Information exchange method and apparatus, electronic device, and storage medium

Abstract

Embodiments of the present disclosure provide an information exchange method and apparatus, an electronic device, and a storage medium. The method comprises: in response to a first operation of a user for creating an application scenario, displaying a scenario creation page; constructing scenario association information of a target scenario on the basis of an editing operation in the scenario creation page; in response to a second operation, displaying at least one data source to be selected, and using a triggered and selected data source as a target data source associated with the target scenario to create the target scenario; and in response to receiving in the target scenario a text to be answered, determining a reply text from the target data source associated with the target scenario.

Description

Information interaction method, device, electronic device and storage medium

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to the Chinese patent application filed on November 21, 2023, with application number 202311560496.3 and invention name “Information interaction method, device, electronic device and storage medium”. The entire contents of that application are incorporated by reference into this application. Technical Field

[0003] The embodiments of the present disclosure relate to the field of information interaction technology, and in particular to an information interaction method, device, electronic device, and storage medium. Background Art

[0004] With the rapid development of computer and internet technologies, a wide variety of service scenarios have emerged. These scenarios often utilize a variety of related services to enrich their functionality and user interaction. For example, a conversation interface can automatically display a corresponding reply text by sending a text to be answered.

[0005] Summary of the Invention

[0006] Embodiments of the present disclosure provide an information interaction method, device, electronic device, and storage medium.

[0007] In a first aspect, an embodiment of the present disclosure provides an information interaction method, the method comprising:

[0008] In response to a first operation of the user for creating an application scenario, displaying a scenario creation page;

[0009] Building scene association information of the target scene based on the editing operation on the scene creation page;

[0010] In response to a second operation, at least one data source to be selected is displayed, and the data source to be selected that triggers the selection is associated with the target scene as a target data source to create the target scene;

[0011] In response to receiving a text to be answered in the target scenario, a reply text is determined from a target data source associated with the target scenario.

[0012] In a second aspect, an embodiment of the present disclosure further provides an information interaction device, the device comprising:

[0013] A page display module, configured to display a scenario creation page in response to a first operation of the user for creating an application scenario;

[0014] An associated information building module, configured to build scene associated information of a target scene based on an editing operation on the scene creation page;

[0015] a data source display module, configured to display at least one data source to be selected in response to a second operation, and associate the data source to be selected that triggers selection as a target data source with the target scene to create the target scene;

[0016] The reply text determination module is configured to, in response to receiving a text to be answered in the target scenario, determine a reply text from a target data source associated with the target scenario.

[0017] In a third aspect, an embodiment of the present disclosure further provides an electronic device, the electronic device comprising:

[0018] one or more processors;

[0019] a storage device for storing one or more programs,

[0020] When the one or more programs are executed by the one or more processors, the one or more processors implement the information interaction method as described in any one of the embodiments of the present disclosure.

[0021] In a fourth aspect, an embodiment of the present disclosure further provides a storage medium containing computer-executable instructions, which, when executed by a computer processor, are used to execute the information interaction method as described in any one of the embodiments of the present disclosure.

[0022] The technical solution of the embodiment of the present disclosure is to display a scenario creation page in response to a first operation of the user for creating an application scenario, and further, based on the editing operation on the scenario creation page, construct scene association information of the target scene, and then, in response to a second operation, display at least one data source to be selected, and associate the triggered selected data source with the target scene as the target data source to create the target scene, and finally, in response to receiving a text to be answered under the target scenario, determine the reply text from the target data source associated with the target scene. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The above and other features, advantages, and aspects of the various embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that the originals and elements are not necessarily drawn to scale.

[0024] FIG1 is a flow chart of an information interaction method provided by an embodiment of the present disclosure;

[0025] FIG2 is a schematic diagram of a scene creation page provided in an embodiment of the present disclosure;

[0026] FIG3 is a schematic diagram of a target data source calling mode setting process provided by an embodiment of the present disclosure;

[0027] FIG4 is a flow chart of an information interaction method provided by an embodiment of the present disclosure;

[0028] FIG5 is a schematic diagram of a conversation interface provided by an embodiment of the present disclosure;

[0029] FIG6 is a schematic diagram of a scene creation page provided by an embodiment of the present disclosure when the information switching control is a scene basic setting control;

[0030] FIG7 is a schematic diagram of a scene creation page provided in an embodiment of the present disclosure when the information switching control is a knowledge selection control;

[0031] FIG8 is a schematic diagram of a data source selection page provided in an embodiment of the present disclosure;

[0032] FIG9 is a flow chart of an information interaction method provided by an embodiment of the present disclosure;

[0033] FIG10 is a schematic diagram of a scene display pop-up window provided in an embodiment of the present disclosure;

[0034] FIG11 is a schematic structural diagram of an information interaction device provided by an embodiment of the present disclosure;

[0035] FIG12 is a schematic structural diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0036] The following describes embodiments of the present disclosure in more detail with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of protection of the present disclosure.

[0037] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed 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 respect.

[0038] As used herein, the term "including" and its variations are open-ended, i.e., "including but not limited to." The term "based on" means "based, at least in part, on." The term "one embodiment" means "at least one embodiment," the term "another embodiment" means "at least one additional embodiment," and the term "some embodiments" means "at least some embodiments." Other terms are defined in the following description.

[0039] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0040] It should be noted that the modifications of "one" and "multiple" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, they should be understood as "one or more".

[0041] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0042] 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.

[0043] For example, in response to a user's active request, a prompt message is sent to the user to clearly inform the user that the operation requested will require the acquisition and use of the user's personal information. This allows the user to independently choose whether to provide personal information to the electronic device, application, server, storage medium, or other software or hardware that performs the operations of the disclosed technical solution based on the prompt message.

[0044] As an optional but non-limiting implementation, in response to receiving a user's active request, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. Furthermore, the pop-up window may also contain a selection control for the user to select "agree" or "disagree" to provide personal information to the electronic device.

[0045] It is understandable that the above notification and user authorization process are merely illustrative and do not limit the implementation of the present disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0046] It is understandable that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) must comply with the requirements of relevant laws, regulations and relevant provisions.

[0047] Currently, when determining the reply text, there is a problem that the reply content does not match the question and answer or has low relevance.

[0048] Before introducing this technical solution, an exemplary application scenario can be first described. The technical solution of the disclosed embodiment can be applied to any information interaction scenario, which can be a scenario where a reply to information corresponding to a question and answer statement is required, such as an artificial intelligence answering scenario or an artificial intelligence execution scenario.

