the interactive function associated with the interactive information. For instance, if the interactive information reflects that the user wants to acquire knowledge in a specific domain, then the interactive function corresponding to that specific domain is determined to be the interactive function associated with the interactive information. One or more interactive functions can be interactive functions that interact with the user based on different dimensions. One or more interactive functions can correspond to a first intelligent agent or to other intelligent agents besides the first intelligent agent. When multiple interactive functions are determined, the multiple interactive functions can partially correspond to the first intelligent agent and partially correspond to other intelligent agents.

[0040] In step S106, one or more interactive function operation controls are displayed.

[0041] The user interface for interacting with the first intelligent agent can include a display area and an input area. The display area can show the interaction information between the user and the first intelligent agent, while the input area can receive and display user input. One or more interactive function controls can be displayed in either the display or input area. Based on the interaction information between the user and the first intelligent agent, one or more interactive functions associated with the interaction information can be automatically recommended to the user.

[0042] In step S108, in response to the user's triggering of the target operation control in one or more interactive function operation controls, the interactive function corresponding to the target operation control is invoked to interact with the user.

[0043] In response to a user's interaction with a target control, the corresponding interactive function can be directly invoked to interact with the user. If the interactive function corresponding to the target control is the same as that of the first agent, then the first agent interacts with the user based on that interactive function. If the interactive function corresponding to the target control is another agent, then that other agent can be invoked to interact with the user based on that interactive function.

[0044] In the method of the above embodiments, during the interaction between the user and the first intelligent agent, one or more interactive functions associated with the interaction information are determined based on the interaction information, and these one or more interactive functions are displayed to the user. Since these one or more functions are determined based on the intent reflected in the interaction information, the user does not need to search for the required interactive function; interactive functions corresponding to the user's intent can be automatically recommended and displayed based on the interaction information. After the user triggers the target operation control, the interactive function corresponding to the target operation control can be directly invoked, interacting with the user based on the user's intent, thus improving the efficiency and accuracy of user interaction.

[0045] Interactive functions can be functions that control the output of an agent based on prompts, resulting in a specific type of response generated by the agent. Interactive functions can also be interactive functions of an already created agent capable of generating specific types of responses. The difference between the two is that in the former case, the response generated by the agent itself may not fully meet the requirements, and prompts can guide the agent's corresponding model to output a specific type of response. In the latter case, the agent itself can generate a specific type of response that meets the requirements.

[0046] In some embodiments, one or more interactive functions associated with interactive information include: interactive functions based on a role associated with the interactive information, interactive functions based on a domain associated with the interactive information, interactive functions based on a scene associated with the interactive information, and interactive functions based on a tool associated with the interactive information. Interactive functions can be distinguished from different dimensions such as role, domain, scene, and tool.

[0047] Information about interactive functions in an application or client can be pre-configured in an interactive function library. Based on the interaction information between the user and the first intelligent agent, one or more interactive functions associated with the interaction information are retrieved from the interactive function library. The following describes, with reference to some embodiments, how to determine one or more interactive functions associated with the interaction information based on the interaction information between the user and the first intelligent agent.

[0048] In some embodiments, a machine learning model is used to understand the intent reflected in the interactive information and generate summary information corresponding to the interactive information; based on the summary information, one or more interactive functions associated with the interactive information are determined from the interactive function library.

[0049] Machine learning models, such as LLM models, can be used. The latest interaction message and a preset number of previous interactions can be input into the machine learning model to obtain summary information. This summary information is then matched with information about various interaction functions in the interaction function library to determine one or more interaction functions associated with the interaction message.

[0050] In some embodiments, based on the summary information, one or more types that match the summary information are determined; in the interactive function library, interactive functions that match the summary information are selected from the interactive functions of each of the one or more types as one or more interactive functions associated with the interactive information.

[0051] Different interactive functions can be categorized into one or more classes for storage. For example, they can be categorized into role classes, domain classes, tool classes, scenario classes, etc., and are not limited to the examples given. The same interactive function can belong to multiple categories. One or more matching types can be determined based on summary information. For example, if the summary information obtained based on the user's interaction with the first agent includes a certain person, then it can be determined that the type matching the summary information includes the role class. Furthermore, it can be determined whether an interactive function corresponding to that person exists within the interactive functions of the role class.

