Dialogue processing method and apparatus, and electronic device

Abstract

A dialogue processing method, comprising: displaying a first dialogue interface for performing interaction with an artificial intelligence system by a user; and in response to a first operation triggered by the user, displaying a first dialogue shorthand card in the first dialogue interface, wherein the first dialogue shorthand card comprises consensus information of a consensus that has been reached by the user and the artificial intelligence system in the first dialogue interface. In this way, during a dialogue with an artificial intelligence system, a user can quickly master key points of the dialogue by means of a dialogue shorthand card, thereby improving the user experience.

Description

Dialogue processing method, device and electronic equipment

[0001] This application claims priority to the Chinese patent application filed with the State Intellectual Property Office of China on December 4, 2023, with application number 202311647974.4 and application name “A dialogue processing method, device and electronic device”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the field of information technology (IT), and in particular to a conversation processing method, device, and electronic device. Background Art

[0003] Currently, AI systems capable of natural semantic understanding and natural conversation are available on electronic devices, such as digital assistants and large language models. Users can engage in interactive conversations with these AI systems on their devices. However, during these conversations, users often need to review most of the previous conversation to grasp the key points, resulting in a poor user experience.

[0004] Summary of the Invention

[0005] The present application provides a conversation processing method, device, electronic device, computer storage medium and computer product, which can enable users to quickly grasp the key points of the conversation and improve the user experience.

[0006] In a first aspect, the present application provides a method for handling conversations, comprising: displaying a first conversation interface for interaction between a user and an artificial intelligence system; and, in response to a first action triggered by the user, displaying a first conversation shorthand card in the first conversation interface, wherein the first conversation shorthand card includes: consensus information reached between the user and the artificial intelligence system in the first conversation interface. In this way, during a conversation with the artificial intelligence system, the user can quickly grasp the key points of the conversation using the conversation shorthand card, thereby improving the user experience.

[0007] In a possible implementation, the first conversation shorthand card also includes: conversation status. In this way, the user can intuitively understand the conversation status, thereby improving the user experience.

[0008] In one possible implementation, the first operation includes one or more of the following: a user triggering an instruction, operation, or event for creating a first conversation note card, or the user's conversational intent with the AI ​​system being a preset intent. This allows for multiple ways to trigger the generation of conversation notes, enriching the methods for generating conversation notes.

[0009] In a possible implementation, the method further includes marking the consensus information in the conversation content displayed on the first conversation interface, so as to help the user understand what information is recorded.

[0010] In one possible implementation, after displaying the first conversation shorthand card, the method further includes updating the consensus information contained in the first conversation shorthand card if the consensus information in the conversation content displayed on the first conversation interface changes. In this way, the content in the conversation shorthand card can be kept up to date.

[0011] In one possible implementation, after displaying the first conversation shorthand card, the process further includes updating the consensus information contained in the first conversation shorthand card in response to a user's editing operation on the consensus information in the first conversation shorthand card. This allows users to modify the content of the conversation shorthand card based on their needs, thereby improving the user experience.

[0012] In one possible implementation, the first conversation shorthand card also includes an automated task control. In this case, after displaying the first conversation shorthand card, the process further includes: displaying a task card in the first conversation interface in response to a triggering operation on the automated task control, the task card indicating the execution process of a task related to the consensus information; and displaying the task execution result in the first conversation shorthand card after the task indicated by the task card is completed. This achieves task automation and improves the user experience.

[0013] One possible implementation also includes: closing the first dialogue interface; in response to the user creating a new dialogue, displaying a second dialogue interface for the user to interact with the AI ​​system; and, upon the user entering at least one consensus information in the second dialogue interface, displaying a first dialogue shorthand card in the second dialogue interface. The first dialogue shorthand card is selected from the stored dialogue shorthand cards based on the consensus information in the second dialogue interface. This allows the user to continue an unfinished conversation without having to repeat multiple rounds of interaction, improving the user experience.

[0014] In a possible implementation, the first conversation shorthand card displayed in the second conversation interface is displayed when the user agrees to continue the conversation in the first conversation interface in the second conversation interface.

[0015] In one possible implementation, when the user adds or modifies consensus information in the second conversation interface, the consensus information is also added or modified in the first conversation shorthand card. In this way, the content in the conversation shorthand card can be made consistent with the user's latest conversation, thereby improving the user experience.

[0016] In a possible implementation, the method further includes: displaying a first prompt message in the first conversation interface, wherein the first prompt message is used to prompt that the first conversation shorthand card has been created, so that the user can be informed that the conversation shorthand card has been generated.

[0017] In a second aspect, the present application provides a dialogue processing device comprising: a first display module and a second display module. The first display module is configured to display a first dialogue interface for interaction between a user and an artificial intelligence system. The second display module is configured to display a first dialogue shorthand card in the first dialogue interface in response to a first operation triggered by the user. The first dialogue shorthand card includes consensus information reached between the user and the artificial intelligence system in the first dialogue interface.

[0018] In one possible implementation, the first operation includes one or more of the following: the user triggers an instruction, operation, or event for creating a first conversation note card, or the conversation intention between the user and the artificial intelligence system is a preset intention.

[0019] In a possible implementation, the second display module is further configured to mark the consensus information in the conversation content displayed on the first conversation interface.

[0020] In a possible implementation, after displaying the first conversation shorthand card, the second display module is further configured to update the consensus information included in the first conversation shorthand card when the consensus information in the conversation content displayed on the first conversation interface changes.

[0021] In a possible implementation, after displaying the first conversation shorthand card, the second display module is further configured to: update the consensus information contained in the first conversation shorthand card in response to a user's editing operation on the consensus information in the first conversation shorthand card.

