Dialog interaction method, electronic device, storage medium and product

Abstract

The present disclosure relates to the technical field of computers, and relates to a dialog interaction method, an electronic device, a storage medium and a product. The dialog interaction method comprises: on a dialog interface between a user and an intelligent agent, in response to an instruction of the user, determining a progress type of a dialog on the basis of interaction between the user and the intelligent agent; in response to the progress type being a first type, displaying prompt information associated with the dialog; and in response to the progress type being a second type, displaying prompt information comprising a new topic.

Description

Dialogue interaction methods, electronic devices, storage media and products

[0001] Cross-references to related applications

[0002] This application is based on and claims priority to Chinese application No. 202411545998.3, filed on October 31, 2024, the disclosure of which is incorporated herein by reference in its entirety. Technical Field

[0003] This disclosure relates to the field of computer technology, and in particular to a dialogue interaction method, electronic device, storage medium, and product. Background Technology

[0004] With the development of artificial intelligence technology, users can interact with intelligent agents. An intelligent agent is an object driven by artificial intelligence technology that can automatically respond to user input. One application scenario for intelligent agents is intelligent dialogue. Users can send messages to the intelligent agent, and the intelligent agent can send response messages to the user based on the messages sent. Summary of the Invention

[0005] According to some embodiments of this disclosure, a dialogue interaction method is provided, including: in a dialogue interface between a user and an intelligent agent, in response to a user's instruction, determining a dialogue progression type based on the interaction between the user and the intelligent agent; in response to the progression type being a first type, displaying prompt information associated with the dialogue; and in response to the progression type being a second type, displaying prompt information including a new topic.

[0006] According to some 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 execute a dialogue interaction method of any embodiment of the present disclosure based on instructions stored in the memory.

[0007] According to some 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 dialogue interaction method of any embodiment described in the present disclosure.

[0008] According to some embodiments of the present disclosure, a computer program product is provided that, when the computer program product is run on a computer, enables the computer to implement the dialogue interaction method of any embodiment described in the present disclosure.

[0009] According to some embodiments of the present disclosure, a computer program is provided, comprising: instructions that, when executed by a processor, cause the processor to perform a dialogue interaction method according to any embodiment of the present disclosure.

[0010] 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

[0011] 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:

[0012] Figure 1 shows a schematic flowchart of a dialogue interaction method according to some embodiments of the present disclosure.

[0013] Figure 2 shows a schematic flowchart of a propulsion type determination method according to some embodiments of the present disclosure.

[0014] Figure 3 illustrates a dialogue interface of an intelligent agent according to some embodiments of the present disclosure.

[0015] Figure 4 illustrates the dialogue interface of an intelligent agent according to other embodiments of the present disclosure.

[0016] Figure 5 illustrates the dialogue interface of an intelligent agent according to some embodiments of the present disclosure.

[0017] Figure 6 illustrates a dialogue interface of an intelligent agent according to some embodiments of the present disclosure.

[0018] Figure 7 shows a schematic diagram of the structure of a dialogue interaction device according to some embodiments of the present disclosure.

[0019] Figure 8 shows a block diagram of an electronic device according to some embodiments of the present disclosure.

[0020] Figure 9 shows a block diagram of an electronic device according to some other embodiments of the present disclosure.

[0021] 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

[0022] 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.

[0023] 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 and numerical 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.

[0024] 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".

[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 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.

[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] In dialogue scenarios with an intelligent agent, after sending a message to the user, the agent sometimes displays several prompts to facilitate follow-up questions. In the interactive interface, a user can send a message asking who the main character of a movie is. The agent then replies with a message stating that the main character is A and the actor playing the role is B. Further, a prompt control can be displayed on the interface, with prompts related to the user's previous message or the agent's reply. These prompts might include phrases like "What awards did actor B win for role A?" or "Recommend some classic movies starring actor B." In response to the user's triggering of the prompt control, a message containing the prompt information from the triggered control can be automatically sent to the user. The agent can then respond to this message. This saves the user time and effort associated with manual input, aiming to improve interaction efficiency.

