Interaction method, device, computer equipment and storage medium

Abstract

The present disclosure provides an interactive method, apparatus, computer equipment and storage medium, wherein the method includes: displaying a target creation page in response to an artificial intelligence object creation request; receiving artificial intelligence object setting information input by a user on the target creation page; the artificial intelligence object setting information includes settings for role attribute information of the artificial intelligence object; the artificial intelligence object setting information is used to determine target service scenario information of the artificial intelligence object; displaying dialogue opening information under the target service scenario generated based on the artificial intelligence object setting information; the artificial intelligence object is used to provide corresponding answer results for user question information; the dialogue opening information includes introduction information of the artificial intelligence object and at least one question prompt information.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology, and more specifically, to an interaction method, apparatus, computer device, and storage medium. Background Art

[0002] Intelligent conversational robots are virtual entities that provide answers to users' questions based on artificial intelligence models. When displaying a conversation page with an intelligent conversational robot, the robot may first display some conversational opening information to entice users to ask further questions. These conversational opening information are pre-set and fixed.

[0003] Since the above-mentioned conversation opening information is fixed, it usually cannot meet the personalized needs of different users, making it difficult to effectively guide users to ask questions. Summary of the Invention

[0004] The embodiments of the present disclosure at least provide an interaction method, apparatus, computer equipment, and storage medium.

[0005] In a first aspect, an embodiment of the present disclosure provides an interaction method, the method comprising:

[0006] In response to an AI object creation request, display a target creation page;

[0007] Receiving artificial intelligence object setting information input by a user on the target creation page; the artificial intelligence object setting information includes setting of role attribute information for the artificial intelligence object; the artificial intelligence object setting information is used to determine target service scenario information of the artificial intelligence object;

[0008] Display the dialogue opening information in the target service scenario generated based on the artificial intelligence object setting information; the artificial intelligence object is used to provide corresponding answer results for user question information; the dialogue opening information includes introduction information of the artificial intelligence object and at least one question prompt information.

[0009] In an optional implementation manner, the dialogue opening information is generated according to the following steps:

[0010] Determining artificial intelligence auxiliary information based on the artificial intelligence object setting information, wherein the artificial intelligence auxiliary information is used to instruct generation of dialogue opening information based on the artificial intelligence object setting information;

[0011] The artificial intelligence object setting information and the artificial intelligence auxiliary information are input into the artificial intelligence model to generate the dialogue opening information of the artificial intelligence object in the target service scenario.

[0012] In an optional implementation, determining the artificial intelligence auxiliary information based on the artificial intelligence object setting information includes:

[0013] Determining, based on the artificial intelligence object setting information, first auxiliary information and second auxiliary information included in the artificial intelligence auxiliary information;

[0014] The first auxiliary information is used to indicate the generation of introduction information of the artificial intelligence object based on the role attribute information; the second auxiliary information is used to indicate the generation of at least one question prompt information based on the target service scenario information associated with the role attribute information.

[0015] In an optional implementation, the target service scenario information of the artificial intelligence object is determined based on the following method:

[0016] Determining attribute information of the artificial intelligence object in multiple attribute dimensions based on the role attribute information in the artificial intelligence object setting information;

[0017] Based on the attribute information under the multiple attribute dimensions, the target service scenario information corresponding to the artificial intelligence object is determined; the target service scenario information is used to indicate the knowledge field and answer style that the artificial intelligence object refers to when providing an answer result.

[0018] In an optional implementation, the display target creation page includes:

[0019] Multiple input areas are displayed on the target creation page, and each input area indicates a corresponding setting dimension; the setting dimension is used to instruct the user to input setting information of the artificial intelligence object under the setting dimension.

[0020] In an optional implementation, the setting dimension includes a description dimension;

[0021] The display target creation page also includes:

[0022] Description prompt information is displayed in an input area corresponding to the description dimension, where the description prompt information includes description template information, or the description prompt information includes multiple description direction information.

[0023] In an optional embodiment, the dialogue opening information further includes an artificial intelligence object image and title information;

[0024] The setting dimension also includes: image dimension and / or name dimension; the image information under the image dimension is used to generate the artificial intelligence object image in the dialogue opening information; the name information under the name dimension is used to generate the title information in the dialogue opening information.

[0025] In an optional implementation, the method further includes:

[0026] In response to a triggering operation on the target question prompt information in the dialogue opening information, an answer result generated based on the target question prompt information and the artificial intelligence object setting information is displayed.

[0027] In an optional embodiment, after displaying the dialogue opening information for the target service scenario generated based on the artificial intelligence object setting information, the method further includes:

[0028] The artificial intelligence object setting information is updated according to the trigger data corresponding to the at least one question prompt information and / or the interaction data between the user and the artificial intelligence object; wherein the updated artificial intelligence object setting information is used to be displayed when the user triggers the artificial intelligence object creation request again.