[0022] In one possible implementation, the first conversation shorthand card also includes an automated task control. In this case, after displaying the first conversation shorthand card, the second display module is further configured to: display a task card in the first conversation interface in response to a triggering operation on the automated task control, the task card indicating the execution process of a task related to the consensus information; and display the task execution result in the first conversation shorthand card after the task indicated by the task card is completed.

[0023] In one possible implementation, the second display module is also used to close the first dialogue interface; in response to the user's operation of creating a new dialogue, display a second dialogue interface for the user to interact with the artificial intelligence system; when the user enters at least one consensus information in the second dialogue interface, display a first dialogue shorthand card in the second dialogue interface, where the first dialogue shorthand card is screened from the stored dialogue shorthand cards based on the consensus information in the second dialogue interface.

[0024] In a possible implementation, the first conversation shorthand card displayed in the second conversation interface is displayed when the user agrees to continue the conversation in the first conversation interface in the second conversation interface.

[0025] In a possible implementation, the second display module is further configured to: when the user adds / modifies the consensus information in the second dialogue interface, add / modify the consensus information in the first dialogue shorthand card.

[0026] In a third aspect, the present application provides an electronic device comprising: one or more processors; and a memory. The memory stores one or more computer programs, each of which includes instructions that, when executed by the one or more processors, cause the electronic device to perform the method described in the first aspect or any possible implementation of the first aspect.

[0027] In a fourth aspect, the present application provides a computer-readable storage medium comprising computer program instructions. When the computer program instructions are executed by a computing device cluster, the computing device cluster performs the method described in the first aspect or any possible implementation of the first aspect. The computing device cluster may include one or more computing devices.

[0028] In a fifth aspect, the present application provides a computer program product comprising instructions, which, when executed by a computing device cluster, causes the computing device cluster to perform the method described in the first aspect or any possible implementation of the first aspect. The computing device cluster may include one or more computing devices.

[0029] It can be understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] FIG1 is a schematic diagram of an application scenario provided by an embodiment of the present application;

[0031] FIG2 is a flow chart of a method for processing a conversation provided in an embodiment of the present application;

[0032] FIG3 is a schematic diagram of interface changes on an electronic device provided by an embodiment of the present application;

[0033] FIG4 is a schematic diagram of interface changes on an electronic device provided in an embodiment of the present application;

[0034] FIG5 is a schematic diagram of interface changes on an electronic device provided in an embodiment of the present application;

[0035] FIG6 is a schematic diagram of interface changes on an electronic device provided in an embodiment of the present application;

[0036] FIG7 is a schematic diagram of interface changes on an electronic device provided in an embodiment of the present application;

[0037] FIG8 is a schematic diagram of interface changes on an electronic device provided in an embodiment of the present application;

[0038] FIG9 is a schematic diagram of interface changes on an electronic device provided in an embodiment of the present application;

[0039] FIG10 is a schematic diagram of interface changes on an electronic device provided in an embodiment of the present application;

[0040] FIG11 is a schematic diagram of interface changes on an electronic device provided in an embodiment of the present application;

[0041] FIG12 is a structural diagram of a conversation processing device provided in an embodiment of the present application;

[0042] FIG13 is a schematic structural diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0043] The term "and / or" as used herein describes an association between related objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, or B exists alone. The symbol " / " as used herein indicates that the related objects are in an "or" relationship, for example, A / B means either A or B.

[0044] The terms "first" and "second" in this specification and claims are used to distinguish different objects rather than to describe a specific order of objects. For example, "first response message" and "second response message" are used to distinguish different response messages rather than to describe a specific order of response messages.

[0045] In the embodiments of this application, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of this application should not be interpreted as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0046] In the description of the embodiments of the present application, unless otherwise specified, "multiple" means two or more, for example, multiple processing units means two or more processing units, etc.; multiple elements means two or more elements, etc.

[0047] In an embodiment of the present application, when a user is having a conversation on an electronic device with an artificial intelligence system that has natural semantic understanding and natural conversation capabilities, the artificial intelligence system can obtain conversation information after detecting the preset input entered by the user, and extract the consensus information reached between the user and the artificial intelligence system from the conversation information, and fill the consensus information into a conversation shorthand card, and display the conversation shorthand card on the conversation interface. In this way, the user can quickly grasp the key points of the conversation through the conversation shorthand card, thereby improving the user experience. For example, the artificial intelligence system can be deployed on the electronic device in the form of a client, but is not limited to the client. The client can be a desktop application, a mobile application, a web application, or a web-based application.

[0048] For example, Figure 1 shows a schematic diagram of an application scenario provided by an embodiment of the present application. As shown in Figure 1, in this application scenario, in Figure 1 (A), user A is using electronic device 100, and, as shown in Figure 1 (B), the user is interacting with an artificial intelligence system on electronic device 100.

[0049] For example, Figure 2 shows a flow chart of a conversation processing method provided in an embodiment of the present application. This method can be applied to, but is not limited to, a client. The client can be associated with, but is not limited to, an artificial intelligence system capable of natural semantic understanding and natural conversation. As shown in Figure 2, the conversation processing method can include the following steps:

[0050] S201: Display a first dialogue interface for interaction between a user and an artificial intelligence system.

[0051] In this embodiment, the user can access the AI ​​system's dialogue interface by clicking on an application icon or webpage on the client. After the user chooses to interact with the AI ​​system, the client can display a first dialogue interface for user interaction with the AI ​​system. The user can then engage in a dialogue with the AI ​​system in this first dialogue interface. Alternatively, the user can activate the client through voice interaction to interact with the AI ​​system.

[0052] S202: In response to a first operation triggered by the user, display a first conversation shorthand card in the first conversation interface, where the first conversation shorthand card includes: consensus information reached between the user and the artificial intelligence system in the first conversation interface.

