Interaction method, interaction device and computer readable storage medium

Abstract

The invention relates to the technical field of computers, in particular to an interaction method, an interaction device, a computer readable storage medium and a computer program product. The interaction method comprises the steps of determining an interaction intention of a user and an intelligent agent; in response to the fact that the interaction intention comprises a creation intention, displaying a first interface which comprises at least one creation instruction template control corresponding to a creation style; in response to the situation that the interaction intention does not comprise a creation intention, displaying a second interface which is a dialogue interface of the user and the intelligent agent; and generating creation content corresponding to a first creation instruction in response to the received first creation instruction input by the user in the first interface or the second interface.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technologies, and particularly to an interaction method, an interaction device, a computer-readable storage medium, and a computer program product. Background Art

[0002] With the development of computer technologies, in addition to having conversations with agents, more and more users use agents to assist in creation, especially in fields such as writing and painting. The artificial intelligence technology can effectively improve the efficiency of user creation, but users' requirements for the creation experience are also getting higher and higher. Summary of the Invention

[0003] In view of this, embodiments of the present disclosure provide an interaction method, an interaction device, a computer-readable storage medium, and a computer program product, which can display different interfaces according to different user intentions after determining the intention of the user to start the agent, so that the user can use corresponding functions without the user having to select the interface by themselves, thereby improving the user experience.

[0004] According to some embodiments of the present disclosure, there is provided an interaction method, including: determining an interaction intention of a user with an agent; in response to the interaction intention including a creation intention, displaying a first interface, where the first interface includes at least one creation instruction template control corresponding to a creation genre; in response to the interaction intention not including a creation intention, displaying a second interface, where the second interface is a dialogue interface between the user and the agent; and in response to receiving a first creation instruction input by the user in the first interface or the second interface, generating a creation content corresponding to the first creation instruction.

[0005] According to some other embodiments of the present disclosure, there is provided an interaction device, including: a determination module configured to determine an interaction intention of a user with an agent; a first display module configured to display a first interface in response to the interaction intention including a creation intention, where the first interface includes at least one creation instruction template control corresponding to a creation genre; a second display module configured to display a second interface in response to the interaction intention not including a creation intention, where the second interface is a dialogue interface between the user and the agent; and a generation module configured to generate a creation content corresponding to a first creation instruction in response to receiving the first creation instruction input by the user in the first interface or the second interface.

[0006] According to some embodiments of the present disclosure, there is provided an interaction device, including: a memory; and a processor coupled to the memory, where the processor is configured to execute the method according to any one of the embodiments of the present disclosure based on instructions stored in the memory.

[0007] According to some embodiments of the present disclosure, there is provided a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the method of any one of the embodiments described in the present disclosure.

[0008] Other features, aspects, and advantages of the present disclosure will become apparent from the following detailed description of the exemplary embodiments of the present disclosure with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Embodiments of the present disclosure will be described below with reference to the accompanying drawings. It should be understood that the drawings in the following description are only related to some embodiments of the present disclosure and do not constitute a limitation on the present disclosure. In the drawings:

[0010] Figure 1 A flowchart showing an interaction method according to some embodiments of the present disclosure;

[0011] Figure 2A A schematic diagram showing a first interface according to some embodiments of the present disclosure;

[0012] Figure 2B A schematic diagram showing a second interface according to some embodiments of the present disclosure;

[0013] Figure 2C A schematic diagram showing a second interface according to some other embodiments of the present disclosure;

[0014] Figure 3 A flowchart showing an interaction method according to some other embodiments of the present disclosure;

[0015] Figures 4A to 4C A schematic diagram showing a new document control according to some embodiments of the present disclosure;

[0016] Figure 4D A schematic diagram showing a third interface according to some embodiments of the present disclosure;

[0017] Figure 4E A schematic diagram showing inputting content and creation instructions in the third interface according to some embodiments of the present disclosure;

[0018] Figure 5A A schematic diagram showing displaying created content according to some embodiments of the present disclosure;

[0019] Figure 5B A schematic diagram showing displaying a created content package according to some embodiments of the present disclosure;

[0020] Figure 6 A schematic diagram showing inputting an editing instruction according to some embodiments of the present disclosure;

[0021] Figure 7is a schematic diagram showing input editing instructions according to other embodiments of the present disclosure;

[0022] Figure 8 is a schematic diagram showing input editing instructions according to still other embodiments of the present disclosure;

[0023] Figure 9 is a schematic diagram showing the display of prompt information according to some embodiments of the present disclosure;

[0024] Figure 10 is a schematic diagram showing the display of historical interaction records according to some embodiments of the present disclosure;

[0025] Figure 11 shows a block diagram of an interaction device according to some embodiments of the present disclosure;

[0026] Figure 12 shows a block diagram of an interaction device according to other embodiments of the present disclosure;

[0027] Figure 13 shows a block diagram of an interaction device according to still other embodiments of the present disclosure.

[0028] It should be understood that, for the sake of description, the sizes of the various parts shown in the drawings are not necessarily drawn according to actual proportional relationships. The same or similar reference numerals are used in the various drawings to represent the same or similar components. Therefore, once an item is defined in one drawing, it may not be further discussed in subsequent drawings. Detailed Embodiments

[0029] Next, the technical solutions in the embodiments of the present disclosure will be clearly and completely described in conjunction with the drawings in the embodiments of the present disclosure. It should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein.

[0030] It should be understood that the various steps recorded in the method embodiments of the present disclosure can be executed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this regard. Unless otherwise specifically stated, the relative arrangements and numerical values of the components and steps set forth in these embodiments should be construed as merely exemplary and not limiting the scope of the present disclosure.

[0031] The term "comprising" and its variants used in the present disclosure mean open terms that include at least the subsequent elements / features, but do not exclude other elements / features, that is, "including but not limited to". The term "based on" means "at least partially based on".