[0049] In order to introduce the present technical solution more clearly, the execution process of the present technical solution can be explained by taking the artificial intelligence answering scenario as an example. For other information interaction scenarios, please refer to the information interaction process in the artificial intelligence answering scenario. For example, in the artificial intelligence answering scenario, when receiving the text to be answered sent by the user, the system can determine the reply text and feed it back to the user. However, when determining the reply text, the reply text corresponding to the text to be answered is usually determined from the full amount of data pre-stored in the system. Moreover, when the text to be answered is received for multiple consecutive times, the process of locating the reply text using the full amount of data needs to be repeatedly executed. In this case, there may be problems of low information interaction efficiency and low reply accuracy. Moreover, when the user asks a relatively broad question, it is impossible to locate the reply text in a targeted manner, and the determined reply text cannot meet the user's question needs.

[0050] At this time, based on the technical solution of the embodiment of the present disclosure, a target scene associated with the user can be created based on the user's editing operation on the scene creation page, and then, the target data source associated with the target scene can be determined, and an association relationship between the target scene and the target data source can be established, so that when a text to be answered is received in the target scene, the reply text can be determined from the target data source associated with the target scene.

[0051] It should be noted that the information interaction method provided by the embodiment of the present disclosure can be applied to the artificial intelligence answering scenario. Among them, the artificial intelligence answering scenario can be understood as a scenario in which interaction is achieved between artificial intelligence and the user. Optionally, the artificial intelligence answering scenario may include scenarios such as artificial intelligence robot question and answer, artificial intelligence robot chatting, or artificial robot writing. Accordingly, the device for executing the information interaction method provided by the embodiment of the present disclosure can be integrated into the application software that supports the artificial intelligence answering function, and the software can be installed in an electronic device. Optionally, the electronic device can be a mobile terminal or a PC terminal, etc. The application software can be a type of software that can support the artificial intelligence answering function, and its specific application software will not be described here one by one. Alternatively, it can also be a specially developed application program, which is integrated into the software that supports information interaction, or integrated into the corresponding page, and the user can realize information interaction through the page integrated in the PC terminal.

[0052] Figure 1 is a flow chart of an information interaction method provided by an embodiment of the present disclosure. The embodiment of the present disclosure is applicable to situations in which the method can be executed by an information interaction device, which can be implemented in the form of software and / or hardware. Optionally, it can be implemented by an electronic device, which can be a mobile terminal, a PC or a server, etc.

[0053] As shown in FIG1 , the method of this embodiment may specifically include:

[0054] S110 : In response to a user's first operation for creating an application scenario, display a scenario creation page.

[0055] Among them, the application scenario can be understood as the construction environment in which the application or service is located, which refers to the environment in which the service is executed, delivered and interacted. Correspondingly, creating an application scenario can be understood as building the application scenario required by the user based on user needs. The first operation can be understood as an operation that displays the scene creation page associated with the creation of the application scenario after being triggered. Among them, the scene creation page can be understood as a page for providing an entry for editing interactive operations of the scene editing items corresponding to the creation of the application scenario. Optionally, the scene creation page includes a first display area and a second display area. The first display area includes multiple information switching controls. The second display area is used to display associated controls associated with the information switching control.

[0056] The first display area and the second display area correspond to different areas on the scene creation page. The first display area can be any area on the scene creation page, and optionally, it can be the upper area on the scene creation page. The second display area can be any area on the scene creation page, and optionally, it can be the lower area on the scene creation page. The information switch control can be a control used to switch scene creation information. The information switch control can be any form of switch control, and optionally, it can be a switch button, a floating control, or a switch card. The information switch control can include various types of controls, and optionally, it can include scene basic setting controls, knowledge selection controls, and other information switch controls. Associated controls can be understood as information setting controls corresponding to corresponding information switch controls. For example, Figure 2 is a schematic diagram of a scene creation page 20. In Figure 2, the upper area of ​​the page is the first display area 21, and the lower area of ​​the page is the second display area 22. The first display area can include information switch control 1, information switch control 2, and information switch control 3. When a trigger operation of the mouse cursor (arrow in the figure) on information switch control 1 is detected, the associated controls associated with information switch control 1 can be displayed in the second display area. The edit boxes displayed in the second display area are associated controls, which may include associated control 1, associated control 2, and associated control 3. This arrangement has the advantage of enabling linkage display between the first display area and the second display area, thereby improving scene creation efficiency.

[0057] In the related art, in the artificial intelligence answering scenario, artificial intelligence question and answer is usually carried out in the default scenario. The user enters a question in the conversation interface, and the artificial intelligence determines the reply corresponding to the question only within the scope of the default scenario set in advance. Based on the above-mentioned method for information interaction, there may be problems such as the reply provided by the artificial intelligence is not the reply required by the user, and cannot solve the user's problem, resulting in a poor user interaction experience. Based on this, the technical solution provided by the embodiment of the present disclosure can be applied to create a personalized application scenario required by the user before entering the question. Furthermore, when the question entered by the user is received in the created application scenario, the corresponding reply can be determined from the data corresponding to the application scenario, thereby improving the adaptability between the provided reply and the question entered by the user.

[0058] In actual applications, a control for triggering the creation of an application scenario can be pre-set, or a program code for triggering the creation of an application scenario can be pre-set. Furthermore, upon detecting that a user has triggered the control, or upon receiving the program code, it can be determined that a first operation has been detected. Furthermore, the first operation can be responded to by displaying a scenario creation page. Optionally, the control can be set in a conversation interface or in a menu list of the corresponding application software, which is not specifically limited in the present embodiment.

[0059] S120. Based on the editing operation on the scene creation page, construct scene association information of the target scene.

[0060] In this embodiment, the editing operation can be understood as an edit trigger operation for the scenario creation item displayed on the scenario creation page. The target scenario can be understood as the application scenario ultimately created, that is, the application scenario that meets user needs. Scenario-related information can be understood as information used to characterize the detailed content of the application scenario. Optionally, the scenario-related information may include at least one of the scenario name, scenario description information, model usage type, and opening remarks information. The scenario name is the name of the application scenario to be created. The scenario description information may be the setting information of the application scenario, which is used to describe the overall construction of the application scenario. The scenario description information may include a variety of information, and may optionally include the response style settings and main function overview of the scenario, the specific workflow of the scenario, and an example of the response format of the scenario. The model usage type can be understood as the type of artificial intelligence model used in the application scenario. In addition, in this embodiment, the scenario-related information may also include a default plug-in. The default plug-in may be any plug-in that provides a data source.

[0061] In actual applications, the information switching control displayed in the first display area may include a scene-based settings control. When a trigger operation is detected for this control, associated controls associated with the scene-based settings control may be displayed in the second display area. Furthermore, by entering corresponding text content for at least one associated control, the corresponding associated control can be edited. Furthermore, scene-related information for the target scene can be constructed based on the text content of at least one associated control.

[0062] S130: In response to the second operation, display at least one data source to be selected, and associate the data source to be selected that triggers the selection as a target data source with a target scene to create a target scene.