[0053] In this embodiment, after the first dialogue interface is displayed, the user can interact with the artificial intelligence system, such as through voice or text. Furthermore, the user can trigger certain commands, operations, or events, or certain dialogue intentions, on the first dialogue interface. Subsequently, the client can display a first dialogue shorthand card on the first dialogue interface in response to the user-triggered operation. This first dialogue shorthand card includes the consensus information reached between the user and the artificial intelligence system in the first dialogue interface. For example, the first operation triggered by the user can be understood as an operation for creating a dialogue shorthand card.

[0054] In this way, when users are talking with the artificial intelligence system, they can quickly grasp the key points of the conversation through the conversation shorthand cards, thereby improving the user experience.

[0055] In some embodiments, the first operation in S202 may include one or more of the following:

[0056] 1) The user enters the preset creation statement in the dialogue interface

[0057] When a user wants to proactively create a conversation note card, they can trigger the creation of the card using a preset creation statement. The creation statement can be a system default or user-defined statement. For example, a creation statement might be "Hey, listen," or "Please take note of this for me." For example, as shown in FIG3(A), a conversation interface 31 is displayed on electronic device 100. In this interface, the user can enter "Please take note of this for me" to trigger the creation of a conversation note card. Subsequently, as shown in FIG3(B), the conversation note card 31 is displayed in the conversation interface 31. In the conversation interface 31, the consensus information reached between the user and the artificial intelligence system is "record content." Therefore, this consensus information can be displayed in the conversation note card 32. In addition, to facilitate notification to the user that a conversation note card has been created, a prompt message (e.g., the content shown in area 33 in FIG3(B)) may be displayed in the conversation interface 31 to indicate that the conversation note card has been created.

[0058] 2) The conversation intention between the user and the AI ​​system is the preset intention

[0059] Each time the AI ​​system receives user input, it analyzes the received conversational intent. If the conversational intent is a preset type, it triggers the creation of a conversational shorthand card. Preset conversational intents can include, but are not limited to, multi-step, ongoing tasks, such as ordering a meal, scheduling a trip, holding a meeting, or writing an email. For example, as shown in FIG4(A), a conversational interface 41 is displayed on electronic device 100. In this interface, a user can enter "Please help me book a Sichuan restaurant nearby." The user's input clearly indicates a need to book a restaurant. Analysis of the user's input indicates that the conversational intent is a restaurant ordering intent, triggering the creation of a conversational shorthand card. Subsequently, as shown in FIG4(B), a conversational shorthand card 42 can be displayed in conversational interface 41. In conversational interface 41, the user and the AI ​​system have reached consensus on "booking a restaurant," "Sichuan cuisine," and "near home." Therefore, this consensus information can be displayed in conversational shorthand card 42.

[0060] 3) After the client displays the card to create the invitation, the user triggers the confirmation operation

[0061] If no user input is received within a preset time during a conversation, the AI ​​system can display a card creation invitation on the conversation interface. If the user confirms acceptance through an operation, a conversation shorthand card is created. For example, the card creation invitation can be displayed on the conversation interface as a conversational query, and the user's confirmation operation can be a conversational input, which can be text input via keyboard, voice input, or voice-to-text input, etc. Of course, the card creation invitation can also be displayed as a pop-up window, and the user's confirmation operation can be interaction with controls within the pop-up window, voice input, etc. For example, as shown in FIG5(A), a user is having a conversation consultation with the AI ​​system, and a conversation interface 51 is displayed on electronic device 100. If the AI ​​system does not receive any user input for a period of time, it can initiate a conversation shorthand card creation invitation to the user, such as "Would you like me to make a reservation for a Sichuan restaurant?" as shown in area 52. After the AI ​​system receives the user's conversational input "OK", the creation of the conversation shorthand card is triggered. Subsequently, as shown in FIG5(B), a conversation shorthand card 53 can be displayed on conversation interface 51. In the dialogue interface 51 , the consensus information reached between the user and the artificial intelligence system is “book a restaurant”, “Sichuan cuisine” and “near home”, so these consensus information can be displayed in the dialogue shorthand card 53 .

[0062] Alternatively, the AI ​​system can first analyze the conversation content and identify at least one user intent based on it. It then sends a card creation invitation based on the user intent, and only sends a card creation invitation when a pre-set type of user intent exists. The main difference between this approach and the second is that the identification of user intent here is more speculative—that is, the user doesn't express that intent, but it's inferred based on the conversation content. In the second approach, the user explicitly expresses their intent.

[0063] 4) The user selects the control for creating a conversation note card in the menu in the conversation interface

[0064] A hidden menu can be provided in the conversation interface. After the user calls out the hidden menu, they can select a control within the menu for creating a conversation note card. Of course, the hidden menu can also be replaced with a non-hidden menu. For example, as shown in FIG6 (A), a conversation interface 61 is displayed on the electronic device 100. In the conversation interface 61, the user can call out a menu 62 and select a control 63 for creating a conversation note card. Afterwards, as shown in FIG6 (B), a conversation note card 64 can be displayed in the conversation interface 61.

[0065] 5) User triggers the action for creating a conversation note card

[0066] The operation for creating a conversation note card can be a preset operation. For example, on a mobile phone, this operation can be a swipe up gesture from the bottom of the conversation interface; on a computer, this operation can be clicking the back button, closing the page, etc. In addition, this operation can also reuse other operations, such as reusing the gesture for exiting the conversation interface. For example, as shown in Figure 7 (A), a conversation interface 71 is displayed on the electronic device 100. In conversation interface 71, after the user performs a swipe up gesture from the bottom of the screen, the creation of a conversation note card is triggered. Thereafter, as shown in Figure 7 (B), a conversation note card 72 can be displayed in conversation interface 71. In addition, if the operation for creating a conversation note card triggers the exit of the conversation interface, the exit of the conversation interface can be interrupted first, and then exit after the creation of the conversation note card is completed; or the exit operation of the conversation interface can be directly terminated, and only the creation of the conversation note card is executed. After the user swipes up again to exit, the conversation interface is exited again. For example, the user's operation on the electronic device can be transmitted to the artificial intelligence system through the electronic device.

