WO2025118687A1 - Dialogue processing method and apparatus, and electronic device - Google Patents

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

A conversation processing method, device and electronic equipment

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”, all contents of which are incorporated by reference in this application.

Technical Field

The present application relates to the field of information technology (IT) technology, and in particular to a dialogue processing method, device and electronic device.

Background Art

Currently, artificial intelligence systems with natural semantic understanding and natural conversation capabilities can be used on electronic devices, such as digital assistants or large language models. Users can have interactive conversations with this type of artificial intelligence system on electronic devices. However, during the conversation, users often need to review most of the historical conversation content to grasp the key points of the conversation, which is a poor experience.

Summary of the invention

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.

In the first aspect, the present application provides a method for processing a dialogue, including: displaying a first dialogue interface for a user to interact with an artificial intelligence system; 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 includes: consensus information that the user and the artificial intelligence system have reached a consensus on in the first dialogue interface. In this way, during the dialogue process with the artificial intelligence system, the user can quickly grasp the key points of the conversation through the dialogue shorthand card, thereby improving the user experience.

In a possible implementation, the first conversation shorthand card also includes: conversation status. In this way, the user can intuitively understand the conversation status, which improves the user experience.

In a possible implementation, 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. In this way, the generation of conversation shorthand cards can be triggered in a variety of ways, enriching the generation methods of conversation shorthand cards.

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.

In a possible implementation, after displaying the first conversation shorthand card, the method further includes: updating 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. In this way, the content in the conversation shorthand card can be kept up to date.

In a possible implementation, 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, updating the consensus information contained in the first conversation shorthand card. In this way, the user can change the content in the conversation shorthand card based on his or her own needs, thereby improving the user experience.

In a possible implementation, the first conversation shorthand card also includes: an automated task control. At this time, after displaying the first conversation shorthand card, it also includes: in response to a trigger operation for the automated task control, displaying a task card in the first conversation interface, the task card is used to indicate the execution process of the 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. In this way, task automation can be achieved, and the user experience can be improved.

In a possible implementation, it also includes: closing the first dialogue interface; in response to the user's operation of creating a new dialogue, displaying the second dialogue interface for the user to interact with the artificial intelligence system; in the case where the user enters at least one consensus information in the second dialogue interface, displaying the first dialogue shorthand card in the second dialogue interface, 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. In this way, the user can continue the previously unfinished dialogue without having to repeat the inquiry through multiple rounds of interaction, thereby improving the user experience.

In a possible implementation, the first conversation shorthand card displayed in the second conversation interface is displayed after the user agrees to Displayed when continuing the conversation in the first conversation interface.

In a possible implementation, the method further includes: when the user adds/modifies consensus information in the second conversation interface, the consensus information is added/modified in the first conversation shorthand card. In this way, the content in the conversation shorthand card can be consistent with the user's latest conversation, thereby improving the user experience.

In a possible implementation, the method further includes: displaying a first prompt message in the first dialogue interface, the first prompt message being used to prompt that the first dialogue shorthand card has been created, so that the user can be informed that the dialogue shorthand card has been generated.

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 used to display a first dialogue interface for a user to interact with an artificial intelligence system. The second display module is used to display a first dialogue shorthand card in the first dialogue interface in response to a first operation triggered by the user, wherein the first dialogue shorthand card includes: consensus information that the user and the artificial intelligence system have reached consensus on in the first dialogue interface.

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.

In a possible implementation, the second display module is further used to: mark the consensus information in the conversation content displayed on the first conversation interface.

In a possible implementation, after displaying the first conversation shorthand card, the second display module is further used 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.

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

In a possible implementation, the first dialogue shorthand card also includes: an automated task control. At this time, after displaying the first dialogue shorthand card, the second display module is further used to: display a task card in the first dialogue interface in response to a trigger operation on the automated task control, the task card being used to indicate the execution process of a task related to the consensus information; after the task indicated by the task card is completed, display the task execution result in the first dialogue shorthand card.

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, the first dialogue shorthand card being screened from stored dialogue shorthand cards based on the consensus information in the second dialogue interface.

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.

In a possible implementation, the second display module is further used 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.

