Conversation interaction method, electronic equipment, storage medium and product

Abstract

The invention relates to a dialogue interaction method, electronic equipment, a storage medium and a product, and relates to the technical field of computers. The dialogue interaction method comprises the following steps: in a dialogue interface of a user and an agent, in response to an instruction of the user, determining a propelling type of a dialogue based on interaction of the user and the agent; in response to the propelling type being the first type, displaying prompt information associated with the dialogue; and in response to the propelling type being the second type, displaying prompt information including the new topic.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to a conversation interaction method, electronic device, storage medium and product. Background Art

[0002] 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 the interaction input by the user. One application scenario of intelligent agents is intelligent dialogue scenarios. Users can send messages to intelligent agents, and intelligent agents can send response messages to users based on the messages sent by users. Summary of the invention

[0003] According to some embodiments of the present disclosure, a conversation interaction method is provided, comprising: in a conversation interface between a user and an intelligent agent, in response to a user's instruction, determining the advancement type of the conversation based on the interaction between the user and the intelligent agent; in response to the advancement type being a first type, displaying prompt information associated with the conversation; in response to the advancement type being a second type, displaying prompt information including a new topic.

[0004] According to some embodiments of the present disclosure, an electronic device is provided, comprising: a memory; and a processor coupled to the memory, wherein the processor is configured to execute the conversation interaction method of any embodiment described in the present disclosure based on instructions stored in the memory.

[0005] According to some embodiments of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the program is executed by a processor, the conversation interaction method of any embodiment described in the present disclosure is performed.

[0006] According to some embodiments of the present disclosure, a computer program product is provided. When the computer program product is executed on a computer, the computer is enabled to implement the dialog interaction method of any embodiment described in the present disclosure.

[0007] Other features, aspects and advantages of the present disclosure will become apparent from the following detailed description of exemplary embodiments of the present disclosure with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] The following is an explanation of the embodiments of the present disclosure with reference to the accompanying drawings. It should be understood that the drawings described below only relate to some embodiments of the present disclosure and do not constitute a limitation to the present disclosure. In the accompanying drawings:

[0009] Figure 1 A flowchart of a dialog interaction method according to some embodiments of the present disclosure is shown.

[0010] Figure 2A schematic flow chart of a method for determining a propulsion type according to some embodiments of the present disclosure is shown.

[0011] Figure 3 A conversation interface of an agent according to some embodiments of the present disclosure is shown.

[0012] Figure 4 A conversation interface of an intelligent agent according to some other embodiments of the present disclosure is shown.

[0013] Figure 5 A conversation interface of an intelligent agent according to yet some other embodiments of the present disclosure is shown.

[0014] Figure 6 A conversation interface of an intelligent agent according to some further embodiments of the present disclosure is shown.

[0015] Figure 7 A schematic structural diagram of a dialog interaction device according to some embodiments of the present disclosure is shown.

[0016] Figure 8 A block diagram of an electronic device according to some embodiments of the present disclosure is shown.

[0017] Fig. 9 A block diagram of an electronic device according to some other embodiments of the present disclosure is shown.

[0018] It should be understood that, for ease of description, the sizes of the various parts shown in the drawings are not necessarily drawn according to the actual proportional relationship. The same or similar reference numerals are used in the various drawings to represent the same or similar parts. Therefore, once an item is defined in one drawing, it may not be further discussed in subsequent drawings. DETAILED DESCRIPTION

[0019] The technical solutions in the embodiments of the present disclosure will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present disclosure. It should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein.

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

[0021] The term “including” and its variations used in the present disclosure are intended to be open terms that include at least the following elements / features but do not exclude other elements / features, that is, “including but not limited to.” The term “based on” means “at least partly based on.”

[0022] It should be noted that the concepts of "first", "second", etc. mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units. Unless otherwise specified, the concepts of "first", "second", etc. are not intended to imply that the objects described in this way must be in a given order in time, space, ranking, or any other manner.

[0023] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0024] 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, stored data, displayed data, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0025] The embodiments of the present disclosure are described in detail below in conjunction with the accompanying drawings, but the present disclosure is not limited to these specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. In addition, in one or more embodiments, specific features, structures or characteristics can be combined in any suitable manner that will be clear from the present disclosure by a person of ordinary skill in the art.