[0029] In a second aspect, an embodiment of the present disclosure further provides an interactive device, including:

[0030] A first display module, configured to display a target creation page in response to an artificial intelligence object creation request;

[0031] A receiving module, configured to receive artificial intelligence object setting information input by a user on the target creation page; the artificial intelligence object setting information includes settings for role attribute information of the artificial intelligence object; the artificial intelligence object setting information is used to determine target service scenario information of the artificial intelligence object;

[0032] The second display module displays the dialogue opening information in the target service scenario generated based on the setting information of the artificial intelligence AI object; the artificial intelligence object is used to provide corresponding answer results for the user's question information; the dialogue opening information includes the introduction information of the artificial intelligence AI object and at least one question prompt information.

[0033] In a third aspect, an embodiment of the present disclosure further provides a computer device comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the computer device is running, the processor and the memory communicate via the bus, and when the machine-readable instructions are executed by the processor, the steps in the above-mentioned first aspect or any optional implementation of the first aspect are performed.

[0034] In a fourth aspect, an embodiment of the present disclosure further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned first aspect or any optional implementation of the first aspect are executed.

[0035] For a description of the effects of the above-mentioned interactive device, computer equipment and computer-readable medium, please refer to the description of the above-mentioned interactive method, which will not be repeated here.

[0036] By adopting any of the above aspects or any implementation methods of any of the aspects, an AI object that meets the user's personalized needs is created by guiding the user to input AI object setting information that meets their preferences and needs. The input AI object setting information may be a setting of the AI ​​object's role attribute information, which can affect the AI ​​object's service scenario, thereby affecting the conversation opening information when engaging in a conversation with the AI ​​object, and also affecting the content or style of the answers subsequently provided to the user's questions. The conversation opening information here includes introduction information of the AI ​​object and at least one question prompt information. Specifically, the introduction information of the AI ​​object is consistent with the user's current characteristic intentions for the conversation object, and the at least one question prompt information is also adapted to the service scenario currently required by the user. In this way, the personalized needs of different users can be met, thereby achieving the purpose of effectively guiding users to ask questions.

[0037] In order to make the above-mentioned objectives, features and advantages of the present disclosure more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the following briefly introduces the drawings required for use in the embodiments. The drawings herein are incorporated into and constitute a part of the specification. These drawings illustrate embodiments consistent with the present disclosure and, together with the specification, are used to illustrate the technical solutions of the present disclosure. It should be understood that the following drawings only illustrate certain embodiments of the present disclosure and should not be regarded as limiting the scope. For those of ordinary skill in the art, other relevant drawings can be obtained based on these drawings without inventive effort.

[0039] Figure 1 A flowchart of an interaction method provided by an embodiment of the present disclosure is shown;

[0040] Figure 2 A schematic diagram illustrating initiating an artificial intelligence object creation request on a dialogue page in the interactive method provided by an embodiment of the present disclosure is shown;

[0041] Figure 3 A schematic diagram of a target creation page in the interactive method provided by an embodiment of the present disclosure is shown;

[0042] Figure 4 A schematic diagram of an artificial intelligence object selection page in the interactive method provided by an embodiment of the present disclosure is shown;

[0043] Figure 5 A schematic diagram showing a user inputting setting information to create an artificial intelligence object in the interactive method provided by an embodiment of the present disclosure;

[0044] Figure 6 A schematic diagram of an opening page of an artificial intelligence object in the interactive method provided by an embodiment of the present disclosure is shown;

[0045] Figure 7 A schematic diagram of another artificial intelligence object opening page in the interactive method provided by an embodiment of the present disclosure is shown;

[0046] Figure 8 A schematic diagram of an interactive device provided by an embodiment of the present disclosure is shown;

[0047] Figure 9 A schematic diagram of a computer device provided by an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical solutions and advantages of the embodiments of the present disclosure clearer, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. The components of the embodiments of the present disclosure generally described and shown in the drawings herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present disclosure provided in the drawings is not intended to limit the scope of the disclosure for which protection is sought, but merely represents selected embodiments of the present disclosure. Based on the embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of the present disclosure.

[0049] Research has found that when the conversation page with the intelligent conversation robot begins to be displayed, the self-introduction information of the intelligent conversation robot can be displayed at the beginning of the conversation page. In addition, in order to lower the threshold for users to ask questions to the intelligent conversation robot, examples of questions that users may be interested in can often be displayed at the same time.

[0050] However, if the above-mentioned conversation opening information is pre-set, it will not be able to adapt to the needs and preferences of each user. This will result in the intelligent conversation robot being unable to meet the user's personalized needs when introducing itself and providing question examples, and it will be difficult to effectively guide users to ask questions.

[0051] Based on the above research, an embodiment of the present disclosure provides an interactive method, which creates an artificial intelligence object that meets the user's personalized needs by guiding the user to input artificial intelligence object setting information that meets his or her preferences and needs. That is, when the artificial intelligence model generates dialogue opening information and subsequently provides answers to related questions, it can generate dialogue opening information and subsequent answer results that meet the user's personalized needs based on the artificial intelligence object setting information.