[0052] The method described in the above embodiments uses a machine learning model to parse interactive information, generates summary information based on the intent of the interactive information, and then matches the interactive function, which can improve the accuracy of the determined interactive function.

[0053] In some embodiments, a machine learning model is used to parse the interactive information and extract keywords from the interactive information; based on the keywords, one or more interactive functions associated with the interactive information are determined from the interactive function library.

[0054] Information about interactive functions includes, for example, their identifiers and descriptions. The descriptions can specify the specific role, domain, tool function, or scenario name associated with the interactive function. The information can also include the category of the interactive function. By directly extracting keywords and matching them with information from various interactive functions in the interactive function library, one or more interactive functions associated with the relevant interactive information can be obtained.

[0055] In some embodiments, one or more types matching the keyword are determined; in the interactive function library, interactive functions matching the keyword are selected from the interactive functions of each of the one or more types as one or more interactive functions associated with the interactive information.

[0056] For example, keywords can include entity words, which correspond to entity categories. One or more types that match the keywords can be determined based on the entity categories, and then interactive functions that match the keywords can be selected from the interactive functions of each type.

[0057] The method described in the above embodiments uses a machine learning model to parse and extract keywords from interactive information, and then matches interactive functions based on these keywords, which can improve the accuracy of the determined interactive functions.

[0058] The methods described above for determining one or more interactive functions associated with interactive information based on summary information and keywords can be applied in combination. A machine learning model is used to determine summary information and keywords, and then one or more interactive functions associated with the interactive information are determined from the interactive function library based on the summary information and keywords. For details, please refer to the foregoing embodiments, which will not be repeated here.

[0059] In some embodiments, one or more candidate interactive functions are matched based on summary information and / or keywords. Based on the one or more candidate interactive functions, an interactive function associated with the one or more candidate interactive functions is determined. The one or more candidate interactive functions and their associated interactive functions are taken as one or more interactive functions associated with the interactive information.

[0060] Based on the summary information and / or keyword matching results, the number of interactive functions can be expanded to provide users with more optional interactive functions, making user operation easier and improving interaction efficiency. For example, interactive functions corresponding to roles related to candidate interactive functions can be identified; interactive functions associated with candidate interactive functions can be identified within the domain of candidate interactive functions; interactive functions associated with candidate interactive functions can be identified within the domain of candidate interactive functions; and interactive functions related to the tool functions of candidate interactive functions can be identified. The relationships between interactive functions can be pre-configured.

[0061] After identifying one or more interactive functions associated with the interactive information, operation controls for one or more interactive functions can be displayed. As shown in Figure 2, in the interaction interface between the user and the first intelligent agent a, the interaction information between the user and a is displayed in the display area 201. During the interaction, the user mentions "what kind of person is b". Based on the method of the above embodiment, it can be determined that one or more interactive functions associated with the interactive information include the interactive functions of the intelligent agent corresponding to b. b belongs to the automotive field. One or more interactive functions associated with the interactive information can also include the interactive functions of the intelligent agent corresponding to the automotive field expert, etc. As shown in Figure 2, one or more interactive function operation controls 203 can be displayed in the display area 201 of the interactive interface near the input area 202. The operation controls 203 of the interactive functions can display the image, name, and other identification information corresponding to the intelligent agent, which is convenient for the user to view and improves the selection and interaction efficiency.

[0062] The role corresponding to the intelligent agent can be a real person or a virtual person. The specific role played or imitated by the intelligent agent in this disclosure is authorized by the role itself or the role's creator or other relevant personnel.

[0063] As shown in Figure 2, the first agent 'a' can generate and display response information based on user input, such as a response to "What kind of person is 'b'?". Agent 'a' can also generate candidate questions to allow further user interaction. These candidate questions are generated based on interaction information. These candidate questions differ from the interaction function; they are information from a single interaction, representing potential input from the user, thus improving input efficiency. In contrast, the interaction function allows the corresponding agent to engage in multiple rounds of interaction with the user, with each round generating a specific type of response. This specific type can be determined based on actual needs.

[0064] One or more interactive functions associated with the interactive information can be interactive functions corresponding to the first intelligent agent or interactive functions corresponding to other intelligent agents. The following describes the different situations.