[0032] It should be noted that the concepts such as "first", "second", etc. mentioned in this disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependent relationships. Unless otherwise specified, the concepts such as "first", "second", etc. are not intended to imply that the objects so described must be in a given order in terms of time, space, ranking or any other way.

[0033] It should be noted that the modifications of "one" and "multiple" mentioned in this disclosure are illustrative rather than restrictive. Those skilled in the art should understand that unless clearly specified otherwise in the context, it should be understood as "one or more".

[0034] The names of the messages or information exchanged between multiple devices in the embodiments of this disclosure are only for illustrative purposes, and are not used to limit the scope of these messages or information.

[0035] The user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties. And the collection, use and processing of relevant data need to comply with the relevant laws, regulations and standards of relevant countries and regions, and corresponding operation entrances are provided for users to choose to authorize or refuse.

[0036] The embodiments of this disclosure will be described in detail below with reference to the accompanying drawings, but this disclosure is not limited to these specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. In addition, in one or more embodiments, specific features, structures or characteristics can be combined in any suitable manner that will be clear to those of ordinary skill in the art from this disclosure.

[0037] In the interaction process in the related art, the user's interaction intention is usually not judged, and the interface corresponding to the function that the user hopes to use cannot be directly provided for the user, resulting in a poor user experience. To improve the user experience, the embodiments of this disclosure provide a new interaction method, which can display different interfaces for different user intentions after determining the user's intention, so that the user can use the corresponding functions and improve the user experience.

[0038] Figure 1 A flowchart showing an interaction method according to some embodiments of this disclosure.

[0039] As Figure 1As shown, the interaction method includes: Step S1, determining the interaction intention between the user and the intelligent agent; Step S2, in response to the interaction intention including a creation intention, displaying a first interface, where the first interface includes at least one creation instruction template control corresponding to a creation genre; Step S3, in response to the interaction intention not including a creation intention, displaying a second interface, where the second interface is a dialogue interface between the user and the intelligent agent; Step S4, in response to receiving a first creation instruction input by the user in the first interface or the second interface, generating creation content corresponding to the first creation instruction.

[0040] The above intelligent agent can be an intelligent agent based on a large language model (LLM) or other natural language processing (NLP) models. For example, machine learning models such as variational autoencoders (VAEs), convolutional neural networks (CNNs), and transformers can be used to construct the intelligent agent.

[0041] The interaction intention between the user and the intelligent agent is, for example, the function that the user hopes to achieve through the intelligent agent. For example, in the case where the user hopes to have a conversation with the intelligent agent, the interaction intention of the user can be determined as a conversation intention.

[0042] The creation intention in the interaction intention includes, for example, intentions such as writing intention, painting intention, and composition intention, which represent the user's creation needs. For example, in the case where the user hopes to write through the intelligent agent, the interaction intention of the user can be determined as a writing intention.

[0043] The interaction intention between the user and the intelligent agent can be judged based on information such as the habits of the intelligent agent used by the user or other behaviors performed by the user before using the intelligent agent. The above information can be collected after the user's authorization. For example, if the user launched the intelligent agent 8 times out of 10 times before this launch for writing, it can be determined that the user's interaction intention with the intelligent agent this time is also a writing intention.

[0044] After determining the interaction intention between the user and the intelligent agent, it can be judged whether the interaction intention includes a creation intention. In the case where the user's interaction intention includes a creation intention, a first interface can be displayed for the user. The first interface is, for example, a creation interface and can include at least one creation instruction template control corresponding to different creation genres. In response to the user's triggering operation on the creation instruction template control, a creation instruction template can be displayed for the user, and the user can complete the creation instruction by modifying the parameters therein to instruct the intelligent agent to perform corresponding creation.

[0045] For example, in the first interface displayed for a user with a writing intention, it may include controls corresponding to different writing styles, such as compositions, papers, promotional copy, etc. After the user clicks on the control corresponding to the paper, a creation instruction template "My research field is [please enter the research field], help me write a paper on [please enter the topic]" can be displayed. The user can complete the creation instruction by entering the research field and the topic, thereby improving the creation efficiency.

[0046] In the case where the user's interaction intention does not include a creation intention, a second interface can be displayed for the user. This second interface can be a dialogue interface between the user and the intelligent agent. The dialogue interface can be an interface where the user has a separate conversation with the intelligent agent, which displays the historical interaction records between the user and the intelligent agent; or it can be a dialogue list interface of the intelligent agents that have had conversations with the user, which displays a list of the intelligent agents that have had conversations with the user.

[0047] When the user needs to create, they can enter a creation instruction in the first interface or the second interface. After receiving the creation instruction, the intelligent agent will generate creation content corresponding to the creation instruction.

[0048] In the above text, in combination with Figure 1 the basic interaction method according to the embodiments of the present disclosure is introduced. The interaction method proposed by the present disclosure can, after determining the user's intention, display different interfaces according to different user intentions, so that the user can use the corresponding functions and improve the user experience.

[0049] Next, in combination with Figures 2A to 2C the schematic diagram of the interface according to the embodiments of the present disclosure will be introduced.

[0050] Figure 2A is a schematic diagram showing a first interface according to some embodiments of the present disclosure.

[0051] As Figure 2A shown, in the case where it is determined that the user's interaction intention includes a creation intention, the first interface can be displayed. The first interface may include creation instruction template controls 201 to 203, and an input box 21. Among them, the creation instruction template controls can correspond to different genres of creation. For example, as Figure 2A shown, control 201 can be a control corresponding to a story, control 202 can be a control corresponding to a paper, and control 203 can be a control corresponding to promotional copy.

[0052] In some embodiments, determining the interaction intention between the user and the intelligent agent includes: determining the interaction intention according to the historical interaction records between the user and the intelligent agent.

[0053] For example, in the case where the user's recent possible needs such as writing a paper or painting are mentioned in the historical interaction records between the user and the intelligent agent, it can be determined that the user's interaction intention includes a creative intention.