[0030] In practical applications, some users have found that the existing prompts sometimes fail to meet their questioning needs. In most cases, users still need to manually enter messages. For example, some users want to start a new topic unrelated to the current chat content, while others want to delve deeper into the current topic, but the displayed prompts do not cover the content they want to ask. This results in relatively low interaction efficiency during the user's dialogue with the agent.

[0031] To address the aforementioned problems, this disclosure provides a dialogue interaction method, an electronic device, a storage medium, and a product. In embodiments of this disclosure, based on the interactions already generated between the user and the intelligent agent, it is determined whether to display prompts related to the current dialogue or prompts for a new topic.

[0032] Figure 1 shows a flowchart of a dialogue interaction method according to some embodiments of the present disclosure. As shown in Figure 1, the dialogue interaction method of this embodiment includes steps S102 to S106.

[0033] In step S102, in the dialogue interface between the user and the intelligent agent, in response to the user's instructions, the type of dialogue progression is determined based on the interaction between the user and the intelligent agent.

[0034] Intelligent agents can generate corresponding content based on dialogues sent by other subjects (such as users or robots) in a conversational scenario. They can be implemented in software, hardware, or a combination of both. Intelligent agents can also be referred to as robots, digital humans, or virtual proxies for machine learning models. Intelligent agents can be implemented using machine learning models, such as Large Language Models (LLMs) or Foundation Models. Machine learning models can be generative models, which output target content based on input information. Generative models include, for example, models that generate content based on text or images, and their output can include text, images, or a combination of both. Of course, the input or output of generative models can also be data from other modalities, such as audio, video, or a combination of multiple data types. Generative models can be single-modal models, such as text-to-text models (referred to as "text-to-text models") or image-to-image models (referred to as "image-to-image models"); or, generative models can be cross-modal models, that is, models whose inputs and outputs belong to different modalities, such as text-to-image models (referred to as "text-to-image models"); or, the inputs of generative models can include multiple modalities, and the outputs can also include multiple modalities.

[0035] The user-agent dialogue interface displays one or more messages sent by the user and the agent. It may also include interactive controls for the user and agent. Examples include input boxes for sending text messages, controls for sending voice messages, and controls for sending files (including images, videos, audio, documents, etc.).

[0036] User commands are used to trigger the display of prompts. These commands can be generated through at least one of the following: gesture commands, voice commands, triggering of virtual controls, or triggering of physical controls.

[0037] Interactions between users and agents can include various types. In some embodiments, the interaction is related to at least one of messages sent by the user and messages sent by the agent. The interaction between the user and the agent can reflect the user's opinion or attitude towards the topic being discussed, such as whether they like the topic, whether the agent's response has met the user's question, etc.

[0038] The progression types of a conversation include at least type one and type two, and the progression type is used to indicate whether a new topic has been started.

[0039] In step S104, in response to the advancement type being the first type, a prompt message associated with the dialogue is displayed.

[0040] The first type is used to indicate that a new topic should not be started. In other words, the first type is used to indicate that the current topic should continue. In this case, displaying prompts related to the conversation allows the user to easily select prompts to continue discussing the content related to the current conversation with the agent.

[0041] In some embodiments, after an agent sends a message, it will by default send a prompt message associated with the dialogue. In this case, if the progression type is type 1, additional prompt messages associated with the dialogue can be added based on the previously sent prompt messages. For example, if there are M original prompt messages, and given a user instruction and the dialogue progression type is determined to be type 1, N more prompt messages associated with the dialogue can be added, where M and N are non-negative integers. Thus, if the user is not satisfied with the currently displayed prompt messages, they can trigger an instruction to obtain more relevant prompt messages. This eliminates the need for the user to input message content, improving user efficiency.

[0042] Of course, if the messages sent by the intelligent agent do not carry any prompts by default, these N prompts related to the dialogue can be displayed directly.

[0043] In step S106, in response to the advancement type being the second type, a prompt message including a new topic is displayed.