[0065] In some embodiments, where one or more interactive functions associated with interactive information include interactive functions corresponding to a first intelligent agent, the interactive function corresponding to the target operation control is a first interactive function corresponding to the first intelligent agent. In response to the user's triggering of the target operation control, the prompt information corresponding to the first interactive function is obtained; based on the prompt information, the first interactive function corresponding to the first intelligent agent is generated; and the first intelligent agent is used to interact with the user based on the first interactive function.

[0066] The first interactive function can be obtained by adjusting the machine learning model corresponding to the first intelligent agent based on the prompt information. The target operation control can be associated with the prompt information corresponding to the first interactive function. In response to the triggering of the target operation control, the prompt information is input into the machine learning model corresponding to the first intelligent agent, thereby obtaining the first interactive function. For example, the first interactive function is a Chinese-English translation function. The prompt information may include descriptions of the Chinese-English translation task, descriptions of the output requirements, etc. When the user triggers the Chinese-English translation operation control, the first intelligent agent and the user will interact in Chinese-English translation. The user inputs Chinese, and the first intelligent agent replies in English; the user inputs English, and the first intelligent agent replies in Chinese.

[0067] Interactive functions can improve the efficiency and accuracy of interaction. Users do not need to repeatedly input prompts into the agent, nor do they need to adjust the form of the input information based on the agent's response so that the agent can output a response that meets their needs.

[0068] The method described in the above embodiments can directly obtain prompt information based on the user's triggering of the target operation control, and obtain the first interactive function based on the prompt information, so that the first intelligent agent can interact with the user based on the first interactive function, thereby improving the efficiency of the user calling the first interactive function and thus improving the efficiency and accuracy of the interaction.

[0069] In some embodiments, in the user's interaction interface with the first intelligent agent, guidance information for enabling the first interaction function is displayed; in response to the first information input by the user based on the guidance information, response information generated by the first intelligent agent based on the first information and the first interaction function is displayed.

[0070] For example, guidance information indicating the activation of the first interactive function can be displayed in the display area or input area. For instance, a preset effect could be used to display "Chinese-English translation" in the input area, or guidance information such as "Start Chinese-English translation now" could be displayed in the display area. Guidance information such as requirements for user input information could also be displayed, and these examples are not limited to those given. The first intelligent agent generates response information based on the first information input by the user using the first interactive function, and displays it in the interactive interface.

[0071] Prompt information helps users perform subsequent interactive operations, improves the user experience, and increases the efficiency and accuracy of interaction.

[0072] In some embodiments, where one or more interactive functions associated with interactive information include interactive functions corresponding to a second intelligent agent, the interactive function corresponding to the target operation control is a second interactive function corresponding to the second intelligent agent. In response to the user's triggering of the target operation control, the second intelligent agent is invoked to interact with the user based on the second interactive function.

[0073] The second agent can be a pre-created agent with second interactive capabilities. When the user triggers the target operation control, the interaction between the first agent and the second agent is switched.

[0074] In some embodiments, an interaction interface between the user and the second intelligent agent is displayed; in response to second information input by the user on the interaction interface with the second intelligent agent, a response message generated by the second intelligent agent based on the second information and the second interaction function is displayed.

[0075] Users can input secondary information in the form of text, voice, etc., and the secondary intelligent agent can directly interact with the user to generate response information.

[0076] In some embodiments, initial input information is generated based on historical input information related to the second interactive function. This initial input information is then displayed on the user's interface with the second agent, along with corresponding response information generated based on the second interactive function. For example, the user's question regarding the second interactive function can be converted into initial input information by changing the subject, thereby automatically generating the corresponding answer. This reduces user operations, improves interaction efficiency, and enhances the user experience.

[0077] For example, as shown in Figure 2, the agent corresponding to 'b' is the second agent. Responding to the user's operation controls on the agent corresponding to 'b', the interactive interface shown in Figure 3 is displayed. As shown in Figure 3, in the user-second agent interaction interface, the user can input "What kind of person are you?", or the system can directly generate "What kind of person are you?" as the initial input information based on the user's previous input "What kind of person is 'b'?", and then the second agent 'b' will generate a corresponding response. Other related interactive functions, such as "Automotive Expert," can also be displayed in the user-second agent 'b' interaction interface for user selection.