[0067] 6) User triggers a preset event

[0068] A preset event may be an event of a preset type. For example, this event may be exiting the dialogue interface; or the artificial intelligence system being switched to the background, and so on. For example, as shown in (A) of FIG8 , a dialogue interface 81 is displayed on the electronic device 100. In the dialogue interface 81, the user slides his finger on the navigation bar at the bottom of the screen. This operation triggers the switching of applications, switches the previous / next application to the front end, and the artificial intelligence system is switched to the background, triggering the dialogue interface closing event. When the dialogue interface closing event is detected, the dialogue interface closing operation is first interrupted to create a dialogue shorthand card. Afterwards, as shown in (B) of FIG8 , a dialogue shorthand card 82 may be displayed in the dialogue interface 81. Finally, the dialogue interface closing operation may be executed and the next application may be switched to. Exemplarily, the event triggered by the user on the electronic device may be transmitted to the artificial intelligence system via the electronic device.

[0069] In some embodiments, in S202, after the user triggers the first operation, the artificial intelligence system may first obtain the conversation content between the user and the artificial intelligence system in the first dialogue interface. It then identifies the acquired conversation content and extracts the consensus information reached between the two parties. Finally, the extracted consensus information is populated into a data template to generate a conversation shorthand card. Finally, the client can display the conversation shorthand card in the dialogue interface. In this embodiment, the consensus information can be derived from the user's response, that is, identified from the user's response, or it can be information repeated to the user in a preset sentence structure by the artificial intelligence system after the user's response. For example, the sentence structure "XXXX, understand" in Figures 7 and 8 is used for repeated description, and the "xxxx" here is the consensus information.

[0070] In addition, in a dialogue interface between a user and an artificial intelligence system, the user can initiate at least one topic. For example, the user can first initiate a topic about ordering food to the artificial intelligence system, then initiate a topic about booking a room to the manual system, and so on. In this scenario, after obtaining the conversation content in the dialogue interface, you can first confirm the topic of the current conversation, and then extract consensus information based on the relevant conversation content of each topic under the topic. In this embodiment, the data in the dialogue context can be stored through a preset data structure, such as stored locally or in the cloud. The data structure can be as follows:

[0071] Explanation of the variables in this data structure:

[0072] Context: A contextual data structure that stores contextual information contained in a conversation.

[0073] Conversational_Name: used to display the name of the saved conversation;

[0074] Conversational_ID: The unique ID of the conversation;

[0075] Conversational_LastUpdateTime: used to display the time of the last exchange of the saved conversation;

[0076] Conversational_CreateTime: used to record the creation time of the conversation;

[0077] Conversational_Intent: identifies the main intent type of the conversation;

[0078] Conversational_Goal: marks the goal to be achieved by the conversation;

[0079] Conversational_Consensus: records the conversation status of the current conversation, including under discussion, completed, and abandoned.

[0080] Topic: A topic data structure used to store contextual information within a topic in a conversation. Generally, a conversation between a user and an AI system (usually a question-and-answer session) corresponds to one topic.

[0081] Topic_Name: used to display the saved topic name;

[0082] Topic_LastUpdateTime: used to display the time when the topic was created;

[0083] Topic_CreateTime: The time when the user records the creation of the topic;

[0084] Topic_Intent: marks the intention of the topic;

[0085] Topic_Entity: records the entity parameter list corresponding to the topic intent; for example, when Topic_Name is the number of people, Topic_Entity can be 4 people.

[0086] In this embodiment, the artificial intelligence system can identify the topic name and intent in each round of conversation. Therefore, it can identify the conversation subject of the current topic based on at least one of the topic name and intent. Thus, after determining the conversation subject of the current topic based on the current time, the artificial intelligence system can determine the relevance of conversation subjects across different topics (Topics), thereby identifying a group of related topics that discuss related matters related to the same topic. For example, Figures 7 and 8 contain multiple topics related to ordering food, indicating that the current conversation subject is ordering food. By identifying consensus information from the conversations corresponding to the current conversation subject, a conversation shorthand card can be generated. Furthermore, a key-value pair structure can be used to store consensus information in each topic data structure. In this key-value pair structure, the key parameter is "Topic_Name" and the value variable is "Topic_Entity." When the key parameter in a topic remains the same but the value variable changes, the latest value variable can replace the previous value variable. For example, in the example of ordering a meal, if the consensus information is "the number of people dining is 4", then the key parameter of the consensus information is "dining voice", and the value variable is "4 people" or "number of people "4 people"; at this time, when the user intends to modify, the sentence provided is "help me change the number of people to 6 people", then the value variable of the consensus information is "6 people" or "number of people: 6 people", and the key parameter remains unchanged. Furthermore, every time a new consensus information is obtained, a key-value pair judgment can be performed on the consensus information to determine whether there is consensus information with the same key parameter. If there is consensus information with the same key parameter, the new value is used to overwrite the value in the original key-value pair, so that the content in the conversation shorthand card can be kept up to date. For example: as shown in (C) of Figure 8, the user's latest conversation input is "Change to a family dinner with elderly people and children", then the new value provided from this round of conversation input is The consensus information obtained is "family dinner, with elderly people and children", and accordingly, the nature of the dinner is modified to "family dinner, with elderly people and children". In addition, in addition to updating the content in the conversation shorthand card, the user can also directly edit the content in the conversation shorthand card. For example, the user can trigger the editing mode of the conversation shorthand card by triggering a preset operation (such as long pressing, single clicking, double clicking the conversation shorthand card, etc.); then, the user can edit in the conversation shorthand card to modify the content of the conversation shorthand card. Furthermore, in order to make it easier for the user to know the content he edited, after the user modifies the conversation shorthand, a modification viewing entrance can be provided in the conversation interface to view the modification record of the conversation shorthand card; through this entrance, the conversation shorthand card before the modification can be viewed, or the modification comparison of the original conversation shorthand card can be viewed.