[0044] New topics are not determined based on existing conversations between the user and the agent. For example, new topics may include those unrelated to the current conversation. New topics may be selected based on popular topics on the platform, or, with the user's authorization, based on the user's interests.

[0045] The second type is used to indicate the start of a new topic. In other words, it indicates that the current topic should not be continued. In this case, displaying a prompt message including the new topic makes it easier for the user to start a conversation with the agent about a new topic. This allows the user to quickly obtain more information about other topics when they no longer want or need to continue the conversation on the current topic, improving the efficiency of information retrieval.

[0046] The embodiments of this disclosure, based on user commands, can display two different prompt messages. Specifically, based on the interaction between the user and the intelligent agent, it is determined whether to continue the current topic or introduce a new topic, and then different prompt messages are displayed according to the determination result. Thus, this disclosure can provide prompt messages that the user is more likely to use during the dialogue between the user and the intelligent agent, increasing the probability that the user will trigger the prompt messages, saving user operations, and improving the efficiency of user information acquisition.

[0047] User-agent interaction includes at least one of dialogue content and interactive operations. In some embodiments, the progression type of the dialogue can be determined by performing intent analysis on the interaction. Figure 2 shows a flowchart illustrating a progression type determination method according to some embodiments of the present disclosure. As shown in Figure 2, the progression type determination method of this embodiment includes steps S202 to S206.

[0048] In step S202, based on at least one of the dialogue content between the user and the intelligent agent and the interaction operation, it is determined whether the user intends to continue the dialogue on the topic of the dialogue content.

[0049] Interactions between a user and an agent can involve a specified number of recently generated messages between the user and the agent. For example, the interaction may include the content of a specified number of messages recently sent by at least one of the user or the agent, such as the content of the last message sent by the user in a conversation; or the interaction may include the user's interactive actions on the content of a specified number of messages recently sent by at least one of the user or the agent, and so on.

[0050] For determining intent based on dialogue content, methods such as semantic understanding and keyword matching can be used. For example, semantic understanding can be performed on the content of the dialogue between the user and the agent; based on the semantic understanding results, it can be determined whether the user intends to continue the conversation on the relevant topic. Since the tone and language style of the messages sent by the user during the dialogue are personalized, semantic understanding can more accurately obtain the intent behind the user's freely input content.

[0051] Semantic understanding can be achieved through machine learning models. In some embodiments, a machine learning model is used to process a specified number of the latest messages in a dialogue between a user and an agent to obtain semantic understanding results. The machine learning model can be a semantic analysis model, a large language model, a base model, etc. Taking a large language model or a base model as an example, a prompt can be generated based on the specified number of the latest messages in the dialogue so that the model can process them. The prompt can also include instructions for processing these messages, such as, "Perform semantic understanding on these messages and output whether the user intends to continue the dialogue on the topic of the content." Thus, the model can process the content of the messages according to the processing instructions in the prompt.

[0052] Semantic understanding results can be analyses of message content. For example, the result of semantic understanding can be the extraction of the topic and key information of the dialogue, or the further determination of intent based on the topic and key information. The result of semantic understanding can be determined based on whether the dialogue can continue or whether the user intends to discuss the topic in depth. For messages involving fewer dimensions (e.g., less than the first threshold), the user's needs are likely to be met after receiving a response from the agent, so there is no need to continue the topic; however, for messages involving more dimensions (e.g., greater than the second threshold), there is a possibility that the user may continue the topic. For example, if a user asks the agent about the temperature of the Himalayas, the question mainly involves geography, and the agent's response may meet the user's needs; but if the user asks about the temperature of Beijing, the question involves not only geography but also tourism and shopping, so after the agent responds, the user may ask further questions about Beijing.

[0053] When using machine learning models to analyze message content, the model can be pre-trained using training data. For example, the training data can include multiple messages, with each message's label determined by whether the user continued the conversation with the agent on the topic after the message was sent. Thus, the model can determine, based on the content of these messages, which types of messages are likely to have follow-up questions.

[0054] Semantic understanding results can also be the result of type identification of dialogue content.

