Content display method and device, readable medium, electronic equipment and program product

Abstract

The invention discloses a content display method and device, a readable medium, electronic equipment and a program product. The content display method comprises the following steps: displaying an intelligent interaction page; in the interaction process with the intelligent object, in response to a configuration operation on a machine learning model associated with the intelligent object, determining a target machine learning model associated with the intelligent object according to the configuration operation; and in response to a content input operation on the intelligent interaction page, determining target input content corresponding to the content input operation, and displaying reply content generated by the target machine learning model according to the target input content. According to the method, the target machine learning model associated with the intelligent object can be configured anytime and anywhere in the interaction process with the intelligent object, for example, different machine learning models can be switched to meet different model use requirements of a user, and the use experience of the user is improved.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular, to a content display method, device, readable medium, electronic device, and program product. Background Art

[0002] With the development of machine learning model technology, more and more intelligent products based on machine learning models have emerged. For example, intelligent products based on the Wenshengwen model can create texts according to user instructions, and intelligent products based on the Wenshengtu model can generate images according to user instructions, and so on.

[0003] In the related art, in the process of interaction between smart products and users, a single machine learning model is usually used to output corresponding reply content based on the user's input content, which cannot meet the user's different model usage requirements and results in a poor user experience. Summary of the invention

[0004] This summary is provided to introduce concepts in a brief form that will be described in detail in the detailed description below. This summary is not intended to identify key features or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0005] In a first aspect, the present disclosure provides a content display method, the content display method comprising: Displaying a smart interaction page, wherein the smart interaction page is used for a user to interact with a smart object, and the smart object is used to generate reply content according to the user's input content through an associated machine learning model; In an interaction process with the smart object, in response to a configuration operation on a machine learning model associated with the smart object, determining a target machine learning model associated with the smart object according to the configuration operation; In response to a content input operation on the intelligent interaction page, the target input content corresponding to the content input operation is determined, and the reply content generated by the target machine learning model based on the target input content is displayed.

[0006] In a second aspect, the present disclosure provides a content display device, the content display device comprising: A first display module, configured to display an intelligent interaction page, wherein the intelligent interaction page is configured to allow a user to interact with an intelligent object, and the intelligent object is configured to generate reply content according to input content of the user through an associated machine learning model; a determination module for determining, in response to a configuration operation on a machine learning model associated with the smart object during interaction with the smart object, a target machine learning model associated with the smart object according to the configuration operation; The second display module is used to respond to the content input operation on the intelligent interaction page, determine the target input content corresponding to the content input operation, and display the reply content generated by the target machine learning model according to the target input content.

[0007] In a third aspect, the present disclosure provides a computer-readable medium having a computer program stored thereon, which implements the steps of the method described in the first aspect when the program is executed by a processing device.

[0008] In a fourth aspect, the present disclosure provides an electronic device, including: a storage device having a computer program stored thereon; A processing device is used to execute the computer program in the storage device to implement the steps of the method in the first aspect.

[0009] In a fifth aspect, the present disclosure provides a computer program product, comprising a computer program, which implements the steps of the method described in the first aspect when executed by a processor.

[0010] Through the above technical solution, during the interaction with the smart object, the target machine learning model associated with the smart object can be determined by configuring the machine learning model associated with the smart object, and then the corresponding target input content can be determined in response to the content input operation on the smart interaction page, and the reply content generated by the target machine learning model according to the target input content can be displayed. With this method, the target machine learning model associated with the smart object can be configured anytime and anywhere during the interaction with the smart object. For example, different machine learning models can be switched to meet the different model usage requirements of users, thereby improving the user experience.