[0063] In this embodiment, the second operation can be understood as a data source display trigger operation. The data source is the source of the data, which is a device or original medium that provides certain required data. All information for establishing a database connection is stored in the data source. In this embodiment, the data source to be selected is a data carrier that provides the reply text corresponding to the text to be answered entered by the user. The data source to be selected can be a predetermined data source. The number of data sources to be selected can be one or more. It should be noted that the data source to be selected can include the data source within the application software, and can also include the data source of a third-party platform. Since the data source of a third-party platform may require access permissions to be accessed, the data source included in the data source to be selected can be a data source with access permissions. The advantage of this setting is that it can avoid the problem that the user cannot access the data source when triggering the corresponding data source to be selected, thereby improving the user experience.

[0064] In actual applications, the information switching control displayed in the first display area may include a knowledge selection control. When a trigger operation is detected for the control, an associated control associated with the knowledge selection control may be displayed in the second display area. In this case, the displayed associated control may be a data source to be selected. Furthermore, the user may select from at least one of the displayed data sources to be selected through a trigger operation. When a trigger operation is detected for any of the data sources to be selected, the data source to be selected may be used as the target data source. Alternatively, another implementation may be: while displaying at least one data source to be selected, a data source selection countdown may also be displayed on the data source display page, where the countdown time is the preset selection duration. Furthermore, when the user selects from at least one data source to be selected, when the selection duration reaches the preset duration, that is, when the selection countdown returns to zero, the data source to be selected triggered by the user at that moment becomes the target data source. Alternatively, when the selection duration reaches the preset duration, the trigger frequency of each data source to be selected in the current data source display page within the preset duration may be counted, and the data source to be selected with the highest trigger frequency may be used as the target data source.

[0065] Furthermore, after determining the target data source, the target data source can be associated with the previously created target scene, that is, an association relationship between the target scene and the target data source is established, thereby obtaining the created target scene.

[0066] S140 : In response to receiving a text to be answered in a target scenario, determining a reply text from a target data source associated with the target scenario.

[0067] In this embodiment, when a text to be answered is received in a target scenario, the reply text may be determined from a target data source associated with the target scenario.

[0068] Among them, the text to be answered can be understood as the text entered by the user in the dialog box and uploaded to the conversation interface. Optionally, the text to be answered can be a question entered by the user, for example, "What is a hierarchical structure"; or, it can also be a requirement entered by the user, for example, "Summarize the core ideas in the documents related to AIGC that have been read this week"; or, it can also be other texts, which are not specifically limited in the embodiments of the present disclosure. The reply text can be the reply text corresponding to the text to be answered. For example, continuing to refer to the above example, if the text to be answered is "What is a hierarchical structure", the reply text is the content associated with the hierarchical structure; if the text to be answered is "Summarize the core ideas in the documents related to AIGC that have been read this week", the reply text can be the content associated with the core ideas of AIGC, and these contents are related to the documents read by the user this week.

[0069] In actual applications, when determining the reply text, it is also possible to perform a structural analysis of the textual form of the reply text and determine whether the reply text is structured or unstructured. In the case where the reply text is structured text, such as a table, an SQL query statement can be constructed based on the reply text, and the reply text can be determined from the target data source based on the query statement; in the case where the reply text is unstructured text, such as text, a vectorized analysis can be performed on the reply text to determine the feature vector corresponding to the reply text, and then the reply text can be determined from the target data source based on the feature vector. If the ability to further perform data analysis for insight attribution and chart drawing is required, there is no need to separate structured and unstructured knowledge for users to choose, nor is there any need to provide question-and-answer and data analysis options for users to choose.

[0070] In some embodiments of the present disclosure, in response to a sharing operation on a created target scene, the target scene is shared with the target user. Alternatively, the created target scene is published on a public platform. When a user obtains permission to use the target scene and does not have permission to access the target data source associated with the target scene, the user can access the target data source. For example, the target data source can be accessed by asking and answering questions about the target scene in a conversation.

[0071] It should be noted that after determining the target data source, a method for calling the target data source can also be set. Consequently, when a text to be answered is received in the target scenario, the target data source can be called based on the pre-set calling method and the corresponding reply text can be determined, thereby improving the intelligence and calling method diversity of the artificial intelligence answering system. Optionally, after determining the target data source associated with the target scenario, the method further includes: configuring the target data source calling method for the target scenario.

[0072] In this embodiment, the data source call mode can be understood as the timing of data source call. Optionally, the data source call mode can include automatic call mode or on-demand call mode. The automatic call mode refers to the process of calling the target data source corresponding to the target scenario to determine the reply text each time a response text is received. The on-demand call mode refers to the process of calling the target data source to determine the reply text only under preset circumstances. In this embodiment, a data source call mode selection control can be provided in the second display area. When a trigger operation is detected for this selection control, a call mode display page can be displayed. This page can include automatic call mode and on-demand call mode. The user can configure the target data source call mode for the target scenario by selecting a trigger operation. For example, Figure 3 is a schematic diagram of the target data source call mode setting process. As shown in Figure 3, the second display area 31 can include a "Knowledge Call Mode" control. When a trigger operation is detected on the "∨" control by the mouse cursor, a call mode display page 32 can be displayed. Furthermore, when a trigger operation is detected on the "Automatic Call" control, the target data source's data source call mode can be set to automatic call mode, and "Automatic Call" can be displayed in the "Knowledge Call Mode" control.

[0073] In actual applications, if the target data source calling mode configured for the target scenario is automatic calling mode, when a text to be answered is received in the target scenario, the target data source associated with the target scenario can be directly called to determine the reply text.

[0074] If the target data source calling method configured for the target scenario is an on-demand calling method, information for triggering the execution of the on-demand calling method can be added to the scene description information in the scene association information when constructing the scene association information of the target scenario. Among them, the on-demand calling method can be determined in at least two ways. Optionally, the on-demand calling method can be determined based on whether the text to be answered triggers key information, or triggers the calling method of the template to be answered. In this embodiment, the key information can be pre-set situation description information associated with calling the target data source. The template to be answered can be understood as an example of the text form of the text to be answered that can call the target data source.

[0075] When the data source calling mode of the target data source is on-demand calling, when receiving the text to be answered, it can be determined whether the text to be answered triggers key information. If so, the target data source can be called to determine the reply text.

[0076] It should be noted that if the target data source call method is not configured, the corresponding data source call method can be automatically set by default. Users can change the call method based on their own needs during actual application.