In a third aspect, the present application provides an electronic device, comprising: one or more processors; a memory. The memory stores one or more computer programs, and the one or more computer programs include instructions. When the instructions are executed by the one or more processors, the electronic device performs the method described in the first aspect or any possible implementation of the first aspect.

In a fourth aspect, the present application provides a computer-readable storage medium, including computer program instructions, when the computer program instructions are executed by a computing device cluster, the computing device cluster executes 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.

In a fifth aspect, the present application provides a computer program product including instructions, which, when executed by a computing device cluster, enables 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.

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

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

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

FIG3 is a schematic diagram of interface changes on an electronic device provided in an embodiment of the present application;

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

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

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

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

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

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

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

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

FIG12 is a schematic diagram of the structure of a conversation processing device provided in an embodiment of the present application;

FIG. 13 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

DETAILED DESCRIPTION

The term "and/or" in this article is a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and/or B can represent: A exists alone, A and B exist at the same time, and B exists alone. The symbol "/" in this article indicates that the associated objects are in an or relationship, for example, A/B means A or B.

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

In the embodiments of the present 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 the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

In the description of the embodiments of the present application, unless otherwise specified, "multiple" means two or more than two. For example, multiple processing units refer to two or more processing units, etc.; multiple elements refer to two or more elements, etc.

In an embodiment of the present application, during a conversation between a user and an artificial intelligence system with natural semantic understanding and natural conversation capabilities on an electronic device, the artificial intelligence system can obtain conversation information after detecting a preset input input 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. Exemplarily, the artificial intelligence system can be deployed on an electronic device in the form of a client, but is not limited to, and the client can be a desktop application, a mobile application, a Web application, or a Web-based application, etc.

Exemplarily, 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 (A) of Figure 1, user A is using an electronic device 100, and, as shown in (B) of Figure 1, the user is interacting with an artificial intelligence system on the electronic device 100.

Exemplarily, FIG2 shows a flow chart of a method for processing a conversation provided in an embodiment of the present application. The method may be, but is not limited to, applied to a client. The client may be, but is not limited to, related to an artificial intelligence system with natural semantic understanding and natural conversation capabilities. As shown in FIG2 , the method for processing a conversation may include the following steps:

S201. Display a first dialogue interface for a user to interact with an artificial intelligence system.

In this embodiment, the user can enter the dialogue interface of the artificial intelligence system by clicking on the application icon or web page of the client. After the user chooses to interact with the artificial intelligence system, the client can display the first dialogue interface for the user to interact with the artificial intelligence system. After that, the user can have a dialogue with the artificial intelligence system in the first dialogue interface. In addition, the user can also start the client through voice interaction to interact with the artificial intelligence system.

S202: In response to a first operation triggered by a user, a first dialogue shorthand card is displayed in a first dialogue interface, where the first dialogue shorthand card includes: consensus information reached by the user and the artificial intelligence system in the first dialogue interface.

In this embodiment, after the first dialogue interface is displayed, the user can interact with the artificial intelligence system, such as voice interaction, text interaction, etc. In addition, the user can trigger some instructions, operations or events, or certain dialogue intentions and other operations on the first dialogue interface. Afterwards, the client can display the first dialogue shorthand card in the first dialogue interface in response to the operation triggered by the user. The first dialogue shorthand card includes: consensus information that the user and the artificial intelligence system have reached a consensus on in the first dialogue interface. Exemplarily, the first operation triggered by the user can be understood as an operation for creating a dialogue shorthand card.

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.

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

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

When the user wants to actively create a conversation shorthand card, the creation of the conversation shorthand card can be triggered by a preset creation statement. The creation statement can be a system default setting or a user-defined one. For example, the creation statement is "Hey, listen", "Help me remember", etc. For example, as shown in FIG3 (A), a conversation interface 31 is displayed on the electronic device 100, and the user can enter "Help me remember" in the conversation interface 31 to trigger the creation of a conversation shorthand card. Afterwards, as shown in FIG3 (B), the conversation shorthand card 31 can be displayed in the conversation interface 31. In the conversation interface 31, the consensus information reached by the user and the artificial intelligence system is "record content", so these consensus information can be displayed in the conversation shorthand card 32. In addition, in order to facilitate the user to know that the conversation shorthand card has been created, a prompt information (for example, the content shown in area 33 in FIG3 (B)) can also be displayed in the conversation interface 31, and the prompt information is used to prompt that the conversation shorthand card has been created.

