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

Abstract

The present disclosure relates to the technical fields of artificial intelligence and computers, and in particular to an interaction method and apparatus, an electronic device, a storage medium, a program, and a program product. The interaction method of the present disclosure comprises: according to interaction information between an intelligent agent and a user, determining a time and related content according to which the intelligent agent actively initiates a real-time call to the user; according to the time, the intelligent agent actively initiating a real-time call to the user, and displaying call information and a connection initiation control for the real-time call; and in response to a trigger operation of the user on the connection initiation control, the intelligent agent conducting a call with the user according to the related content.

Description

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

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

[0002] With the development of AI (Artificial Intelligence) and ML (Machine Learning) technologies, interactive AI applications or devices have emerged that can engage in more fluent dialogues with users.

[0003] Interactive AI applications or devices can generate response information based on user input, using machine learning models such as LLM (Large Language Model), providing users with a more realistic chat experience.

[0004] Summary of the Invention

[0005] According to some embodiments of this disclosure, an interaction method is provided, including: determining the time and related content for the intelligent agent to initiate a real-time call to the user based on interaction information between the intelligent agent and the user; initiating a real-time call to the user by the intelligent agent based on the time, and displaying the call information and connection control of the real-time call; and responding to the user's triggering operation of the connection control, having the intelligent agent conduct a call with the user based on the related content.

[0006] According to some other embodiments of this disclosure, an interactive device is provided, including: a determining module configured to determine the time and related content for the intelligent agent to initiate a real-time call to the user based on interaction information between the intelligent agent and the user; an initiating module configured to initiate a real-time call to the user by the intelligent agent based on the time, and display the call information and connection control of the real-time call; and a calling module configured to respond to the user's triggering operation of the connection control, and have the intelligent agent conduct a call with the user based on the related content.

[0007] According to further embodiments of the present disclosure, an electronic device is provided, including: a memory; and a processor coupled to the memory, the processor being configured to perform an interaction method as described in any embodiment of the present disclosure based on instructions stored in the memory.

[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, wherein the instructions, 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, wherein the instructions, 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] Embodiments of this disclosure are described below with reference to the accompanying drawings. It should be understood that the drawings described below are merely illustrative of some embodiments of this disclosure and are not intended to limit the scope of this disclosure. In the drawings:

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

[0014] Figures 2 to 9 show schematic diagrams of the display interfaces of some embodiments of this disclosure;

[0015] Figure 10 shows a schematic diagram of the structure of an apparatus according to some embodiments of the present disclosure;

[0016] Figure 11 shows a schematic diagram of the structure of an electronic device according to some embodiments of the present disclosure;

[0017] Figure 12 shows a schematic diagram of the structure of an electronic device according to other embodiments of the present disclosure. Detailed Implementation

[0018] The technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. It should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein.

[0019] 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 of steps set forth in these embodiments should be interpreted as merely exemplary and does not limit the scope of this disclosure.

[0020] 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". The term "based on" means "at least partially based on".

[0021] 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".

[0022] 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.

[0023] The user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data shall comply with the relevant laws, regulations and standards of the relevant countries and regions, and corresponding operation portals shall be provided for users to choose to authorize or refuse.

[0024] 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.

[0025] Currently, various interactive AI applications or devices, such as agents and bots, can generate answers to user-input questions, generally interacting passively with users based on their input. With the development of voice processing technology, this question-and-answer interaction can be implemented via voice. Interactive AI applications or devices typically use two methods for voice interaction with users. One method involves the application or device responding to user triggers on voice input controls, receiving the user's voice input, generating a response voice, and playing the response voice upon user triggers on playback controls. The other method involves responding to user interaction by monitoring the user's voice in real time, and if the user's voice contains a wake word (e.g., the name of the interactive AI application), using the voice following the wake word as the user's input, generating and playing a response voice. Regardless of the method, active user operation and control are required for interaction to occur.

[0026] Furthermore, while interactive AI applications or devices are increasingly resembling human experiences, significant gaps still exist. Users expect interactive applications to not only act as assistants and question-and-answer tools, but also to simulate real humans or virtual avatars, becoming emotional companions, knowledge experts, and proactively engaging in more authentic interactions with users.

[0027] This disclosure proposes an interaction method. Taking an interactive AI application or device as an intelligent agent, by analyzing the interaction information between the intelligent agent and the user, the intelligent agent can proactively initiate real-time calls with the user. This allows for timely and proactive communication with the user when they request a call. Furthermore, real-time calls are more natural and fluid than question-and-answer interactions, simplifying user operations and more closely resembling real-life human conversations, thus enhancing the realism and effectiveness of the interaction. Some embodiments of this interaction method are described below with reference to Figures 1-9.

[0028] The interaction method disclosed herein can be executed by an interactive device or electronic device, which may consist of software and / or hardware. For example, the interactive device may be an interactive AI application or device. For instance, the interactive device may be an intelligent agent, include an intelligent agent, or be part of an intelligent agent, or may be an application or device set up separately and independently from the intelligent agent.

[0029] Figure 1 is a flowchart of some embodiments of the interaction method of this disclosure. As shown in Figure 1, the interaction method of this embodiment includes steps S102 to S106.

[0030] In step S102, based on the interaction information between the agent and the user, the time and related content for the agent to initiate a real-time call to the user are determined.

[0031] The interaction information between the agent and the user can be displayed or not. For example, in response to the user triggering the corresponding start control of the agent, the interaction interface between the user and the agent can be displayed, and the interaction information between the user and the agent can be displayed in the interaction interface.

[0032] The interaction information between the agent and the user can include dialogue information from one or more conversations, and can be interactive information in any form. For example, this interaction information can be in the form of text, voice, or generated during a real-time call, and is not limited to the examples given. Based on the interaction information between the agent and the user, it can be determined whether the agent should initiate a real-time call to the user. If it is determined that the agent should initiate a real-time call to the user, the time and related content of the real-time call can be determined based on the interaction information. For example, it can be determined after each interaction between the agent and the user whether the agent should initiate a real-time call to the user. By recognizing and understanding the interaction information between the agent and the user, it is possible to determine whether the user has a need or intention to have a real-time call with the agent, and the time required for such a call. This allows for the determination of whether the agent should initiate a real-time call to the user, and the time and related content of such a call.

[0033] For example, the time when an intelligent agent initiates a real-time call to a user can be the present or immediately, or it can be at a specific future time. For example, the relevant content of the real-time call between the intelligent agent and the user can include at least one of the following: an opening statement issued by the intelligent agent during the real-time call, interactive content, interactive topics, and memory information generated based on the interactive information.