[0026] In the dialogue scene with the agent, after the agent sends a message to the user, it sometimes displays several prompts to facilitate the user to ask questions. In the interactive interface, the user can send a message to ask who is the protagonist of a movie. Then, the agent sends a message to reply to the user, the content is that the protagonist of the movie is A, and the actor who plays the protagonist is B. Furthermore, a prompt control can be displayed on the interface, and the prompt information in the prompt control is related to the user's last message sent or the agent's reply. The prompt information includes, for example, "What awards did actor B win for role A?" "Recommend some classic movies starring actor B" and so on. In response to the user's triggering operation on the prompt control, a message including the prompt information in the triggered prompt control can be automatically sent to the user. And the agent can further respond to the message. In this way, the user's manual input time and operation can be saved, in the hope of improving the interaction efficiency.

[0027] In actual applications, some users found that the existing prompt information sometimes cannot meet the user's question needs. In most cases, users still need to manually enter messages. For example, some users want to start a new topic that is not related to the current chat content, and some users want to continue to delve into the current topic, but the displayed prompt information cannot cover the content that the user wants to continue to ask. This leads to low interaction efficiency during the user's dialogue with the intelligent agent.

[0028] In order to solve the above problems, the present disclosure provides a conversation interaction method, electronic device, storage medium and product. In an embodiment of the present disclosure, it is determined whether to display prompt information associated with the current conversation or prompt information of a new topic according to the interaction between the user and the agent.

[0029] Figure 1 FIG. 1 is a flow chart showing a method for dialog interaction according to some embodiments of the present disclosure. Figure 1 As shown, the dialogue interaction method of this embodiment includes steps S102 to S106.

[0030] In step S102, in the dialogue interface between the user and the agent, in response to the user's instructions and based on the interaction between the user and the agent, the advancement type of the dialogue is determined.

[0031] The agent can generate corresponding content based on the dialogue sent by other subjects (such as users or robots) in the dialogue scene. It can be implemented in software, hardware, or a combination of software and hardware. The agent can also be called a robot, a digital person, or a virtual agent of a machine learning model. The agent can be implemented based on a machine learning model, for example, based on a large language model (LLM) or a foundation model. The machine learning model can be a generative model, which is used to output target content based on input information. The generative model includes, for example, a model generated based on text or a model generated based on an image, and the output of the generative model can include text, images, or a combination of the two. Of course, the input or output of the generative model can also be data of other modalities, such as audio, video, or a combination of multiple types of data. The generative model can be a single-modal model, such as a model that generates text from text (referred to as the "text-to-text model") or a model that generates images from images (referred to as the "image-to-image model"). Alternatively, the generative model can be a cross-modal model, that is, a model whose input and output belong to different modalities, such as a model that generates images from text (referred to as the "text-to-image model"). Alternatively, the input of the generative model can include multiple modalities, and the output can also include multiple modalities.

[0032] The dialogue interface between the user and the agent is used to display one or more messages sent by the user and the agent. In addition, it can also include interactive controls between the user and the agent. For example, an input box for sending text messages, a control for sending voice messages, a control for sending files (including images, videos, audio, documents, etc.), and so on.

[0033] The user's instruction is used to trigger the display of the prompt information. The instruction can be generated by at least one of a gesture instruction, a voice instruction, a triggering of a virtual control, and a triggering of a physical control.

[0034] The interaction between the user and the agent may include multiple types. In some embodiments, the interaction is related to at least one of a message sent by the user and a message sent by the agent. The interaction between the user and the agent can reflect the user's opinion or attitude towards the topic currently being discussed, for example, whether the user likes the topic, whether the agent's reply has satisfied the user's questioning needs, etc.

[0035] The advancement type of a conversation includes at least a first type and a second type, and the advancement type is used to indicate whether to start a new topic.

[0036] In step S104, in response to the advancement type being the first type, prompt information associated with the dialogue is displayed.

[0037] The first type is used to indicate not to start a new topic. In other words, the first type is used to indicate to continue the current topic. In this case, by displaying the prompt information associated with the conversation, it is convenient for the user to select the prompt information to continue discussing the content associated with the current conversation with the agent.

[0038] In some embodiments, after the agent sends a message, it will send the prompt information associated with the conversation by default. In this case, if the advancement type is the first type, then the prompt information associated with the conversation can be added based on the prompt information that has been sent. For example, if there are M original prompt information, after obtaining the user's instructions and determining that the advancement type of the conversation is the first type, N more prompt information associated with the conversation can be added, where M and N are non-negative integers. Therefore, if the user is not satisfied with the currently displayed prompt information, he can obtain more relevant prompt information by triggering the instruction. In this way, the user can save the operation of inputting the message content, thereby improving the user's operation efficiency.