2) The conversation intention between the user and the AI system is the preset intention

Each time the artificial intelligence system receives the user's dialogue input, it can analyze the received dialogue intention. When the dialogue intention is a preset type of dialogue intention, the creation of a dialogue shorthand card can be triggered. The preset type of dialogue intention can be, but is not limited to, a task intention that requires multiple steps and is carried out continuously, such as ordering food, scheduling, meetings, writing emails, etc. For example, as shown in FIG4 (A), a dialogue interface 41 is displayed on the electronic device 100, and the user can enter "Please help me book a nearby Sichuan restaurant" in the dialogue interface 41. The user's dialogue input clearly indicates the need to book a restaurant. By analyzing the content input by the user, it can be known that the dialogue intention at this time is an ordering intention, and the creation of a dialogue shorthand card can be triggered. Afterwards, as shown in FIG4 (B), a dialogue shorthand card 42 can be displayed in the dialogue interface 41. In the dialogue interface 41, the consensus information reached by 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 42.

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

During the conversation, if the user input is not received within the preset time, the artificial intelligence system can display a card creation invitation on the conversation interface, and if the user confirms to accept the invitation through operation, a conversation shorthand card is created. Exemplarily, the card creation invitation can be displayed on the conversation interface in the form of a conversation inquiry, and correspondingly, the user's confirmation operation can be a conversation input, and the conversation input can be text input by keyboard or voice input or voice-to-text input, etc. Of course, the card creation invitation can also be a pop-up window program, and correspondingly, the user's confirmation operation can be an interaction with the control in the pop-up window, or voice input, etc. For example: As shown in (A) of Figure 5, the user is having a conversation consultation with the artificial intelligence system, and a conversation interface 51 is displayed on the electronic device 100. The artificial intelligence system has not received the user's conversation input for a period of time, and it can initiate a conversation shorthand card creation invitation to the user, that is, "Do you need to book a Sichuan restaurant for you?" shown in area 52. After the artificial intelligence system receives the user's conversation input "OK", the creation of the conversation shorthand card is triggered. Afterwards, as shown in (B) of Figure 5, a conversation shorthand card 53 can be displayed in the 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 .

In addition, the artificial intelligence system can also analyze the content of the conversation first and identify at least one user intent based on the content of the conversation. Then, a card creation invitation is sent based on the user intent, and a card creation invitation is only sent when there is a preset type of user intent. The main difference between this method and the second method is that the identification of user intent here is more speculative, that is, the user does not express such intent, but it is inferred that the user has such intent based on the content of the conversation; while in the second method, the user expresses a clear intent.

4) The user selects a control in the menu in the conversation interface to create a conversation note card

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

5) User-triggered action to create a conversation note card

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

6) User triggers a preset event

The 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 the application, switches the previous/next application to the front end to run, 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 performed and switched to the next application. Exemplarily, the event triggered by the user on the electronic device may be transmitted to the artificial intelligence system via the electronic device.

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. Then, the obtained dialogue content is identified and the consensus information reached between the two is extracted. Finally, the extracted consensus information is filled into the data template to generate a dialogue shorthand card. Finally, the client can display the dialogue shorthand card in the dialogue interface. In this embodiment, the consensus information may come from the user's answer, that is, it is identified from the user's answer, or it may be the information that the artificial intelligence system repeats to the user in a preset sentence pattern after the user answers. For example, the "XXXX, understand" sentence pattern in Figures 7 and 8 is information used for repeated description, and the "xxxx" here is the consensus information.