[0034] During real-time communication between an intelligent agent and a user, the user does not need to perform control operations with each input, nor does the voice need to contain wake words or keywords. Similar to a regular voice call or phone call, the user can directly and continuously interact with the intelligent agent. For example, real-time calls include real-time voice calls or real-time video calls using the internet or mobile networks.

[0035] In step S104, based on the time, the intelligent agent initiates a real-time call to the user and displays the call information and connection control for the real-time call.

[0036] For example, the agent could proactively initiate a real-time call to the user immediately, or the agent could initiate a real-time call to the user every morning at 8:00 AM, or the agent could initiate a real-time call to the user at 3:00 PM on a future Saturday. The agent could simulate a human initiating a real-time call to the user.

[0037] For example, the currently displayed page shows the call information and connection control for a real-time call. The currently displayed page could be the interaction interface between the smart agent and the user, or a page from any application on the user's terminal device, or the main page of the user's terminal device, or the incoming call notification page of the user's terminal device, etc., and is not limited to the examples given.

[0038] For example, call information includes at least one of the following: information about the agent, and prompts regarding the real-time call content or topic. The agent's information may include identifying information such as the agent's name and avatar, and is not limited to the examples given. Call information is used to prompt the user about at least one of the following: the initiator of the real-time call, and call-related information.

[0039] For example, the connect control and the reject control can be displayed simultaneously. The connect control is used to connect the real-time call between the agent and the user, and the reject control is used to reject the real-time call between the agent and the user.

[0040] In step S106, in response to the user's trigger operation of the connection control, the intelligent agent initiates a call with the user based on relevant content.

[0041] The relevant content for the real-time call between the agent and the user has been determined beforehand. After the real-time call is connected, the agent can communicate with the user based on the determined relevant content. For example, if the relevant content is an opening remark, the agent can say the opening remark after the real-time call is connected, greeting the user, introducing itself, and briefly stating the purpose or topic of the real-time call. Alternatively, if the relevant content is at least one of the interactive content or topic, during the real-time call, the agent can generate a response voice and send it to the user based on at least one of the interactive content or topic and the user's voice input. Finally, if the relevant content is memory information generated based on the interactive information, the agent can generate a response voice and send it to the user based on the memory information and the user's voice input.

[0042] During a real-time call, the AI ​​will generate a response speech based on the user's voice input. For example, if the user changes the topic during the call, the AI ​​will engage in a conversation about the new topic based on the user's voice input, not limited to previously determined content. For instance, a first machine learning model might convert the user's voice input into first text, a second machine learning model might generate a second text response based on the first text, and a third machine learning model might convert the second text into a response speech. For example, the first machine learning model could be an Automatic Speech Recognition (ASR) model, the second machine learning model could be an LLM model, and the third machine learning model could be a Text-to-Speech (TTS) model, but the examples are not limited to these.

[0043] During a real-time call, the user can end the call with the agent at any time, for example, by responding to the user triggering the end control to terminate the real-time call between the agent and the user.

[0044] In the interaction method of the above embodiments, based on the interaction information between the agent and the user, the time and related content for the agent to initiate a real-time call with the user can be determined. The agent then initiates a real-time call with the user based on this time, and if the user answers, the agent engages in a real-time call with the user based on the related content. In the interaction method of the above embodiments, the agent initiates the real-time call with the user without requiring any additional user operation, simplifying the user's operation and improving convenience. It can proactively and promptly initiate a call with the user when the user has a call need, improving the efficiency of initiating real-time calls. Furthermore, real-time calls are more natural and fluid than question-and-answer interactions, simplifying user operation and more closely resembling real-human chat scenarios, thus enhancing the realism and effectiveness of the interaction.

[0045] The following describes, with reference to some embodiments, how to determine the time and related content for an intelligent agent to initiate a real-time call to a user based on the interaction information between the intelligent agent and the user.

[0046] In some embodiments, it is determined whether the agent initiates a real-time call to the user based on at least one of the semantic information of the interaction information and the number of interactions corresponding to the interaction information; in response to determining that the agent initiates a real-time call to the user, the time and related content of the agent initiating the real-time call to the user are determined based on the semantic information.

[0047] For example, machine learning models can be used to identify the semantic information of interactive information. For instance, the number of interactions can be determined based on the number of times the user inputs information. Based on at least one of the semantic information of the interactive information and the number of interactions, it can be determined whether the user has a need or intention to have a real-time call with the agent, and thus whether the agent should proactively initiate a real-time call to the user. Semantic information can determine whether the user is willing to have a real-time call and whether the content of the interaction is suitable for a real-time call. The number of interactions can determine whether the user is interested in the content of the interaction and whether they are willing to interact with the agent or engage in further interaction. Through the methods described in the above embodiments, real-time calls can be initiated from the agent to the user more accurately and promptly, improving the interaction effect and experience.

[0048] Furthermore, behavioral data can be used to determine whether the agent proactively initiates a real-time call to the user. In some embodiments, the agent is determined to initiate a real-time call to the user based on at least one of the semantic information of the interaction information and the number of interactions corresponding to the interaction information, as well as behavioral data, wherein the behavioral data includes at least one of the user's historical behavioral data and the historical behavioral data of the user's user group.

[0049] For example, behavioral data includes at least one of the following: a user's historical behavioral data and the historical behavioral data of the user's user group. For example, a user's historical behavioral data includes at least one of the following: historical interaction data between the user and an intelligent agent, and historical interaction data between the user and similar intelligent agents. For example, at least one of the following: the number of real-time calls the user has historically made with an intelligent agent or a similar intelligent agent, the topic, the time, the number of times the user has refused a real-time call, and the feedback information after the call. The type of intelligent agent can be determined based on at least one of the following: the intelligent agent's function and the role it plays. For example, multiple users can be divided into one or more user groups based on at least one of the following: the user's attribute information and profile information. The historical behavioral data of a user group can be obtained by statistically analyzing the historical behavioral data of multiple users within the user group. For example, the total number of calls, the average number of calls, the type of call topics, the number of calls in different time periods, and the number of positive and negative feedback messages after the call, etc., are not limited to the examples given.

[0050] Some users may not like real-time calls and prefer to control the progress and pace of the interaction through a question-and-answer format. For example, if a user has zero history of calls with the agent, or has refused more than a preset number of real-time calls, or has directly indicated that they do not want to make real-time calls, then it can be determined that the agent will not initiate real-time calls with these users.