[0077] The technical solution of the embodiment of the present disclosure is to display a scenario creation page in response to the user's first operation for creating an application scenario, and further, based on the editing operation on the scenario creation page, construct the scenario association information of the target scenario, and then, in response to the second operation, display at least one data source to be selected, and associate the triggered data source to be selected with the target scenario as the target data source to create the target scenario, and finally, in response to receiving the text to be answered in the target scenario, determine the reply text from the target data source associated with the target scenario, so as to solve the problems in the related art that the reply text can only be determined from the full amount of data pre-stored in the system, resulting in low reply efficiency and accuracy, and low matching and correlation between the reply text and the text to be answered, and realize the effect of custom creation of personalized application scenarios and custom configuration of the application scenarios, thereby improving the adaptability between the question and answer text input by the user, the application scenario and the data source, and improving the accuracy of the reply text.

[0078] Figure 4 is a flow chart of an information interaction method provided by an embodiment of the present disclosure. The technical solution of this embodiment is based on the above embodiment, and displays a conversation interface, and based on the first operation of the first preset control included in the conversation interface, displays a scene creation page. Furthermore, based on the editing operation of the scene basic setting control and its associated associated controls, the scene association information of the target scene is created, and based on the second operation of the knowledge selection control, at least one data source to be selected is displayed. Thus, the data source to be selected that triggers the selection can be associated with the target scene as the target data source. For the specific implementation method, please refer to the description of this embodiment. Among them, the technical features that are the same or similar to those of the above embodiment are not repeated here.

[0079] As shown in FIG4 , the method of this embodiment may specifically include:

[0080] S210: Display a conversation interface; wherein the conversation interface includes a first preset control.

[0081] In this embodiment, the conversation interface can be an interactive portal for information exchange. The conversation interface can include conversation information between at least two parties. Optionally, one of the two parties included in the conversation interface can be a user, and the other can be an artificial intelligence robot. The first preset control is used to trigger the display of a scenario creation page in the conversation interface. Optionally, the conversation interface is a conversation interface with an intelligent assistant. The intelligent assistant can be understood as a program that uses artificial intelligence technology to enable conversations with users.

[0082] In actual applications, in application software supporting information interaction, a conversational interface capable of executing AI responses can be displayed based on the corresponding terminal display interface. Furthermore, the conversational interface includes a first preset control for triggering the display of a scenario creation page within the conversational interface. For example, Figure 5 illustrates a conversational interface 50. As shown in Figure 5, conversational interface 50 may include a text edit box 51 and a conversation display page 52. The conversation display page may include conversation information between subject A and the AI ​​assistant, and the conversational interface may also include a first preset control.

[0083] S220. Based on the first operation on the first preset control, display a scene creation page, wherein the scene creation page includes a first display area and a second display area, the first display area includes multiple information switching controls, and the second display area is used to display associated controls associated with the information switching controls.

[0084] The first operation may be a selection trigger operation.

[0085] In actual applications, when a first operation on a first preset control is detected, the first operation can be responded to and a scenario creation page can be displayed in the conversation interface. The displayed scenario creation page can include a first display area and a second display area. When the user triggers the information switching control included in the first display area, the associated controls associated with the corresponding information switching control can be displayed in the second display area. Furthermore, the user can edit the associated controls displayed in the second display area to determine the associated information corresponding to the corresponding information switching control. For example, Figure 2 is a schematic diagram of the scenario creation page.

[0086] S230: When the information switching control is a scene-based setting control, edit corresponding text content for at least one associated control.

[0087] In this embodiment, the scene basic setting control can be understood as a control associated with the scene basic setting information. The associated control is the basic setting control associated with the scene basic setting control. The associated control may include a variety of controls associated with the setting scene associated information, optionally including the scene name, scene setting, model usage type, default plug-in, and opening remarks, etc. It should be noted that based on the different types of scene associated information corresponding to the associated control, the control form of the associated control also includes multiple, optionally including a text edit box form and / or a selection box form, etc. The text content is the content entered by the user, or the content selected by the user.

[0088] In actual applications, when a trigger operation is detected for a scene-based setting control included in the first display area, at least one associated control corresponding to the scene-based setting control can be displayed in the second display area. Furthermore, the corresponding text content of the at least one associated control can be edited based on the scene setting requirements.

[0089] For example, FIG6 is a schematic diagram of a scene creation page under a scene basic setting control in which the information switching control is a scene basic setting control. As shown in FIG6 , when a trigger operation of the mouse cursor (the arrow in the figure) on the scene basic setting control is detected, the control state of the scene basic setting control in the first display area is selected. The associated controls displayed in the second display area may include a scene name, scene setting, model usage type, default plug-in, and opening remarks. Among them, "XXX Assistant" can be entered in the scene name; and the scene description information of the target scene can be entered in the scene setting. The associated control corresponding to the model usage type can be a selection control. When a trigger operation for the control is detected, at least one model usage type to be selected can be displayed in the preset area corresponding to the control. The user can select from at least one model usage type to be selected through the trigger operation, and the model usage type to be selected that is triggered is displayed in the associated control. The "Enterprise Custom Model" shown in FIG6 is the model usage type to be selected that is triggered. The associated control corresponding to the opening remarks can be a text editing box, in which the user can enter the opening remarks information. The opening remarks information can include the scene name, such as, "Hello, under the topic [XXX Assistant], you can ask me questions about XXX, XXX, etc."

[0090] S240: In response to the target operation, construct scene association information of the target scene based on the text content of the associated control.

[0091] In this embodiment, the target operation may be a create confirmation operation. In actual applications, a "Create" control and a "Cancel" control may be pre-set on the scene setting page. When a trigger operation for the "Create" control is detected, the target operation is detected. The scene-related information includes at least one of a scene name, a scene description, a model usage type, and opening remarks.

[0092] Furthermore, in response to the target operation, the text content corresponding to each associated control in the second display area is obtained, and a target scene is created based on the obtained text content, and scene association information corresponding to the target scene is determined.

[0093] For example, continuing to refer to Figure 6, when the target operation is detected, the scene association information of the target scene created based on the text content of the associated control can be: the scene name of the target scene is "XXX Assistant"; the scene description information is that the model usage type is "Enterprise Custom Model"; the opening remarks information is "Hello, under the topic [XXX Assistant], you can ask me questions about XXX, XXX, etc."

[0094] S250: When the information switching control is a knowledge selection control, in response to a second operation triggering the knowledge selection control, display at least one type of data source in the second display area.

[0095] In this embodiment, after creating the target scenario, the target data source associated with the target scenario can also be determined to provide a reply text query basis for the text to be answered received in the target scenario based on the target data source. The knowledge selection control can be a control associated with the data source selection. The type data source can be understood as the application type of the data source. Optionally, at least one type data source includes an in-domain type data source and an out-of-domain type data source. The in-domain type data source and the out-of-domain type data source include at least one of a database, a question-and-answer robot, a cloud document, and a website. Among them, the in-domain type data source can be understood as a data source inside the application software. The out-of-domain type data source can be understood as a data source of a third-party platform.