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 of ordering meals to the artificial intelligence system, and then initiate a topic of booking a room to the artificial system, and so on. In this scenario, after obtaining the conversation content in the dialogue interface, you can first confirm the topic of the conversation at the current time, 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 by a preset data structure, such as locally or in the cloud. Among them, the data structure can be as follows:

Explanation of the variables in this data structure:

Context: a context data structure that stores context information contained in a conversation;

Conversational_Name: used to display the name of the saved conversation;

Conversational_ID: The unique ID of the conversation;

Conversational_LastUpdateTime: used to display the last time of the saved conversation;

Conversational_CreateTime: used to record the creation time of the conversation;

Conversational_Intent: marks the main intent type of the conversation;

Conversational_Goal: marks the goal of the conversation;

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

Topic: a topic data structure used to store contextual information about a topic in a conversation. Generally, a conversation between a user and an AI system (usually one question and one answer) corresponds to one Topic.

Topic_Name: used to display the saved topic name;

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

Topic_CreateTime: the time when the user records the creation of the topic;

Topic_Intent: marks the intention of the topic;

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.

In this embodiment, the artificial intelligence system can identify the topic name and intention in each round of dialogue, and thus can identify the conversation topic of the current topic based on at least one of the topic name and intention. Thus, after determining the conversation topic of the current topic according to the current time, the artificial intelligence system can determine the relevance of the conversation topics of different topics (Topic), thereby determining a group of related topics, which are all related matters about the same topic. For example, Figures 7 and 8 contain multiple topics related to ordering, so that the current conversation topic is ordering, and then the consensus information is identified from the conversation corresponding to the current conversation topic, and the conversation shorthand card can be obtained. In addition, the key-value pair structure can be used to store consensus information in each topic data structure. In the key-value pair structure, the key parameter is "Topic_Name" and the value variable is "Topic_Entity". When the key parameters in the topic are the same, but the value variable changes, the latest value variable can be used to 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 is expected 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 value in the original key-value pair is overwritten with the new value, 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 "changed to a family dinner with elderly and children", then the conversation input from this round is obtained. The consensus information obtained is "family dinner, with elderly and children", and accordingly, the nature of the dinner is modified to "family dinner, with elderly 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 conversation shorthand card to enter the editing mode by triggering a preset operation (such as long pressing, single clicking, double clicking the conversation shorthand card, etc.); then, the user can edit the conversation shorthand card to modify the content of the conversation shorthand card. Furthermore, in order to facilitate 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, or the modification comparison of the original conversation shorthand card can be viewed.

In this embodiment, the recognition of consensus information is mainly based on each topic (Topic), specifically, it is based on the dialogue text of each topic. Exemplarily, it can be directly extracted from the repeated confirmation statement. In other ways, it is also possible to obtain consensus information after refining information based on the content of the dialogue text. For example, before asking a question, the user only ends a round of conversation with "OK, I understand". At this time, it is impossible to obtain consensus information based on the ending sentence, so it is obtained by the content relevance between the keywords in the question and the user's answer. The keywords that answer the question in the user's answer are used as consensus information. For example, if the question is how many people are dining, then the answer keyword is the number of people "4 people", and 4 people is the consensus information. Alternatively, based on the question and answer, the consensus information is combined, the question keyword is the number of people dining, the answer keyword is 4 people, and the number of people dining has a content relevance with 4 people, then "The number of people dining is 4 people" or "The number of people: 4 people" is used as consensus information. The content relevance between keywords is judged by the artificial intelligence system.

In addition, the end of a round of dialogue is determined by the artificial intelligence system. Taking the conversations in Figures 7 and 8 as an example, in addition to questions and answers, the artificial intelligence system also repeatedly confirms the key points of the user's answer before asking new questions. Therefore, the end of a round of dialogue starts with a question and ends with the key points of the answer repeatedly confirmed by the artificial intelligence system. That is, a round of dialogue includes questions and answers, or includes questions, answers and repeated confirmation statements.

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 preset 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". The 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, the user will not be able to express it in the later stage. When checking the conversation shorthand card, 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.

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 into the conversation shorthand card, and correspondingly, the created conversation shorthand card is a blank card.

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. Among them, the conversation shorthand card can be displayed at the top of the conversation interface, or it can be displayed in other locations of the conversation interface. Of course, the conversation shorthand card can also be displayed above the conversation content in a suspended manner, so that it will not occupy the display of the conversation content, but block part of the conversation content. In addition, the conversation shorthand card can also be used as an additional interactive interface that can be called up, and it will be displayed on the conversation interface when the user calls it up or there is information update.