[0051] The method described in the above embodiments, combined with user behavior data, can more accurately determine whether the intelligent agent should proactively initiate a real-time call to the user, thereby improving the effectiveness and experience of the interaction.

[0052] Based on the semantic information and behavioral data of the interaction information, it can be determined whether the intelligent agent should proactively initiate a real-time call to the user. In some embodiments, the topic type corresponding to the interaction information is determined based on the semantic information of the interaction information; and the intelligent agent should proactively initiate a real-time call to the user is determined based on the topic type and behavioral data.

[0053] For example, a fourth machine learning model can be used to understand the semantic information of the interaction and determine the topic type corresponding to the interaction. This fourth machine learning model can be an LLM (Local Level Model), and is not limited to the examples given. For instance, topic types include casual conversation, knowledge-based question answering, oral practice, travel recommendations, etc., and are not limited to the examples given. Knowledge-based question answering can be further divided into different types, such as mathematical knowledge-based question answering, geographical knowledge-based question answering, etc., and are not limited to the examples given. For example, the fourth machine learning model outputs the topic type, and the topic type and behavioral data are input into a recommendation model, which then determines whether the agent should proactively initiate a real-time call to the user.

[0054] Some topic types are not suitable for live calls. For example, math Q&A may involve formulas and function graphs, which are not suitable for live calls. Other topic types are suitable for live calls. For example, oral practice is better suited for practice conducted directly through live calls.

[0055] If the topic type corresponding to the interaction information is suitable for real-time communication, determine the behavioral data corresponding to that topic type in the behavioral data, and determine whether the agent should proactively initiate a real-time call to the user based on the behavioral data corresponding to that topic type.

[0056] By identifying the topic type corresponding to the interactive information and then combining it with behavioral data, it is possible to more accurately determine whether the intelligent agent should proactively initiate a real-time call to the user, thereby improving the effectiveness and experience of the interaction.

[0057] Based on the semantic information of the interaction information, the number of interactions, and behavioral data, it can be determined whether the agent should proactively initiate a real-time call to the user. In some embodiments, it is determined whether the number of interactions corresponding to the interaction information has reached a threshold; in response to the number of interactions corresponding to the interaction information reaching the threshold, the topic type corresponding to the interaction information is determined based on the semantic information of the interaction information, and the agent should proactively initiate a real-time call to the user based on the topic type and behavioral data.

[0058] The number of interactions can be used to determine the depth of the user's interaction with the agent and whether the user is willing to interact with the agent. For example, if the number of interactions reaches a threshold, it indicates that the user is basically satisfied with the agent's responses and is willing to interact with the agent. In this case, the semantic information of the interaction information can be used to determine the topic type corresponding to the interaction information. Based on the topic type and behavioral data, it can be determined whether the agent should proactively initiate a real-time call to the user.

[0059] If the number of interactions between the user and the agent does not reach the threshold, the decision on whether to initiate a real-time call can be omitted, reducing subsequent calculations and saving computing resources.

[0060] Based on the number of interactions and behavioral data, it can be determined whether the agent should proactively initiate a real-time call to the user. In some embodiments, it is determined whether the number of interactions corresponding to the interaction information has reached a threshold; in response to the number of interactions corresponding to the interaction information reaching the threshold, it is determined whether the agent should proactively initiate a real-time call to the user based on behavioral data.

[0061] Intelligent agents can be categorized into different types, such as general assistant agents and agents that simulate (or play) different roles. General assistant agents can answer various questions for users but do not possess specific role attributes or functions. Agents that simulate specific roles possess specific role attributes or functions. For example, an agent acting as a spoken English teacher can primarily communicate with users in spoken English; an agent acting as a virtual character can mimic the character's personality, tone, and behavior when communicating with users. Agents simulating specific roles can provide emotional support or act as knowledge experts to offer relevant knowledge to users.

[0062] For an agent simulating a specific role, it can be determined whether the agent should proactively initiate a real-time call to the user based on the number of interactions and behavioral data. In some embodiments, in response to the agent simulating a specific role, it is determined whether the number of interactions corresponding to the interaction information has reached a threshold; in response to the number of interactions corresponding to the interaction information reaching the threshold, it is determined whether the agent should proactively initiate a real-time call to the user based on behavioral data.

[0063] If the agent is simulating a specific role, the more times a user interacts with that agent, the more satisfied the user is with its responses and functions, and the more willing the user is to interact with it. Therefore, for agents simulating specific roles, combining interaction frequency and behavioral data to determine whether the agent should proactively initiate a real-time call to the user can more accurately determine whether to proactively initiate a real-time call, thus improving the effectiveness and experience of the interaction.

[0064] It is possible to determine whether an agent should initiate a real-time call to a user based solely on the interaction information. In some embodiments, the semantic information of the interaction information is used to determine whether the interaction information includes subscription request information for real-time calls; in response to the interaction information including subscription request information for real-time calls, it is determined that the agent should initiate a real-time call to the user.

[0065] Subscription demand information for live calling can include requests for reminder services, user plans, or schedules. The semantic information of the interaction can be used to identify whether a user has a need to subscribe to live calling. For example, if a user enters "Please remind me to go to the gym on Saturday morning" or "How can I get up before 8 am?", it explicitly or implicitly indicates that the user needs reminders and has some plans or schedules. In this case, live calling can promptly remind the user to complete their plans or schedules, meaning the user is likely to have a subscription demand for live calling, thus the agent will proactively initiate a live calling with the user.

[0066] By recognizing the semantics of interactive information, and when the interactive information includes information about subscription requests for real-time calls, it can determine whether the agent should proactively initiate a real-time call to the user. This can promptly remind the user of their plans or schedules, thereby improving the interaction effect and user experience.

[0067] Alternatively, the agent can initiate a real-time call with the user based solely on the number of interactions. For example, it can determine whether the number of interactions corresponding to the interaction information has reached a threshold; in response to the threshold being reached, it can determine whether the agent initiates a real-time call with the user.

[0068] In some embodiments, the interaction information between the agent and the user includes receiving ambient sounds corresponding to the user during the interaction process, and determining whether the agent should immediately initiate a real-time call to the user based on the ambient sounds corresponding to the user.

[0069] With user authorization, the system can acquire ambient sounds corresponding to the user, identify the type of ambient sound, and, in response to a preset type of ambient sound, determine that the intelligent agent should immediately and proactively initiate a real-time call to the user. For example, by identifying ambient sounds, it can determine if the user is unable to type or operate their phone, and then determine that the intelligent agent should initiate a real-time call to the user.