[0096] In actual applications, when a trigger operation is detected for a knowledge selection control displayed in the first display area, the second display area can be switched to a page associated with the knowledge selection control. Furthermore, in response to a trigger operation for a data source add control displayed in the second display area, a data source to be selected associated with the target scenario can be added. Upon detecting a trigger operation for a data source add control, it is determined that a second trigger operation has been detected. Furthermore, the trigger operation is responded to, and at least one type of data source is displayed in the second display area.

[0097] For example, FIG7 is a schematic diagram of a scene creation page when the information switching control is a knowledge selection control. As shown in FIG7, when the trigger operation of the mouse cursor (arrow in the figure) on the knowledge switching control is detected, the control state of the knowledge selection control in the first display area is selected. Furthermore, when the trigger operation of the "+ Add data source" control displayed in the second display area is detected, at least one type of data source can be displayed in the second display area, which can include in-domain type data source A, in-domain type data source B and in-domain type data source C, and also include out-of-domain type data source A, out-of-domain type data source B and out-of-domain type data source C.

[0098] S260: Based on a triggering operation on at least one type of data source, display a data source selection page including at least one data source to be selected, and associate the triggered data source to be selected as a target data source with a target scenario to create a target scenario.

[0099] The data source selection page may be a page including at least one data source to be selected, and the at least one data source is associated with a data source of the type triggered by the selection.

[0100] In actual applications, upon detecting a trigger operation for at least one type of data source displayed in the second display area, a response can be performed to the trigger operation, and at least one data source to be selected corresponding to the type of data source selected as the trigger is determined. The determined data sources to be selected can include data sources with access permissions and / or data sources without access permissions. Furthermore, to facilitate user operation and enable the user to determine whether they have access permissions to a data source based on the display of the data source on the page, at least one data source to be selected with access permissions can be displayed based on the data source selection page.

[0101] Furthermore, a selection can be made from at least one of the displayed data sources to be selected through a trigger operation. When a selection trigger operation for any data source to be selected is detected, the data source to be selected that is triggered can be used as the target data source, and an association relationship between the target data source and the target scene can be established. For example, FIG8 is a schematic diagram of a data source selection page. As shown in FIG8 , when a trigger operation for an intra-domain type data source A is detected, a data source selection page corresponding to the intra-domain type data source A can be displayed. The page can include four data sources of the intra-domain type data source A, namely, data source a to be selected, data source b to be selected, data source c to be selected, and data source d to be selected. When a selection trigger operation for data source a to be selected and data source b to be selected is detected, data source a to be selected and data source b to be selected can be used as data sources to be selected that are triggered, and associated with the target scene.

[0102] It should be noted that if at least one of the data sources displayed on the data source selection page does not meet the user's data source configuration requirements, you can perform an operation to add a data source. Furthermore, when the operation to add a data source is detected, the user is redirected to the data source search page, which can be displayed in a new tab or in the browser. Furthermore, based on the edit operation on the data source search page, the newly added data source is retrieved. Furthermore, after returning to the data source selection page, the newly added data source is displayed on the page as a data source to be selected.

[0103] In actual applications, after determining the target data source associated with the target scene, the target scene can be determined to be created. A target scene entry control can be pre-set so that when a trigger operation for the control is detected, it can be determined that the target scene has been entered. Then, when a text to be answered is received in the target scene, the target data source associated with the target scene can be called, and the reply text corresponding to the text to be answered can be determined from the target data source. In this embodiment, there are multiple ways to enter the target scene. Optionally, after the target scene is created, it also includes: displaying a control for entering the scene display interface at a preset position in the conversation interface.

[0104] The preset position may be any position in the conversation interface, and optionally, may be above the dialog edit box in the conversation interface. The control for entering the scene display interface may be a control for displaying at least one pre-created target scene after being triggered.

[0105] In actual applications, after detecting that the target scene has been created, the created scene associated with the user can be obtained. To enable users to quickly locate their created personalized scene, a control for entering the scene display interface can be displayed in the conversation interface. Furthermore, a trigger operation can be input into this control to display the created scene associated with the user.

[0106] S270 : In response to receiving a text to be answered in a target scenario, determining a reply text from a target data source associated with the target scenario.

[0107] The technical solution of the embodiment of the present disclosure is to display a conversation interface; wherein the conversation interface includes a first preset control, and then, based on a first operation on the first preset control, display a scene creation page, wherein the scene creation page includes a first display area and a second display area, the first display area includes a plurality of information switching controls, and the second display area is used to display associated controls associated with the information switching control, and then, in the case where the information switching control is a scene-based setting control, edit corresponding text content for at least one associated control, and then, in response to a target operation, construct scene-related information of the target scene based on the text content of the associated control, and then, in the case where the information switching control is a knowledge selection control, respond In response to the second operation of triggering the knowledge selection control, at least one type of data source is displayed in the second display area. Afterwards, based on the triggering operation of at least one type of data source, a data source selection page including at least one data source to be selected is displayed, and the data source to be selected that is triggered is associated with the target scenario as the target data source to create a target scenario. Finally, in response to receiving the text to be answered under the target scenario, the reply text is determined from the target data source associated with the target scenario, thereby realizing the effect of customizing the creation of personalized application scenarios and customizing the application scenarios, thereby improving the adaptability between the question and answer text input by the user, the application scenario and the data source, and improving the accuracy of the reply text.

[0108] Figure 9 is a flow chart illustrating an information interaction method provided by an embodiment of the present disclosure. The technical solution of this embodiment, based on the above-described embodiments, displays a conversation interface. When a triggering operation is detected for a scene display control within the conversation interface, at least one created scene is displayed. Based on the triggering operation for at least one created scene, the conversation interface displays the opening remarks for the triggered scene. For detailed implementation details, please refer to the description of this embodiment. Technical features identical or similar to those of the above-described embodiments are not further detailed here.

[0109] As shown in FIG9 , the method of this embodiment may specifically include:

[0110] S310: In response to a user's first operation for creating an application scenario, display a scenario creation page.

[0111] S320: Construct scene association information of the target scene based on the editing operation on the scene creation page.

[0112] S330: In response to the second operation, display at least one data source to be selected, and associate the data source to be selected that triggers the selection as a target data source with a target scene to create a target scene.

[0113] S340 : In response to receiving a text to be answered in a target scenario, determining a reply text from a target data source associated with the target scenario.

[0114] S350: Display the conversation interface.

[0115] In actual applications, in application software that supports information interaction functions, a conversation interface that can perform artificial intelligence answers can be displayed based on the corresponding terminal display interface.

[0116] S360: When a scene display control in the triggering session interface is detected, at least one created scene is displayed.

[0117] In this embodiment, the conversation interface may include a scene display control for triggering the display of a scene display page in the conversation interface. The created scene may include a target scene created based on user needs, and may also include a default scene pre-created by the system.