[0055] In some embodiments, based on the semantic understanding results, it is determined whether the message sent by the user includes an adjustment instruction to the message sent by the agent. In response to the user-sent message including an adjustment instruction, it is determined that the user intends to continue the conversation on the topic of the dialogue content. Whether the message includes an adjustment instruction type can determine whether the user is satisfied with the message sent by the agent. For example, the user sends message 1, and the agent generates reply message 2 based on message 1. If the user is not satisfied with reply message 2, they can send message 3 with adjustment instructions such as "regenerate the answer," "longer," or "more concise." The user sending the adjustment instruction indicates that they are not satisfied with the content previously sent by the agent, and therefore expect to continue the conversation on the previous topic; that is, they intend to continue the conversation on the topic of the dialogue content.

[0056] In some embodiments, the semantic understanding results can also be used to determine whether a message sent by the user is a closing remark. A closing remark is language used to end a conversation, such as "Okay, thank you" or "Received." If a message sent by the user is a closing remark, it can be determined that the user does not intend to continue the conversation on the topic of that topic.

[0057] The semantic understanding results may also include the user's sentiment towards the topic of the conversation. In some embodiments, determining whether a user intends to continue the conversation on the topic of the conversation content includes: determining the user's sentiment towards the conversation based on the semantic understanding results; and determining whether the user intends to continue the conversation on the topic of the conversation content based on the sentiment. For example, if the user's sentiment towards the conversation is positive (e.g., likes), it is determined that the user intends to continue the conversation on the topic of the conversation content; if the user's sentiment towards the conversation is negative (e.g., dislikes), it is determined that the user does not intend to continue the conversation on the topic of the conversation content.

[0058] Interactions may include, for example, actions taken by a user on a message sent by an agent. In some embodiments, it is determined whether the interaction is a positive or negative action on a message sent by the agent; if the action is positive, it is determined that the user has the intention; if the action is negative, it is determined that the user does not have the intention.

[0059] Affirmative actions indicate that the user agrees with the content sent by the agent and expresses this preference through interactive actions. Affirmative actions include at least one of the following: liking, saving, sharing, selecting, and copying. Liking directly indicates that the user approves of the content sent by the agent. Saving and sharing indicate that the user considers the content valuable and wants to view it later or share it with others. Liking, saving, and sharing can be triggered through controls in the dialog interface or default gestures. Selecting means that the user uses the cursor to highlight part or all of the text in the message, indicating that the user is paying attention to part or all of the message's content. Copying indicates that the user wants to continue using the information elsewhere. Therefore, the above actions can express the user's affirmation of the content sent by the agent.

[0060] A negation action indicates that the user disagrees with the content sent by the agent, and this tendency is expressed through interactive actions. Negation actions include at least one of negative feedback or regeneration. Negative feedback, such as a "downvote," directly indicates the user's disapproval of the content sent by the agent. Regeneration indirectly indicates the user's dissatisfaction with the currently generated content. Negative feedback and regeneration actions can be triggered through controls in the dialog interface or default gestures.

[0061] Furthermore, the user's intention to continue the conversation on the relevant topic can be determined by combining the dialogue content and interactive actions. In some embodiments, the topic of each round of dialogue is determined based on the semantic understanding results of the dialogue content; if a topic appears consecutively in the dialogue for more than a threshold number of rounds, it is determined that the user intends to continue the conversation on that topic. A round of dialogue may include a message sent by the user and a response message from the agent to that message, i.e., the message sent by the user and the message sent by the agent following and adjacent to that message. The topic of each round of dialogue can be determined based on the content of each round of dialogue. For example, a topic analysis model can be used to extract the topic of each round of dialogue. If a topic appears consecutively in the dialogue for more than a threshold number of rounds, it indicates that the user and the agent have had an in-depth discussion on that topic, and therefore it is very likely that the discussion will continue, i.e., there is an intention to continue the conversation on that topic.

[0062] In step S204, in response to the user's intention, the advancement type is determined to be the first type. Therefore, prompt information associated with the current conversation can be displayed to the user.