[0011] Other features and advantages of the present disclosure will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The above and other features, advantages and aspects of the 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 the originals and elements are not necessarily drawn to scale. In the drawings: Figure 1 is a schematic diagram of an intelligent interactive page according to an exemplary embodiment of the present disclosure; Figure 2is a flowchart of a content display method according to an exemplary embodiment of the present disclosure; Figure 3 is a schematic diagram of a model selection page according to an exemplary embodiment of the present disclosure; Figure 4 is a schematic diagram of a smart interaction page for single-model experience according to an exemplary embodiment of the present disclosure; Figure 5 is a schematic diagram of a multi-model comparison intelligent interaction page according to an exemplary embodiment of the present disclosure; Figure 6 is a schematic diagram of a multi-model comparison intelligent interaction page according to an exemplary embodiment of the present disclosure; Figure 7 is a schematic diagram of a multi-model comparison intelligent interaction page according to an exemplary embodiment of the present disclosure; Figure 8 is a schematic diagram of a process of synchronizing historical interaction content according to an exemplary embodiment of the present disclosure; Fig. 9 is a schematic diagram of a process of deleting or adding a model according to an exemplary embodiment of the present disclosure; Fig.10 is a schematic diagram of a process of configuring model parameters according to an exemplary embodiment of the present disclosure; Fig.11 is a structural block diagram of a content display device according to an exemplary embodiment of the present disclosure; Fig.12 It is a schematic structural diagram of an electronic device according to an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0013] Embodiments of the present disclosure will be described in more detail below 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 being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0014] 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.

[0015] The term "including" and its variations used herein are open inclusions, 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"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0016] It should be noted that the concepts such as "first" and "second" mentioned in the present 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.

[0017] It should be noted that the modifications of "one" and "plurality" 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, it should be understood as "one or more".

[0018] 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.

[0019] It is understandable that before using the technical solutions disclosed in the embodiments of the present disclosure, the types, scope of use, usage scenarios, etc. of the personal information involved in the present 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.

[0020] For example, in response to receiving an active request from a user, a prompt message is sent to the user to clearly prompt the user that the operation requested to be performed will require obtaining and using the user's personal information. Thus, the user can autonomously choose whether to provide personal information to software or hardware such as an electronic device, application, server, or storage medium that performs the operation of the technical solution of the present disclosure according to the prompt message.

[0021] As an optional but non-limiting implementation, in response to receiving an active request from the user, 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. In addition, the pop-up window may also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0022] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation of the present disclosure. Other methods that meet the relevant laws and regulations may also be applied to the implementation of the present disclosure.

[0023] At the same time, 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) shall comply with the requirements of relevant laws, regulations and relevant provisions.

[0024] Smart products connected to different machine learning models can provide different functions to users. For example, smart products based on the text-to-text model can create text according to user instructions, and smart products based on the text-to-image model can generate images according to user instructions, and so on. Figure 1 In the smart interaction page of the smart product shown, users can interact with smart objects on the smart interaction page, and the machine learning model associated with the smart object can output and display corresponding reply content based on the user input content. Since the smart objects corresponding to the same smart interaction page are usually connected to a single machine learning model, it cannot meet the different model usage needs of users, resulting in poor user experience.

[0025] In view of this, the present disclosure provides a content display method, device, readable medium, electronic device and program product to solve the above technical problems.

[0026] The embodiments of the present disclosure are further explained below with reference to the accompanying drawings.

[0027] Figure 2 is a flowchart of a content display method according to an exemplary embodiment of the present disclosure, referring to Figure 2 , the content display method may include the following steps: S201: Displaying the intelligent interaction page.

[0028] Among them, the smart interaction page is used for users to interact with smart objects, and the smart objects are used to generate reply content based on the user's input content through associated machine learning models.

[0029] For example, the machine learning model can be a large language model, or other neural network models, deep learning models, etc., or based on the model function, the machine learning model can be a text-to-text model, a text-to-graph model, a graph-to-graph model, etc., and the present disclosure does not limit this.

[0030] It should be noted that the intelligent interaction page can be an interactive page in an intelligent product that provides model services to users, such as an intelligent product that is connected to a robot customer service, and the intelligent interaction page can be a dialogue interaction page for interacting with the robot customer service. The intelligent interaction page can also be a page of a model service platform where a model manufacturer provides model applications to users. The model service platform can provide a full range of platform functions and services such as model fine-tuning, evaluation, and reasoning, and provide machine learning models of different specifications or functions for users to choose from, creating a model ecosystem, and providing users with simple, intuitive, and comprehensive model experience capabilities. For example, a user can purchase the above-mentioned machine learning model that provides robot customer service functions and connect it to the intelligent product released by the user. The intelligent interaction page can be an interactive page of the model service platform for users to experience different machine learning models. The specific details can be determined based on the actual business scenario, and this disclosure does not limit this.