[0052] The AI ​​object configuration information input here can be the setting of the AI ​​object's role attribute information. This role attribute information can be used to determine the AI ​​object's service scenario, thereby influencing the opening information of a conversation with the AI ​​object and the content or style of the subsequent responses to user questions. The conversation opening information here includes the AI ​​object's introduction information and at least one question prompt. Specifically, the AI ​​object's introduction information is consistent with the user's current characteristic intentions for the conversation object, and the at least one question prompt is also adapted to the user's current service scenario. In this way, the personalized needs of different users can be met, thereby effectively guiding users to ask questions.

[0053] The defects of the above solutions and the proposed solutions are the results obtained by the inventor after practice and careful research. Therefore, the discovery process of the above problems and the solutions proposed in the present disclosure for the above problems below should be the contributions made by the inventor to the present disclosure during the disclosure process.

[0054] The technical solutions in the present disclosure will be clearly and completely described below in conjunction with the drawings in the present disclosure. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all of the embodiments. The components of the present disclosure generally described and shown in the drawings herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present disclosure provided in the drawings is not intended to limit the scope of the present disclosure for protection, but merely represents selected embodiments of the present disclosure. Based on the embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of the present disclosure.

[0055] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings.

[0056] It is understandable that before using the technical solutions disclosed in the various embodiments of this disclosure, the type, scope of use, usage scenarios, etc. of the personal information involved in this disclosure should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with relevant laws and regulations.

[0057] To facilitate understanding of this embodiment, an interactive method disclosed in an embodiment of the present disclosure is first introduced in detail. The execution subject of the interactive method provided in the embodiment of the present disclosure is generally a computer device with certain computing capabilities.

[0058] The interactive method provided in the embodiment of the present disclosure is described below by taking the execution subject as a terminal device as an example.

[0059] See also Figure 1 FIG. 1 is a flow chart of an interactive method provided by an embodiment of the present disclosure, wherein the method includes S101 to S103, wherein:

[0060] S101: In response to an artificial intelligence object creation request, a target creation page is displayed.

[0061] The artificial intelligence object creation request here can be triggered at any possible entrance, and is not limited in the embodiments of the present disclosure. For example, it can be triggered at a multimedia content display page or at a dedicated artificial intelligence function entrance.

[0062] For example, while browsing the target page, if the user has a need to communicate with the artificial intelligence object, the artificial intelligence identifier displayed on the target page is triggered to initiate a dialogue request with the artificial intelligence object; at this time, in one way, the dialogue page can be displayed in response to the dialogue request, and the artificial intelligence object creation identifier can be displayed on the dialogue page (for example, a plus sign is displayed in the upper right corner of the page). By triggering the artificial intelligence object creation identifier (the user can directly trigger the setting of the artificial intelligence object before initiating a question on the dialogue page, or can trigger the setting of the artificial intelligence object at any time during the dialogue), the target creation page for creating the artificial intelligence object can be displayed, and the creation (or setting) of the artificial intelligence object is completed on the target creation page. After that, the user can enter the dialogue page again. At this time, the dialogue page will display the dialogue opening information corresponding to the created artificial intelligence object (see the subsequent description for details); in another way, the target creation page can be directly entered in response to the dialogue request. After the creation of the artificial intelligence object is completed on the target creation page, the user can enter the dialogue page again. The dialogue page will display the dialogue opening information corresponding to the created artificial intelligence object (see the subsequent description for details).

[0063] In addition, during the process of dialogue and interaction between the user and the currently created artificial intelligence object, if the user has the need to re-create the artificial intelligence object, the user can trigger the artificial intelligence object creation identifier displayed on the current dialogue page at any time to initiate a request to create a new artificial intelligence object and enter the new target creation page. After completing the creation of the artificial intelligence object on the new target creation page, enter the dialogue page again. At this time, the dialogue page will display the dialogue opening information corresponding to the re-created artificial intelligence object.

[0064] For example, you can find and trigger the artificial intelligence function in the application's function options, enter the dialogue page, trigger the artificial intelligence object creation identifier on the dialogue page, display the target creation page for creating the artificial intelligence object, and complete the creation of the artificial intelligence object; or, you can find and trigger the artificial intelligence object creation function in the application's function options to directly initiate a request to create an artificial intelligence object and enter the target creation page.

[0065] like Figure 2 The figure below shows a schematic diagram of initiating an AI object creation request on a conversation page. In a specific implementation, a user can trigger an AI object creation request by clicking the "+" sign in the upper right corner of the current conversation page. In response to the user triggering the AI ​​object creation request, the current conversation page is updated and displayed as the target creation page.

[0066] like Figure 3 In the embodiment of the present disclosure, the target creation page may include multiple input areas, each of which may display a corresponding setting dimension, for instructing the user to enter setting information under the corresponding setting dimension in the input area.