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. In this way, it 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 adding underlining to remind users that these contents are associated with the conversation shorthand card.

In addition, when new consensus information covers the original consensus information, the decorative logo/text effect of the text corresponding to the original consensus information can be cancelled in the dialogue interface, and the new consensus information can be marked. For example, as shown in (C) of Figure 8, the mark of "family dinner with elderly people" can be cancelled, and "family dinner with elderly people and children" can be marked.

In some embodiments, in addition to displaying the consensus information reached between the user and the artificial intelligence system, the conversation shorthand card can also support the creation and execution of automated tasks based on the conversation shorthand card. Taking the restaurant booking described in FIG8 as an example, the artificial intelligence system can create an automated task of automatically booking a restaurant based on the information recorded in the conversation shorthand card and according to the conversation intention, and the artificial intelligence system calls the local application (applications, applets, service cards, HTML cards, etc., which are presented as cards/windows at runtime, and can be included in the application concept) to create a task of booking a restaurant. Exemplarily, in addition to displaying the consensus information on the conversation shorthand card, an automated task control can also be displayed. The automated task control can be used to execute automated tasks on an electronic device. When the user clicks the automated task control, the artificial intelligence system can create an automated task based on the consensus information. After that, the client can display a task card on the conversation interface. The task card can be used to indicate the execution process of the automated task, and after further interaction by the user, the automated task is completed; at this time, the task execution result can be displayed in the conversation shorthand card. For example, please refer to FIG9, as shown in FIG9 (A), a conversation interface 91 is displayed on the electronic device 100. In the dialogue interface 91, the user slides his finger on the navigation bar at the bottom of the screen. This operation triggers the switching of the application, switches the previous/next application to the front end, and switches the artificial intelligence system to the background, which triggers 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 FIG9 (B), a dialogue shorthand card 92 can be displayed in the dialogue interface 91. At the same time, an automated task control 93 for "booking a restaurant" is displayed in the dialogue shorthand card 92. Then, the user can click on the automated task control 93, and then the electronic device 100 can display an interface as shown in FIG9 (C), that is, a task card 95 is displayed. In FIG9 (C), the user can click on "xx restaurant" to complete the reservation of the restaurant. Afterwards, the electronic device 100 can display an interface as shown in FIG9 (D). Among them, a status control 94 for indicating the task status can also be displayed on the dialogue shorthand card 92. Through the status control 94, the user can 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 inquiry statement of the artificial intelligence system, which is the intention of the current inquiry statement. For example, if the inquiry 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)", where "Discussing" means that the artificial intelligence system is discussing with the user, and "To be determined the number of people for the dinner party" means the intention of the current discussion.

In addition, the artificial intelligence system can automatically determine whether to support the creation of automated tasks based on the existing consensus information in the conversation shorthand card. When the existing consensus information is not sufficient to support the creation of automated tasks (such as the number of people at the dinner, the dishes, etc. are not determined), the automated task control can be set to unavailable; only when the existing consensus information can support the creation of automated tasks, the automated task control is set to available.

In some embodiments, after the conversation shorthand card is created, it can be saved locally or in the cloud. Since the conversation shorthand card saves text information in a predetermined data structure instead of saving all the conversation content, it does not need to occupy token resources.

Furthermore, when the user triggers the creation of a conversation shorthand card, the artificial intelligence system can automatically match existing conversation shorthand cards to find out whether there are conversation shorthand cards with the same or similar intentions. If an existing conversation shorthand card is matched, the existing conversation shorthand card is directly called and displayed on the current conversation interface through the client. For example, referring to Figure 8, in Figure 8 (C), the user did not take the next step but ended the conversation; then as shown in Figure 10 (A), when the user makes a reservation at a restaurant/hotel again, after the user triggers the generation of a "conversation shorthand card", it can first automatically match the conversation shorthand card created in Figure 8, and then ask the user whether it needs it. Continue the last conversation, that is, display the interface shown in FIG10 (B). After the user agrees to continue the last conversation, the conversation shorthand card created in FIG8 can be displayed on the conversation interface 101, that is, display the interface shown in FIG10 (C). In this way, the user only needs to make a simple modification to the conversation shorthand card to make a restaurant reservation through the automated task, without having to conduct multiple rounds of conversation interactions to repeatedly ask the user. Exemplarily, after creating a new conversation interface, the user can choose to close the original conversation interface.