[0054] In response to the user's triggering of the control for the creation instruction template control, the creation instruction template corresponding to the control can be displayed in the input box 21 of the first interface. Figure 2A In the example shown, in response to the user triggering the control 201, the input box 21 displays the creation instruction template "Help me write [5] brand marketing promotion copies for promoting [product] to [target audience], which are concise, eye-catching, and creative", where the target audience and the promoted product can be input by the user, and the number of promotion copies can be either directly input by the user or input by the user, for example, by selecting through a drop-down tab.

[0055] In the case where it is determined that the user wishes to create, the above-mentioned creation instruction template control is displayed for the user when the user starts. Through the above-mentioned creation instruction template control, the user can determine the creation instruction template corresponding to the desired genre and fill in or select the parameters therein to complete the creation instruction for creation, thereby improving the user experience.

[0056] Figure 2B It is a schematic diagram showing a second interface according to some embodiments of the present disclosure.

[0057] As Figure 2B shown, the second interface, that is, the dialogue interface between the user and the intelligent agent, can be a separate dialogue interface between the user and a specific intelligent agent, which includes an input box 22 for the user to communicate with the intelligent agent and the historical dialogue record 23 between the user and the intelligent agent. Figure 2B The intelligent agent A shown in the figure can be, for example, the intelligent agent that has the most conversations with the user or the intelligent agent with the widest application field.

[0058] Figure 2C It is a schematic diagram showing a second interface according to some other embodiments of the present disclosure.

[0059] As Figure 2C shown, the dialogue interface between the user and the intelligent agent can also be a dialogue list interface of the intelligent agents that have had conversations with the user, which includes intelligent agents 241 to 245 and an input box 25. The intelligent agent corresponding to the input box 25 can be set as the first intelligent agent in the dialogue list, and the user can input a creation instruction through the input box 25 to instruct the intelligent agent 241 to create. In addition, in response to the user's triggering operation on different intelligent agents displayed in the dialogue interface, a separate dialogue interface with the corresponding intelligent agent can be entered.

[0060] When the user starts up, by displaying a dialogue interface with the agent for the user, it is possible to meet the diverse needs of the user as much as possible without knowing the user's intention.

[0061] In the above text, in combination with Figures 2A to 2C the interface examples proposed in this disclosure were introduced. Next, in combination with Figure 3 FIG. 5, the content display interface in this disclosure will be introduced. By displaying the created content in the content display interface, it is beneficial for the user to perform subsequent editing. Figure 3 is a schematic flowchart of an interaction method according to some other embodiments of this disclosure.

[0062] Figure 3 In [reference], three ways to enter the content display interface (i.e., the third interface) are respectively shown. First, in combination with Figures 4A to 4E the first way to enter the third interface will be introduced, that is, entering the third interface through the new document control. As Figure 3 shown, based on steps S1 to S4 in Figure 1 , the interaction method according to some embodiments of this disclosure may further include: step S5A, in response to the user's trigger operation on the new document control in the first interface or the second interface, enter the third interface, where the third interface displays the created content in full screen for editing the created content; step S6A, display the corresponding created content according to at least one of the content input by the user in the third interface and the second creation instruction.

[0063] Among them, steps S1 to S4 have been introduced above and will not be elaborated here. Next, steps S5A and S6A will be mainly introduced. Based on steps S5A and S6A, when the user hopes to create, it is also possible to first enter the third interface, that is, the content display interface, and then perform creation by inputting at least one of the content and the creation instruction.

[0064] Figures 4A to 4C is a schematic diagram showing the new document control according to some embodiments of this disclosure. Figure 4D is a schematic diagram showing the third interface according to some embodiments of this disclosure.

[0065] Figure 4A What is shown is the new document control 40 displayed in the first interface, Figure 4B what is shown is the new document control 40 displayed when the second interface is a separate dialogue interface, Figure 4C what is shown is the new document control 40 displayed when the second interface is a dialogue list interface.

[0066] It can be seen that in different interfaces, the new document control 40 can be displayed in different ways. For example, it can be directly displayed in the interface, or displayed in a collapsed tab list in the interface, etc. It should be noted that the above display methods are only exemplary and not restrictive. The new document control can be displayed in the same way in different interfaces, or can be displayed using a display method different from the one shown in the above figures.

[0067] In step S5A, the user can enter, through the new document control 40 as shown in Figures 4A to 4C , the third interface as shown in Figure 4D , that is, the content display interface. Among them, Figure 4D the content display interface shown displays a newly created blank document. As shown in Figure 4D , the third interface can be a content display interface displayed in full-screen mode, which can include a title part 41, a content part 42, an input box 43, and a creation instruction template control 44.

[0068] For the newly created blank document, the title part 41 can, for example, display a prompt "Please enter a title", the content part 42 can, for example, display a prompt "Write any content, or start creating through instructions", and the input box can, for example, display a prompt "Please enter a creation instruction".

[0069] In addition, in the content display interface, there can also be a creation instruction template control 44 similar to the one in Figure 2A . In response to the user's triggering operation on the creation instruction template control 44, a creation instruction template corresponding to the genre can be displayed in the input box 43.

[0070] In step S6A, the user can input at least one of content and a second creation instruction in the content display interface to perform creation.

[0071] Figure 4E is a schematic diagram showing the input of content and creation instructions in the third interface according to some embodiments of the present disclosure. As shown in Figure 4E , for example, in the case where the user hopes to write a composition, the user can enter the title "Spring" in the title part 41 of the blank document as shown in Figure 4D , enter the beginning of the composition "Spring is a season when all things recover" in the content part 42, and then enter the corresponding creation instruction in the input box 43, such as "Continue to write a composition with 800 words".

[0072] Through the above input, it can be indicated that the intelligent agent combines the content and creation instructions input by the user to perform creation, improving the flexibility of the user to use the intelligent agent for creation and enhancing the user's creation experience.