[0087] In this embodiment, consensus information is primarily identified based on each topic, specifically the conversation text for each topic. For example, it can be directly extracted from repeated confirmation statements. Alternatively, consensus information can be extracted from the content of the conversation text. For example, a user may simply end a conversation with "OK, I understand" before asking a question. In this case, consensus information cannot be derived from the closing sentence. Instead, consensus information can be derived by analyzing the content relevance between the question and the user's answer. Keywords in the user's answer are used as consensus information. For example, if the question is "how many people are dining at the table?" and the answer keyword is "4 people," then 4 people constitutes consensus information. Alternatively, consensus information is derived from the question and answer, where the question keyword is "number of people dining at the table" and the answer keyword is "4 people." If there is a content relevance between the number of people dining at the table and the number of people dining at the table, then "number of people dining at the table" or "number of people: 4 people" is used as consensus information. The content relevance between keywords is determined by the artificial intelligence system.

[0088] Furthermore, the end of a conversation round is determined by the AI ​​system. For example, in the conversations shown in Figures 7 and 8, in addition to the question and answer, the AI ​​system also repeatedly confirms the key points of the user's answer before asking a new question. Therefore, a conversation round ends when the question begins and the AI ​​system repeatedly confirms the key points of the answer. In other words, a conversation round includes a question and an answer, or a question, an answer, and repeated confirmation statements.

[0089] In some cases, after the artificial intelligence system obtains the consensus information, it can also combine the scene information obtained by the electronic device to pre-process the consensus information so that the consensus information is expressed more clearly. Scene information includes: current location information or current time information, etc. For example, the user's dialogue input is "Please help me find a Sichuan restaurant at 7 o'clock tomorrow night", and the consensus information includes "7 o'clock tomorrow night" and "Sichuan cuisine". Among them, 7 o'clock tomorrow night is inferred based on the current time information. If 7 o'clock tomorrow night is directly recorded on the dialogue shorthand card, when the user views the dialogue shorthand card later, the time information of 7 o'clock tomorrow night cannot be accurately expressed. Therefore, "7 o'clock tomorrow night" is edited again in combination with the current time information (November 17), and the dining time information of "November 18 19:00" is obtained as the consensus information.

[0090] If no consensus information is identified from the current conversation content / the conversation content of the current topic, the consensus information is empty, that is, no consensus information is filled in the conversation shorthand card, and correspondingly, the created conversation shorthand card is a blank card.

[0091] In some embodiments, after the conversation shorthand card is filled with consensus information, the client can display the conversation shorthand card on the conversation interface. The conversation shorthand card can be displayed at the top of the conversation interface or elsewhere in the conversation interface. Of course, the conversation shorthand card can also be displayed above the conversation content in a floating manner, so that it does not occupy the display of the conversation content but rather obscures part of the conversation content. In addition, the conversation shorthand card can also serve as an additional interactive interface that can be called up and displayed on the conversation interface when the user calls it up or when there is information update.

[0092] After the consensus information is added to the conversation shorthand card, decorative marks can be added to the text corresponding to the consensus information in the conversation interface, and these marks can be displayed through the client. This helps users understand what information is recorded. Among them, decorative marks may include: underline, shading or star marks, etc. In addition, the text corresponding to the consensus information can also be changed, such as iterating, changing the font color, changing the font size, etc. For example, as shown in (B) or (C) of Figure 8, the consensus information can be highlighted by bolding, italicizing and underlining to remind users that these contents are associated with the conversation shorthand card.

[0093] In addition, when new consensus information overwrites the original consensus information, the decorative logo / text effects corresponding to the original consensus information in the dialogue interface can be canceled accordingly, and the new consensus information can be marked. For example, as shown in Figure 8 (C), the mark for "Family dinner with elderly people" can be canceled and "Family dinner with elderly people and children" can be marked.

[0094] In some embodiments, in addition to displaying the consensus information reached between the user and the AI ​​system, conversational shorthand cards can also support the creation and execution of automated tasks based on these cards. Taking the restaurant booking example depicted in Figure 8 , the AI ​​system can create an automated task for automatically booking a restaurant based on the information recorded in the conversational shorthand card and the conversational intent. The AI ​​system then calls a local application (applications, applets, service cards, HTML cards, and other programs that appear as cards / windows at runtime are all included within the concept of application) to create the restaurant booking task. For example, in addition to displaying the consensus information, the conversational shorthand card can also display an automated task control. This automated task control can be used to execute the automated task on the electronic device. When the user clicks the automated task control, the AI ​​system can create an automated task based on the consensus information. The client can then display a task card on the conversation interface. This task card can indicate the execution process of the automated task. After further user interaction, the automated task is completed; at this point, the task execution results can be displayed on the conversational shorthand card. For example, referring to Figure 9 , as shown in (A) of Figure 9 , a conversational interface 91 is displayed on electronic device 100. In conversation interface 91, a user swipes their finger across the navigation bar at the bottom of the screen. This action triggers an application switch, switching the previous / next application to the foreground and switching the artificial intelligence system to the background, triggering a conversation interface close event. Upon detecting the conversation interface close event, the conversation interface close operation is interrupted and a conversation note card is created. Subsequently, as shown in FIG9(B), conversation note card 92 is displayed in conversation interface 91. Simultaneously, an automated task control 93 for "Restaurant Booking" is displayed in conversation note card 92. The user can then click on automated task control 93, which will cause the electronic device 100 to display the interface shown in FIG9(C), which displays task card 95. In FIG9(C), the user can click on "Restaurant xx" to complete the reservation. The electronic device 100 then displays the interface shown in FIG9(D). A status control 94 indicating the task status can also be displayed on conversation note card 92. Status control 94 allows the user to intuitively observe the completion status of the automated task. In addition, the status control 94 can also display the status of the current conversation. For example, the current conversation status is usually associated with the query statement of the artificial intelligence system, which is the intention of the current query statement. For example, if the query statement is "How many people are there?", the conversation status can be represented by "Discussing (To be determined the number of people for the dinner party)". Discussing means that the artificial intelligence system is discussing with the user, and To be determined the number of people for the dinner party indicates the intention of the current discussion.