[0118] In actual applications, when a trigger operation is detected for a scene display control displayed in the conversation interface, the target scene associated with the user and / or the system's pre-created default scene can be determined and treated as the created scene. The created scene can then be displayed. It should be noted that the display method for the created scene may include at least one of the following: optionally, displaying at least one created scene includes: displaying a scene display pop-up window corresponding to the scene display control in the upper layer of the conversation interface; and displaying the scene name of at least one created scene and the data source abbreviation of the portion of the data source corresponding to the created scene in the scene display pop-up window.

[0119] The scene display pop-up window can be a page that summarizes the scene, including the created scene. Displaying the scene display pop-up window above the conversation interface can be understood as displaying the scene display pop-up window as a separate floating layer floating above the conversation interface. The scene display pop-up window can be displayed anywhere in the conversation interface, optionally above, below, to the left, or to the right of the scene display control. A partial data source can be understood as at least one data source from all data sources corresponding to the created scene. The data source abbreviation is a name composed of partial characters from the data source name.

[0120] In actual use, when a trigger action is detected for a scene display control, a pop-up window corresponding to the scene display control is displayed on the upper layer of the conversation interface. Furthermore, the pop-up window can display the name of at least one created scene and the abbreviations of the data sources corresponding to each created scene. This setting allows users to clearly browse the currently created scenes and the data sources associated with each created scene, helping them quickly locate the desired target scene and improving the user experience.

[0121] For example, FIG10 is a schematic diagram of a scene display pop-up window displayed in a conversation interface. As shown in FIG10 , when a trigger operation is detected by inputting a mouse cursor (arrow in the figure) on a scene display control, a scene display pop-up window 100 is displayed above the scene display control and in the upper layer of the conversation interface. Furthermore, the scene display pop-up window may display the name of at least one created scene, which may include created scene A, created scene B, and created scene C. At the same time, the data source abbreviations of the partial data sources corresponding to each created scene may also be displayed: the partial data sources corresponding to created scene A may include data source 1, data source 2, and data source 3; the partial data sources corresponding to created scene B may include data source 4, data source 5, data source 6, and data source 7; and the partial data sources corresponding to created scene C may include data source 8, data source 9, and data source 10.

[0122] S370: Based on the triggering operation of at least one created scene, display the opening remarks of the triggered scene on the conversation interface.

[0123] The opening remarks information is information in the scene-related information.

[0124] In actual applications, at least one created scene displayed in the scene display pop-up window can be pre-set to a triggerable selection state. Then, upon detecting a trigger operation for at least one created scene, the created scene that triggered the selection can be treated as the triggered scene, and scene association information corresponding to the triggered scene can be determined, and the opening remarks information in the scene association information can be obtained. The opening remarks information of the triggered scene can then be displayed in the conversation interface.

[0125] In practical applications, the conversation interface may include a text edit box where the user can edit text. Upon detecting a trigger action on a text send control, the text in the text edit box is sent to the conversation interface as the pending reply. Furthermore, upon receiving the pending reply, the conversation interface determines the corresponding reply text based on the data source associated with the triggered scenario.

[0126] Based on the above embodiments, the method further includes: when a text to be answered is sent on the conversation interface, a reply text is determined according to a preset data source calling method.

[0127] The reply text is the response text that matches the text to be answered. The reply text can include various types of text information, optionally including at least one of text content, schematic diagrams, and the predicted question and answer sentence to be selected. The text content can be a text reply. The schematic diagram can be a picture reply. The predicted question and answer sentence to be selected can be used to indicate the user's question and answer intent based on analysis of the text to be answered.

[0128] In actual applications, when a text to be answered is sent to the conversation interface, the associated data source can be called according to a pre-set data source calling method to determine the corresponding reply text based on the data source. This configuration has the advantages of increasing the intelligence of the AI ​​answering system and providing a wider range of data source calling methods to meet the needs of users in different situations. In this embodiment, the data source calling methods include automatic calling and on-demand calling. Different data source calling methods result in different corresponding reply text determination methods.

[0129] Optionally, if the calling mode is an automatic calling mode, a reply text corresponding to the text to be answered is determined from all data sources associated with the triggered scenario.

[0130] In actual applications, if the data source call method is automatic, when receiving the text to be answered, all data sources associated with the triggered scenario can be directly called. Based on the text to be answered, the data in all called data sources can be queried, and the reply text corresponding to the text to be answered can be determined from all data sources. The benefit of this setting is that it improves the efficiency of reply text and enhances the intelligence of the AI ​​answering system.

[0131] Optionally, if the calling method is on-demand calling, the text to be answered is analyzed and processed to determine the reply text corresponding to the text to be answered from all data sources associated with the triggering scenario when triggering key information or triggering the to-be-answered template.

[0132] The trigger key information may be key information for triggering the call of a data source associated with the triggered scenario, and the trigger unanswered template may be template information for triggering the call of a data source associated with the triggered scenario.

[0133] In actual applications, if the data call method is on-demand, then when the text to be answered is received, the text to be answered can be analyzed and processed to determine whether the text to be answered includes triggering key information, or to determine whether the text to be answered is text information edited based on a triggering template to be answered. Furthermore, when the triggering key information or the triggering template to be answered is detected, the triggering call data source can be determined. Furthermore, all data sources associated with the triggered scenario can be called, and the data in all called data sources can be queried based on the text to be answered, and the reply text corresponding to the text to be answered can be determined from all data sources.

[0134] The technical solution of the embodiment of the present disclosure is to display a scenario creation page in response to a first operation of a user for creating an application scenario, and further, based on the editing operation on the scenario creation page, construct scene association information of the target scene, and then, in response to a second operation, display at least one data source to be selected, and associate the data source to be selected that triggers selection with the target scene as the target data source to create the target scene, and then, in response to receiving a text to be answered in the target scene, determine the reply text from the target data source associated with the target scene, and display the conversation interface. When it is detected that a scene display control in the conversation interface is triggered, at least one created scene is displayed, and based on the triggering operation of at least one created scene, the opening remarks information of the triggered scene is displayed in the conversation interface, thereby achieving the effect that the created scene associated with the user can be displayed in the conversation interface, and the target scene can be entered through the conversation interface.

[0135] FIG11 is a schematic structural diagram of an information interaction device provided by an embodiment of the present disclosure. As shown in FIG11 , the device includes: a page display module 410 , an associated information construction module 420 , a data source display module 430 and a reply text determination module 440 .

[0136] Among them, the page display module 410 is used to display the scenario creation page in response to the user's first operation for creating an application scenario; the association information construction module 420 is used to construct the scenario association information of the target scene based on the editing operation on the scenario creation page; the data source display module 430 is used to display at least one data source to be selected in response to the second operation, and associate the triggered selected data source with the target scene as the target data source to create the target scene; the reply text determination module 440 is used to determine the reply text from the target data source associated with the target scene in response to receiving the text to be answered under the target scenario.