[0067] Furthermore, the setting dimensions may include a name dimension (i.e., the nickname in the corresponding figure), an image dimension (i.e., the character image in the corresponding figure), and a description dimension, etc. Before the user enters the setting information, description prompt information may be displayed in the input area corresponding to the description dimension; wherein, the description prompt information may include description template information, such as: "You play a **, your gender is **, your character profile is **, and the limited answer conditions include **", and the user can directly customize the "**" part to be filled in the description template information to generate the artificial intelligence object they expect; alternatively, the description prompt information may also prompt the user with multiple description directions and display the prompt information in grayscale. After the user triggers the description prompt information, the description information editing begins. For example, the description prompt information may be "You can describe the artificial intelligence object from various identity attributes such as the character name, speaking style, and the limitation of the answer results of the artificial intelligence object."

[0068] In another embodiment, after the user enters the AI ​​object's configuration information, the character description can be automatically optimized and supplemented based on the AI ​​object's configuration information to better create the AI ​​object and provide conversational opening information and subsequent responses that better meet the user's needs. Furthermore, during implementation, multiple optimized and supplemented descriptions can be provided for the user to choose from.

[0069] In addition, after completing the creation of an AI object, the user can also choose to share the setting information of the AI ​​object for other users to view or choose to use. Figure 4 The figure shows the schematic diagram of the AI ​​object selection page. In this page, users can select different types of AI objects. In addition, when the current user is creating an AI object, if he needs to view the relevant setting information of the AI ​​objects created by other users, he can trigger the drop-down button in the upper left corner of the AI ​​object page (such as Figure 2 ), displays the AI ​​object selection page, allowing users to view other users' settings for AI objects as a reference when setting their own AI objects. Alternatively, upon finding an AI object that meets their needs, users can directly select it. The AI ​​object selection page includes multiple pre-set AI object information cards. Each card contains a character image and a brief description of the corresponding AI object, allowing users to select the AI ​​object based on the information cards. The pre-set AI objects can include basic AI objects pre-set by the system or AI objects pre-created by other users.

[0070] S102: Receive setting information of the artificial intelligence object input by the user on the target creation page; the artificial intelligence object setting information includes the setting of role attribute information of the artificial intelligence object; the artificial intelligence object setting information is used to determine the target service scenario information of the artificial intelligence object.

[0071] In practice, users can sequentially enter the AI ​​object's settings for each dimension on the target creation page. Alternatively, users can choose to enter only some of the settings, assuming the user has no specific requirements for other dimensions or that the AI ​​model can make its own decisions based on learned user preferences. Furthermore, prompts for each dimension can be provided on the target creation page. These could include the aforementioned display of each dimension, as well as some exemplary information or prompts for setting directions for each dimension.

[0072] In an embodiment of the present disclosure, the received AI object setting information entered by the user on the target creation page may include the AI ​​object's role attribute information in at least one attribute dimension. For example, the role attribute information may include the AI ​​object's role name, role occupation, and speaking style. Based on the user-entered AI object setting information, the corresponding service scenario of the AI ​​object may be determined. This service scenario influences the content of the AI ​​object's introduction information and the content of the question prompt information provided in the conversation opening information, and also affects the knowledge domain and answer style referenced by the AI ​​object when providing answers.

[0073] That is, in specific implementation, the attribute information of the artificial intelligence object under multiple attribute dimensions can be determined based on the role attribute information in the artificial intelligence object setting information; based on the attribute information under multiple attribute dimensions, the target service scenario information corresponding to the artificial intelligence object can be determined; the target service scenario information here determines the knowledge field and dialogue style that the artificial intelligence object refers to when providing dialogue content.

[0074] like Figure 5 The following figure shows a schematic diagram of creating an AI object for user input of setting information. The user can enter information in the input area corresponding to the name dimension (corresponding to the nickname in the figure), such as "Wise Old Man Wilson"; and in the input area corresponding to the role description dimension, such as "You will play the role of a wise old man, male, 83 years old, formerly a professor of economics and philosophy at a world-leading university. Now retired and in good health, you spend your days in your hometown gardening and raising birds. 1. Do not call yourself a wise old man. If a user asks you who you are, just say you are a retired professor. You can disclose personal information appropriately when communicating with users, but avoid showing off. Speak in a colloquial, concise, and easy-to-understand manner, using less written language, and do not elaborate on your points. 2. You have rich life experience, a very calm heart, and a detached attitude towards life. When users mention some of their life's confusions, listen attentively and show understanding. Do not judge their comments or make random suggestions." ( Figure 5 The description information is briefly shown in

[0075] In the embodiment of the present disclosure, an image can also be uploaded in the input area corresponding to the image dimension as a character image of the artificial intelligence object; or, descriptive information about the image of the artificial intelligence object can be input in the input area corresponding to the image dimension to generate a character image that matches the descriptive information through the artificial intelligence model; or, text description information can be input while uploading the image, so that the artificial intelligence model can generate a new character image for the user with reference to the uploaded image and text description information.