[0039] Of course, when the message sent by the agent does not carry prompt information by default, the N prompt information associated with the conversation can be directly displayed.

[0040] In step S106, in response to the push type being the second type, prompt information including a new topic is displayed.

[0041] The new topic is not determined based on the conversation that the user has already had with the agent. For example, the new topic may include a topic that is not related to the current conversation. The new topic may be selected based on the hot topics of the platform, or, with the user's authorization, based on the user's interests.

[0042] The second type is used to indicate the start of a new topic. In other words, the second type is used to indicate that the current topic is no longer being continued. In this case, displaying prompt information including a new topic to the user can facilitate the user to start a conversation with the agent about the new topic. In this way, when the user no longer wants or needs to have a conversation about the current topic, it can facilitate the user to quickly obtain more information related to the topic, thereby improving the efficiency of information acquisition.

[0043] The embodiment of the present disclosure can display two different prompt information based on the user's instructions. Specifically, according to the interaction between the user and the intelligent agent, it is determined whether to continue to advance the current topic or to advance a new topic, and then different prompt information is displayed according to the determination result. Therefore, the present disclosure can provide prompt information that the user is more likely to use during the dialogue between the user and the intelligent agent, thereby increasing the probability of the user triggering the prompt information, saving the user's operation, and improving the efficiency of the user's information acquisition.

[0044] The interaction between the user and the agent includes, for example, at least one of the content of the conversation and the interactive operation. In some embodiments, the advancement type of the conversation can be determined by performing intention analysis on the interaction. Figure 2 FIG. 2 shows a flow chart of a method for determining a propulsion type according to some embodiments of the present disclosure. Figure 2 As shown, the propulsion type determination method of this embodiment includes steps S202 to S206.

[0045] In step S202, based on the conversation content and at least one of the interactive operations between the user and the agent, it is determined whether the user has the intention to continue the conversation on the topic of the conversation content.

[0046] The interaction between the user and the agent may involve a specified number of messages recently generated between the user and the agent. For example, the interaction includes the content of the specified number of messages recently sent by at least one of the user and the agent, such as the content of the last message sent by the user in the conversation; for another example, the interaction includes the user's interactive operation on the content of the specified number of messages recently sent by at least one of the user and the agent, and so on.

[0047] The method of determining the intention based on the conversation content can be achieved through semantic understanding, keyword matching, etc. For example, the content of the conversation between the user and the agent is semantically understood; based on the semantic understanding results, it is determined whether the user has the intention to continue the conversation on the topic of the conversation content. Since the tone and language style used in the messages sent by the user during the conversation are personalized, semantic understanding can more accurately obtain the intention of the content freely input by the user.

[0048] Semantic understanding can be achieved through a machine learning model. In some embodiments, a machine learning model is used to process the latest specified number of messages in a conversation between a user and an agent to obtain a semantic understanding result. The machine learning model can be a semantic analysis model, a large language model, a basic model, and the like. Taking a large language model or a basic model as an example, a prompt for the model can be generated based on the latest specified number of messages in the conversation so that the model can process them. The prompt of the model can also include processing instructions for these messages, for example, "semantically understand these messages and output whether the user has the intention to continue the conversation on the topic of the conversation content." Thus, the model can process the content of the message according to the processing instructions in the prompt information.

[0049] The result of semantic understanding can be an analysis of the content of the message. For example, the result of semantic understanding can be the extraction of the topic and key information of the conversation content, or the intention further determined based on the topic and key information. The result of semantic understanding can be determined based on whether the conversation content can be continued or whether the user has the intention to discuss the topic of the conversation in depth. For messages involving fewer dimensions (for example, less than the first threshold), the user's needs are likely to be met after obtaining the reply of the agent, and there is no need to continue the topic; while for messages involving more dimensions (for example, greater than the second threshold), the user has the possibility of continuing the topic. For example, if a user asks the agent about the temperature of the Himalayas, the question mainly involves geography, and after the agent replies, the user's needs may be met; if the user asks about the temperature of Beijing, the question may involve travel and shopping in addition to geography, so after the agent replies to the question, the user may further ask questions about relevant information in Beijing.

[0050] When a machine learning model is used to analyze the content of a message, the model can be trained in advance based on training data. For example, the training data may include multiple messages, and the tag value of each training data is determined based on whether the user continues to talk to the agent about the topic involved in the message after the message is sent. Thus, the model can determine what kind of messages have continuity based on the content of these messages, that is, the user may continue to ask questions.

[0051] The semantic understanding result can also be the result of type recognition of the conversation content.