[0078] Operation controls for one or more interactive functions

[0079] In some embodiments, one or more operation controls for interactive functions are displayed in the user's interaction interface with the first intelligent agent; and / or in response to the user's triggering of the interactive function entry control, one or more operation controls for interactive functions are displayed on the recommendation tag page.

[0080] As shown in Figure 2 or 3, one or more interactive function operation controls can be directly displayed in the interactive interface. The area displaying one or more interactive function operation controls supports sliding display; for example, users can view all interactive functions associated with interactive information by sliding.

[0081] Alternatively, an interactive function entry control can be displayed in the interactive interface. In response to the user's triggering of the interactive function entry control, the interactive function display interface is displayed, and one or more operation controls for interactive functions are displayed on the recommended tab page of the interactive function display interface. As shown in Figure 2 or 3, the interactive function entry control is, for example, a "command" control. In response to the user's triggering of the "command" control, the recommended tab page shown in Figure 4 is displayed.

[0082] As shown in Figure 4, the recommended tag page 401 can be displayed as a half-page, or as a window, overlay, or other forms; there are no restrictions here. Interactive functions and agents based on prompts can be displayed differently. For example, as shown in Figure 4, agents correspond to image icons, and interactive functions based on prompts, such as "Chinese-English translation," can be identified using preset identifiers for easy user differentiation.

[0083] When there are multiple interactive functions, and a large number of them, only some interactive functions can be displayed in the interactive interface, while all interactive functions associated with the interactive information can be displayed in full on the recommendation tag page. Users can view interactive functions in different ways for easier selection. The display order can be determined based on the relevance between interactive functions and interactive information.

[0084] In some embodiments, one or more controls corresponding to one or more functional categories are displayed; in response to a user triggering a control corresponding to a target functional category in one or more functional categories, one or more interactive functions belonging to the target functional category are displayed on the tab page of the target functional category.

[0085] The one or more functional categories here may be the same as or different from the classification of interactive function types involved in the foregoing embodiments. For example, the one or more functional categories here may be more granular types.

[0086] For example, one or more controls corresponding to one or more functional categories can be displayed in the interactive function display interface, or one or more controls corresponding to one or more functional categories can be displayed in the user's interaction interface with the first intelligent agent. As shown in Figure 4, for example, one or more functional categories include categories such as AI drawing, copywriting, and emotional interaction. The controls 402 corresponding to these categories can be used to switch between displaying interactive functions of different functional categories. In response to the triggering of the tab page of the user's target functional category, the tab page of the target functional category is displayed, and one or more interactive functions are displayed. The tab page of one or more functional categories can contain interactive functions associated with interactive information or unrelated interactive functions. It can also contain interactive functions of various functional categories recommended to the current user based on the usage rate of all users, the popularity of interactive functions, etc.

[0087] By showing users more interactive functions categorized by function, we can increase the usage rate of these functions, thereby improving the efficiency and accuracy of our interactions with users.

[0088] After completing the interaction with the function corresponding to the target operation control, the user can exit the interaction function. For example, the user can switch from the interaction interface of the second intelligent agent to the interaction interface of the first intelligent agent, or exit directly. In some embodiments, in response to the user's operation to end the interaction function corresponding to the target operation control, the target operation control is displayed in the interaction interface between the user and the first intelligent agent.

[0089] After the user finishes interacting with the target operation control, the target operation control can be displayed in the interaction interface of the first intelligent agent. This allows the user to directly call the interaction function when they want to interact with the target operation control again, improving the convenience and efficiency of the operation.

[0090] In some embodiments, in response to a user's triggering of the search function, interactive functions corresponding to the search information are displayed based on the search information entered by the user.

[0091] Users can search for interactive functions. As shown in Figure 2, a search control 204 can be displayed to search for intelligent agents or interactive functions. In response to the user's triggering of the search control, a search input interface is displayed. In response to the search information entered by the user, one or more interactive functions corresponding to the search information are determined and displayed.

[0092] Setting up a search function makes it easier for users to find the interactive features they need, thus improving the user experience.

[0093] It should be noted that the acquisition and use of user-related information in this disclosure are all authorized by the user, and the user-related information has been de-identified.

[0094] This disclosure also provides an interactive device, which will be described below with reference to Figure 5.

[0095] 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, a second display module 530, and an interaction module 540.