[0137] Based on the above technical solutions, optionally, the page display module 410 includes: a conversation interface display unit and a page display unit.

[0138] A conversation interface display unit, configured to display a conversation interface; wherein the conversation interface includes a first preset control, the first preset control being configured to trigger display of the scenario creation page in the conversation interface;

[0139] A page display unit is used to display the scene creation page based on the first operation on the first preset control.

[0140] Based on the above technical solutions, optionally, the scene creation page includes a first display area and a second display area, the first display area includes multiple information switching controls, and the second display area is used to display associated controls associated with the information switching controls.

[0141] Based on the above technical solutions, optionally, the information switching control is a scene basic setting control, and the second display area displays associated controls associated with the scene basic setting control. The associated information construction module 420 includes: a text content editing unit and an associated information construction unit.

[0142] A text content editing unit, configured to edit corresponding text content for at least one associated control;

[0143] The association information construction unit is used to construct the scene association information of the target scene based on the text content of the association control in response to the target operation.

[0144] Based on the above technical solutions, optionally, the scene association information includes at least one of a scene name, scene description information, a model usage type, and opening remarks information.

[0145] Based on the above technical solutions, optionally, the information switching control is a knowledge selection control, and the second display area is used to display at least one data source to be selected corresponding to the knowledge selection control. The data source display module 430 includes: a type data source display unit and a page display unit.

[0146] a data source type display unit, configured to display at least one data source type in the second display area in response to a second operation triggering the knowledge selection control;

[0147] The page display unit is configured to display a data source selection page including at least one data source to be selected based on a triggering operation on the at least one type of data source.

[0148] Based on the above technical solutions, optionally, the at least one type of data source includes an in-domain type data source and an out-of-domain type data source, and the in-domain type data source and the out-of-domain type data source include at least one of a database, a question-and-answer robot, a cloud document, and a website.

[0149] On the basis of the above technical solutions, optionally, the device further includes: a calling mode configuration module.

[0150] The calling mode configuration module is used to configure the target data source calling mode for the target scenario after determining the target data source associated with the target scenario; wherein the data source calling mode includes an automatic calling mode or an on-demand calling mode.

[0151] On the basis of the above technical solutions, optionally, the on-demand calling method is determined based on whether the text to be answered triggers key information, or triggers the calling method of the template to be answered.

[0152] On the basis of the above technical solutions, optionally, the device further includes: a conversation interface display module, a scene display module and an opening remarks information display module.

[0153] A conversation interface display module, used to display the conversation interface;

[0154] A scene display module, configured to display at least one created scene when detecting that a scene display control in the conversation interface is triggered;

[0155] An opening remarks information display module is used to display the opening remarks information of the triggered scene on the conversation interface based on the triggering operation of the at least one created scene; wherein the opening remarks information is the information in the scene association information.

[0156] On the basis of the above technical solutions, optionally, the scene display module includes: a pop-up display unit and a scene name display unit.

[0157] A pop-up window display unit, configured to display a scene display pop-up window corresponding to the scene display control on the upper layer of the conversation interface;

[0158] The scene name display unit is used to display the scene name of at least one created scene and the data source abbreviation of part of the data source corresponding to the created scene in the scene display pop-up window.

[0159] On the basis of the above technical solutions, optionally, the device further includes: a reply text determination module.

[0160] The reply text determination module is used to determine the reply text according to a preset data source calling method when sending a text to be answered on the conversation interface.

[0161] On the basis of the above technical solutions, optionally, the reply text determination module includes: a first reply text determination unit and a second reply text determination unit.

[0162] a first reply text determining unit, configured to determine, if the calling mode is an automatic calling mode, a reply text corresponding to the text to be answered from all data sources associated with the triggering scenario;

[0163] The second reply text determination unit is used to analyze and process the text to be answered if the calling method is an on-demand calling method, so as to determine the reply text corresponding to the text to be answered from all data sources associated with the triggering scenario when triggering key information or triggering a template to be answered is detected.

[0164] On the basis of the above-mentioned technical solutions, optionally, the reply text includes at least one of text content, schematic diagram and predicted question and answer sentence to be selected.

[0165] Based on the above technical solutions, optionally, the conversation interface is a dialogue interface with an intelligent assistant.

[0166] The technical solution of the embodiment of the present disclosure is to display a scenario creation page in response to the user's first operation for creating an application scenario, and further, based on the editing operation on the scenario creation page, construct the scenario association information of the target scenario, and then, in response to the second operation, display at least one data source to be selected, and associate the triggered data source to be selected with the target scenario as the target data source to create the target scenario, and finally, in response to receiving the text to be answered in the target scenario, determine the reply text from the target data source associated with the target scenario, so as to solve the problems in the related art that the reply text can only be determined from the full amount of data pre-stored in the system, resulting in low reply efficiency and accuracy, and low matching and correlation between the reply text and the text to be answered, and realize the effect of custom creation of personalized application scenarios and custom configuration of the application scenarios, thereby improving the adaptability between the question and answer text input by the user, the application scenario and the data source, and improving the accuracy of the reply text.

[0167] The information interaction device provided in the embodiments of the present disclosure can execute the information interaction method provided in any embodiment of the present disclosure, and has the corresponding functional modules and beneficial effects of the execution method.

[0168] It is worth noting that the various units and modules included in the above-mentioned device are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the protection scope of the embodiments of the present disclosure.

[0169] Figure 12 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present disclosure. Referring to Figure 12 below, it shows a schematic diagram of the structure of an electronic device (such as the terminal device or server in Figure 12) 500 suitable for implementing an embodiment of the present disclosure. The terminal device in the embodiment of the present disclosure may include but is not limited to mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. The electronic device shown in Figure 12 is only an example and should not bring any limitations to the functions and scope of use of the embodiments of the present disclosure.

[0170] As shown in FIG12 , the electronic device 500 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage device 508 into a random access memory (RAM) 503. Various programs and data required for the operation of the electronic device 500 are also stored in the RAM 503. The processing device 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An edit / output (I / O) interface 505 is also connected to the bus 504.

[0171] Typically, the following devices may be connected to the I / O interface 505: an input device 506 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 507 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 508 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 509. The communication device 509 may allow the electronic device 500 to communicate with other devices wirelessly or by wire to exchange data. Although FIG12 shows the electronic device 500 with various devices, it should be understood that it is not required to implement or have all of the devices shown. More or fewer devices may be implemented or have alternatively.

[0172] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 509, or installed from the storage device 508, or installed from the ROM 502. When the computer program is executed by the processing device 501, the above-mentioned functions defined in the method of the embodiment of the present disclosure are performed.