[0073] In some embodiments, the user can also input relatively complete creative content. Without inputting a creative instruction anymore, the user can directly proceed with subsequent editing. For example, in the case where the user has already completed an essay and hopes for an intelligent agent to modify it, the user's own essay can be input in the title part 41 and the content part 42 of the content display interface.

[0074] Through the above interaction method, a new way to start creating can be provided for the user. Creation can be performed based on the content input by the user in the content display interface, thereby improving the user's creation efficiency and enhancing the user experience. In addition, the content display interface of the present disclosure displays the creative content in a full-screen manner, allowing the user to perform immersive creation and also enhancing the user experience.

[0075] As introduced above, the content display interface is entered through the new document control. After entering the content display interface, creation is performed by inputting at least one of content and a creative instruction. Next, in combination with Figure 5A and Figure 5B it will be introduced how to enter the third interface after inputting a creative instruction in the first interface or the second interface, that is, two other ways to enter the third interface will be introduced.

[0076] As Figure 3 shown, based on Figure 1 the interaction method according to some other embodiments of the present disclosure may further include: step S5B, generating an encapsulation body of the creative content as the interaction record between the user and the intelligent agent, and entering the third interface, where the third interface displays the creative content in a full-screen manner for editing the creative content.

[0077] Figure 5A is a schematic diagram showing the display of creative content according to some embodiments of the present disclosure. Figure 5B is a schematic diagram showing the display of the encapsulation body of creative content according to some embodiments of the present disclosure.

[0078] Based on step S5B, after the user inputs a creative instruction in the first interface or the second interface, the user can automatically enter the third interface as shown in Figure 5A while saving the generated encapsulation body of the creative content in the interaction record between the user and the intelligent agent, as shown in Figure 5B for subsequent viewing.

[0079] It should be understood that Figure 5A and Figure 5B the display manners shown are only exemplary and not restrictive. The content display interface can also adopt other layouts or display manners to display the creative content, and the encapsulation body of the creative content can also be displayed in other ways, such as a preview window.

[0080] As Figure 5AAs shown, the content display interface may include, for example, a title section 51, a content section 52, and a sharing control 53. After the user inputs a creation instruction, the user can directly enter the content display interface, and the creation content generated by the agent in response to the user's creation instruction is displayed in the title section 51 and the content section 52. In some embodiments, in response to the user's triggering operation on the sharing control 53 in the third interface, the creation content is shared.

[0081] In the case where the user wishes to share the creation content of the user or the agent, the sharing can be directly performed through the sharing control in the content display interface, without sharing the conversation record between the user and the agent in the conversation interface. By the above method, it is possible to avoid including other content such as conversation records in the shared content, thereby improving the sharing experience.

[0082] It should be understood that the above sharing control can be used not only for the third interface as Figure 5A shown, but also for any other third interface according to the embodiments of the present disclosure, so that the user can perform sharing.

[0083] Figure 5A What is shown is the situation where the creation content is displayed in the content display interface after the user inputs a writing creation instruction. In addition to the writing creation instruction, the user can also input other types of creation instructions such as a painting creation instruction, a composition creation instruction, etc. The agent can use third interfaces with different presentation methods to display the creation content generated in response to other types of creation instructions of the user.

[0084] In addition, in step S5B, after generating the creation content according to the first creation instruction input by the user, an encapsulation body of the creation content can be generated. The encapsulation body of the creation content can be, for example, a card, a preview image, etc. Through the encapsulation body of the creation content, the creation content can be displayed in a smaller area, so that the user can quickly browse it.

[0085] After the agent generates the encapsulation body, the encapsulation body can be saved to the interaction record and provided to the user when the user subsequently views the interaction record or returns to the conversation interface with the agent.

[0086] For example, after the user finishes browsing or editing the content in the content display interface, the user can return from the content display interface to the individual conversation interface between the user and the agent. In the individual conversation interface, the interaction record between the user and the agent as Figure 5B shown can be displayed, which may include the above encapsulation body, thereby allowing the user to combine and browse the creation content, creation instructions, and other historical interactions, improving the user experience.

[0087] In some embodiments, after entering the content display interface, the creation process of the creation content can be presented in the content display interface. For example, when writing, the typing process can be imitated, and the creation content can be presented to the user word by word. Another example is that when painting, the creation process of the painting can be dynamically presented. Through the above display, the user's sense of participation in creation can be further enhanced, thereby improving the user experience.

[0088] The above text introduced a way to enter the third interface after inputting a creation instruction, which can directly enter the third interface as shown in Figure 5A and display the creation content. If the user needs, they can return to the separate conversation interface to display the interaction record as shown in Figure 5B Below, another way to enter the third interface after inputting a creation instruction will be introduced.

[0089] As shown in Figure 3 Based on this, according to some further embodiments of the present disclosure, the interaction method may further include: Step S5C, in the conversation interface between the user and the agent, display the encapsulation of the creation content; Step S6C, in response to the user's triggering operation on the encapsulation, enter the third interface, where the third interface displays the creation content in full screen for editing the creation content. Figure 1

[0090] For example, after completing the creation content, the interaction record as shown in Figure 5B can be first displayed in the separate conversation interface between the user and the agent, which includes the encapsulation of the creation content. Only after the user's triggering operation, will it enter the third interface as shown in Figure 5A to display the creation content in full screen.

[0091] In step S5C, the interaction record as shown in Figure 5B can be displayed in the separate conversation interface for the user to quickly preview.

[0092] As shown in Figure 5B the encapsulation can be generated in the form of a card 54. In the separate conversation interface, the creation content can be displayed within the area of the card 54. The card 54 includes, for example, a title 541, content 542, and an expansion control 543. In the content 542, an overview of the creation content can be displayed.

[0093] In some embodiments, the creation content itself can also be displayed at the content 542. In response to the user's swiping operation on the card, the content displayed on the card can be changed to allow the user to browse.

[0094] ​Users can make a preliminary judgment on whether the creative content generated by the intelligent agent meets the requirements through the creative content displayed in the encapsulation body. In the case of non-compliance, the intelligent agent can be directly instructed to regenerate.