[0052] In some embodiments, based on the semantic understanding results, it is determined whether the message sent by the user includes an adjustment instruction for the message sent by the agent; in response to the message sent by the user including an adjustment instruction for the message sent by the agent, it is determined that the user has the intention to continue the conversation on the subject of the conversation content. Whether the message includes a message of the adjustment instruction type can determine whether the user is satisfied with the message sent by the agent. For example, the user sent message 1, and the agent generated a reply message 2 based on message 1. If the user is not satisfied with the reply message 2, message 3 can be sent, with the content such as adjustment instructions such as "regenerate the answer", "make it longer", "make it more concise", etc. The user sent the adjustment instruction, indicating that the user is not satisfied with the content sent by the agent before, and the user also hopes to continue the conversation based on the previous conversation topic, that is, there is an intention to continue the conversation on the subject of the conversation content.

[0053] In some embodiments, it is also possible to determine whether the message sent by the user is a closing statement based on the semantic understanding result. The closing statement refers to the language used to end the conversation, such as "OK, thank you" or "Got it". In the case where the message sent by the user is a closing statement, it can be determined that the user has no intention to continue the conversation on the topic of the conversation content.

[0054] The semantic understanding result may also include the user's emotional inclination towards the topic of the conversation. In some embodiments, determining whether the user has the intention to continue the conversation on the topic of the conversation content includes: determining the user's emotional inclination towards the conversation based on the semantic understanding result; and determining whether the user has the intention to continue the conversation on the topic of the conversation content based on the emotional inclination. For example, when the user's emotional inclination towards the conversation is positive (e.g., like), it is determined that the user has the intention to continue the conversation on the topic of the conversation content; when the user's emotional inclination towards the conversation is negative (e.g., dislike), it is determined that the user has no intention to continue the conversation on the topic of the conversation content.

[0055] The interactive operation includes, for example, an operation of a user on a message sent by an agent. In some embodiments, it is determined whether the interactive operation is an affirmative operation or a negative operation on the message sent by the agent; in response to the operation being an affirmative operation, it is determined that the user has the intention; in response to the operation being a negative operation, it is determined that the user does not have the intention.

[0056] Affirmative operations indicate that the user agrees with the content sent by the agent and reflects this tendency through interactive operations. Affirmative operations include, for example, at least one of like, favorite, share, select, and copy. Like can directly indicate the user's approval of the content sent by the agent. Favorite and share indicate that the user thinks the content sent by the agent is valuable and wants to read it later or show it to others. Like, favorite, and share can be triggered by controls in the dialogue interface or default gestures. Selection means that the user uses the cursor to highlight part or all of the text in the message, indicating the user's attention to part or all of the content of the message. Copy means that the user wants to continue using the information elsewhere. Therefore, the above operations can indicate the user's affirmation of the content sent by the agent.

[0057] Negative operation means that the user does not agree with the content sent by the agent, and this tendency is reflected through interactive operation. Negative operation includes at least one of negative feedback and regeneration. Negative feedback is, for example, "thumb down", which directly indicates that the user does not agree with the content sent by the agent. Regeneration indirectly indicates that the user is dissatisfied with the currently generated content. Negative feedback and regeneration operations can be triggered by controls in the dialogue interface or default gestures.

[0058] In addition, it is also possible to combine the conversation content and the interactive operation to determine whether the user has the intention to continue the conversation on the topic of the conversation content. In some embodiments, based on the semantic understanding results of the content of the conversation, the topic of each round of conversation in the conversation is determined; in response to a certain topic appearing continuously in the conversation for more than a threshold number of rounds, it is determined that the user has the intention to continue the conversation on the topic of the conversation content. A round of conversation may include a message sent by a user and a response message of the agent to the message, that is, a message sent by the user and a message sent by the agent after and adjacent to the message. The topic of each round of conversation can be determined based on the content of each round of conversation. For example, a topic analysis model can be used to extract the topic of each round of conversation. When a certain topic appears continuously in the conversation for more than a threshold number of rounds, it means that the user and the agent have had an in-depth discussion around the topic, so it is very likely to continue the discussion, that is, there is an intention to continue the conversation on the topic.

[0059] In step S204, in response to the user's intention, the advancement type is determined to be the first type. Thus, prompt information associated with the current conversation can be displayed to the user.

[0060] In step S206, in response to the user not having the intention, the push type is determined to be the second type. Thus, prompt information including a new topic can be displayed to the user.