[0031] It is worth noting that the content display method provided in the embodiments of the present disclosure can be applied to terminal devices such as mobile phones, laptop computers, and tablet computers, and the present disclosure does not limit this.

[0032] S202: During the interaction with the smart object, in response to a configuration operation on a machine learning model associated with the smart object, a target machine learning model associated with the smart object is determined according to the configuration operation.

[0033] It is worth noting that the user can configure the machine learning model associated with the smart object before entering the smart interaction page, and then enter the smart interaction page. The smart object on the smart interaction page defaults to the configured machine learning model. The user can also configure the machine learning model associated with the smart object through the model configuration entry in the smart interaction page after entering the smart interaction page. The present disclosure does not limit this. In addition, during the interaction between the user and the smart object, the machine learning model associated with the smart object can be configured anytime and anywhere, for example, different machine learning models can be switched to compare the use effects of smart objects associated with different machine learning models.

[0034] S203: In response to the content input operation on the intelligent interaction page, determine the target input content corresponding to the content input operation, and display the reply content generated by the target machine learning model according to the target input content.

[0035] By using the above method, the target machine learning model associated with the smart object can be configured anytime and anywhere during the interaction with the smart object. For example, different machine learning models can be switched to meet the different model usage requirements of users, thereby improving the user experience.

[0036] In a possible manner, displaying the smart interaction page includes: displaying a model selection page, the model selection page displays a target interaction entry corresponding to the machine learning model, the target interaction entry is used to trigger the smart interaction page corresponding to the smart object associated with multiple machine learning models; in response to the triggering operation of the target interaction entry, the smart interaction page is displayed. Displaying the reply content generated by the target machine learning model according to the target input content includes: displaying the reply content generated by each machine learning model in the multiple machine learning models according to the target input content.

[0037] For example, taking the above-mentioned model service platform as an example, the model selection page can be a page in the model service platform for users to select models for experience, which can be determined according to actual business scenarios, and the present disclosure does not limit this. Figure 3 As shown, the model selection page can provide one or more interactive entrances corresponding to machine learning models for users to choose. For example, trigger the interactive entrance corresponding to model 1 to enter Figure 4 The smart interaction page shown in the figure shows the response content generated by model 1 based on the user input content, which can be used to experience the use effect of the smart object connected to a single machine learning model. Or trigger the interaction entrance corresponding to model 1 and model 2 to enter the following Figure 5 The smart interaction page shown can compare the usage effects of smart objects connected to different machine learning models by displaying the response content generated by model 1 and model 2 based on user input content in the smart interaction page.

[0038] For example, interactive entrances for comparing different models can be pre-set according to actual business scenarios to shorten the time for users to select models and improve the user experience. For example, an interactive entrance for comparing the model between the text graph model A and the text graph model B is provided, and an interactive entrance for comparing the model between the text graph model A version 1 and the text graph model A version 2 is provided, etc., and the present disclosure does not limit this.

[0039] It is worth noting that the candidate machine learning models can be displayed in a list on the model selection page. In response to the user's selection operation of model 1 in the candidate machine learning models, the following is entered: Figure 4 In the intelligent interaction page shown in FIG. 1 , in response to the user's selection operation of model 1 and model 2 in the candidate machine learning models, the user enters the following Figure 5 Alternatively, the candidate machine learning models can be displayed in a list on the intelligent interaction page for the user to choose from, which can be determined according to the needs and is not limited by the present disclosure.

[0040] In a possible manner, there are multiple target machine learning models, and the reply content generated by the target machine learning model according to the target input content is displayed, including: determining the reply content generated by each target machine learning model according to the target input content, obtaining multiple reply contents, and displaying the multiple reply contents in different areas on the smart interaction page.

[0041] For example, if the user configures multiple target machine learning models, such as Figure 5 As shown, the response content generated by different machine learning models according to the target input content can be displayed in different regions, so that the usage effects of smart objects connected to different machine learning models can be compared.