[0095] In addition, the AI ​​system can automatically determine whether to support the creation of automated tasks based on the consensus information already in the conversation shorthand card. When the existing consensus information is insufficient to support the creation of an automated task (for example, the number of people at the dinner party and the dishes are not determined), the automated task control can be set to be disabled. Only when the existing consensus information can support the creation of an automated task will the automated task control be set to be enabled.

[0096] In some embodiments, after a conversation note card is created, it can be saved locally or in the cloud. Since the conversation note card stores text information in a predetermined data structure rather than storing the entire conversation content, it does not require token resources.

[0097] Furthermore, when a user triggers the creation of a conversation card, the AI ​​system can automatically match existing conversation cards to see if there are any with the same or similar intent. If a match is found, the existing conversation card is directly called and displayed on the current conversation interface via the client. For example, referring to Figure 8 , in Figure 8 (C), the user did not proceed to the next step but ended the conversation. Then, as shown in Figure 10 (A), when the user attempts to reserve a restaurant / hotel again, after the user triggers the generation of a "conversation card," the AI ​​system can automatically match the conversation card created in Figure 8 . The user is then asked whether they wish to continue the previous conversation, displaying the interface shown in Figure 10 (B). If the user agrees to continue the previous conversation, the conversation card created in Figure 8 can be displayed on the conversation interface 101 , displaying the interface shown in Figure 10 (C). In this way, the user only needs to make simple modifications to the conversation card to complete the restaurant reservation through the automated task, without having to go through multiple rounds of conversational interaction and repeatedly ask the user. For example, after creating a new dialogue interface, the user can choose to close the original dialogue interface.

[0098] Furthermore, when matching conversational shorthand cards, the AI ​​system can incorporate contextual information captured by electronic devices to improve matching accuracy. For example, it can combine current location information to match previously created conversational shorthand cards for restaurant reservations near the current location. Furthermore, it can also combine the status information of historical conversational shorthand cards to match cards, prioritizing those with a "discussing" status. This avoids having to start from scratch to inquire about requirements and avoids the issue of jumping straight into the modification phase, which can lead to a poor conversational experience.

[0099] In addition, users can search for conversational shorthand cards through conversational input. Users can include at least one consensus question attribute in their conversational input. When searching for conversational shorthand cards, the AI ​​system can then use the question attribute to match conversational shorthand cards with the same or similar attributes. For example, if a user's conversational input is "Please help me book a Sichuan restaurant nearby," conversational shorthand cards with previously reserved restaurants can be matched. Furthermore, the system can use the user's current location to search for conversational shorthand cards with the same location (or a historical location closest to the current location). Furthermore, it can also search for conversational shorthand cards with Sichuan cuisine as the dish being reserved.

[0100] Users can also add or modify new consensus information during conversation input. When displaying conversation shorthand cards, the AI ​​system can modify historical conversation shorthand cards based on the consensus information obtained from parsing the conversation input before displaying them. For example, as shown in Figure 11, the AI ​​system matches existing conversation shorthand cards based on the user's conversation input. The user's conversation input contains new consensus information, such as "dinner time is tomorrow night at 7 pm." Therefore, when presenting the conversation shorthand card, the AI ​​system does not directly display the card. Instead, it modifies the dinner time and displays it in the conversation interface. If the user's conversation input is "Please help me find a restaurant near my company that I haven't booked in July this year," then the user has not expressed any new consensus information. Therefore, the AI ​​system directly calls and displays the matched historical conversation shorthand card.

[0101] It should be understood that the order of execution of the steps in the above embodiments does not necessarily imply a specific order of execution. The order of execution of each process should be determined by its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of this application. In addition, the various embodiments described above can be combined according to actual circumstances, and the combined solutions are still within the scope of protection of this application.

[0102] Based on the method in the above embodiment, an embodiment of the present application also provides a dialogue processing device.

[0103] For example, FIG12 shows a schematic diagram of the structure of a dialogue processing device provided in an embodiment of the present application. As shown in FIG12 , the dialogue processing device 1200 includes a first display module 1201 and a second display module 1202. The first display module 1201 is configured to display a first dialogue interface for interaction between a user and an artificial intelligence system. The second display module 1202 is configured to display a first dialogue shorthand card in the first dialogue interface in response to a first operation triggered by the user. The first dialogue shorthand card includes consensus information reached between the user and the artificial intelligence system in the first dialogue interface.

[0104] In some embodiments, the first operation includes one or more of the following: the user triggers an instruction, operation, or event for creating a first conversation note card, or the conversation intention between the user and the artificial intelligence system is a preset intention.

[0105] In some embodiments, the second display module 1202 is further configured to mark consensus information in the conversation content displayed on the first conversation interface.

[0106] In some embodiments, after displaying the first conversation shorthand card, the second display module 1202 is further used to: update the consensus information contained in the first conversation shorthand card when the consensus information in the conversation content displayed on the first conversation interface changes.

[0107] In some embodiments, after displaying the first conversation shorthand card, the second display module 1202 is further configured to: update the consensus information contained in the first conversation shorthand card in response to a user's editing operation on the consensus information in the first conversation shorthand card.