[0061] The above-mentioned embodiment utilizes at least one of the conversation content and interactive operations to determine the user's intention, so that it can more comprehensively cover the user's behavioral information in the conversation with the intelligent agent, and thus accurately determine the user's intention, thereby improving the accuracy of determining the prompt information type and improving the user's operating efficiency.

[0062] Figure 3 The dialog interface of the intelligent agent according to some embodiments of the present disclosure is shown. Figure 3 In the dialogue interface 3 shown, the user sends a message 31 to agent A, namely, "What do watermelon seedlings look like?" Then, agent A responds to the message 31 sent by the user through a message 32, in which the watermelon seedlings are described.

[0063] Whether the user intends to continue the topic related to watermelon seedlings or plant seedlings can be determined based on the content of at least one of the messages 31 and 32. If the user continues to send messages including adjustment instructions, such as "regenerate answer" or "more details", the advancement type can be determined to be the first type.

[0064] Figure 3In the example, some interactive controls are attached to the message 32 sent by the agent. If the user triggers the copy control 321 and 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. As needed, more controls can be presented to the user, or the user can trigger the display of more interactive controls by long pressing the message, which will not be described here.

[0065] In the interface 3, prompt messages 33 and 34 are shown as examples. These two prompt messages are automatically displayed after the message 32 is sent.

[0066] The user can send an instruction by, for example, sliding up a gesture. For example, in interface 3, the user performs a sliding up gesture to trigger the display of more prompt information associated with the current conversation, or the display of a new topic.

[0067] In some embodiments, when it is determined that the advancement type is the first type, more prompt information associated with the current conversation can be displayed in response to the user's instruction.

[0068] For example, in response to the user performing a swipe up gesture in interface 3, interface 3 may be as follows: Figure 4 Compared to Figure 3 , Figure 4 In the interface 3 in the example, two new prompt information 41 and 42 associated with the dialogue are added. Therefore, when the advancement type of the dialogue is determined to be the first type, more prompt information can be displayed to the user, so that the user can more easily find the questions he wants to continue asking and quickly ask questions. Figure 4 Continuing to send instructions in the interface 3 shown, such as continuing to execute the swipe up gesture, more prompt information associated with the conversation can continue to be displayed to the user.

[0069] In some embodiments, when the advancement type is determined to be the first type, the new topic may be displayed in a new page or a current page.

[0070] For example, when displaying a new topic, the current conversation interface may be cleared before displaying it. In some embodiments, after clearing the historical conversation, a prompt message including the new topic is displayed. Thus, when it is determined that a new topic is currently being opened, the historical conversation is also cleared. This avoids the topic that the user is no longer interested in interfering with the user's subsequent conversation.

[0071] Taking the user's swipe up gesture trigger instruction as an example, when it is determined that the advancement type of the dialogue is the second type, the content in the current dialogue interface can be scrolled up and a new page can be slid in.

[0072] Figure 5The dialog interface of the agent according to some other embodiments of the present disclosure is shown. The interface 5 may be a new dialog interface displayed after the interface 3 is cleared, and the interface includes new topics 51 to 54. Figure 5 It is still a conversation between the user and agent A, but Figure 3 Existing conversations in the interface are cleared. Thus, users can focus more on new topics.

[0073] For another example, when displaying a new topic, it can also be displayed based on the existing messages in the current dialogue interface. As needed, regardless of whether the current interface includes prompt information, the prompt information corresponding to the new topic can be displayed in the interface in a newly added manner. Alternatively, if the dialogue interface also includes prompt information associated with the message sent by the agent, the prompt information associated with the message sent by the agent can be cancelled and the prompt information including the new topic can be displayed.

[0074] Figure 6 The dialog interface of the intelligent agent according to some other embodiments of the present disclosure is shown. Figure 3 After the interface shown in the figure triggers the instruction (for example, executing the upward sliding gesture), the following Figure 6 In the interface 6, the original Figure 3 The displayed prompt information 33 and 34 are cancelled and replaced by new topics 61 to 63. This can not only display new topics for users, but also facilitate users to quickly view historical messages.

[0075] In some embodiments, in response to any prompt message being triggered, the triggered prompt message sent by the user is displayed; and the reply to the prompt message sent by the agent is displayed. That is, whether it is the prompt message attached to the message sent by the agent, or the prompt message displayed in response to the user's instruction (including prompt information associated with the conversation, and prompt information of new topics), it can be applied to the method of this embodiment. That is, after the user triggers the prompt message, the effect is consistent with the user manually reading the content of the prompt message and sending it. The agent will respond to the message sent by the user. Thus, the prompt message can simplify the user's operating efficiency. In combination with the aforementioned embodiments, the scheme of displaying different prompt messages is selected according to the advancement mode of the conversation. The embodiment of the present disclosure can quickly provide the user with prompt information that matches the user's needs, thereby improving the operating efficiency and the efficiency of information acquisition.