[0042] In a possible manner, the smart interaction page displays model identifiers corresponding one-to-one to multiple target machine learning models, and multiple reply contents are displayed in different areas on the smart interaction page, including: displaying multiple reply contents in columns or rows respectively on the smart interaction page; or, in response to a triggering operation on a first model identifier on the smart interaction page, displaying first reply content generated by the target machine learning model corresponding to the first model identifier according to target input content on the smart interaction page; in response to a triggering operation on a second model identifier on the smart interaction page, displaying second reply content generated by the target machine learning model corresponding to the second model identifier according to the target input content at a preset position around the first reply content displayed on the smart interaction page.

[0043] For example, multiple reply contents can be displayed in columns, such as Figure 5 The reply content generated by model 1 based on the input content and the reply content generated by model 2 based on the input content can be displayed in left and right areas, or multiple reply contents can be displayed separately in rows. For example, the reply content generated by model 1 based on the input content and the reply content generated by model 2 based on the input content can be displayed in upper and lower areas.

[0044] For example, model identifiers corresponding to multiple target machine learning models may be displayed on the intelligent interaction page, and according to the user's triggering operation on the model identifier, the reply content generated by the corresponding machine learning model based on the input content is displayed. Figure 6 As shown, the user first triggers the model identifier corresponding to model 1, and the reply content generated by model 1 according to the input content is displayed. Then the user triggers the model identifier corresponding to model 2, and the reply content generated by model 2 according to the input content is displayed, and so on. The preset position can be set according to demand, for example, the second reply content is displayed below the first reply content, and the present disclosure does not limit this.

[0045] In addition, after the user triggers the model identifier corresponding to model 1, it can switch to the selected style, and then in response to the user canceling the selection of the model identifier corresponding to model 1, the reply content generated by model 1 according to the input content can be synchronously canceled. The specific settings can be based on needs, and the present disclosure does not impose any restrictions on this.

[0046] In a possible manner, the content display method also includes: displaying model identifiers corresponding one-to-one to multiple target machine learning models at the top of the smart interaction page; or, displaying model identifiers corresponding one-to-one to multiple target machine learning models at the bottom of the smart interaction page; or, displaying an expansion control on the smart interaction page, and displaying model identifiers corresponding one-to-one to multiple target machine learning models in response to a triggering operation on the expansion control.

[0047] For example, the model identifier corresponding to the machine learning model can be intuitively displayed at the top, bottom, and side of the display area, and an expansion control can also be provided for the user to trigger and then expand to display the model identifiers corresponding to multiple machine learning models. The specific settings can be based on needs, and this disclosure does not impose any restrictions on this.

[0048] In a possible manner, there are multiple target machine learning models, and the reply content generated by the target machine learning model based on the target input content is displayed, including: displaying the third reply content generated by the first machine learning model among the multiple target machine learning models based on the target input content; in response to the content switching operation, switching the third reply content to the fourth reply content generated by the second machine learning model among the multiple target machine learning models based on the target input content.

[0049] For example, when the configured target machine learning model includes multiple machine learning models, the reply content generated by one of the machine learning models based on the user input content can be displayed on the smart interaction page, and then in response to the content switching operation, the reply content generated by other machine learning models based on the user input content can be displayed on the smart interaction page, thereby ensuring the display area of ​​the reply content corresponding to each machine learning model and improving the user experience.

[0050] It is worth noting that multiple display modes of reply contents can be preset, and configuration items of display modes can also be provided for configuration according to user needs, and the present disclosure does not limit this. This improves the flexibility of content display, so as to compare the use effects of smart objects connected to different machine learning models.

[0051] In a possible manner, the smart interaction page displays model identifiers corresponding one-to-one to multiple target machine learning models, and in response to a content switching operation, the third reply content is switched to a fourth reply content generated by a second machine learning model among the multiple target machine learning models according to the target input content, including: in response to a trigger operation on the model identifier corresponding to the second machine learning model, the third reply content is switched to the fourth reply content generated by the second machine learning model according to the target input content; or, in response to a content sliding operation on the third reply content, the third reply content is switched to the fourth reply content generated by the second machine learning model according to the target input content.