In addition, when matching conversation shorthand cards, the artificial intelligence system can match them in combination with the scene information obtained by the electronic device to improve the accuracy of the match. For example, combined with the current location information, the previously created conversation shorthand card for booking a restaurant near the current location is matched. In addition, the status information of historical conversation shorthand cards can be combined to match the cards, giving priority to matching conversation shorthand cards with a status of "under discussion". In this way, you can avoid asking for requirements from the beginning, and avoid the problem of no conversation experience caused by going directly to the modification stage.

In addition, users can also search for dialogue shorthand cards through dialogue input. Users can carry at least one question attribute of consensus information in the dialogue input. When searching for dialogue shorthand cards, the artificial intelligence system can match dialogue shorthand cards with the same or similar attributes in combination with the question attributes. For example: the user's dialogue input can be "Please help me book a Sichuan restaurant nearby", then the dialogue shorthand cards of historically booked restaurants can be matched; further, the dialogue shorthand cards of the same location (or the historical location closest to the current location) can be searched in combination with the user's current location; further, dialogue shorthand cards with Sichuan dishes as the reserved dishes can be searched.

The user can also add/modify new consensus information during the dialogue input. When the artificial intelligence system displays the dialogue shorthand card, it can modify the historical dialogue shorthand card based on the consensus information obtained by parsing the dialogue input, and then display it. For example, as shown in Figure 11, the artificial intelligence system matches the existing dialogue shorthand card according to the user's dialogue input, and the user's dialogue input describes the new consensus information, "The dinner time is 7 o'clock tomorrow night". Therefore, when presenting the dialogue shorthand card, it does not directly present the dialogue shorthand card, but modifies the dinner time and then displays it in the dialogue interface. If the user's dialogue input is "Help me find a restaurant near the company that has not been booked in July this year", the user has not expressed new consensus information at this time, so the matched historical dialogue shorthand card can be directly called and displayed.

It is understandable that the order of execution of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application. In addition, the various embodiments described above can be combined according to actual conditions, and the combined solutions are still within the scope of protection of the present application.

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

Exemplarily, FIG12 shows a schematic diagram of the structure of a dialogue processing device provided by 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. Among them, the first display module 1201 is used to display a first dialogue interface for a user to interact with an artificial intelligence system. The second display module 1202 is used to display a first dialogue shorthand card in the first dialogue interface in response to a first operation triggered by a user, and the first dialogue shorthand card includes: consensus information that the user and the artificial intelligence system have reached a consensus on in the first dialogue interface.

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.

In some embodiments, the second display module 1202 is further used to: mark the consensus information in the conversation content displayed on the first conversation interface.

In some embodiments, after displaying the first conversation shorthand card, the second display module 1202 is further used 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.

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

In some embodiments, the first dialogue shorthand card also includes: an automated task control. At this time, after displaying the first dialogue shorthand card, the second display module 1202 is further used to: in response to a trigger operation on the automated task control, display a task card in the first dialogue interface, the task card is used to indicate the execution process of the task related to the consensus information; after the task indicated by the task card is completed, display the task execution result in the first dialogue shorthand card.

In some embodiments, the second display module 1202 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 based on the consensus information in the second dialogue interface and is screened from the stored dialogue shorthand cards.

In some embodiments, 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.

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

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, which will not be repeated here.

It can be understood that the electronic devices in the embodiments of the present application can be mobile phones, tablet computers, desktop computers, laptop computers, handheld computers, notebook computers, ultra-mobile personal computers (UMPC), netbooks, as well as cellular phones, personal digital assistants (PDA), 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, etc. The embodiments of the present application do not impose any special restrictions on the specific type of the electronic device.