[0076] The above describes the methods of various embodiments of the present disclosure. The following describes the apparatus for executing the above methods.

[0077] Figure 7 FIG. 2 shows a schematic diagram of the structure of a dialog interaction device according to some embodiments of the present disclosure. Figure 7As shown, the dialogue interaction device 7 of this embodiment includes: a determination module 71, which is configured to determine the advancement type of the dialogue in response to the user's instructions and based on the interaction between the user and the agent in the dialogue interface between the user and the agent; a display module 72, which is configured to display prompt information associated with the dialogue in response to the advancement type being the first type; and to display prompt information including a new topic in response to the advancement type being the second type.

[0078] In some embodiments, the interaction includes dialogue content and interactive operations, and the determination module 71 is further configured to: determine whether the user has the intention to continue the conversation 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; in response to the user having the intention, determine the advancement type as the first type; in response to the user not having the intention, determine the advancement type as the second type.

[0079] In some embodiments, the determination module 71 is further configured to: perform semantic understanding on the content of the conversation between the user and the agent; and determine whether the user has the intention to continue the conversation on the topic of the conversation content based on the semantic understanding result.

[0080] In some embodiments, the determination module 71 is further configured to: utilize a machine learning model to process the latest specified number of messages in the conversation between the user and the agent to obtain a semantic understanding result.

[0081] In some embodiments, the determination module 71 is further configured to: determine whether the message sent by the user includes an adjustment indication to the message sent by the agent based on the semantic understanding result; and determine that the user has the intention to continue the conversation on the topic of the conversation content in response to the message sent by the user including an adjustment indication to the message sent by the agent.

[0082] In some embodiments, the semantic understanding results include the user's emotional inclination towards the topic of the conversation, and the determination module 71 is further configured to: determine the user's emotional inclination towards the conversation based on the semantic understanding results; and determine whether the user has the intention to continue the conversation on the topic of the conversation content based on the emotional inclination.

[0083] In some embodiments, the determination module 71 is further configured to: determine whether the interactive operation is an affirmative operation or a negative operation of the message sent by the agent; in response to the operation being an affirmative operation, determine that the user has an intention; in response to the operation being a negative operation, determine that the user has no intention.

[0084] In some embodiments, the affirmative operation includes at least one of like, favorite, share, select, and copy; the negative operation includes at least one of negative feedback and regeneration.

[0085] In some embodiments, the determination module 71 is further configured to: determine the topic of each round of conversation in the conversation based on the semantic understanding results of the content of the conversation; in response to a certain topic appearing in the conversation for more rounds than a threshold, determine that the user has the intention to continue the conversation on the topic of the conversation content.

[0086] In some embodiments, the display module 72 is further configured to display prompt information including new topics after clearing the historical conversations.

[0087] In some embodiments, the display module 72 is further configured to: cancel the display of prompt information associated with the message sent by the agent; and display prompt information including the new topic.

[0088] In some embodiments, the user's instruction includes at least one of a gesture instruction and a voice instruction.

[0089] In some embodiments, the gesture instruction includes a swipe up gesture.

[0090] In some embodiments, the display module 72 is further configured to: in response to any prompt message being triggered, display the triggered prompt message sent by the user; and display the reply to the prompt message sent by the agent.

[0091] Figure 8 A block diagram of an electronic device according to some embodiments of the present disclosure is shown.

[0092] The memory 81 is used to store one or more computer-readable instructions. The 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), flash memory. The memory 81 may store, for example, an operating system, an application, a boot loader (BootLoader), a database, and other programs, and may also store various applications and various data.

[0093] The processor 82 is used to run computer-readable instructions to implement the conversation interaction method of any of the above embodiments or the method of any of the above embodiments. The specific implementation of each step of the method can refer to the above embodiments, and the repeated parts are not repeated here.

[0094] The processor 82 may be configured to perform the steps of the aforementioned embodiments. The processor 82 may be embodied as various processing devices, such as a central processing unit (CPU), a network processor (NP), etc.; it may 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, discrete hardware components. The central processing unit (CPU) may be an X86 or ARM architecture, etc.