[0095] In step S6C, in the case where the user hopes to further view the complete creative content, the third interface can be entered through a triggering operation on the encapsulation body.

[0096] For example, the user can double-click the encapsulation body or the expansion control in the encapsulation body to enter from the separate conversation interface into the Figure 5A content display interface as shown, so as to further view and edit the creative content.

[0097] It should be understood that the above separate conversation interface is only exemplary, and the interaction record of the encapsulation body including the creative content as Figure 5B shown can also be displayed in other interfaces.

[0098] In the above, different ways to enter the content display interface in the present disclosure are introduced in combination with Figure 3 to FIG. 5. The content display interface in the full-screen mode provides an immersive creative environment for users and provides users with multiple ways to enter the content display interface, thereby improving the user's creative experience and enhancing the user experience. Next, how to edit the creative content will be further introduced in combination with Figures 6 to 8 further.

[0099] In some embodiments, the interaction method may further include: in the third interface, an input box for communicating with the intelligent agent is displayed in the form of a floating layer; the creative content is edited according to the first editing instruction input by the user in the input box.

[0100] Figure 6 is a schematic diagram showing the input of an editing instruction according to some embodiments of the present disclosure. As Figure 6 shown, in the third interface, an input box 61 may be displayed in the form of a floating layer.

[0101] The user can input an editing instruction through the above input box in the form of text or voice, for example, to edit the creative content.

[0102] In the Figure 6 example, in the case where the user hopes to modify the entire creative content, for example, hopes to add some rhetorical devices, the user can input "Polish the full text in a style with more rhetorical devices" as an editing instruction through the input box 61, so as to achieve the editing of the creative content.

[0103] In addition, the creative content can be not only written content, but also other forms of creative content such as painting content. When the creative content is a painting, the content display interface can display the painting in an immersive manner, and an input box can also be displayed in the form of a floating layer at the bottom of the interface to receive the user's editing instructions.

[0104] In some embodiments, the agent can understand the editing instructions input by the user through the input box, thereby determining the content in the creative content that the user wishes to edit, and editing this part of the content based on the editing instructions. The ways to understand the editing instructions can include semantic understanding, visual understanding, syntax tree positioning, etc.

[0105] When the content that the user wishes to edit is only a part of the creative content, by first understanding the editing instructions, the workload of editing can be reduced, the user's creative efficiency can be improved, and thus the user's creative experience can be enhanced.

[0106] For example, when the editing instruction input by the user is "Expand the ending paragraph", the semantic understanding of the user's editing instruction can be performed first to determine that the content the user wishes to edit is the ending paragraph of the creative content, and based on the editing instruction, the ending paragraph can be expanded.

[0107] In the above interaction method, by displaying the input box in the form of a floating layer in the full-screen third interface to receive the user's editing instructions, the immersive experience of the user's creative process can be improved, and the user is prevented from being disturbed by the repeated generation of content.

[0108] The above interaction method provides a way to edit the entire creative content. Another way to edit the entire creative content will be introduced below.

[0109] In some embodiments, the interaction method may further include: in the third interface, in response to the user's triggering operation on the creative content, recommending at least one candidate editing instruction related to the creative content to the user; and editing the creative content according to the second editing instruction selected by the user from the candidate editing instructions.

[0110] The user's triggering operation on the creative content may include, for example, staying for a specified time, or a control associated with the creative content being triggered, etc. Based on the above triggering operation, it can be determined that the user may wish to modify the creative content, and candidate editing instructions can be recommended to the user.

[0111] Figure 7 It is a schematic diagram showing the input of an editing instruction according to other embodiments of the present disclosure. As Figure 7As shown, in the third interface, there may be a control 71 associated with the creation content and displayed. In response to a triggering operation of the user on the control 71, recommended candidate editing instructions 72 may be displayed in the third interface.

[0112] As Figure 7 shown, in the case where the user is writing, the candidate editing instructions may be common writing editing instructions such as "polish the full text", "increase the number of words", "decrease the number of words", etc. The user can modify the creation content by selecting a second editing instruction from the candidate editing instructions. In the above manner, the user can be allowed to quickly input editing instructions by selection, improving the user experience.

[0113] In some embodiments, the candidate editing instructions may also be determined based on the understanding of the creation content. For example, the candidate editing instructions for novel content may include "modify characters", while the candidate editing instructions for a thesis may include "add citation literature", etc. By understanding the creation content, more suitable candidate editing instructions can be provided for the user, thereby improving the user experience.

[0114] In the interaction method proposed by the present disclosure, in addition to modifying the entire creation content as described above, a part of the creation content can also be edited. Below will introduce specifically how to edit a part of the creation content.

[0115] In some embodiments, the interaction method further includes: in the third interface, in response to a triggering operation of the user on the target content in the creation content, recommending at least one candidate editing instruction related to the target content to the user, and editing the target content according to the third editing instruction selected by the user in the candidate editing instructions.

[0116] In other embodiments, the interaction method further includes: in the third interface, in response to a triggering operation of the user on the target content in the creation content, editing the target content according to the fourth editing instruction input by the user in the input box in the third interface.

[0117] The triggering operation of the user on the target content may be, for example, selecting the target content, or the control associated with the target content being triggered, etc. Through the above triggering operation, the target content that the user hopes to edit can be determined, and the target content may be a part of the creation content.

[0118] The above embodiments give two ways for the user to edit a part of the creation content, which can recommend candidate editing instructions related to the target content for the user to select, or receive the editing instructions input by the user from the input box.

[0119] Figure 8It is a schematic diagram showing input editing instructions according to some further embodiments of the present disclosure. As Figure 8 shown, when a user selects a specific paragraph in the created content, for example, an input box 81 and candidate editing instructions 82 can be displayed in the third interface.