[0052] For example, Figure 7 In the method 1 shown, in response to the user's triggering operation on the model identifier in the intelligent interaction page, the reply content generated by the machine learning model corresponding to the model identifier according to the user input content can be displayed. Figure 7 The method 2 shown can respond to the user's content sliding operation in the intelligent interaction page, such as sliding the screen left and right to switch to display the reply content generated by different machine learning models based on the user input content. The specific settings can be made according to the needs, and the present disclosure does not limit this. This makes it easier for users to browse the reply content generated by different machine learning models.

[0053] In addition, the display style of the model identifier can change synchronously with the display of the reply content. For example, when the reply content corresponding to model 1 is displayed, the model identifier corresponding to model 1 is highlighted, and the model identifier corresponding to model 2 is grayed out. In response to the content switching operation, the display style of the model identifier is switched synchronously. It can be set according to specific needs, and the present disclosure does not impose any restrictions on this.

[0054] In a possible manner, the smart interaction page displays a model switching control, and in response to a configuration operation on the machine learning model associated with the smart object, determines the target machine learning model associated with the smart object according to the configuration operation, including: in response to a first trigger operation on the model switching control, displaying a model switching panel, the model switching panel displays at least one candidate machine learning model for user selection; in response to a first selection operation among at least one candidate machine learning model, determining the machine learning model corresponding to the first selection operation as the target machine learning model associated with the smart object.

[0055] For example, Figure 4 As shown in the figure, the smart interaction page displays a model switching control. Figure 5 As shown, when there are multiple target machine learning models, the model identifier and model switching control corresponding to the same machine learning model can be integrated into one page component so that different machine learning models can be switched separately. The specific settings can be made according to the needs, and this disclosure does not impose any restrictions on this.

[0056] For example, Figure 4 Taking the single-model intelligent interaction page shown as an example, in response to the triggering operation of the model switching control, the model switching panel is displayed, and then the machine learning model to be switched can be selected from the candidate machine learning models displayed in the model switching panel, for example, switching model 1 to model 2. The present disclosure does not impose any restrictions on this.

[0057] It should be noted that whether it is a single-model experience scenario or a multi-model comparison scenario, users are supported to switch machine learning models anytime and anywhere during the interaction with smart objects, thereby improving the flexibility of the user experience and meeting users' different model usage needs.

[0058] In a possible manner, the content display method also includes: after displaying the reply content generated by the target machine learning model according to the target input content, in response to a second trigger operation on the model switching control, displaying a model switching panel; in response to a second selection operation in at least one candidate machine learning model, determining a fifth machine learning model corresponding to the second selection operation, and displaying a synchronization confirmation pop-up window, wherein the synchronization confirmation pop-up window is used for the user to determine whether to synchronize the historical interaction content in the smart interaction page to the fifth machine learning model; in response to the operation of synchronizing the historical interaction content in the synchronization confirmation pop-up window, synchronously displaying the historical interaction content on the smart interaction page; or, in response to the operation of not synchronizing the historical interaction content in the synchronization confirmation pop-up window, clearing the historical interaction content on the smart interaction page.

[0059] For example, Figure 8 As shown, the smart interaction page displays historical interaction content. After changing the machine learning model associated with the smart object, a synchronization confirmation pop-up window can be displayed. If you choose to synchronize historical interaction content, the historical interaction content will be synchronously displayed on the smart interaction page. If you choose not to synchronize historical interaction content, the historical interaction content displayed on the smart interaction page will be cleared. Accordingly, when there are multiple target machine learning models, if one of the machine learning models is switched, the historical interaction content will be synchronized or cleared in the display area corresponding to the machine learning model according to the user's selection operation.

[0060] In the related art, after a user has conducted a conversation interaction on a smart interaction page corresponding to a smart object associated with a machine learning model, if the user needs to use a smart object associated with another machine learning model, the corresponding smart interaction page needs to be opened. In this case, the previous conversation content cannot be synchronized in the new smart interaction page. The embodiment of the present disclosure supports synchronization of historical interaction information after switching models, and synchronizes the original conversation content to the new model with one click, so that users can continue to interact seamlessly, reduce user time consumption, and improve user experience.