[0095] The processor 82 and the memory 81 may communicate with each other directly or indirectly. For example, the processor 82 and the memory 81 may communicate with each other via a network. The network may include a wireless network, a wired network, and / or any combination of a wireless network and a wired network. The processor 82 and the memory 81 may also communicate with each other via a system bus, which is not limited in the present disclosure.

[0096] It should be noted that Figure 8 The components of the electronic device 8 shown are only exemplary and non-restrictive. The electronic device 8 may also have other components according to actual application requirements. The processor 82 may control other components in the electronic device 8 to perform desired functions.

[0097] The electronic device 8 may be implemented by software, firmware and / or hardware, and may be integrated into a device installed with relevant application programs.

[0098] Fig. 9 A block diagram of an electronic device according to some other embodiments of the present disclosure is shown.

[0099] Fig. 9 The electronic device 9 shown may be a computer system with a dedicated hardware structure, which can execute corresponding functions when a relevant application program is installed.

[0100] Electronic devices include, but are not limited to, mobile terminals such as smart phones, laptops, personal digital assistants (PDA), tablet computers (Tablet Personal Computer, Tablet PC), PMP (portable multimedia player), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), wearable devices, etc., as well as fixed terminals such as digital televisions, desktop computers, etc.

[0101] like Fig. 9As shown, a central processing unit (CPU) 91 performs various processes according to a program stored in a read-only memory (ROM) 92 or a program loaded from a storage section 98 to a random access memory (RAM) 93. In the RAM 93, data required when the CPU 91 performs various processes is stored as needed. The central processing unit is merely exemplary, and it may also be other types of processors, such as the various processors described above. The ROM 92, the RAM 93, and the storage section 98 may be various forms of computer-readable storage media. It should be noted that although Fig. 9 ROM 92, RAM 93 and storage section 98 are shown separately in the figure, but one or more of them may be combined or located in the same or different memory or storage modules.

[0102] The CPU 91, the ROM 92, and the RAM 93 are connected to one another via a bus 94. To the bus 94, an input / output interface 95 is also connected.

[0103] The following components are connected to the input / output interface 95: an input section 96, such as a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output section 97, including a display, such as a cathode ray tube (CRT), a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage section 98, including a hard disk, a magnetic tape, etc.; and a communication section 99, including a network interface card such as a LAN card, a modem, etc. The communication section 99 allows communication processing to be performed via a network such as the Internet. It is easy to understand that although Fig. 9 Some of the electronic devices 9 are shown to communicate via a bus 94, but they may also communicate via a network or other means, wherein the network may include a wireless network, a wired network, and / or any combination of a wireless network and a wired network.

[0104] A drive 910 is also connected to the input / output interface 95 as needed. A removable medium 911 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory or the like is mounted on the drive 910 as needed so that a computer program read therefrom is installed into the storage section 98 as needed.

[0105] When the above-described series of processing is realized by software, a program constituting the software can be installed from a network such as the Internet or a storage medium such as the removable medium 911 .

[0106] According to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, some embodiments of the present disclosure include a computer program product, which, when the computer program product is run on a computer, enables the computer to implement the method described in any of the aforementioned embodiments. The computer program product includes a computer instruction carried on a computer-readable medium, containing a program code for executing the method shown in the flowchart. In such an embodiment, the computer instruction can be downloaded and installed from a network through a communication part 99, or installed from a storage part 98, or installed from a ROM 92. When the computer program is executed by a CPU 91, the method of the embodiment of the present disclosure is executed.

[0107] It should be noted that, in the context of the present disclosure, a computer-readable medium may be a tangible medium that may contain or store a program for use by an instruction execution system, apparatus, or device or for use in conjunction with an instruction execution system, apparatus, or device.

[0108] The computer readable medium may be a computer readable storage medium, or a computer readable signal medium, or any combination of the two.

[0109] Computer-readable storage media include, but are not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or components, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, electrical connections with one or more wires, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROMs), optical storage devices, magnetic storage devices, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, device, or device. Computer instructions are stored on a computer-readable storage medium, and when the instructions are executed by a processor, the method described in any of the foregoing embodiments is implemented.

[0110] Computer readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer readable program codes. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer readable signal media may also be any computer readable medium other than a computer readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, device, 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 cables, RF (radio frequency), etc., or any suitable combination of the above.

[0111] The computer-readable medium may be included in the electronic device, or may exist independently without being installed in the electronic device.

[0112] In some embodiments, a computer program is further provided, comprising: instructions, which, when executed by a processor, cause the processor to execute the method described in any of the above embodiments. For example, the instructions may be embodied as computer program codes.