[0063] In step S206, in response to the user's lack of intent, the advancement type is determined to be the second type. Therefore, a prompt message including a new topic can be displayed to the user.

[0064] The above embodiments utilize at least one of the dialogue content and interactive operations to determine the user's intent, thereby comprehensively covering the user's behavioral information in the dialogue with the intelligent agent. Therefore, the user's intent can be accurately determined, thereby improving the accuracy of determining the type of prompt information and increasing the user's operating efficiency.

[0065] Figure 3 illustrates a dialogue interface of an agent according to some embodiments of the present disclosure. In the dialogue interface 3 shown in Figure 3, the user sends message 31 to agent A, namely, "What do watermelon seedlings look like?". Then, agent A responds to message 31 sent by the user with message 32, which describes the watermelon seedlings.

[0066] Based on the content of at least one of messages 31 and 32, it can be determined whether the user intends to continue discussing topics related to watermelon seedlings or plant seedlings. If the user continues to send messages including adjustment instructions, such as "regenerate answer" or "more details," the progression type can be determined to be Type I.

[0067] Figure 3 also exemplarily includes some interactive controls attached to message 32 sent by the agent. If the user triggers the copy control 321 or the share control 322, the advancement type can be determined to be the second type. If the user triggers the regenerate control 323, the advancement type can be determined to be the first type. More controls can be presented to the user as needed, or the user can trigger the display of more interactive controls by long-pressing the message; these will not be elaborated further here.

[0068] In interface 3, prompt messages 33 and 34 are shown as an example. These two prompt messages are automatically displayed after message 32 is sent.

[0069] Users can send commands, for example, by swiping up. For instance, in interface 3, a user can perform an up swipe to trigger the display of more prompts related to the current conversation or a new topic.

[0070] In some embodiments, if the advancement type is determined to be the first type, more prompts related to the current conversation can be displayed in response to the user's instruction.

[0071] For example, in response to a user performing an upward swipe gesture in interface 3, interface 3 can be as shown in Figure 4. Compared to Figure 3, interface 3 in Figure 4 adds two new dialogue-related prompts, 41 and 42. Therefore, if the dialogue progression type is determined to be type one, more prompts can be displayed to the user, making it easier for them to find the questions they want to follow up on and quickly ask them. If, as needed, the user continues to send commands in interface 3 as shown in Figure 4, such as continuing to perform the upward swipe gesture, more dialogue-related prompts can be displayed to the user.

[0072] In some embodiments, if the promotion type is determined to be the first type, the new topic can be displayed on a new page or the current page.

[0073] For example, when displaying a new topic, the current conversation can be cleared before it is shown. In some embodiments, after clearing the conversation history, a prompt message including the new topic is displayed. This ensures that if a new topic is started, the conversation history is also cleared. This prevents topics that are no longer of interest to the user from interfering with subsequent conversations.

[0074] Taking the user's swipe gesture as an example, if the dialogue progression type is determined to be the second type, the user can scroll up the content in the current dialogue interface and slide into a new page.

[0075] Figure 5 illustrates a dialogue interface of an intelligent agent according to some embodiments of the present disclosure. This interface 5 may be a new dialogue interface displayed after interface 3 has been cleared, and this interface includes new topics 51 to 54. Figure 5 still shows a dialogue between the user and intelligent agent A, except that the existing dialogue in Figure 3 has been cleared in this interface. Thus, the user can focus more on the new topics.

[0076] For example, when displaying a new topic, it can be added to the existing messages in the current conversation. Depending on the needs, regardless of whether the current interface includes notification information, the notification information corresponding to the new topic can be added to the interface. Alternatively, if the conversation interface also includes notification information associated with messages sent by the agent, the notification information associated with those messages can be removed, and the notification information including the new topic can be displayed instead.

[0077] Figure 6 illustrates a dialogue interface of an intelligent agent according to some embodiments of the present disclosure. After a user triggers a command on the interface shown in Figure 3 (e.g., performs an up swipe gesture), interface 6 as shown in Figure 6 can be displayed. In interface 6, the prompts 33 and 34 originally displayed in Figure 3 are removed and replaced by new topics 61 to 63. This allows the user to see new topics and also facilitates quick access to historical messages.