[0108] In some embodiments, the first conversation shorthand card further includes an automated task control. In this case, after displaying the first conversation shorthand card, the second display module 1202 is further configured to: display a task card in the first conversation interface in response to a triggering operation on the automated task control, the task card indicating the execution process of a task related to the consensus information; and display the task execution result in the first conversation shorthand card after the task indicated by the task card is completed.

[0109] In some embodiments, the second display module 1202 is further used to: close the first dialogue interface; in response to the user's operation of creating a new dialogue, display a second dialogue interface for the user to interact with the artificial intelligence system; when the user enters at least one consensus information in the second dialogue interface, display a first dialogue shorthand card in the second dialogue interface, where the first dialogue shorthand card is based on the consensus information in the second dialogue interface and is screened from the stored dialogue shorthand cards.

[0110] In some embodiments, the first conversation note card displayed in the second conversation interface is displayed when the user agrees to continue the conversation in the first conversation interface in the second conversation interface.

[0111] In some embodiments, the second display module 1202 is further configured to add / modify consensus information in the first dialogue shorthand card when the user adds / modifies consensus information in the second dialogue interface.

[0112] It should be understood that the above-mentioned device is used to execute the method in the above-mentioned embodiment. The implementation principle and technical effect of the corresponding program module in the device are similar to those described in the above-mentioned method. The working process of the device can refer to the corresponding process in the above-mentioned method and will not be repeated here.

[0113] It will be understood that the electronic devices in the embodiments of the present application may be mobile phones, tablet computers, desktop computers, laptop computers, handheld computers, notebook computers, ultra-mobile personal computers (UMPCs), netbooks, as well as cellular phones, personal digital assistants (PDAs), augmented reality (AR) devices, virtual reality (VR) devices, artificial intelligence (AI) devices, wearable devices, vehicle-mounted devices, smart home devices and / or smart city devices, and the embodiments of the present application do not impose any special restrictions on the specific type of the electronic devices.

[0114] For example, Figure 13 shows a schematic diagram of the structure of an electronic device provided by an embodiment of the present application. As shown in Figure 13, the electronic device 13300 may include: a processor 1310, a memory 1320, a display 1330, a sensor module 1340 and a battery 1350.

[0115] Processor 1310 is the computing and control core of electronic device 1300. Processor 1310 may include one or more processing units. For example, processor 1310 may include one or more of an application processor (AP), a modem, a graphics processing unit (GPU), an image signal processor (ISP), a controller, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural network processing unit (NPU). The different processing units may be independent devices or integrated into one or more processors. In this embodiment, the NPU may be a neural network (NN) computing processor that rapidly processes input information by drawing on the structure of biological neural networks, such as the transmission patterns between neurons in the human brain, and can also continuously self-learn. The NPU can implement intelligent cognitive applications such as image recognition, face recognition, speech recognition, text comprehension, and text recognition in electronic device 1300. For example, processor 1300 may be used, but is not limited to, to execute the methods described in the aforementioned embodiments.

[0116] The memory 1320 may store a program that can be executed by the processor 1310, causing the processor 1310 to execute the method performed by the electronic device 1300 provided in the embodiments of the present application. The memory 1320 may also store data. The processor 1310 may read the data stored in the memory 1320. The memory 1320 and the processor 1310 may be provided separately. Alternatively, the memory 1320 may be integrated into the processor 1310.

[0117] Display screen 1330 can be used to display images, videos, and the like. Display screen 1330 includes a display panel. The display panel can be a liquid crystal display (LCD), an organic light-emitting diode (OLED), an active-matrix organic light-emitting diode (AMOLED), a flexible light-emitting diode (FLED), a MiniLED, a MicroLED, a Micro-oLed, or a quantum dot light-emitting diode (QLED).

[0118] The electronic device 1300 may further include a sensor module 1340. The sensor module 1340 may include a touch sensor. The touch sensor may be used to detect touch operations acting on or near the electronic device 1300. Exemplarily, the touch sensor may be implemented in a variety of ways, such as resistive, capacitive, infrared, and surface acoustic wave. The touch sensor may be disposed on the display screen 1330, and the touch sensor and the display screen 1330 may form a touch screen, also known as a "touch screen." Of course, the touch sensor may also be disposed on the surface of the electronic device 1300, at a different location from the display screen 1330. In some embodiments, the sensor module 1340 may also include a pressure sensor, a gyroscope sensor, an air pressure sensor, a magnetic sensor, an acceleration sensor, a distance sensor, a proximity light sensor, a fingerprint sensor, a temperature sensor, an ambient light sensor, or a bone conduction sensor.

[0119] The electronic device 1300 may also be provided with a battery 1350 , which can supply power to the electronic device 1300 .

[0120] It should be understood that the structure illustrated in FIG. 13 of this embodiment does not constitute a specific limitation on the electronic device 1300. In other embodiments, the electronic device 1300 may include more or fewer components than shown, or may combine or separate certain components, or may have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0121] Based on the method in the above embodiment, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program. When the computer program is run on a computing device cluster including at least one computing device, the computing device cluster executes the method described in the above embodiment. Exemplarily, the computer-readable storage medium can be any available medium that can be stored by a computing device or a data storage device such as a data center containing one or more available media. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium (for example, a solid-state drive), etc.

[0122] Based on the method in the above embodiment, an embodiment of the present application provides a computer program product containing instructions. When the computer program product is run on a computing device cluster including at least one computing device, the computing device cluster executes the method in the above embodiment.

[0123] It is understood that the processor in the embodiments of the present application may be a central processing unit (CPU), or may be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. The general-purpose processor may be a microprocessor or any conventional processor.

[0124] The method steps in the embodiments of the present application can be implemented by hardware or by a processor executing software instructions. The software instructions can be composed of corresponding software modules, which can be stored in random access memory (RAM), flash memory, read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), registers, hard disks, mobile hard disks, CD-ROMs or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an ASIC.

[0125] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted via the computer-readable storage medium. The computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid state drive (SSD)).