[0076] In one possible implementation, Figure 5 As shown, the target creation page can also include a timbre selection option. Users can click the drop-down button corresponding to the timbre setting dimension to select a timbre option that matches the setting information of the artificial intelligence object. A timbre input area can also be provided for users to actively enter timbre description information, such as "the timbre of a certain star" for broadcasting. After selecting the corresponding timbre, in the subsequent dialogue stage, the artificial intelligence object can voice broadcast the content of the dialogue based on the timbre selected by the user, including the initial dialogue opening information and the subsequent related answer results. These can be automatically voice broadcast, or they can be voice broadcast based on the user's trigger operation.

[0077] In one possible implementation, Figure 5 As shown, the target creation page can also include an "Allow Discovery" setting button to set whether the created AI object can be obtained by other users. When the user sets the currently created AI object to the discoverable state, after the AI ​​object is created, other users can view the relevant settings information of the AI ​​object (including role description information) when selecting the AI ​​object and use it according to their actual situation. Conversely, when the user sets the currently created AI object to the undiscoverable state, other users cannot obtain information about the AI ​​object.

[0078] S103: Displaying the dialogue opening information in the target service scenario generated based on the artificial intelligence object setting information; the artificial intelligence object is used to provide corresponding answer results for user question information; the dialogue opening information includes introduction information of the artificial intelligence object and at least one question prompt information.

[0079] In a specific implementation, the conversation opening information can be obtained by inputting the artificial intelligence object setting information into the artificial intelligence model; that is, the artificial intelligence model can determine the target service scenario of the artificial intelligence object based on the setting information, and then generate the conversation opening information under the target service scenario, including introduction information of the artificial intelligence object and at least one question prompt information.

[0080] In order to better assist the artificial intelligence model in generating conversation opening information, some artificial intelligence auxiliary information can also be generated in combination with the user's setting information to give the artificial intelligence model a better direction when generating conversation opening information.

[0081] In specific implementation, the artificial intelligence auxiliary information can be first determined based on the setting information of the artificial intelligence object input by the user; then the setting information and artificial intelligence auxiliary information of the artificial intelligence object can be input into the artificial intelligence model used to create the artificial intelligence object to generate the dialogue opening information of the artificial intelligence object in the target service scenario.

[0082] For example, after the user inputs a section of setting information about the artificial intelligence object, the artificial intelligence auxiliary information can be determined based on the input setting information. Taking the setting information described in S102 as an example, after the user completes the input of the setting information of "Wise Old Man Wilson", the background can input auxiliary information into the artificial intelligence model based on the setting information input by the user, such as "This paragraph is your character setting. You need to generate a self-introduction and three questions that users may ask based on this setting", "The generated self-introduction and questions must be strongly related to this setting", and other instructions to instruct the generation of dialogue opening information based on the artificial intelligence object setting information.

[0083] Here, the artificial intelligence auxiliary information may include instruction information for instructing the artificial intelligence model to generate an introduction information and a certain number of question prompt information based on the input artificial intelligence object setting information. In addition, specific limitations may be made on the introduction information and question prompt information. For example, it may indicate which introduction dimensions should be included in the introduction information, and indicate the number of question prompt information to be given.

[0084] In an embodiment of the present disclosure, the artificial intelligence auxiliary information includes first auxiliary information and second auxiliary information; wherein, the first auxiliary information is used to indicate the generation of introduction information of the artificial intelligence object based on the role attribute information in the setting information. For example, the first auxiliary information may include "This is a piece of role attribute information, which contains your name and description information. You need to generate a self-introduction based on the role attribute information"; the second auxiliary information is used to indicate the generation of question prompt information based on the target service scenario. For example, the second auxiliary information may include "This is your role setting information. You need to understand the content of the setting information and generate three questions based on the setting information."

[0085] Here, for the above-mentioned first auxiliary information, in addition to indicating the introduction dimensions that need to be included in the introduction information of the dialogue opening information, the introduction information under each introduction dimension can also be further limited, such as limiting the number of characters of the introduction information under some introduction dimensions (such as a nickname must be no less than two characters), the feature requirements that should be met (such as the occupational field needs to be accurate to the sub-field, rather than the generalized upper-level field such as white-collar and blue-collar), etc. For the above-mentioned second auxiliary information, the number of question prompt information that can be generated and the limitation information on the question prompt information can be determined according to the setting information, such as the correlation between different question prompt information is less than the set threshold; the user's historical question information can also be obtained with the user's authorization, the user's preference direction can be analyzed, and the preference direction can be provided to the artificial intelligence model to allow the artificial intelligence model to generate question prompt information that meets the user's preferences. The question prompt information here is also provided to the user for the user to directly trigger to initiate questioning.

[0086] In the disclosed embodiment, title information in the dialogue opening page with the artificial intelligence object can also be generated based on the character image set by the user and the character name input, so that the user can clearly see the artificial intelligence object with which he is talking during the conversation, thereby having a better conversation experience.