[0120] As Figure 8 shown, after the user selects the target content, the input box 81 can be displayed in the form of a floating layer below the paragraph selected by the user. The user can enter editing instructions in the input box to edit the target content selected by the user.

[0121] In addition, after the user selects the target content, candidate editing instructions 82 related to the target content, such as common paragraph editing instructions like "expand paragraph", "abbreviate paragraph", "polish paragraph", etc., can be displayed in the form of a floating layer below the paragraph selected by the user.

[0122] In some embodiments, the candidate editing instructions can also be determined according to the semantic understanding of the target content and the relative position relationship of the target content in the created content. Through the above determination method, more suitable candidate editing instructions for the target content can be provided to the user, thereby improving the user's editing experience.

[0123] It should be understood that the above display method is only exemplary. In the interaction method proposed by the present disclosure, only the input box 81 or only the candidate editing instructions 82 can also be displayed.

[0124] In the above interaction method, on the basis of all modifications, the user can be allowed to select a part of the created content displayed in the content display interface for modification. When modifying a paragraph, only the paragraph that needs to be modified can be regenerated, without regenerating all the created content, further improving the user's editing experience.

[0125] The above describes how to edit the created content in the content display interface. Next, how the agent prompts the user that the editing is completed will be described.

[0126] In some embodiments, the interaction method may further include: in response to completing the editing of the created content, displaying corresponding prompt information in the third interface in the form of a floating layer, where the prompt information includes at least one of a progress prompt for completing the editing and recommended editing instructions for subsequent editing.

[0127] Figure 9 It is a schematic diagram showing the display of prompt information according to some embodiments of the present disclosure. As Figure 9As shown, after the editing is completed, the prompt message 91 and the input box 92 can be displayed in the form of a floating layer on the content display interface. Among them, the prompt message 91 can include a progress prompt 911, a candidate editing instruction 912, and an undo control 913.

[0128] When writing and creating, when the editing instruction input by the user includes "full text polishing", the progress prompt 911 associated with the editing performed with the intelligent agent can be "Full text polishing has been completed", and the recommended candidate editing instructions 912 can be "Tone adjustment", "Length adjustment", etc.

[0129] Through the above prompt message, the user can be allowed to obtain information related to the editing instruction input by the user in the full-screen third interface, without having to display the complete interaction record between the user and the intelligent agent, thereby improving the user's immersive experience.

[0130] In addition, after the editing is completed, the user can judge whether to perform this editing based on the edited creative content. For example, if the user believes that this editing is unreasonable, they can Figure 9 use the undo control 913 in it to undo this editing and return to display the creative content before editing.

[0131] Similarly, after the intelligent agent completes generating the edited creative content, the edited creative content can also be displayed in the third interface in the form of a floating layer, for example, for the user to confirm. In response to receiving the user's confirmation trigger operation, the edited content can be used to replace the content before editing. The confirmation trigger operation can include, for example, clicking the confirmation control, staying for a specified time, etc.

[0132] Figure 9 An input box 92 for voice input is also shown in. In response to the user's trigger operation on the input box 92, the user's input voice information can be started to be received, and the voice information can be converted into text as the editing instruction input by the user.

[0133] In some embodiments, displaying the corresponding prompt message can include: displaying the corresponding prompt message within a specified time after completing the editing of the creative content.

[0134] In other words, the prompt message can be displayed, for example, only within 5 seconds after the editing is completed, so as to avoid disturbing the user from browsing the edited creative content and improve the user's immersive experience.

[0135] It should be understood that the above display method is only exemplary. In the interaction method proposed by the present disclosure, only the progress prompt 911 or only the candidate editing instruction 912 can also be displayed.

[0136] In some embodiments, the interaction method may further include: in response to a triggering operation of the user on the prompt information, in the third interface, displaying, in the form of a floating layer, historical interaction records related to the first creation instruction, where the historical interaction records include encapsulations of the edited creation content.

[0137] Figure 10 FIG. is a schematic diagram showing historical interaction records according to some embodiments of the present disclosure. As Figure 10 shown, after the user triggers the prompt information, for example Figure 9 the prompt information 91 in, historical interaction records 101 related to the first creation instruction can be displayed. In the historical interaction records 101, the first creation instruction 1011 and the encapsulation 1012 of the edited creation content may be included for the user to browse.

[0138] The triggering operation of the user on the prompt information 91 may include, for example, clicking on the prompt information 91 or dragging the prompt information 91, etc. In response to the user's triggering operation, the prompt information 91 may be expanded, for example, so as to display, in the form of a floating layer in the content display interface, the historical interaction records between the user and the agent related to the first creation instruction.

[0139] In the above manner, information related to the creation and editing being performed can be provided to the user when needed, thereby improving the user's creation experience.

[0140] The above is the interaction method provided by the embodiments of the present disclosure. The above interaction method of the present disclosure can, after determining the user's intention, display different interfaces for different user intentions so that the user can use the corresponding functions and improve the user experience.

[0141] Next, reference is made to Figure 11 and Figure 12 to describe an interaction device according to an embodiment of the present disclosure, which is used to execute any one of the above interaction methods. Figure 11 FIG. shows a block diagram of an interaction device according to some embodiments of the present disclosure.

[0142] As Figure 11As shown, the interaction device 11 includes: a determination module 111 configured to determine the interaction intention of the user with the agent; a first display module 112 configured to display a first interface in response to the interaction intention including a creation intention, where the first interface includes at least one creation instruction template control corresponding to a creation genre; a second display module 113 configured to display a second interface in response to the interaction intention not including a creation intention, where the second interface is a dialogue interface between the user and the agent; and a generation module 114 configured to generate creation content corresponding to the first creation instruction in response to receiving the first creation instruction input by the user in the first interface or the second interface.

[0143] The determination module 111 of the interaction device 11 can be used, for example, to execute Figure 1 step S1. The first display module 112 of the interaction device 11 can be used, for example, to execute Figure 1 step S2. The second display module 113 of the interaction device 11 can be used, for example, to execute Figure 1 step S3. The generation module 114 of the interaction device 11 can be used, for example, to execute Figure 1 step S4.