[0096] The first display module 510 is configured to display the interaction interface between the user and the first intelligent agent.

[0097] The determination module 520 is configured to determine one or more interactive functions associated with the interaction information between the user and the first intelligent agent.

[0098] The second display module 530 is configured to display one or more interactive operation controls.

[0099] The interaction module 540 is configured to respond to the user's triggering of the target operation control in one or more interactive function operation controls, and to call the corresponding interactive function of the target operation control to interact with the user.

[0100] In some embodiments, the determining module 520 is configured to use a machine learning model to understand the intent reflected in the interaction information, generate summary information corresponding to the interaction information, and determine one or more interaction functions associated with the interaction information from the interaction function library based on the summary information.

[0101] In some embodiments, the determining module 520 is configured to determine one or more types that match the summary information based on the summary information; and in the interactive function library, select interactive functions that match the summary information from the interactive functions of each of the one or more types as one or more interactive functions associated with the interactive information.

[0102] In some embodiments, the determining module 520 is configured to use a machine learning model to parse the interaction information and extract keywords from the interaction information; and based on the keywords, determine one or more interaction functions associated with the interaction information from the interaction function library.

[0103] In some embodiments, the interactive function corresponding to the target operation control is a first interactive function corresponding to the first intelligent agent. The interaction module 540 is configured to respond to the user's triggering of the target operation control, obtain the prompt information corresponding to the first interactive function, generate the first interactive function corresponding to the first intelligent agent based on the prompt information, and interact with the user using the first intelligent agent based on the first interactive function.

[0104] In some embodiments, the interaction module 540 is configured to display guidance information for enabling the first interaction function in the interaction interface between the user and the first intelligent agent; and to display response information generated by the first intelligent agent based on the first information and the first interaction function in response to the first information input by the user based on the guidance information.

[0105] In some embodiments, the interactive function corresponding to the target operation control is a second interactive function corresponding to the second intelligent agent. The interaction module 540 is configured to respond to the user's triggering of the target operation control, call the second intelligent agent, and interact with the user based on the second interactive function.

[0106] In some embodiments, the interaction module 540 is configured to display an interaction interface between the user and the second intelligent agent; and in response to second information input by the user in the interaction interface with the second intelligent agent, to display response information generated by the second intelligent agent based on the second information and the second interaction function.

[0107] In some embodiments, the second display module 530 is configured to display one or more operation controls for interactive functions in the user's interaction interface with the first intelligent agent.

[0108] In some embodiments, the second display module 530 is configured to display operation controls for one or more interactive functions on the recommendation tab page in response to a user's triggering of the interactive function entry control.

[0109] In some embodiments, the second display module 530 is further configured to display one or more controls corresponding to one or more functional categories; in response to a user triggering a control corresponding to a target functional category in one or more functional categories, one or more interactive functions belonging to the target functional category are displayed on the tab page of the target functional category.

[0110] In some embodiments, the second display module 530 is further configured to display the target operation control in the interaction interface between the user and the first intelligent agent in response to the user's end operation on the interactive function corresponding to the target operation control.

[0111] In some embodiments, one or more interactive functions associated with interactive information include one or more of the following: interactive functions based on a role associated with the interactive information, interactive functions based on a domain associated with the interactive information, interactive functions based on a scene associated with the interactive information, and interactive functions based on a tool associated with the interactive information.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] CPU 701, ROM 702 and RAM 703 are interconnected via bus 704. Input / output interface 705 is also connected to bus 704.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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).

[0130] 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, may 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.

[0131] 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.

[0132] 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.

[0133] According to some embodiments of this disclosure, an interaction method is provided, including: displaying an interaction interface between a user and a first intelligent agent; determining one or more interaction functions associated with the interaction information between the user and the first intelligent agent, wherein the one or more interaction functions are used to interact with the user based on the intent reflected in the interaction information; displaying operation controls for the one or more interaction functions; and, in response to the user triggering a target operation control among the operation controls of the one or more interaction functions, calling the interaction function corresponding to the target operation control to interact with the user.

[0134] In some embodiments, determining one or more interactive functions associated with the interaction information based on the interaction information between the user and the first intelligent agent includes: using a machine learning model to understand the intent reflected by the interaction information and generating summary information corresponding to the interaction information; and determining one or more interactive functions associated with the interaction information from an interaction function library based on the summary information.