[0070] The above embodiments can be combined. For example, based on the semantic information of the interaction information, it can be determined whether the interaction information includes subscription request information for real-time calls. If the interaction information does not include subscription request information for real-time calls, it can be determined that the agent actively initiates a real-time call to the user based on at least one of the semantic information of the interaction information, the number of interactions corresponding to the interaction information, and behavioral data. Specific methods can be referred to the foregoing embodiments and will not be repeated here.

[0071] The following describes, with reference to some embodiments, how to determine the time when an agent initiates a real-time call to a user.

[0072] In some embodiments, based on the semantic information of the interaction information, it is determined whether the interaction information includes a demand time for a real-time call; if the interaction information includes a demand time for a real-time call, the demand time is determined as the time when the agent actively initiates a real-time call to the user; if the interaction information does not include a demand time for a real-time call, the time when the agent actively initiates a real-time call to the user is determined based on behavioral data, wherein the behavioral data includes at least one of the user's historical behavioral data and the historical behavioral data of the user's user group.

[0073] Users can specify their desired time for a real-time call in the interaction information. For example, if a user enters "Please remind me to go to the gym on Saturday morning" or "How can I get up before 8 am?", containing explicit time information, then the time when the user requests a real-time call can be used as the time for the agent to proactively initiate a real-time call with the user. If the interaction information does not include a desired time, the time when the agent proactively initiates a real-time call with the user can be determined based on behavioral data. For example, a user's historical behavioral data includes their historical call behavior data at different times, and a user group's historical behavioral data includes the user group's historical call behavior data at different times. For instance, a user's historical call behavior data at different times includes the number of calls made by that user in different time periods, and a user group's historical call behavior data at different times includes the total number of calls made by that user group in different time periods, the average number of calls made, etc. For example, if a user's historical call count exceeds a corresponding threshold within a certain time period, that time period can be designated as the time when the agent initiates a real-time call to the user. Alternatively, the time period with the highest historical call count can be selected as the time when the agent initiates a real-time call to the user. Or, if a user group's average historical call count exceeds a corresponding threshold within a certain time period, that time period can be designated as the time when the agent initiates a real-time call to the user. Alternatively, the time period with the highest average historical call count can be selected as the time when the agent initiates a real-time call to the user, and so on, and is not limited to the examples given.

[0074] Furthermore, in some embodiments, based on the semantic information of the interaction information, it is determined whether the user intends to continue interacting; in response to the user's intention to continue interacting, based on at least one of the user's historical call behavior data at different times and the user group's historical call behavior data at different times, it is determined whether the agent should immediately initiate a real-time call to the user, and / or, it is determined when the agent should initiate a real-time call to the user in the future.

[0075] If the user has ended the conversation with the agent on the current topic, the user is unlikely to continue interacting. Based on the semantic information of the interaction, it can be determined whether the user intends to continue interacting. If there is an intention to interact, the agent can determine whether to initiate a real-time call to the user immediately or at a specific future time.

[0076] The method described in the above embodiments determines whether the user intends to continue interacting based on the semantic information of the interaction information, determines whether the user needs time for real-time calls, and then determines the time for the intelligent agent to initiate a real-time call to the user based on the historical behavior data of the user or user group. This can reduce the probability of disturbing the user, make the real-time call more effective, and improve the interaction effect and experience.

[0077] The following describes, with reference to some embodiments, how to determine the relevant content of a real-time call initiated by an intelligent agent to a user.

[0078] In some embodiments, based on the semantic information of the interaction information, it is determined whether the user has subscribed to the topic of the live call; in response to the user subscribing to the topic of the live call, relevant content is determined based on the topic; in response to the user not subscribing to the topic of the live call, based on the interaction information, the target topic of the live call is determined, and relevant content is determined based on the target topic.

[0079] For example, if a user mentions "how can I practice English every day" in their interaction message, it indicates that the user wants to engage in an interaction on the topic of "English speaking." This means the user has subscribed to the topic of the live call or expressed a need for that topic. Therefore, the relevant content of the live call is determined based on this topic. If the user does not express a desired topic in their interaction message, the target topic for the live call can be determined based on the topics in the interaction message. For example, one or more topics in the interaction message can be summarized to obtain the target topic, or the topic corresponding to the most recent interaction among one or more topics can be used as the target topic.

[0080] For example, relevant content includes opening remarks from the agent during a live call. These opening remarks can be generated based on the user's subscribed or target topics, expressing the purpose of the live call and facilitating the discussion. During the live call, the agent will also interact with the user based on their subscribed or target topics.

[0081] In some embodiments, the agent's voice is generated based on the relevant content of the real-time call and the voice information entered by the user during the real-time call, and the agent's voice is used to communicate with the user.

[0082] For example, the relevant content of a real-time call includes memory information generated based on the interaction information. This memory information may include topics subscribed to or target topics by the user, as well as summaries of the interaction information. During a real-time call, referring to the memory information and the user's voice input can improve the accuracy of the call, especially in scenarios where the agent and user initiate a real-time call immediately after interaction. This allows the call to continue from the previous topic, enhancing the interaction effect and user experience.

[0083] The following describes how to display interactive information and real-time call information, using some examples.

[0084] In some embodiments, interactive information is displayed in the interaction interface between the agent and the user; after determining the time and related content of the real-time call, a reply message is generated for the agent to send to the user based on the time and related content, wherein the reply message includes guidance information or inquiry information for the real-time call; the reply message is displayed in the interaction interface.

[0085] Before initiating a live call, a guiding message or a question can be sent to the user. For example, the guiding message could be, "How about we practice our spoken English together?" The question could be, "May I call you?" In response to the user's agreement to the question, the agent proactively initiates a live call. Displaying guiding or questioning messages helps users prepare for a live call, minimizing disruption.

[0086] In some embodiments, in response to an agent initiating a real-time call to a user, the interaction interface between the agent and the user is in a displayed state, and the call information and connection control of the real-time call are displayed in the interaction interface; in response to an agent initiating a real-time call to a user, the interaction interface between the agent and the user is in a closed state, and the call information and connection control of the real-time call are displayed on the currently displayed page or on the main page of the terminal, wherein the call information includes the identification information of the agent.

[0087] The following are schematic diagrams of some interfaces of the interactive method disclosed herein, with reference to Figures 2 to 9.