[0087] Take the above setting information as an example, Figure 6 The figure below shows a schematic diagram of the AI ​​object's opening page. This page uses the character name entered by the user as the title, and displays a self-introduction message generated based on the user's settings: "Hello, I'm a retired professor. I'm glad to be chatting with you." It also displays corresponding question prompts: "What good books have you read recently?", "What are your thoughts on the current economic situation?", and "How do you think philosophy can help you in life?" This information demonstrates a high degree of correlation between its generation and the user's settings, consistent with the user's settings for the AI ​​object.

[0088] Another possible implementation method is as follows: Figure 7 As shown, the AI ​​object opening page can display an image of the character image generated based on the character image description information input by the user. Here, a dedicated image generation model (with the function of generating corresponding images based on the user's text description) can be used, or the AI ​​model of the embodiment of the present disclosure can be used to generate an image that matches the user's character image description information. In other words, based on the user's description of the character image, an image of the character image can be automatically generated for the user.

[0089] Furthermore, the AI ​​object's opening page also includes a voice broadcast button. Users can set the automatic broadcast function, so that the AI ​​object's dialogue opening information is automatically broadcasted when entering the page. In addition, users can also set the broadcast mode to trigger. In this case, if the user triggers the voice broadcast button, the AI ​​object's self-introduction information and / or question prompt information will be broadcasted in voice form.

[0090] As mentioned above, users can select the timbre of an artificial intelligence object in the artificial intelligence object setting information (they can select from a variety of timbre options or actively input descriptive information about the timbre, such as setting it to the timbre of a certain star AA). In this case, when performing the above-mentioned voice broadcast, the voice broadcast will be performed in the timbre selected by the user.

[0091] After the above-mentioned conversation opening information is displayed, the user can judge whether there are any questions of interest to them based on the displayed question prompt information. If so, the user can trigger the corresponding question prompt information to ask the artificial intelligence object a question. The question prompt information triggered by the user at this time will be reflected in the conversation record as the question entered by the user. Then, the background calls the artificial intelligence model to provide the artificial intelligence object setting information that matches the user, as well as the answer to the question. If the user is not interested in the question prompt information given by the artificial intelligence object, they can also send a voice question instruction to the artificial intelligence object by triggering the "Press and Speak" button below; or, by clicking the keyboard wake-up button, send a question instruction to the artificial intelligence object in the corresponding question input area. The artificial intelligence object can recognize the question instruction sent by the user and give an answer based on the setting information.

[0092] Furthermore, in some embodiments, during the process of the artificial intelligence object communicating with the user based on the above-mentioned setting information, the above-mentioned setting information can be updated and adjusted according to the conversation record. Specifically, it can be updated and adjusted in real time, or the conversation record can be collected first and suggestions can be given as prompt information when the user re-triggers the creation of the artificial intelligence object.

[0093] That is, based on the trigger data corresponding to the at least one question prompt information and / or the interaction data between the user and the artificial intelligence object, the artificial intelligence object setting information is updated, and the updated setting information can be directly used in the dialogue process with the user, so that the artificial intelligence object can better meet the user's personalized needs and preferences during the dialogue process; in addition, the updated setting information here can also be used as prompt information when the user creates an artificial intelligence object next time.

[0094] Here, for example, if the user does not trigger the given question prompt information, and based on the interaction data between the user and the artificial intelligence object, it is found that the setting information of the artificial intelligence object does not meet the user's needs, then based on the question information actively input by the user, the user's needs can be analyzed and the setting information can be automatically updated and modified for the user. In this way, when providing answers in the future, answers can be given based on the updated and modified setting information, or when the user triggers the creation of the artificial intelligence object again and enters the setting information, the updated setting information can be suggested.

[0095] Those skilled in the art will understand that in the above-mentioned method of the specific implementation method, the writing order of each step does not mean a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of each step should be determined by its function and possible internal logic.

[0096] Based on the same inventive concept, an interactive device corresponding to the interactive method is also provided in the embodiment of the present disclosure. Since the principle of solving the problem by the device in the embodiment of the present disclosure is similar to the above-mentioned interactive method in the embodiment of the present disclosure, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0097] Reference Figure 8 FIG. 8 is a schematic diagram of the architecture of an interactive device provided by an embodiment of the present disclosure, wherein the device includes: a first display module 801, a receiving module 802, and a second display module 803; wherein,

[0098] The first display module 801 is used to display a target creation page in response to an artificial intelligence object creation request;

[0099] Receiving module 802, configured to receive AI object setting information input by a user on the target creation page; the AI ​​object setting information includes setting of role attribute information for the AI ​​object; the AI ​​object setting information is used to determine target service scenario information of the AI ​​object;

[0100] The second display module 803 displays the dialogue opening information in the target service scenario generated based on the artificial intelligence AI object setting information; the artificial intelligence object is used to provide corresponding answer results for user question information; the dialogue opening information includes introduction information of the artificial intelligence AI object and at least one question prompt information.

[0101] In a possible implementation, the device further includes:

[0102] A generation module 804 is used to determine artificial intelligence auxiliary information based on the artificial intelligence object setting information, where the artificial intelligence auxiliary information is used to indicate the generation of dialogue opening information based on the artificial intelligence object setting information; the artificial intelligence object setting information and the artificial intelligence auxiliary information are input into the artificial intelligence model to generate dialogue opening information for the artificial intelligence object in the target service scenario.