[0135] In some embodiments, determining one or more interactive functions associated with interactive information from an interactive function library based on summary information includes: determining one or more types that match the summary information based on the summary information; and selecting interactive functions that match the summary information from the interactive functions of each of the one or more types in the interactive function library as one or more interactive functions associated with the interactive information.

[0136] In some embodiments, determining one or more interactive functions associated with the interaction information based on the interaction information between the user and the first intelligent agent includes: parsing the interaction information using a machine learning model to extract keywords from the interaction information; and determining one or more interactive functions associated with the interaction information from an interaction function library based on the keywords.

[0137] In some embodiments, the interactive function corresponding to the target operation control is a first interactive function corresponding to the first intelligent agent. In response to the user's triggering of the target operation control among the operation controls of one or more interactive functions, calling the interactive function corresponding to the target operation control to interact with the user includes: in response to the user's triggering of the target operation control, obtaining the prompt information corresponding to the first interactive function; generating the first interactive function corresponding to the first intelligent agent based on the prompt information; and using the first intelligent agent to interact with the user based on the first interactive function.

[0138] In some embodiments, using a first intelligent agent to interact with a user based on a first interactive function includes: displaying guidance information indicating that the first interactive function is enabled in the interaction interface between the user and the first intelligent agent; and displaying response information generated by the first intelligent agent based on the first information and the first interactive function in response to first information input by the user based on the guidance information.

[0139] In some embodiments, the interactive function corresponding to the target operation control is a second interactive function corresponding to the second agent. In response to the user's triggering of the target operation control in one or more interactive function operation controls, calling the interactive function corresponding to the target operation control to interact with the user includes: in response to the user's triggering of the target operation control, calling the second agent to interact with the user based on the second interactive function.

[0140] In some embodiments, invoking a second intelligent agent to interact with a user based on a second interactive function includes: displaying an interactive interface between the user and the second intelligent agent; and, in response to second information input by the user on the interactive interface with the second intelligent agent, displaying response information generated by the second intelligent agent based on the second information and the second interactive function.

[0141] In some embodiments, the operation controls for displaying one or more interactive functions include: displaying operation controls for one or more interactive functions in the interaction interface between the user and the first intelligent agent.

[0142] In some embodiments, the operation controls for displaying one or more interactive functions include: in response to a user's triggering of the interactive function entry control, displaying operation controls for one or more interactive functions on the recommendation tag page.

[0143] In some embodiments, the interaction method further includes: displaying one or more controls corresponding to one or more functional categories; and in response to a user triggering a control corresponding to a target functional category in one or more functional categories, displaying one or more interactive functions belonging to the target functional category on the tab page of the target functional category.

[0144] In some embodiments, the interaction method further includes: in response to the user's end operation on the interaction function corresponding to the target operation control, displaying the target operation control in the interaction interface between the user and the first intelligent agent.

[0145] In some embodiments, one or more interactive functions associated with interactive information include one or more of the following: interactive functions based on a role associated with the interactive information, interactive functions based on a domain associated with the interactive information, interactive functions based on a scene associated with the interactive information, and interactive functions based on a tool associated with the interactive information.

[0146] According to some other embodiments of this disclosure, an interactive device is provided, comprising: a first display module configured to display an interactive interface between a user and a first intelligent agent; a determining module configured to determine one or more interactive functions associated with the interaction information between the user and the first intelligent agent; a second display module configured to display operation controls for one or more interactive functions; and an interaction module configured to, in response to a user triggering a target operation control among the operation controls of one or more interactive functions, invoke the interactive function corresponding to the target operation control to interact with the user.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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: Displays the user interface for interacting with the first intelligent agent; Based on the interaction information between the user and the first intelligent agent, one or more interactive functions associated with the interaction information are determined, wherein the one or more interactive functions are used to interact with the user based on the intention reflected by the interaction information. Operation controls that display one or more of the aforementioned interactive functions; In response to the user's triggering of a target operation control among the operation controls of one or more interactive functions, the interactive function corresponding to the target operation control is invoked to interact with the user.

2. The interaction method according to claim 1, wherein, The step of determining one or more interactive functions associated with the interaction information based on the interaction information between the user and the first intelligent agent includes: Using a machine learning model, the intent reflected in the interaction information is understood, and summary information corresponding to the interaction information is generated; Based on the summarized information, one or more interactive functions associated with the interactive information are determined from the interactive function library.