[0078] In some embodiments, in response to the triggering of any prompt message, the user-sent, triggered prompt message is displayed; the agent's response to the prompt message is also displayed. That is, the method of this embodiment can be applied to prompt messages attached to messages sent by the agent, or to prompt messages displayed in response to user instructions (including prompt messages associated with the dialogue and prompt messages for new topics). In other words, after the user triggers the prompt message, the effect is the same as if the user manually selected and sent the content of the prompt message. The agent responds to the message sent by the user. Thus, the prompt messages can simplify the user's operation efficiency. By combining the foregoing embodiments and selecting different prompt message display schemes according to the dialogue progression, the embodiments of this disclosure can quickly provide users with prompt messages matching their needs, thereby improving operational efficiency and information acquisition efficiency.

[0079] The methods of various embodiments of this disclosure have been described above. The apparatus for performing the above methods is described below.

[0080] Figure 7 shows a schematic diagram of the structure of a dialogue interaction device according to some embodiments of the present disclosure. As shown in Figure 7, the dialogue interaction device 7 of this embodiment includes: a determining module 71, configured to determine the progression type of the dialogue based on the interaction between the user and the intelligent agent in response to the user's instruction at the dialogue interface between the user and the intelligent agent; a display module 72, configured to display prompt information associated with the dialogue in response to the progression type being a first type; and to display prompt information including a new topic in response to the progression type being a second type.

[0081] In some embodiments, the interaction includes dialogue content and interactive operations, and the determining module 71 is further configured to: determine whether the user has an intention to continue the dialogue on the topic of the dialogue content based on at least one of the dialogue content and interactive operations between the user and the agent; determine the advancement type as a first type in response to the user having an intention; and determine the advancement type as a second type in response to the user not having an intention.

[0082] In some embodiments, the determining module 71 is further configured to: perform semantic understanding on the content of the dialogue between the user and the agent; and determine, based on the semantic understanding result, whether the user intends to continue the dialogue on the topic of the dialogue content.

[0083] In some embodiments, the determining module 71 is further configured to: utilize a machine learning model to process a specified number of the latest messages in the dialogue between the user and the agent to obtain semantic understanding results.

[0084] In some embodiments, the determining module 71 is further configured to: determine, based on the semantic understanding result, whether the message sent by the user includes an adjustment instruction for the message sent by the agent; and in response to the message sent by the user including an adjustment instruction for the message sent by the agent, determine that the user has an intention to continue the conversation on the topic of the dialogue content.

[0085] In some embodiments, the semantic understanding result includes the user's sentiment towards the topic of the conversation, and the determining module 71 is further configured to: determine the user's sentiment towards the conversation based on the semantic understanding result; and determine, based on the sentiment, whether the user has the intention to continue the conversation on the topic of the conversation content.

[0086] In some embodiments, the determining module 71 is further configured to: determine whether the interaction operation is a positive or negative operation on a message sent by the agent; determine that the user has an intention in response to the operation being a positive operation; and determine that the user does not have an intention in response to the operation being a negative operation.

[0087] In some embodiments, positive actions include at least one of liking, favorite, sharing, selecting, and copying; negative actions include at least one of negative feedback and regenerating.

[0088] In some embodiments, the determining module 71 is further configured to: determine the topic of each round of dialogue based on the semantic understanding results of the dialogue content; and determine that the user has the intention to continue the dialogue on the topic of the dialogue content in response to a topic appearing continuously in the dialogue for more than a threshold.

[0089] In some embodiments, the display module 72 is further configured to display a prompt message including a new topic after the history of conversations has been cleared.

[0090] In some embodiments, the display module 72 is further configured to: cancel the display of prompts associated with messages sent by the agent; and display prompts including new topics.

[0091] In some embodiments, the user's instructions include at least one of gesture instructions and voice instructions.

[0092] In some embodiments, gesture commands include an up swipe gesture.