[0088] As shown in Figure 2, the interaction interface between the agent and user A includes an interaction information display area 201 and an input area 202. The interaction information display area shows the interaction information 203 between agent A and the user, including their English interaction regarding ordering food. Based on this interaction information 203, it can be determined that the agent has initiated a real-time call with the user. Agent A can then send an inquiry message 204 to the user and display the real-time call information 205 and a connection control 206. In response to the user triggering the connection control 206, the call interface can be displayed, and a "call in progress" message and call duration information can also be displayed on this interaction interface. In response to the end of the call between agent A and the user, the interface shown in Figure 3 can be displayed. As shown in Figure 3, after the call ends, a "call ended" message and call duration information can be displayed on the interaction interface.

[0089] As shown in Figure 4, the interaction interface between agent B and the user includes an interaction information display area 401 and an input area 402. The interaction information display area shows the interaction information 403 between agent B and the user. The interaction information 403 includes information between agent B and the user regarding wake-up time. Determining that the user has a subscription requirement for real-time calling, the system determines the time and content for the agent to initiate a real-time call with the user, and then agent B can send guidance information 404 to the user. Agent B can be an agent simulating a specific role.

[0090] As shown in Figure 5, when agent B initiates a real-time call to the user, it may be in a locked screen state. The call information 501 and the connection control 502 can be displayed on the lock screen. An SMS control 503 and a reminder control 504 can also be displayed. In response to the user's triggering of the SMS control 503, information sent by the user to agent B can be received via SMS. In response to the user's triggering of the reminder control 504, a reminder task can be set to remind the user to reply to information from agent B.

[0091] As shown in Figure 6, when agent B initiates a real-time call to the user, it is on the main page of the terminal device. The main page can display call information 601 and connection control 602, and can also display rejection control 603.

[0092] As shown in Figure 7, the interaction interface between the agent and C includes an interaction information display area 701 and an input area 702. The interaction information display area displays the interaction information 703 between the agent C and the user. The interaction information 703 may include interactive questions about how to practice spoken English. Based on this interaction information 703, it can be determined that the agent actively initiates a real-time call to the user, and then the agent C can send guidance information 704 to the user.

[0093] As shown in Figure 8, agent C initiates a real-time call to the user. If the user is currently on the lock screen, the call information and the answer control 801 can be displayed on the lock screen. In response to the user clicking the answer control 801, the call interface shown in Figure 9 can be displayed. The call interface can display information about agent C, and the hang-up control 902, etc.

[0094] This disclosure also provides an interactive device, which will be described below with reference to FIG10.

[0095] Figure 10 is a structural diagram of an interactive device according to some embodiments of the present disclosure. As shown in Figure 6, the interactive device 100 of this embodiment includes: a determining module 110, an initiating module 120, and a call module 130.

[0096] The determination module 110 is configured to determine the time and related content when the agent initiates a real-time call to the user based on the interaction information between the agent and the user.

[0097] The initiation module 120 is configured to initiate a real-time call to the user by the intelligent agent based on time, and to display the call information and connection control of the real-time call.

[0098] The call module 130 is configured to respond to a user's trigger operation of the connection control, and the agent conducts a call with the user based on relevant content.

[0099] In some embodiments, the determining module 110 is configured to determine whether the agent actively initiates a real-time call to the user based on at least one of the semantic information of the interaction information and the number of interactions corresponding to the interaction information; in response to determining that the agent actively initiates a real-time call to the user, the determining module 110 determines the time and related content of the agent actively initiating the real-time call to the user based on the semantic information.

[0100] In some embodiments, the determining module 110 is configured to determine whether the agent actively initiates a real-time call to the user based on at least one of the semantic information of the interaction information and the number of interactions corresponding to the interaction information, as well as behavioral data, wherein the behavioral data includes at least one of the user's historical behavioral data and the historical behavioral data of the user group to which the user belongs.

[0101] In some embodiments, the determining module 110 is configured to determine the topic type corresponding to the interaction information based on the semantic information of the interaction information; and to determine whether the agent should initiate a real-time call to the user based on the topic type and behavioral data.

[0102] In some embodiments, the determining module 110 is configured to determine whether the number of interactions corresponding to the interaction information has reached a threshold; in response to the number of interactions corresponding to the interaction information reaching the threshold, the topic type corresponding to the interaction information is determined based on the semantic information of the interaction information.

[0103] In some embodiments, the determining module 110 is configured to determine whether the number of interactions corresponding to the interaction information has reached a threshold in response to the intelligent agent being an intelligent agent simulating a specific role; and in response to the number of interactions corresponding to the interaction information reaching the threshold, to determine whether the intelligent agent should proactively initiate a real-time call to the user based on the behavioral data.

[0104] In some embodiments, the determining module 110 is configured to determine whether the interaction information includes subscription request information for real-time calls based on the semantic information of the interaction information; and in response to the interaction information including subscription request information for real-time calls, to determine that the agent actively initiates a real-time call to the user.

[0105] In some embodiments, the determining module 110 is configured to determine, based on semantic information, whether the interaction information includes a demand time for a real-time call; if the interaction information includes a demand time for a real-time call, the demand time is determined as the time when the agent actively initiates a real-time call to the user; if the interaction information does not include a demand time for a real-time call, the time when the agent actively initiates a real-time call to the user is determined based on behavioral data, wherein the behavioral data includes at least one of the user's historical behavioral data and the historical behavioral data of the user's user group.

[0106] In some embodiments, the user's historical behavior data includes the user's historical call behavior data at different times, and the user group's historical behavior data includes the user group's historical call behavior data at different times. The determining module 110 is configured to determine, based on semantic information, whether the user intends to continue interacting; in response to the user's intention to continue interacting, based on at least one of the user's historical call behavior data at different times and the user group's historical call behavior data at different times, whether the agent should immediately initiate a real-time call to the user, and / or, determine when the agent should initiate a real-time call to the user in the future.

[0107] In some embodiments, the interaction information between the agent and the user includes receiving ambient sounds corresponding to the user during the interaction process. The determination module 110 is configured to determine whether the agent should immediately and proactively initiate a real-time call to the user based on the ambient sounds corresponding to the user.

[0108] In some embodiments, the determining module 110 is configured to determine whether a user has subscribed to the topic of a live call based on semantic information; in response to the user subscribing to the topic of a live call, determine relevant content based on the topic; in response to the user not subscribing to the topic of a live call, determine the target topic of the live call based on interaction information, and determine relevant content based on the target topic, wherein the relevant content includes an opening statement issued by the agent in the live call.

[0109] In some embodiments, the initiating module 120 is configured to, in response to the agent initiating a real-time call to the user, display the interaction interface between the agent and the user, and display the call information and connection control of the real-time call in the interaction interface; or, in response to the agent initiating a real-time call to the user, close the interaction interface between the agent and the user, and display the call information and connection control of the real-time call on the currently displayed page or on the main page of the terminal, wherein the call information includes the identification information of the agent.