[0061] In a possible manner, the content display method also includes: in response to a model addition operation in the smart interaction page, determining a fourth machine learning model corresponding to the model addition operation, and displaying a synchronization confirmation pop-up window, wherein the synchronization confirmation pop-up window is used for the user to determine whether to synchronize the historical interaction content in the smart interaction page to the fourth machine learning model; in response to the operation of synchronizing the historical interaction content in the synchronization confirmation pop-up window, displaying the interaction areas corresponding to the target machine learning model and the fourth machine learning model respectively in the smart interaction page, and synchronously displaying the historical interaction content in the interaction area corresponding to the fourth machine learning model; or, in response to the operation of not synchronizing the historical interaction content in the synchronization confirmation pop-up window, displaying the interaction areas corresponding to the target machine learning model and the fourth machine learning model respectively in the smart interaction page, wherein the interaction area corresponding to the fourth machine learning model does not display the historical interaction content.

[0062] For example, Fig. 9 As shown, a model addition control can be displayed on the smart interaction page. In response to the triggering operation of the model addition control, a model selection panel similar to the above-mentioned model switching panel is displayed, and a new machine learning model is selected from the candidate machine learning models displayed in the model selection panel. Correspondingly, after adding a new machine learning model, the following can also be displayed: Figure 8 The synchronization confirmation pop-up window shown allows users to choose to synchronize or not synchronize historical interaction content to the interaction area corresponding to the newly added model. The specific settings can be made according to needs, and the present disclosure does not limit this. Thus, the original conversation content is synchronized to the new model with one click, which facilitates users to continue to interact seamlessly, reduces users' time consumption, and improves users' experience.

[0063] In a possible manner, there are multiple target machine learning models, and the content display method also includes: in response to a deletion operation on a third machine learning model among the multiple target machine learning models, clearing the reply content generated by the displayed third machine learning model based on the target input content on the intelligent interaction page.

[0064] For example, continue to refer to Fig. 9 , the model deletion control corresponding to each target machine learning model can be displayed on the smart interaction page, so that users can delete the machine learning models that do not need to be compared further according to their needs.

[0065] It is worth noting that through the model addition and deletion controls, users can add or reduce the machine learning models associated with smart objects according to their needs, supporting flexible switching from single model to multiple modes or from multiple models to single model to meet users' different model usage needs.

[0066] In a possible manner, the smart interaction page is displayed with a model editing control, and in response to a configuration operation on the machine learning model associated with the smart object, a target machine learning model associated with the smart object is determined according to the configuration operation, including: in response to a trigger operation on the model editing control, a model editing panel is displayed, and the model editing panel is used to configure model parameters of the machine learning model associated with the smart object; in response to a parameter configuration operation in the model editing panel, based on the parameter configuration operation, parameters of the machine learning model currently associated with the smart object in the smart interaction page are updated to obtain the target machine learning model associated with the smart object.

[0067] For example, Fig.10 As shown, the intelligent interaction page displays the model editing controls corresponding to each target machine learning model. Based on the model editing controls, the model editing panel of the corresponding machine learning model can be triggered to configure the parameters of the machine learning model, such as the sampling temperature parameters of the machine learning model, the core sampling probability threshold, the maximum number of tokens, etc. The specific settings can be based on demand, and the present disclosure does not impose any restrictions on this.

[0068] It should be noted that when selecting, adding or switching a machine learning model, you can directly display the model editing panel for parameter configuration after determining the selected machine learning model, or you can trigger the corresponding model editing control to display the model editing panel for parameter configuration after selecting the machine learning model. The specific settings can be based on needs, and this is not limited in the present disclosure.

[0069] It is worth noting that in the intelligent interactive page for multi-model comparison, the model identification and controls such as model deletion, switching, editing, and order adjustment for the same target machine learning model can be integrated into the same page component so as to perform corresponding operations on different machine learning models respectively. The specific settings can be made according to needs, and the present disclosure does not impose any restrictions on this.