[0103] In a possible implementation, the generating module 804 is specifically configured to:

[0104] Determining, based on the artificial intelligence object setting information, first auxiliary information and second auxiliary information included in the artificial intelligence auxiliary information;

[0105] The first auxiliary information is used to indicate the generation of introduction information of the artificial intelligence object based on the role attribute information; the second auxiliary information is used to indicate the generation of at least one question prompt information based on the target service scenario information associated with the role attribute information.

[0106] In a possible implementation, the device further includes:

[0107] Determination module 805 is used to determine the attribute information of the artificial intelligence object under multiple attribute dimensions based on the role attribute information in the artificial intelligence object setting information; based on the attribute information under the multiple attribute dimensions, determine the target service scenario information corresponding to the artificial intelligence object; the target service scenario information is used to indicate the knowledge field and answer style that the artificial intelligence object refers to when providing an answer result.

[0108] In a possible implementation, the first display module 801 is specifically configured to:

[0109] Multiple input areas are displayed on the target creation page, and each input area indicates a corresponding setting dimension; the setting dimension is used to instruct the user to input setting information of the artificial intelligence object under the setting dimension.

[0110] In a possible implementation, the first display module 801 is specifically configured to:

[0111] Description prompt information is displayed in an input area corresponding to the description dimension, where the description prompt information includes description template information, or the description prompt information includes multiple description direction information.

[0112] In a possible implementation, the dialogue opening information further includes an artificial intelligence object image and title information;

[0113] The setting dimension also includes: image dimension and / or name dimension; the image information under the image dimension is used to generate the artificial intelligence object image in the dialogue opening information; the name information under the name dimension is used to generate the title information in the dialogue opening information.

[0114] In a possible implementation, the second display module 803 is further configured to:

[0115] In response to a triggering operation on the target question prompt information in the dialogue opening information, an answer result generated based on the target question prompt information and the artificial intelligence object setting information is displayed.

[0116] In a possible implementation, the second display module 803 is further configured to:

[0117] After displaying the conversation opening information for the target service scenario generated based on the artificial intelligence object setting information, the artificial intelligence object setting information is updated according to the trigger data corresponding to the at least one question prompt information and / or the interaction data between the user and the artificial intelligence object; wherein the updated artificial intelligence object setting information is used to be displayed when the user triggers the artificial intelligence object creation request again.

[0118] For descriptions of the processing flow of each module in the device and the interaction flow between each module, reference can be made to the relevant descriptions in the above method embodiment, which will not be described in detail here.

[0119] Based on the same technical concept, the embodiment of the present disclosure also provides a computer device. Figure 7 900 , which includes a processor 901 , a memory 902 , and a bus 903 . The memory 902 is used to store execution instructions and includes a memory 9021 and an external memory 9022 . The memory 9021 , also referred to as internal memory, is used to temporarily store computational data in the processor 901 and data exchanged with an external memory 9022 , such as a hard disk. The processor 901 exchanges data with the external memory 9022 via the memory 9021 . When the computer device 900 is running, the processor 901 communicates with the memory 902 via the bus 903 , enabling the processor 901 to execute the following instructions:

[0120] In response to an AI object creation request, display a target creation page;

[0121] Receiving artificial intelligence object setting information input by a user on the target creation page; the artificial intelligence object setting information includes setting of role attribute information for the artificial intelligence object; the artificial intelligence object setting information is used to determine target service scenario information of the artificial intelligence object;

[0122] Display the dialogue opening information in the target service scenario generated based on the artificial intelligence object setting information; the artificial intelligence object is used to provide corresponding answer results for user question information; the dialogue opening information includes introduction information of the artificial intelligence object and at least one question prompt information.

[0123] The present disclosure also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, executes the steps of the interactive method described in the above method embodiment. The storage medium may be a volatile or non-volatile computer-readable storage medium.

[0124] The embodiments of the present disclosure also provide a computer program product, which carries program code. The instructions included in the program code can be used to execute the steps of the interactive method described in the above method embodiment. For details, please refer to the above method embodiment and will not be repeated here.

[0125] The computer program product may be implemented in hardware, software, or a combination thereof. In one embodiment, the computer program product is implemented as a computer storage medium. In another embodiment, the computer program product is implemented as a software product, such as a software development kit (SDK).

[0126] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems and devices described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. In the several embodiments provided in the present disclosure, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0127] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0128] In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0129] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present disclosure, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present disclosure. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0130] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present disclosure, which are used to illustrate the technical solutions of the present disclosure, rather than to limit them. The scope of protection of the present disclosure is not limited thereto. Although the present disclosure has been described in detail with reference to the above-described embodiments, those skilled in the art should understand that any person skilled in the art can modify or easily conceive of changes to the technical solutions described in the above-described embodiments within the technical scope disclosed in the present disclosure, or replace some of the technical features therein with equivalents. Such modifications, changes, or replacements do not deviate from the spirit and scope of the technical solutions of the embodiments of the present disclosure, and should be included in the scope of protection of the present disclosure. Therefore, the scope of protection of the present disclosure should be based on the scope of protection of the claims.