[0110] In some embodiments, the call module 130 is configured to generate the agent's voice based on relevant content and voice information input by the user during a real-time call, wherein the relevant content includes memory information generated based on interaction information; and to use the agent's voice to conduct a call with the user.

[0111] In some embodiments, the interactive device 100 further includes: a display module 140 configured to display interactive information in an interactive interface between the agent and the user; a determination module further configured to, after determining the time and related content of the real-time call, generate a reply message sent by the agent to the user based on the time and related content, wherein the reply message includes guidance information or inquiry information for the real-time call; and the display module 140 further configured to display the reply message in the interactive interface.

[0112] This disclosure also provides an electronic device, and FIG11 shows a block diagram of an electronic device according to some embodiments of the present disclosure.

[0113] Memory 111 is used to store one or more computer-readable instructions. Memory 111 may include any combination of various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory, including but not limited to random access memory (RAM), dynamic random access memory (DRAM), static random access memory (SRAM), read-only memory (ROM), and flash memory. Memory 111 may, for example, store operating systems, application programs, boot loaders, databases, and other programs, as well as various application programs and various data.

[0114] The processor 112 is configured to execute computer-readable instructions to implement the song selection method or the method described in any of the foregoing embodiments. Specific implementations of each step of the method can be found in the above embodiments; repeated details will not be elaborated here.

[0115] Processor 112 can be configured to execute the steps shown in Figures 1 through 9. Processor 112 can be various processing devices, such as a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The central processing unit (CPU) can be an x86 or ARM architecture, etc.

[0116] The processor 112 and the memory 111 can communicate with each other directly or indirectly. For example, the processor 112 and the memory 111 can communicate via a network. The network can include a wireless network, a wired network, and / or any combination of wireless and wired networks. The processor 112 and the memory 111 can also communicate with each other via a system bus, which is not limited in this disclosure.

[0117] It should be noted that the components of the electronic device 11 shown in Figure 11 are exemplary and not limiting. The electronic device 11 may have other components depending on the actual application requirements. The processor 112 can control other components in the electronic device 11 to perform the desired functions.

[0118] Electronic device 11 can be implemented by software, firmware and / or hardware, and can be integrated into a device with relevant applications installed.

[0119] Figure 12 shows a block diagram of an electronic device according to other embodiments of the present disclosure.

[0120] The electronic device 12 shown in Figure 12 can be a computer system with a dedicated hardware structure, which can perform corresponding functions when relevant applications are installed.

[0121] Electronic devices include, but are not limited to, mobile terminals such as smartphones, laptops, personal digital assistants (PDAs), tablet computers (PCs), PMPs (portable multimedia players), in-vehicle terminals (such as in-vehicle navigation terminals), wearable devices, and fixed terminals such as digital televisions and desktop computers.

[0122] As shown in Figure 12, the Central Processing Unit (CPU) 121 performs various processes based on programs stored in the Read-Only Memory (ROM) 122 or programs loaded from the Storage Section 128 into the Random Access Memory (RAM) 123. The RAM 123 stores data required as needed when the CPU 121 performs various processes. The CPU is merely exemplary and can also be other types of processors, such as the various processors described above. The ROM 122, RAM 123, and Storage Section 128 can be various forms of computer-readable storage media. It should be noted that although the ROM 122, RAM 123, and Storage Section 128 are shown separately in Figure 12, one or more of them can be combined or located in the same or different memories or storage modules.

[0123] CPU 121, ROM 122 and RAM 123 are interconnected via bus 124. Input / output interface 125 is also connected to bus 124.

[0124] The following components are connected to the input / output interface 125: input section 126, such as a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output section 127, including displays such as cathode ray tube (CRT), liquid crystal display (LCD), speakers, vibrators, etc.; storage section 128, including hard disks, magnetic tapes, etc.; and communication section 129, including network interface cards such as LAN cards, modems, etc. The communication section 129 allows communication processing to be performed via a network such as the Internet. It is readily understood that although parts of the electronic device 12 shown in Figure 12 communicate via bus 124, 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.

[0125] As needed, drive 1210 is also connected to input / output interface 125. Removable media 1211, such as disks, optical disks, magneto-optical disks, semiconductor memories, etc., are installed on drive 1210 as needed, so that computer programs read from them can be installed into storage section 128 as needed.

[0126] 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 a removable medium 1211.

[0127] According to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, some embodiments of this disclosure include a computer program product that, when run on a computer, causes the computer to perform the methods described in any of the foregoing embodiments. The computer program product includes computer instructions carried on a computer-readable medium, containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer instructions can be downloaded and installed from a network via communication section 129, or installed from storage section 128, or installed from ROM 122. When the computer program is executed by CPU 121, the methods of the embodiments of this disclosure are performed.

[0128] 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 programs for use by or in conjunction with an instruction execution system, apparatus, or device.

[0129] A computer-readable medium may be a computer-readable storage medium, a computer-readable signal medium, or any combination thereof.

[0130] Computer-readable storage media include, but are not limited to, systems, apparatuses, or devices that are electrical, magnetic, optical, electromagnetic, infrared, or semiconductor, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, electrical connections having one or more wires, portable computer disks, hard disks, 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 devices, magnetic storage devices, 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. Computer instructions are stored on the computer-readable storage medium that, when executed by a processor, implement the methods described in any of the foregoing embodiments.

[0131] Computer-readable signal media may include data signals 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. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of sending, propagating, or transmitting programs 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.

[0132] 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.

[0133] 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 described in any of the foregoing embodiments. For example, the instructions may be embodied in computer program code.

[0134] 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).

[0135] 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.

[0136] The functions described above 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 Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0137] According to some embodiments of this disclosure, an interaction method is provided, including: determining the time and related content for the intelligent agent to initiate a real-time call to the user based on the interaction information between the intelligent agent and the user; initiating a real-time call to the user by the intelligent agent based on the time, and displaying the call information and connection control of the real-time call; and responding to the user's triggering operation of the connection control, having the intelligent agent conduct a call with the user based on the related content.

[0138] In some embodiments, determining the time and related content for the intelligent agent to initiate a real-time call to the user based on the interaction information between the intelligent agent and the user includes: determining whether the intelligent agent initiates a real-time call to the user based on at least one of the semantic information of the interaction information and the number of interactions corresponding to the interaction information; in response to determining that the intelligent agent initiates a real-time call to the user, determining the time and related content for the intelligent agent to initiate a real-time call to the user based on the semantic information.