[0070] Alternatively, the page components corresponding to different target machine learning models can be hidden, and an integrated interaction portal can be displayed in the intelligent interaction page. The page components corresponding to different target machine learning models can be expanded and displayed by triggering the interaction portal. The specific settings can be made according to needs, and the present disclosure does not impose any restrictions on this.

[0071] Alternatively, an integrated control portal can be displayed in the smart interaction page, and the control panel can be displayed by triggering the control portal. In the control panel, the target machine learning model associated with the smart object can be added or deleted, and the parameters of the target machine learning model can be configured. The specific settings can be made according to the needs, and the present disclosure does not limit this.

[0072] In addition, the operation controls corresponding to the smart interaction page of the single model experience can refer to the control display method of the multi-model comparison, which will not be repeated in this disclosure.

[0073] It should be noted that the above Figure 3-10 The page layout, display style, interactive controls and other contents of the smart interactive page shown can be set according to needs, and this disclosure does not make specific limitations on this.

[0074] Based on the same concept, the present disclosure provides a content display device, such as Fig.11 As shown, the content display device 110 includes: A first display module 111 is used to display an intelligent interaction page, where the intelligent interaction page is used for a user to interact with an intelligent object, where the intelligent object is used to generate a reply content according to the user's input content through an associated machine learning model; A determination module 112 is used to determine a target machine learning model associated with the smart object in response to a configuration operation on the machine learning model associated with the smart object during the interaction with the smart object according to the configuration operation; The second display module 113 is used to respond to the content input operation on the intelligent interaction page, determine the target input content corresponding to the content input operation, and display the reply content generated by the target machine learning model according to the target input content.

[0075] Optionally, the first display module 111 is used for: Displaying a model selection page, wherein the model selection page displays a target interaction entrance corresponding to the machine learning model, and the target interaction entrance is used to trigger a smart interaction page corresponding to a smart object associated with multiple machine learning models; In response to a triggering operation on the target interaction portal, displaying the smart interaction page; The second display module 113 is used for: Display response content generated by each of the multiple machine learning models based on the target input content.

[0076] Optionally, there are multiple target machine learning models, and the second display module 103 is used to: Determine the reply content generated by each target machine learning model according to the target input content, obtain multiple reply contents, and display the multiple reply contents in different areas on the intelligent interaction page.

[0077] Optionally, the intelligent interaction page displays model identifiers corresponding to the multiple target machine learning models, and the second display module 113 is used to: Displaying the multiple reply contents in columns or rows in the intelligent interaction page; or, In response to a triggering operation on a first model identifier on the smart interaction page, displaying on the smart interaction page a first reply content generated by a target machine learning model corresponding to the first model identifier according to the target input content; In response to a triggering operation on a second model identifier on the smart interaction page, a second reply content generated by a target machine learning model corresponding to the second model identifier based on the target input content is displayed at a preset position around the first reply content displayed on the smart interaction page.

[0078] Optionally, the content display device 110 further includes a third display module, and the third display module is used to: Displaying model identifiers corresponding to the multiple target machine learning models one by one at the top of the intelligent interaction page; or, Displaying model identifiers corresponding to the multiple target machine learning models at the bottom of the intelligent interaction page; or, An expansion control is displayed on the intelligent interaction page, and in response to a triggering operation on the expansion control, model identifiers corresponding one-to-one to the multiple target machine learning models are displayed.

[0079] Optionally, there are multiple target machine learning models, and the second display module 113 is used to: Displaying a third reply content generated by a first machine learning model among the multiple target machine learning models according to the target input content; In response to a content switching operation, the third reply content is switched to a fourth reply content generated by a second machine learning model among the multiple target machine learning models based on the target input content.

[0080] Optionally, the intelligent interaction page displays model identifiers corresponding to the multiple target machine learning models, and the second display module 113 is used to: In response to a triggering operation on a model identifier corresponding to the second machine learning model, switching the third reply content to fourth reply content generated by the second machine learning model according to the target input content; or, In response to a content sliding operation on the third reply content, the third reply content is switched to a fourth reply content generated by the second machine learning model according to the target input content.