[0126] It will be understood that the various numerical numbers involved in the embodiments of the present application are merely distinctions for the convenience of description and are not intended to limit the scope of the embodiments of the present application.

[0127] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the protection scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for processing a conversation, characterized in that: include: Displaying a first dialogue interface for a user to interact with the artificial intelligence system; In response to a first operation triggered by the user, a first dialogue shorthand card is displayed in the first dialogue interface, wherein the first dialogue shorthand card includes: consensus information reached by the user and the artificial intelligence system in the first dialogue interface.

2. The method according to claim 1, characterized in that The first conversation shorthand card also includes: conversation status.

3. The method according to claim 1 or 2, characterized in that: The first operation includes one or more of the following: The user triggers an instruction, operation or event for creating the first conversation shorthand card, or the conversation intention between the user and the artificial intelligence system is a preset intention.

4. The method according to any one of claims 1 to 3, characterized in that: Also includes: The consensus information is marked in the conversation content displayed on the first conversation interface.

5. The method according to any one of claims 1 to 4, characterized in that: After displaying the first conversation shorthand card, the method further includes: When the consensus information in the conversation content displayed on the first conversation interface changes, the consensus information included in the first conversation shorthand card is updated.

6. The method according to any one of claims 1 to 5, characterized in that: After displaying the first conversation shorthand card, the method further includes: In response to the user's editing operation on the consensus information in the first conversation shorthand card, the consensus information included in the first conversation shorthand card is updated.

7. The method according to any one of claims 1 to 6, characterized in that: The first conversation shorthand card also includes: an automated task control; After displaying the first conversation shorthand card, the method further includes: In response to a trigger operation on the automated task control, a task card is displayed in the first dialogue interface, wherein the task card is used to indicate an execution process of a task related to the consensus information. After the task indicated by the task card is completed, the task execution result is displayed in the first conversation shorthand card.

8. The method according to any one of claims 1 to 7, characterized in that: Also includes: Close the first dialogue interface; In response to the user's operation of creating a new dialogue, displaying a second dialogue interface for the user to interact with the artificial intelligence system; When the user inputs at least one of the consensus information in the second dialogue interface, the first dialogue shorthand card is displayed in the second dialogue interface, and the first dialogue shorthand card is screened from the stored dialogue shorthand cards based on the consensus information in the second dialogue interface.

9. The method according to claim 8, characterized in that The first conversation shorthand card displayed in the second conversation interface is displayed when the user agrees to continue the conversation in the first conversation interface in the second conversation interface.

10. The method according to claim 8, characterized in that Also includes: When the user adds / modifies the consensus information in the second dialogue interface, the consensus information is added / modified in the first dialogue shorthand card.

11. The method according to any one of claims 1 to 10, characterized in that: Also includes: A first prompt message is displayed in the first dialogue interface, where the first prompt message is used to prompt that the first dialogue shorthand card has been created.

12. A dialogue processing device, characterized in that: include: A first display module, used to display a first dialogue interface for a user to interact with the artificial intelligence system; A second display module is used to display a first dialogue shorthand card in the first dialogue interface in response to the first operation triggered by the user, wherein the first dialogue shorthand card includes: consensus information reached by the user and the artificial intelligence system in the first dialogue interface.

13. The device according to claim 12, characterized in that The first operation includes one or more of the following: The user triggers an instruction, operation or event for creating the first conversation shorthand card, or the conversation intention between the user and the artificial intelligence system is a preset intention.

14. The device according to claim 12 or 13, characterized in that The second display module is further used for: The consensus information is marked in the conversation content displayed on the first conversation interface.

15. The device according to any one of claims 12 to 14, characterized in that: After displaying the first conversation shorthand card, the second display module is further used to: When the consensus information in the conversation content displayed on the first conversation interface changes, the consensus information included in the first conversation shorthand card is updated.

16. The device according to any one of claims 12 to 15, characterized in that: After displaying the first conversation shorthand card, the second display module is further used to: In response to the user's editing operation on the consensus information in the first conversation shorthand card, the consensus information included in the first conversation shorthand card is updated.

17. The device according to any one of claims 12 to 16, characterized in that: The first conversation shorthand card also includes: an automated task control; After displaying the first conversation shorthand card, the second display module is further used to: In response to a trigger operation on the automated task control, displaying a task card in the first dialogue interface, the task card being used to indicate an execution process of a task related to the consensus information; After the task indicated by the task card is completed, the task execution result is displayed in the first conversation shorthand card.

18. The device according to any one of claims 12 to 17, characterized in that: The second display module is further used for: Close the first dialogue interface; In response to the user's operation of creating a new dialogue, displaying a second dialogue interface for the user to interact with the artificial intelligence system; When the user inputs at least one of the consensus information in the second dialogue interface, the first dialogue shorthand card is displayed in the second dialogue interface, and the first dialogue shorthand card is screened from the stored dialogue shorthand cards based on the consensus information in the second dialogue interface.

19. The device according to claim 18, characterized in that The first conversation shorthand card displayed in the second conversation interface is displayed when the user agrees to continue the conversation in the first conversation interface in the second conversation interface.

20. The device according to claim 18, characterized in that The second display module is further used for: When the user adds / modifies the consensus information in the second dialogue interface, the consensus information is added / modified in the first dialogue shorthand card.

21. An electronic device, characterized in that: include: one or more processors; Memory; One or more computer programs are stored in the memory, and the one or more computer programs include instructions. When the instructions are executed by the one or more processors, the electronic device executes the method according to any one of claims 1 to 12.

22. A computer-readable storage medium storing a computer program, wherein when the computer program is executed on an electronic device, the electronic device executes the method according to any one of claims 1 to 12.

23. A computer program product, characterized in that When the computer program product runs on an electronic device, the electronic device executes the method according to any one of claims 1 to 12.

Images