[0113] In embodiments of the present disclosure, computer program codes for performing the operations of the present disclosure may be written in one or more programming languages ​​or combinations thereof, including but not limited to object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code may be executed entirely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer, partially on a remote computer, or entirely on a remote computer or server. In situations involving a remote computer, the remote computer may 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 may be connected to an external computer (e.g., using an Internet service provider to connect via the Internet).

[0114] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0115] The functions described above may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0116] Although some specific embodiments of the present disclosure have been described in detail by way of example, it should be understood by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the present disclosure. It should be understood by those skilled in the art that the above embodiments may be modified without departing from the scope and spirit of the present disclosure. The scope of the present disclosure is defined by the appended claims.

Claims

1. A conversation interaction method, comprising: In a dialogue interface between a user and an agent, in response to an instruction of the user and based on the interaction between the user and the agent, determining a type of advancement of the dialogue; In response to the advancement type being the first type, displaying prompt information associated with the dialogue; In response to the advancement type being the second type, prompt information including a new topic is displayed.

2. The method for dialog interaction according to claim 1, wherein: The interaction includes dialogue content and interactive operations, and the determining of the advancement type of the dialogue based on the interaction between the user and the agent includes: Based on at least one of the conversation content and interactive operation between the user and the agent, determining whether the user has an intention to continue the conversation on the topic of the conversation content; In response to the user having the intention, determining the propulsion type as the first type; In response to the user not having the intention, the propulsion type is determined to be the second type.

3. The method for dialog interaction according to claim 2, wherein: The determining whether the user has an intention to continue the conversation on the topic of the conversation content includes: Performing semantic understanding on the content of the conversation between the user and the agent; Based on the semantic understanding result, it is determined whether the user has the intention to continue the conversation on the topic of the conversation content.

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

5. The dialog interaction method according to claim 3 or 4, wherein: Determining, based on the semantic understanding result, whether the user has an intention to continue the conversation on the topic of the conversation content includes: Determining, based on the semantic understanding result, whether the message sent by the user includes an adjustment instruction for the message sent by the agent; In response to the message sent by the user including an adjustment indication to the message sent by the agent, it is determined that the user has an intention to continue the conversation on the subject of the conversation content.

6. The dialog interaction method according to claim 3 or 4, wherein: The semantic understanding result includes the user's emotional inclination toward the topic of the conversation, and determining whether the user has an intention to continue the conversation on the topic of the conversation content includes: Determining the user's emotional inclination toward the conversation according to the semantic understanding result; Based on the emotional tendency, determine whether the user has an intention to continue the conversation on the topic of the conversation content.

7. The method for dialog interaction according to claim 2, wherein: The determining whether the user has an intention to continue the conversation on the topic of the conversation content includes: Determining whether the interactive operation is a positive operation or a negative operation of the message sent by the agent; In response to the operation being an affirmative operation, determining that the user has the intention; In response to the operation being a negative operation, it is determined that the user does not have the intention.

8. The method for dialog interaction according to claim 7, wherein: The affirmative operation includes at least one of like, favorite, share, select, and copy; The negative operation includes at least one of negative feedback and regeneration.

9. The dialog interaction method according to claim 2, wherein: The determining whether the user has an intention to continue the conversation on the topic of the conversation content includes: Determining the topic of each round of dialogue in the dialogue based on the semantic understanding result of the content of the dialogue; In response to a certain topic appearing continuously in the conversation for a number of turns greater than a threshold, it is determined that the user has an intention to continue the conversation on the topic of the conversation content.

10. The dialog interaction method according to claim 1, wherein: The display of the prompt information including the new topic includes: After clearing the historical conversation, the prompt information including the new topic is displayed.

11. The method for dialog interaction according to claim 1, wherein: The dialogue interface also includes prompt information associated with the message sent by the agent, and the prompt information displayed including the new topic includes: cancelling the display of prompt information associated with the message sent by the agent; The prompt information including the new topic is displayed.

12. The dialog interaction method according to claim 1, wherein: The user's instruction includes at least one of a gesture instruction and a voice instruction.

13. The dialog interaction method according to claim 12, wherein: The gesture instruction includes a slide-up gesture.

14. The dialog interaction method according to claim 1, further comprising: In response to any prompt information being triggered, displaying the triggered prompt information sent by the user; The reply to the prompt message sent by the agent is displayed.

15. An electronic device, comprising: Memory; as well as A processor coupled to the memory, the processor being configured to execute the conversation interaction method according to 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, wherein the program, when executed by a processor, implements the dialog interaction method according to any one of claims 1 to 14.

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

Images