[0144] The above interaction device of the present disclosure can, after determining the user's intention, display different interfaces for different user intentions so that the user can use the corresponding functions, improving the user experience.

[0145] Figure 12 The block diagram of the interaction device according to some other embodiments of the present disclosure is shown.

[0146] As Figure 12 shown, the interaction device 12 includes: a memory 121; and a processor 122 coupled to the memory, where the processor is configured to execute the interaction method described in any of the foregoing embodiments based on instructions stored in the memory.

[0147] The memory 121 is used to store one or more computer-readable instructions. The memory 121 can include any combination of various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory, including but not limited to random access memory (RAM), dynamic random access memory (DRAM), static random access memory (SRAM), read-only memory (ROM), and flash memory. The memory 121 can store, for example, an operating system, application programs, a boot loader (BootLoader), a database, and other programs, and can also store various application programs and various data, etc.

[0148] The processor 122 is used to run computer-readable instructions to implement the interaction method described in any of the foregoing embodiments or the method described in any of the foregoing embodiments. For the specific implementation of each step of the method, reference may be made to the foregoing embodiments. For example Figure 1 and Figure 3 each step in, and the repeated parts will not be elaborated here.

[0149] By executing the steps of the above interaction method, after determining the user's intention, different interfaces can be displayed for different user intentions, so that the user can use the corresponding functions and improve the user experience.

[0150] The processor 122 can be embodied as various processing devices, such as a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The central processing unit (CPU) can be of the X86 or ARM architecture, etc.

[0151] The processor 122 and the memory 121 can communicate with each other directly or indirectly. For example, the processor 122 and the memory 121 can communicate through a network. The network can include a wireless network, a wired network, and / or any combination of a wireless network and a wired network. The processor 122 and the memory 121 can also communicate with each other through a system bus, and the present disclosure does not limit this.

[0152] It should be noted that Figure 12 the components of the interaction device 12 shown are exemplary and not restrictive. According to actual application needs, the interaction device 12 may also have other components. The processor 122 can control other components in the interaction device 12 to perform the desired functions.

[0153] The interaction device 12 can be implemented in a software, firmware, and / or hardware manner and can be integrated in a device installed with relevant application programs.

[0154] Figure 13 The block diagram of the interaction device according to some further embodiments of the present disclosure is shown.

[0155] Figure 13 The interaction device 13 shown can be a computer system with a dedicated hardware structure and can perform corresponding functions when installed with relevant application programs.

[0156] The interactive device includes, but is not limited to, mobile terminals such as smart phones, laptop computers, personal digital assistants (PDAs), tablet personal computers (Tablet PCs), portable multimedia players (PMPs), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), wearable devices, etc., and fixed terminals such as digital TVs, desktop computers, etc.

[0157] As Figure 13 shown, the central processing unit (CPU) 131 executes various processes according to the programs stored in the read-only memory (ROM) 132 or the programs loaded from the storage section 138 into the random access memory (RAM) 133. In the RAM 133, data required when the CPU 131 executes various processes, etc. is stored as needed. The central processing unit is merely exemplary, and it can also be other types of processors, such as the various processors described above. The ROM 132, RAM 133, and storage section 138 can be various forms of computer-readable storage media. It should be noted that although Figure 13 the ROM 132, RAM 133, and storage section 138 are shown separately, one or more of them can be combined, or located in the same or different memories or storage modules.

[0158] The CPU 131, ROM 132, and RAM 133 are connected to each other via the bus 134. The input / output interface 135 is also connected to the bus 134.

[0159] The following components are connected to the input / output interface 135: an input section 136, such as a touch screen, touch pad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; an output section 137, including a display, such as a cathode ray tube (CRT), liquid crystal display (LCD), speaker, vibrator, etc.; a storage section 138, including a hard disk, magnetic tape, etc.; and a communication section 139, including a network interface card such as a LAN card, modem, etc. The communication section 139 allows communication processing to be performed via a network such as the Internet. It is easy to understand that although Figure 13 some parts in the interactive device 13 are shown to communicate via the bus 134, they can also communicate via a network or other means, where the network can include a wireless network, a wired network, and / or any combination of a wireless network and a wired network.

[0160] As needed, the drive 1310 is also connected to the input / output interface 135. A removable medium 1311 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc. is installed on the drive 1310 as needed, so that a computer program read therefrom is installed in the storage section 138 as needed.

[0161] In the case where the above-described series of processes are implemented by software, a program constituting the software can be installed from a network such as the Internet or a storage medium such as the removable medium 1311.

[0162] According to an embodiment of the present disclosure, the processes described above with reference to the flowcharts can be implemented as a computer software program. For example, some embodiments of the present disclosure include a computer program product that, when run on a computer, causes the computer to implement the interaction method described in any of the foregoing embodiments. The computer program product includes computer instructions carried on a computer-readable medium and includes program code for executing the method shown in the flowchart. In such an embodiment, the computer instructions can be downloaded and installed from the network through the communication section 139, or installed from the storage section 138, or installed from the ROM 132. When the computer program is executed by the CPU 131, the method of the embodiment of the present disclosure is executed.

[0163] By executing the steps of the above interaction method, after determining the user's intention, different interfaces can be displayed for different user intentions so that the user can use the corresponding functions, improving the user experience.

[0164] It should be noted that in the context of the present disclosure, a computer-readable medium can be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device.

[0165] A computer-readable medium can be a computer-readable storage medium, a computer-readable signal medium, or any combination of the above two.

[0166] Computer-readable storage media include, but are not limited to: electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or components, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In the present disclosure, a computer-readable storage media can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, device, or component. Computer instructions are stored on the computer-readable storage media, and when executed by a processor, implement the interaction method described in any of the foregoing embodiments.