[0139] In some embodiments, determining whether an agent actively initiates a real-time call to a user based on at least one of the semantic information of the interaction information and the number of interactions corresponding to the interaction information includes: determining whether an agent actively initiates a real-time call to a user based on at least one of the semantic information of the interaction information and the number of interactions corresponding to the interaction information, as well as behavioral data, wherein the behavioral data includes at least one of the user's historical behavioral data and the historical behavioral data of the user's user group.

[0140] In some embodiments, determining whether an agent actively initiates a real-time call to a user based on at least one of the semantic information of the interaction information and the number of interactions corresponding to the interaction information, as well as behavioral data, includes: determining the topic type corresponding to the interaction information based on the semantic information of the interaction information; and determining whether the agent actively initiates a real-time call to the user based on the topic type and behavioral data.

[0141] In some embodiments, determining the topic type corresponding to the interaction information based on the semantic information of the interaction information includes: determining whether the number of interactions corresponding to the interaction information has reached a threshold; and in response to the number of interactions corresponding to the interaction information reaching the threshold, determining the topic type corresponding to the interaction information based on the semantic information of the interaction information.

[0142] In some embodiments, determining whether an agent actively initiates a real-time call to a user based on at least one of the semantic information of the interaction information and the number of interactions corresponding to the interaction information, as well as behavioral data, includes: in response to the agent being an agent simulating a specific role, determining whether the number of interactions corresponding to the interaction information has reached a threshold; and in response to the number of interactions corresponding to the interaction information reaching the threshold, determining whether the agent actively initiates a real-time call to the user based on behavioral data.

[0143] In some embodiments, determining whether an agent actively initiates a real-time call to a user based on at least one of the semantic information of the interaction information and the number of interactions corresponding to the interaction information includes: determining whether the interaction information includes subscription request information for real-time calls based on the semantic information of the interaction information; and determining that the agent actively initiates a real-time call to the user in response to the interaction information including subscription request information for real-time calls.

[0144] In some embodiments, determining the time and related content for the agent to initiate a real-time call to the user based on semantic information includes: determining whether the interaction information includes a time requirement for a real-time call; if the response interaction information includes a time requirement for a real-time call, determining the time requirement as the time for the agent to initiate a real-time call to the user; if the response interaction information does not include a time requirement for a real-time call, determining the time for the agent to initiate a real-time call to the user based on behavioral data, wherein the behavioral data includes at least one of the user's historical behavioral data and the historical behavioral data of the user's user group.

[0145] In some embodiments, the user's historical behavior data includes the user's historical call behavior data at different times, and the user group's historical behavior data includes the user group's historical call behavior data at different times. Determining the time for the agent to proactively initiate a real-time call to the user based on the behavior data includes: determining whether the user intends to continue interacting based on semantic information; in response to the user's intention to continue interacting, determining whether the agent should immediately proactively initiate a real-time call to the user based on at least one of the user's historical call behavior data at different times and the user group's historical call behavior data at different times, and / or determining the time for the agent to proactively initiate a real-time call to the user in the future.

[0146] In some embodiments, the interaction information between the agent and the user includes receiving ambient sounds corresponding to the user during the interaction process. Determining the time and related content for the agent to initiate a real-time call to the user based on the interaction information between the agent and the user includes: determining whether the agent should immediately initiate a real-time call to the user based on the ambient sounds corresponding to the user.

[0147] In some embodiments, determining the time and related content for an agent to initiate a real-time call to a user based on semantic information includes: determining whether the user has subscribed to the topic of the real-time call based on semantic information; determining related content based on the topic in response to the user subscribing to the topic of the real-time call; and determining the target topic of the real-time call based on interaction information in response to the user not subscribing to the topic of the real-time call, and determining related content based on the target topic, wherein the related content includes an opening statement issued by the agent during the real-time call.

[0148] In some embodiments, displaying call information and connection control for a real-time call includes: when the agent initiates a real-time call to the user, the interaction interface between the agent and the user is in a displayed state, and the call information and connection control for the real-time call are displayed in the interaction interface; when the agent initiates a real-time call to the user, the interaction interface between the agent and the user is in a closed state, and the call information and connection control for the real-time call are displayed on the currently displayed page or on the main page of the terminal, wherein the call information includes the identification information of the agent.

[0149] In some embodiments, having an agent communicate with a user based on relevant content includes: generating the agent's voice based on the relevant content and voice information input by the user during a real-time call, wherein the relevant content includes memory information generated based on interaction information; and communicating with the user using the agent's voice.

[0150] In some embodiments, the interaction method further includes: displaying interaction information in the interaction interface between the agent and the user; after determining the time and related content of the real-time call, generating a reply message sent by the agent to the user based on the time and related content, wherein the reply message includes guidance information or inquiry information for the real-time call; and displaying the reply message in the interaction interface.

[0151] According to some other embodiments of this disclosure, an interactive device is provided, comprising: a determining module configured to determine, based on interaction information between an agent and a user, the time and related content for the agent to initiate a real-time call to the user; an initiating module configured to, based on the time, initiate a real-time call to the user by the agent, and display the call information and connection control of the real-time call; and a calling module configured to, in response to a user's triggering operation of the connection control, have the agent conduct a call with the user based on the related content.

[0152] According to further embodiments of the present disclosure, an electronic device is provided, comprising: a memory; and a processor coupled to the memory, the processor being configured to perform an interaction method as described in any embodiment of the present disclosure based on instructions stored in the memory.

[0153] 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, implements the interactive method of any embodiment of the present disclosure.

[0154] According to some other embodiments of the present disclosure, a computer program is provided, comprising: instructions that, when executed by a processor, cause the processor to perform an interactive method of any embodiment of the present disclosure.

[0155] According to further embodiments of the present disclosure, a computer program product is provided, including instructions that, when executed by a processor, implement the interactive methods of any embodiment of the present disclosure.

[0156] 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: Based on the interaction information between the intelligent agent and the user, determine the time and related content when the intelligent agent initiates a real-time call to the user. Based on the time, the intelligent agent proactively initiates the real-time call to the user and displays the call information and connection control of the real-time call; In response to the user's triggering operation on the connection control, the intelligent agent initiates a call with the user based on the relevant content.