[0093] In some embodiments, the display module 72 is further configured to: display the triggered prompt message sent by the user in response to any prompt message being triggered; and display the response sent by the agent to the prompt message.

[0094] Figure 8 shows a block diagram of an electronic device according to some embodiments of the present disclosure.

[0095] Memory 81 is used to store one or more computer-readable instructions. Memory 81 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 81 may, for example, store operating systems, application programs, boot loaders, databases, and other programs, as well as various application programs and various data.

[0096] The processor 82 is configured to execute computer-readable instructions to implement the dialogue interaction method of any of the foregoing embodiments 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 upon here.

[0097] The processor 82 can be configured to perform the steps of the foregoing embodiments. The processor 82 can be embodied in 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.

[0098] The processor 82 and the memory 81 can communicate with each other directly or indirectly. For example, the processor 82 and the memory 81 can communicate via a network. The network can include wireless networks, wired networks, and / or any combination of wireless and wired networks. The processor 82 and the memory 81 can also communicate with each other via a system bus, which is not limited in this disclosure.

[0099] It should be noted that the components of the electronic device 8 shown in Figure 8 are exemplary and not limiting. The electronic device 8 may have other components depending on the specific application requirements. The processor 82 can control other components in the electronic device 8 to perform the desired functions.

[0100] Electronic device 8 can be implemented by software, firmware and / or hardware, and can be integrated into a device with the relevant application installed.

[0101] Figure 9 shows a block diagram of an electronic device according to some other embodiments of the present disclosure.

[0102] The electronic device 9 shown in Figure 9 can be a computer system with a dedicated hardware structure, capable of performing corresponding functions when relevant applications are installed.

[0103] 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.

[0104] As shown in Figure 9, the Central Processing Unit (CPU) 91 executes various processes based on programs stored in Read-Only Memory (ROM) 92 or programs loaded from Storage Section 98 into Random Access Memory (RAM) 93. RAM 93 stores data required as needed when the CPU 91 executes various processes. The CPU is merely exemplary and can also be other types of processors, such as the various processors described above. ROM 92, RAM 93, and Storage Section 98 can be various forms of computer-readable storage media. It should be noted that although ROM 92, RAM 93, and Storage Section 98 are shown separately in Figure 9, one or more of them can be combined or located in the same or different memories or storage modules.

[0105] CPU 91, ROM 92 and RAM 93 are interconnected via bus 94. Input / output interface 95 is also connected to bus 94.

[0106] The following components are connected to the input / output interface 95: input section 96, such as a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output section 97, including displays such as cathode ray tube (CRT), liquid crystal display (LCD), speakers, vibrators, etc.; storage section 98, including hard disk, magnetic tape, etc.; and communication section 99, including network interface cards such as LAN cards, modems, etc. The communication section 99 allows communication processing to be performed via a network such as the Internet. It is readily understood that although some parts of the electronic device 9 shown in Figure 9 communicate via bus 94, 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.

[0107] As needed, drive 910 is also connected to input / output interface 95. Removable media 911, such as disks, optical disks, magneto-optical disks, semiconductor memories, etc., are installed on drive 910 as needed, so that computer programs read from them can be installed into storage section 98 as needed.

[0108] 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 a storage medium such as a removable medium 911.

[0109] 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 99, or installed from storage section 98, or installed from ROM 92. When the computer program is executed by CPU 91, the methods of embodiments of this disclosure are performed.

[0110] 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.

[0111] A computer-readable medium may be a computer-readable storage medium, a computer-readable signal medium, or any combination thereof.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] In some embodiments, a computer program is also provided, comprising: instructions that, when executed by a processor, cause the processor to perform the methods described in any of the foregoing embodiments. For example, the instructions may be embodied in computer program code.

[0116] 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).

[0117] 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.

[0118] 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.

[0119] 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. A dialogue interaction method, comprising: In the dialogue interface between the user and the intelligent agent, in response to the user's instructions, the type of dialogue progression is determined based on the interaction between the user and the intelligent agent; In response to the advancement type being the first type, a prompt message associated with the dialogue is displayed; In response to the advancement type being the second type, a prompt message including a new topic is displayed.