Claims

1. An interactive method, characterized in that: include: In response to an AI object creation request, display a target creation page; Receiving artificial intelligence object setting information input by the user on the target creation page; The artificial intelligence object setting information includes the setting of role attribute information for the artificial intelligence object; the artificial intelligence object setting information is used to determine the target service scenario information of the artificial intelligence object; Displaying conversation opening information for a target service scenario generated based on the artificial intelligence object setting information; The artificial intelligence object is used to provide corresponding answer results for user question information; the dialogue opening information includes introduction information of the artificial intelligence object and at least one question prompt information, The dialogue opening information is generated according to the following steps: Determining artificial intelligence auxiliary information based on the artificial intelligence object setting information, wherein the artificial intelligence auxiliary information is used to instruct generation of dialogue opening information based on the artificial intelligence object setting information; The artificial intelligence object setting information and the artificial intelligence auxiliary information are input into the artificial intelligence model to generate the dialogue opening information of the artificial intelligence object in the target service scenario.

2. The method according to claim 1, characterized in that The determining of artificial intelligence auxiliary information based on the artificial intelligence object setting information includes: Determining, based on the artificial intelligence object setting information, first auxiliary information and second auxiliary information included in the artificial intelligence auxiliary information; The first auxiliary information is used to indicate that the introduction information of the artificial intelligence object is generated based on the role attribute information; the second auxiliary information is used to indicate that the at least one question prompt information is generated based on the target service scenario information.

3. The method according to claim 1, characterized in that The target service scenario information of the artificial intelligence object is determined based on the following method: Determining attribute information of the artificial intelligence object in multiple attribute dimensions based on the role attribute information in the artificial intelligence object setting information; Determining target service scenario information corresponding to the artificial intelligence object based on the attribute information under the multiple attribute dimensions; The target service scenario information is used to indicate the knowledge domain and answer style that the artificial intelligence object refers to when providing the answer result.

4. The method according to claim 1, wherein The display target creation page includes: Multiple input areas are displayed on the target creation page, and each input area indicates a corresponding setting dimension; the setting dimension is used to instruct the user to input setting information of the artificial intelligence object under the setting dimension.

5. The method according to claim 4, characterized in that The setting dimension includes a description dimension; The display target creation page also includes: Description prompt information is displayed in an input area corresponding to the description dimension, where the description prompt information includes description template information, or the description prompt information includes multiple description direction information.

6. The method according to claim 4 or 5, characterized in that The dialogue opening information also includes an artificial intelligence object image and title information; The setting dimension also includes: image dimension and / or name dimension; the image information under the image dimension is used to generate the artificial intelligence object image in the dialogue opening information; the name information under the name dimension is used to generate the title information in the dialogue opening information.

7. The method according to claim 1, characterized in that The method further comprises: In response to a triggering operation on the target question prompt information in the dialogue opening information, an answer result generated based on the target question prompt information and the artificial intelligence object setting information is displayed.

8. The method according to claim 1, characterized in that After displaying the dialogue opening information in the target service scenario generated based on the artificial intelligence object setting information, the method further includes: The artificial intelligence object setting information is updated according to the trigger data corresponding to the at least one question prompt information and / or the interaction data between the user and the artificial intelligence object; wherein the updated artificial intelligence object setting information is used to be displayed when the user triggers the artificial intelligence object creation request again.

9. An interactive device, characterized in that: include: A first display module, configured to display a target creation page in response to an artificial intelligence object creation request; A receiving module, configured to receive artificial intelligence object setting information input by a user on the target creation page; The artificial intelligence object setting information includes the setting of role attribute information for the artificial intelligence object; the artificial intelligence object setting information is used to determine the target service scenario information of the artificial intelligence object; A second display module is used to display the dialogue opening information in the target service scenario generated based on the artificial intelligence object setting information; The artificial intelligence object is used to provide corresponding answer results for the user's question information; the dialogue opening information includes the introduction information of the artificial intelligence AI object and at least one question prompt information, The device further includes a generating module, configured to: Determining artificial intelligence auxiliary information based on the artificial intelligence object setting information, wherein the artificial intelligence auxiliary information is used to instruct generation of dialogue opening information based on the artificial intelligence object setting information; as well as The artificial intelligence object setting information and the artificial intelligence auxiliary information are input into the artificial intelligence model to generate the dialogue opening information of the artificial intelligence object in the target service scenario.

10. A computer device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the computer device is running, the processor and the memory communicate via the bus, and when the machine-readable instructions are executed by the processor, the steps of the interaction method according to any one of claims 1 to 8 are performed.

11. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, which, when executed by a processor, executes the steps of the interaction method according to any one of claims 1 to 8.

Images