2. The interaction method according to claim 1, wherein, The step of determining the time and related content for the intelligent agent to initiate a real-time call to the user based on the interaction information between the intelligent agent and the user includes: Based on at least one of the semantic information of the interaction information and the number of interactions corresponding to the interaction information, determine whether the intelligent agent actively initiates the real-time call to the user; In response to determining that the agent actively initiates the real-time call to the user, the time and related content of the real-time call initiated by the agent to the user are determined based on the semantic information.

3. The interaction method according to claim 2, wherein, Determining whether the agent actively initiates the real-time call to the user based on at least one of the semantic information of the interaction information and the number of interactions corresponding to the interaction information includes: Based on at least one of the semantic information of the interaction information and the number of interactions corresponding to the interaction information, as well as behavioral data, it is determined whether the intelligent agent actively initiates the real-time call to the user. The behavioral data includes at least one of the user's historical behavioral data and the historical behavioral data of the user group to which the user belongs.

4. The interaction method according to claim 3, wherein, The step of determining whether the intelligent agent actively initiates the real-time call to the user based on at least one of the semantic information of the interaction information and the number of interactions corresponding to the interaction information, as well as behavioral data, includes: Based on the semantic information of the interaction information, determine the topic type corresponding to the interaction information; Based on the topic type and the behavioral data, determine whether the intelligent agent should proactively initiate the real-time call to the user.

5. The interaction method according to claim 4, wherein, Determining the topic type corresponding to the interaction information based on the semantic information of the interaction information includes: Determine whether the number of interactions corresponding to the interactive information has reached a threshold. In response to the number of interactions corresponding to the interaction information reaching a threshold, the topic type corresponding to the interaction information is determined based on the semantic information of the interaction information.

6. The interaction method according to claim 3, wherein, The step of determining whether the intelligent agent actively initiates the real-time call to the user based on at least one of the semantic information of the interaction information and the number of interactions corresponding to the interaction information, as well as behavioral data, includes: In response to the fact that the agent is an agent simulating a specific role, determine whether the number of interactions corresponding to the interaction information has reached a threshold; In response to the number of interactions corresponding to the interactive information reaching a threshold, the agent determines whether to initiate the real-time call to the user based on the behavioral data.

7. The interaction method according to claim 2, wherein, Determining whether the agent actively initiates the real-time call to the user based on at least one of the semantic information of the interaction information and the number of interactions corresponding to the interaction information includes: Based on the semantic information of the interaction information, determine whether the interaction information includes subscription request information for the real-time call; In response to the interaction information, including subscription request information for the real-time call, the agent determines that it will proactively initiate the real-time call to the user.

8. The interaction method according to any one of claims 2-7, wherein, The step of determining the time and related content of the real-time call initiated by the intelligent agent to the user based on the semantic information includes: Based on the semantic information, determine whether the interaction information includes the required time for the real-time call; The response information includes a request for the real-time call time, and the request time is determined as the time when the intelligent agent actively initiates the real-time call to the user. The response information does not include the time required for the real-time call. Based on the behavioral data, the time when the agent actively initiates the real-time call to the user is determined. The behavioral data includes at least one of the user's historical behavioral data and the historical behavioral data of the user group to which the user belongs.

9. The interaction method according to claim 8, wherein, The user's historical behavior data includes the user's historical call behavior data at different times, and the user group's historical behavior data includes the user group's historical call behavior data at different times. Determining the time when the intelligent agent initiates the real-time call to the user based on the behavior data includes: Based on the semantic information, determine whether the user intends to continue interacting; In response to the user's intention to continue interacting, based on at least one of the user's historical call behavior data at different times and the user group's historical call behavior data at different times, it is determined whether the agent should immediately initiate the real-time call to the user, and / or, it is determined when the agent should initiate the real-time call to the user in the future.

10. The interaction method according to any one of claims 1-9, wherein, The interaction information between the intelligent agent and the user includes receiving ambient sound corresponding to the user during the interaction process. The step of determining the time and related content for the intelligent agent to initiate a real-time call to the user based on the interaction information includes: Based on the ambient sound corresponding to the user, determine whether the intelligent agent should immediately and proactively initiate a real-time action with the user. Call during the call.

11. The interaction method according to any one of claims 2-10, wherein, The step of determining the time and related content of the real-time call initiated by the intelligent agent to the user based on the semantic information includes: Based on the semantic information, determine whether the user has subscribed to the topic of the real-time call; In response to the user subscribing to the topic of the live call, determine the relevant content based on the topic; In response to the user not subscribing to the topic of the real-time call, the target topic of the real-time call is determined based on the interaction information, and the relevant content is determined based on the target topic, wherein the relevant content includes the opening remarks made by the agent in the real-time call.

12. The interaction method according to any one of claims 1-11, wherein, The call information and connection control for displaying the real-time call include: When the agent initiates the real-time call to the user, the interaction interface between the agent and the user is displayed, and the call information and the connection control of the real-time call are displayed in the interaction interface. When the agent initiates the real-time call to the user, the interaction interface between the agent and the user is closed. The call information and the connection control of the real-time call are displayed on the currently displayed page or on the main page of the terminal. The call information includes the identification information of the agent.

13. The interaction method according to any one of claims 1-12, wherein, The process of the intelligent agent communicating with the user based on the relevant content includes: Based on the relevant content and the voice information input by the user during the real-time call, the voice of the intelligent agent is generated, wherein the relevant content includes memory information generated based on the interaction information; The intelligent agent uses its voice to communicate with the user.

14. The interaction method according to any one of claims 1-13, further comprising: The interaction information is displayed in the interaction interface between the intelligent agent and the user; After determining the time and related content of the real-time call, the agent generates a response message to be sent to the user based on the time and related content. The response message includes guidance information or inquiry information for the real-time call. The response information is displayed in the interactive interface.

15. An interactive device, comprising: The determination module is configured to determine the time and related content when the intelligent agent initiates a real-time call to the user based on the interaction information between the intelligent agent and the user; The initiation module is configured to initiate the real-time call to the user by the intelligent agent based on the time, and to display the call information and connection control of the real-time call. The call module is configured to respond to the user's trigger operation on the call control, and the agent conducts a call with the user based on the relevant content.

16. An electronic device comprising: Memory; as well as A processor coupled to the memory, the processor being configured to execute the interaction method as described in any one of claims 1 to 14 based on instructions stored in the memory.

17. A computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the interactive method of any one of claims 1 to 14.

18. A computer program product comprising: Instructions, wherein when executed by a processor, the instructions implement the interaction method of any one of claims 1 to 14.

19. A computer program comprising: Instructions, wherein when executed by a processor, the instructions implement the interaction method of any one of claims 1 to 14.

Images