[0167] By performing the steps of the above interaction method, after determining the user's intention, different interfaces can be displayed for different user intentions so that the user can use the corresponding functions, improving the user experience.

[0168] Computer-readable signal media can include data signals propagated in a baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media can also be any computer-readable media other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, device, or component. The program code contained on the computer-readable media can be transmitted using any appropriate media, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0169] The above computer-readable media can be included in the above interaction device; or it can exist separately and not be assembled into the interaction device.

[0170] In some embodiments, a computer program is also provided, including: instructions that, when executed by a processor, cause the processor to execute the method described in any of the foregoing embodiments. For example, the instructions can be embodied as computer program code.

[0171] In embodiments of the present disclosure, computer program code for performing the operations of the present disclosure may be written in one or more programming languages or combinations thereof. The foregoing programming languages include, but are not limited to, object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, executed as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network (including a local area network (LAN) or a wide area network (WAN)), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0172] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a segment of a program, or a portion of code that contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions noted in the blocks may occur in a different order than noted in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, or they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and combinations of blocks in the block diagram and / or flowchart, may be implemented by a dedicated hardware-based system that performs the specified functions or operations, or may be implemented by a combination of dedicated hardware and computer instructions.

[0173] The functions described above may be performed, at least in part, by one or more hardware logic components. For example, by way of non-limitation, exemplary hardware logic components that may be used include: field programmable gate arrays (FPGA), application specific integrated circuits (ASIC), application specific standard products (ASSP), system on a chip (SOC), complex programmable logic devices (CPLD), and the like.

[0174] Although some specific embodiments of the present disclosure have been described in detail by way of examples, those skilled in the art should understand that the above examples are for illustrative purposes only and are not intended to limit the scope of the present disclosure. Those skilled in the art should understand that the above embodiments may be modified without departing from the scope and spirit of the present disclosure. The scope of the present disclosure is defined by the appended claims.

Claims

1. An interactive method, comprising: Determine the interaction intention between the user and the agent; In response to the interaction intention including the creation intention, displaying a first interface, wherein the first interface includes at least one creation instruction template control corresponding to the creation genre; In response to the interaction intention not including the creative intention, displaying a second interface, wherein the second interface is a dialogue interface between the user and the agent; In response to receiving a first creation instruction input by the user in the first interface or the second interface, creation content corresponding to the first creation instruction is generated.

2. The interactive method according to claim 1, wherein: Determining the interaction intention between the user and the agent includes: The interaction intention is determined according to the historical interaction records between the user and the agent.

3. The interactive method according to claim 1, further comprising: In response to the user triggering an operation of creating a new document control in the first interface or the second interface, entering a third interface, wherein the third interface displays the creative content in full screen mode so as to edit the creative content; The corresponding creation content is displayed according to the content input by the user in the third interface and at least one of the second creation instructions.

4. The interactive method according to claim 1, further comprising: Generate an encapsulation of the creative content as a record of the interaction between the user and the intelligent agent, and enter a third interface, wherein the third interface displays the creative content in full screen mode so as to edit the creative content.

5. The interactive method according to claim 1, further comprising: Displaying the package of the created content on the dialogue interface between the user and the agent; In response to the user's triggering operation on the package, a third interface is entered, wherein the third interface displays the creative content in a full-screen manner so as to edit the creative content.

6. The interactive method according to any one of claims 3 to 5, further comprising: In response to completing the editing of the creative content, corresponding prompt information is displayed in the third interface in the form of a floating layer, wherein the prompt information includes at least one of a progress prompt for completing the editing and recommended editing instructions for subsequent editing.

7. The interactive method according to claim 6, wherein: The corresponding prompt information displayed includes: Within a specified time after the editing of the creative content is completed, the corresponding prompt information is displayed.

8. The interactive method according to claim 6, further comprising: In response to the user's triggering operation on the prompt information, in the third interface, a historical interaction record related to the first creation instruction is displayed in the form of a floating layer, wherein the historical interaction record includes an encapsulation of the edited creation content.

9. The interactive method according to any one of claims 3 to 5, further comprising: In the third interface, an input box for communicating with the agent is displayed in a floating layer; The creative content is edited according to a first editing instruction input by the user in the input box.

10. The interactive method according to any one of claims 3 to 5, further comprising: In the third interface, in response to the user's triggering operation on the creative content, recommending to the user at least one candidate editing instruction related to the creative content; The creative content is edited according to a second editing instruction selected by the user from among the candidate editing instructions.

11. The interactive method according to any one of claims 3 to 5, further comprising: In the third interface, in response to the user's triggering operation on the target content in the creative content, at least one candidate editing instruction related to the target content is recommended to the user, and the target content is edited according to a third editing instruction selected by the user from the candidate editing instructions; or In the third interface, in response to the user's triggering operation on the target content in the creative content, the target content is edited according to a fourth editing instruction input by the user in the input box of the third interface.

12. The interactive method according to any one of claims 3 to 5, further comprising: In response to the user triggering an operation on a sharing control in the third interface, the created content is shared.

13. An interactive device, comprising: A determination module, configured to determine the interaction intention between the user and the agent; A first display module is configured to display a first interface in response to the interaction intention including a creative intention, wherein the first interface includes at least one creative instruction template control corresponding to a creative genre; A second display module is configured to display a second interface in response to the interaction intention not including the creation intention, wherein the second interface is a dialogue interface between the user and the agent; The generation module is configured to generate creation content corresponding to the first creation instruction in response to receiving the first creation instruction input by the user in the first interface or the second interface.

14. An interactive device, comprising: Memory; as well as A processor coupled to the memory, wherein the processor is configured to execute the interaction method according to any one of claims 1 to 12 based on instructions stored in the memory.

15. A computer-readable storage medium having computer instructions stored thereon, wherein the instructions, when executed by a processor, implement the interactive method according to any one of claims 1 to 12.

16. A computer program product, when the computer program product is run on a computer, enables the computer to implement the interactive method according to any one of claims 1 to 12.

Images