[0173] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0174] The electronic device provided by the embodiment of the present disclosure and the information interaction method provided by the above embodiment belong to the same inventive concept. For technical details not fully described in this embodiment, please refer to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0175] An embodiment of the present disclosure provides a computer storage medium on which a computer program is stored. When the program is executed by a processor, the information interaction method provided by the above embodiment is implemented.

[0176] It should be noted that the computer-readable medium mentioned above in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device, or component. In the present disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to wires, optical cables, RF (radio frequency), etc., or any suitable combination thereof.

[0177] In some embodiments, the client and server can communicate using any currently known or later developed network protocol, such as HTTP (Hypertext Transfer Protocol), and can be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or later developed network.

[0178] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0179] The above-mentioned computer-readable medium carries one or more programs. When the above-mentioned one or more programs are executed by the electronic device, the electronic device: displays a scenario creation page in response to the user's first operation for creating an application scenario; constructs scenario association information of the target scene based on the editing operation on the scenario creation page; displays at least one data source to be selected in response to the second operation, and associates the triggered selected data source with the target scene as the target data source to create the target scene; and determines the reply text from the target data source associated with the target scene in response to receiving the text to be answered under the target scene.

[0180] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages, or a combination thereof, including, but not limited to, object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on the remote computer or server. In cases involving 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).

[0181] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the module, program segment, or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0182] The units involved in the embodiments described in this disclosure may be implemented in software or hardware. In some cases, the name of a unit does not limit the unit itself. For example, the first acquisition unit may also be described as a "unit for acquiring at least two Internet Protocol addresses."

[0183] The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, and without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chip (SOCs), complex programmable logic devices (CPLDs), and the like.

[0184] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0185] The above description is merely a preferred embodiment of the present disclosure and an illustration of the technical principles employed. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by the specific combination of the above-mentioned technical features, but also includes other technical solutions formed by any combination of the above-mentioned technical features or their equivalents without departing from the above-mentioned disclosed concepts. For example, a technical solution formed by replacing the above-mentioned features with (but not limited to) technical features with similar functions disclosed in this disclosure.

[0186] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details have been included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0187] Although the subject matter has been described in language specific to structural features and / or methodological logical acts, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are merely example forms of implementing the claims.

Claims

1. An information interaction method, comprising: In response to the user's first operation for creating an application scenario, the scene creation page is displayed; Based on the editing operation of creating pages in the scene, the scene association information of the target scene is constructed; In response to the second operation, at least one data source to be selected is displayed and the triggered selection data source to be selected is associated with the target scene as a target data source to create the target scene; Responsive to receiving the text to be answered in the target scenario, the reply text is determined from the target data source associated with the target scenario.

2. The method of claim 1, wherein the display of a scene creation page in response to a first operation of creating an application scenario, including: Displaying a session interface; wherein the session interface includes a first preset control, the first preset control is used to trigger displaying the scene creation page in the session interface; Based on a first operation of the first preset control, the scene creation page is displayed.

3. The method according to claim 1 or 2, wherein the scene creation page includes a first display area and a second display area, the first display area includes a plurality of information switching controls, and the second display area is used to display associated controls associated with the information switching controls.

4. The method according to claim 3, wherein the information switching control is a scene basic setting control, the second display area displays an associated control associated with the scene basic setting control, and the scene association information of the target scene is constructed based on the editing operation on the scene creation page, comprising: Edit the corresponding text content for at least one associated control; In response to the target operation, scene association information of the target scene is constructed based on the text content of the associated control.

5. The method of claim 4, wherein the scene association information includes at least one of a scene name, scene description information, model usage type, and opening statement information.

6. The method according to claim 3, wherein the information switching control is a knowledge selection control, the second display area is used to display at least one data source to be selected corresponding to the knowledge selection control, and the displaying of at least one data source to be selected in response to the second operation comprises: In response to triggering the second operation of the knowledge selection control, at least one type of data source is displayed in the second display area; Based on a triggering operation on the at least one type of data source, a data source selection page including at least one data source to be selected is displayed.

7. A method according to claim 1 or 6, wherein the at least one type of data source includes an in-domain type data source and an out-of-domain type data source, and the in-domain type data source and the out-of-domain type data source include at least one of a database, a question-and-answer robot, a cloud document, and a website.

8. The method of claim 1, wherein after determining the target data source associated with the target scenario, the method further comprises: Configure the target data source calling method for the target scenario; Among them, the data source calling method includes an automatic calling method or an on-demand calling method.

9. The method according to claim 8, wherein the on-demand calling mode is determined based on whether the text to be answered triggers key information, or triggers the calling mode of the template to be answered.

10. The method according to claim 1, further comprising: Display the conversation interface; When it is detected that a scene display control in the conversation interface is triggered, displaying at least one created scene; Based on the triggering operation of the at least one created scene, displaying the opening remarks information of the triggered scene on the conversation interface; The opening remarks information is information in the scene association information.

11. The method according to claim 10, wherein displaying at least one created scene comprises: Displaying a scene display pop-up window corresponding to the scene display control on the upper layer of the conversation interface; The scene name of at least one created scene and the abbreviation of the data source of part of the data source corresponding to the created scene are displayed in the scene display pop-up window.

12. The method according to claim 10, further comprising: When a text to be answered is sent in the conversation interface, the reply text is determined according to a preset data source calling method.

13. The method according to claim 12, wherein determining the reply text according to a preset data source calling method comprises: If the calling mode is an automatic calling mode, determining a reply text corresponding to the text to be answered from all data sources associated with the triggering scene; If the calling method is an on-demand calling method, the text to be answered is analyzed and processed so that when triggering key information or triggering a template to be answered is detected, a reply text corresponding to the text to be answered is determined from all data sources associated with the triggering scenario.

14. The method according to claim 12, wherein the reply text comprises at least one of text content, a schematic diagram, and a predicted question and answer sentence to be selected.

15. The method according to claim 2, wherein the conversational interface is a dialogue interface with an intelligent assistant.

16. An information interaction device, comprising: A page display module, configured to display a scenario creation page in response to a first operation of a user for creating an application scenario; An associated information building module, used to build scene associated information of a target scene based on an editing operation on the scene creation page; a data source display module, configured to display at least one data source to be selected in response to a second operation, and associate the data source to be selected that triggers the selection with the target scene as a target data source to create the target scene; The reply text determination module is used to determine the reply text from a target data source associated with the target scenario in response to receiving the text to be answered in the target scenario.

17. An electronic device, comprising: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the information interaction method as described in any one of claims 1-15.

18. A storage medium comprising computer executable instructions, wherein the computer executable instructions are used to execute the information interaction method according to any one of claims 1 to 15 when executed by a computer processor.

Images