3. The interaction method according to claim 2, wherein, The step of determining one or more interactive functions associated with the interactive information from the interactive function library based on the summarized information includes: Based on the summary information, determine one or more types that match the summary information; In the interactive function library, from the interactive functions of each of the one or more types, an interactive function that matches the summary information is selected as one or more interactive functions associated with the interactive information.

4. The interaction method according to claim 1, wherein, The step of determining one or more interactive functions associated with the interaction information based on the interaction information between the user and the first intelligent agent includes: The interaction information is parsed using a machine learning model to extract keywords from the interaction information; Based on the keywords, determine one or more interactive functions associated with the interactive information from the interactive function library.

5. The interaction method according to any one of claims 1-4, wherein, The interactive function corresponding to the target operation control is the first interactive function corresponding to the first intelligent agent. The step of responding to the user's triggering of the target operation control among the operation controls of one or more interactive functions, and calling the interactive function corresponding to the target operation control to interact with the user, includes: In response to the user's triggering of the target operation control, obtain the prompt information corresponding to the first interactive function; Based on the prompt information, generate the first interactive function corresponding to the first intelligent agent; The first intelligent agent interacts with the user based on the first interactive function.

6. The interaction method according to claim 5, wherein, The step of interacting with the user using the first intelligent agent based on the first interactive function includes: In the user's interaction interface with the first intelligent agent, guidance information for enabling the first interaction function is displayed; In response to the first information input by the user based on the guidance information, the first agent displays the response information generated by the first agent based on the first information and the first interaction function.

7. The interaction method according to any one of claims 1-6, wherein, The interactive function corresponding to the target operation control is the second interactive function corresponding to the second intelligent agent. The step of responding to the user's triggering of the target operation control among the operation controls of one or more interactive functions, and calling the interactive function corresponding to the target operation control to interact with the user, includes: In response to the user's triggering of the target operation control, the second intelligent agent is invoked to interact with the user based on the second interaction function.

8. The interaction method according to claim 7, wherein, The invocation of the second intelligent agent to interact with the user based on the second interactive function includes: Display the interaction interface between the user and the second intelligent agent; In response to the second information input by the user on the interaction interface with the second agent, the response information generated by the second agent based on the second information and the second interaction function is displayed.

9. The interaction method according to any one of claims 1-8, wherein, The operation controls for displaying one or more interactive functions include: The user interface for interacting with the first intelligent agent displays operation controls for one or more interactive functions.

10. The interaction method according to any one of claims 1-8, wherein, The operation controls for displaying one or more interactive functions include: In response to the user's triggering of the interactive function entry control, the operation controls for one or more interactive functions are displayed on the recommendation tag page.

11. The interaction method according to claim 10, further comprising: Display one or more controls corresponding to one or more functional categories; In response to the user's triggering of the control corresponding to the target function category in the one or more function categories, one or more interactive functions belonging to the target function category are displayed on the tab page of the target function category.

12. The interaction method according to any one of claims 1-11, further comprising: In response to the user's termination of the interaction function corresponding to the target operation control, the target operation control is displayed in the interaction interface between the user and the first intelligent agent.

13. The interaction method according to any one of claims 1-12, wherein, The one or more interactive functions associated with the interactive information include one or more of the following: interactive functions based on the role associated with the interactive information, interactive functions based on the domain associated with the interactive information, interactive functions based on the scene associated with the interactive information, and interactive functions based on the tool associated with the interactive information.

14. An interactive device, comprising: The first display module is configured to display the interaction interface between the user and the first intelligent agent; The determining module is configured to determine one or more interactive functions associated with the interaction information between the user and the first intelligent agent. The second display module is configured to display operation controls for one or more interactive functions; The interaction module is configured to respond to the user's triggering of a target operation control among the operation controls of one or more interactive functions, and to call the interactive function corresponding to the target operation control to interact with the user.

15. 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 1-13.

16. 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 1-13.

17. A computer program product comprising: Instructions that, when executed by a processor, implement the interaction method as described in any one of claims 1-13.

18. A computer program comprising: Instructions that, when executed by a processor, implement the interaction method as described in any one of claims 1-13.

Images