2. The dialogue interaction method according to claim 1, wherein, The interaction includes dialogue content and interactive operations. Determining the progression type of the dialogue based on the interaction between the user and the intelligent agent includes: Based on at least one of the dialogue content and interactive operations between the user and the intelligent agent, determine whether the user intends to continue the dialogue on the topic of the dialogue content; In response to the user's stated intent, the advancement type is determined to be the first type; In response to the user not having the stated intent, the advancement type is determined to be the second type.

3. The dialogue interaction method according to claim 2, wherein, Determining whether the user intends to continue the conversation regarding the topic of the conversation includes: Perform semantic understanding on the content of the dialogue between the user and the intelligent agent; Based on the semantic understanding results, it is determined whether the user intends to continue the conversation on the topic of the dialogue content.

4. The dialogue interaction method according to claim 3, wherein, The semantic understanding of the content of the dialogue between the user and the intelligent agent includes: Using a machine learning model, the latest specified number of messages in the dialogue between the user and the agent are processed to obtain the semantic understanding result.

5. The dialogue interaction method according to claim 3 or 4, wherein, Determining whether the user intends to continue the conversation on the topic of the dialogue content based on the semantic understanding results includes: Based on the semantic understanding results, determine whether the message sent by the user includes an adjustment instruction for the message sent by the agent; In response to a message sent by the user, including an adjustment instruction to a message sent by the agent, it is determined that the user intends to continue the conversation on the topic of the dialogue content.

6. The dialogue interaction method according to claim 3 or 4, wherein, The semantic understanding result includes the user's sentiment towards the topic of the conversation, and determining whether the user intends to continue the conversation regarding the topic of the conversation content includes: Based on the semantic understanding results, determine the user's emotional inclination towards the dialogue; Based on the stated emotional inclination, determine whether the user intends to continue the conversation on the topic of the dialogue content.

7. The dialogue interaction method according to claim 2, wherein, Determining whether the user intends to continue the conversation regarding the topic of the conversation includes: Determine whether the interaction operation is a positive or negative operation for the message sent by the agent; In response to the operation being affirmative, it is determined that the user has the intent. In response to a negative operation, it is determined that the user does not have the stated intent.

8. The dialogue interaction method according to claim 7, wherein: The affirmative operation includes at least one of the following: liking, saving, sharing, selecting, and copying; The negation operation includes at least one of negative feedback and regeneration.

9. The dialogue interaction method according to claim 2, wherein, Determining whether the user intends to continue the conversation regarding the topic of the conversation includes: Based on the semantic understanding results of the content of the dialogue, the topic of each round of dialogue in the dialogue is determined; If a certain topic appears in the conversation for more than a threshold number of consecutive rounds, it is determined that the user intends to continue the conversation on the topic of the conversation content.

10. The dialogue interaction method according to claim 1, wherein, The display includes notifications for new topics, including: After clearing the history of conversations, a prompt message including the new topic is displayed.

11. The dialogue interaction method according to any one of claims 1 to 10, wherein, The dialogue interface also includes prompt information associated with messages sent by the intelligent agent, and the display of prompt information for new topics includes: Cancel the display of prompts associated with messages sent by the intelligent agent; The system displays a notification message that includes a new topic.

12. The dialogue interaction method according to any one of claims 1 to 11, wherein, The user's instructions include at least one of gesture instructions and voice instructions.

13. The dialogue interaction method according to claim 12, wherein, The gesture commands include an upward swipe gesture.

14. The dialogue interaction method according to any one of claims 1 to 13, further comprising: In response to any prompt being triggered, the prompt sent by the user and the triggered prompt being displayed; Displays the agent's response to the prompt message.

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

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

17. A computer program product, when run on a computer, causes the computer to implement the dialogue interaction method according to any one of claims 1 to 14.

18. A computer program comprising: Instructions, which, when executed by a processor, cause the processor to perform the dialogue interaction method according to any one of claims 1 to 14.

Images