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

The processor 1310 is the computing core and control core of the electronic device 1300. The processor 1310 may include one or more processing units. For example, the processor 1310 may include one or more of an application processor (application processor, AP), a modem, a graphics processor (graphics processing unit, GPU), an image signal processor (image signal processor, ISP), a controller, a video codec, a digital signal processor (digital signal processor, DSP), a baseband processor, and/or a neural network processor (neural-network processing unit, NPU). Among them, different processing units can be independent devices or integrated in one or more processors. In this embodiment, the NPU can be a neural network (neural-network, NN) computing processor, which can quickly process input information by drawing on the biological neural network structure, such as drawing on the transmission mode between neurons in the human brain, and can also continuously self-learn. Through the NPU, applications such as intelligent cognition of the electronic device 1300 can be realized, such as: image recognition, face recognition, voice recognition, text understanding, text recognition, etc. Exemplarily, the processor 1300 can be used but not limited to execute the method in the aforementioned embodiment.

The memory 1320 may store a program, and the program may be executed by the processor 1310, so that the processor 1310 executes the method performed by the electronic device 1300 provided in the embodiment 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. Optionally, the memory 1320 may also be integrated in the processor 1310.

The display screen 1330 can be used to display images, videos, etc. The 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 or an active-matrix organic light-emitting diode (AMOLED), a flexible light-emitting diode (FLED), Miniled, MicroLed, Micro-oLed, a quantum dot light-emitting diode (QLED), etc.

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 a touch operation 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 waves. 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, etc.

A battery 1350 may also be provided on the electronic device 1300. The battery 1350 may be used to supply power to the electronic device 1300.

It is understood that the structure shown 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 in the figure, or combine some components, or split some components, or arrange the components differently. The components shown in the figure may be implemented in hardware, software, or a combination of software and hardware.

Based on the method in the above embodiment, the embodiment of the present application provides a computer-readable storage medium, which stores a computer program. When the computer program runs 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 the 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 (e.g., a floppy disk, a hard disk, a magnetic tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state hard disk), etc.

Based on the method in the above embodiment, an embodiment of the present application provides a computer program product including 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.

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

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 a 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.

In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented by 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 may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted through the computer-readable storage medium. The computer instructions may be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium may 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 may 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)), etc.

It should be understood that the various numerical numbers involved in the embodiments of the present application are only used for the convenience of description and are not used to limit the scope of the embodiments of the present application.

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 it. 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 cause the essence of the corresponding technical solutions to deviate from the protection scope of the technical solutions of the embodiments of the present application.

Claims (23)

A method for processing a conversation, characterized by comprising: 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. The method according to claim 1 is characterized in that the first conversation shorthand card also includes: conversation status. The method according to claim 1 or 2, characterized in that the first operation comprises 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. The method according to any one of claims 1 to 3, characterized in that it also includes: The consensus information is marked in the conversation content displayed on the first conversation interface. The method according to any one of claims 1 to 4, characterized in that after displaying the first conversation shorthand card, it also 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. The method according to any one of claims 1 to 5, characterized in that after displaying the first conversation shorthand card, it also 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. The method according to any one of claims 1-6, characterized in that the first conversation shorthand card further 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. The method according to any one of claims 1 to 7, characterized in that it 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 obtained by filtering from the stored dialogue shorthand cards based on the consensus information in the second dialogue interface. The method according to claim 8 is 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. The method according to claim 8, further comprising: 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. The method according to any one of claims 1 to 10, characterized in that it 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. A conversation processing device, characterized by comprising: 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. The device according to claim 12, wherein the first operation comprises 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. 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. 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. 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. The device according to any one of claims 12-16, characterized in that the first conversation shorthand card further 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. 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 obtained by filtering from the stored dialogue shorthand cards based on the consensus information in the second dialogue interface. The device according to claim 18 is 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. 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. An electronic device, comprising: one or more processors; Memory; Wherein, 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 any one of the methods described in claims 1-12. A computer-readable storage medium stores a computer program, and 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. A computer program product, characterized in that when the computer program product is run on an electronic device, the electronic device executes the method according to any one of claims 1 to 12.