[0081] Optionally, there are multiple target machine learning models, and the content display device 100 further includes a deletion module, which is used to: In response to a deletion operation on a third machine learning model among the multiple target machine learning models, the reply content generated by the third machine learning model based on the target input content and displayed on the intelligent interaction page is cleared.

[0082] Optionally, the content display device 110 further includes a new module, and the new module is used to: In response to a model adding operation in the smart interaction page, a fourth machine learning model corresponding to the model adding operation is determined, and a synchronization confirmation pop-up window is displayed, where the synchronization confirmation pop-up window is used for the user to determine whether to synchronize the historical interaction content in the smart interaction page to the fourth machine learning model; In response to the operation of synchronizing the historical interaction content in the synchronization confirmation pop-up window, the interaction areas corresponding to the target machine learning model and the fourth machine learning model are displayed in the intelligent interaction page, and the historical interaction content is synchronously displayed in the interaction area corresponding to the fourth machine learning model; or, In response to the operation of not synchronizing the historical interaction content in the synchronization confirmation pop-up window, the interaction areas corresponding to the target machine learning model and the fourth machine learning model are displayed in the smart interaction page, wherein the interaction area corresponding to the fourth machine learning model does not display the historical interaction content.

[0083] Optionally, the intelligent interaction page displays a model switching control, and the determination module 112 is used to: In response to a first trigger operation on the model switching control, displaying a model switching panel, wherein the model switching panel displays at least one candidate machine learning model for selection by the user; In response to a first selection operation among the at least one candidate machine learning model, the machine learning model corresponding to the first selection operation is determined as the target machine learning model associated with the smart object.

[0084] Optionally, the content display device 110 further includes a synchronization module, and the synchronization module is used to: After displaying the reply content generated by the target machine learning model according to the target input content, in response to a second trigger operation on the model switching control, displaying the model switching panel; In response to a second selection operation in the at least one candidate machine learning model, a fifth machine learning model corresponding to the second selection operation is determined, and a synchronization confirmation pop-up window is displayed, where the synchronization confirmation pop-up window is used for the user to determine whether to synchronize the historical interaction content in the smart interaction page to the fifth machine learning model; In response to the operation of synchronizing the historical interaction content in the synchronization confirmation pop-up window, synchronously displaying the historical interaction content on the smart interaction page; or, In response to an operation of not synchronizing the historical interaction content in the synchronization confirmation pop-up window, the historical interaction content is cleared on the smart interaction page.

[0085] Optionally, the intelligent interaction page displays a model editing control, and the determination module 112 is used to: In response to a triggering operation on the model editing control, a model editing panel is displayed, wherein the model editing panel is used to configure model parameters of the machine learning model associated with the smart object; In response to the parameter configuration operation in the model editing panel, based on the parameter configuration operation, the parameters of the machine learning model currently associated with the smart object in the smart interaction page are updated to obtain the target machine learning model associated with the smart object.

[0086] Based on the same concept, an embodiment of the present disclosure further provides a computer-readable medium on which a computer program is stored, and when the program is executed by a processing device, the steps of the above-mentioned content display method are implemented.

[0087] Based on the same concept, the present disclosure also provides an electronic device, which may include: a storage device having a computer program stored thereon; A processing device is used to execute the computer program in the storage device to implement the steps of the above-mentioned content display method.

[0088] Based on the same concept, an embodiment of the present disclosure further provides a computer program product, including a computer program, which implements the steps of the above-mentioned content display method when executed by a processor.

[0089] Reference below Fig.12 , which shows a schematic diagram of the structure of an electronic device 120 suitable for implementing the 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, laptop computers, 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. Fig.12 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0090] like Fig.12As shown, the electronic device 120 may include a processing device (e.g., a central processing unit, a graphics processor, etc.) 121, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 122 or a program loaded from a storage device 128 to a random access memory (RAM) 123. In the RAM 123, various programs and data required for the operation of the electronic device 120 are also stored. The processing device 121, the ROM 122, and the RAM 123 are connected to each other via a bus 124. An input / output (I / O) interface 125 is also connected to the bus 124.

[0091] Typically, the following devices may be connected to the I / O interface 125: an input device 126 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 127 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 128 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 129. The communication device 129 may allow the electronic device 120 to communicate with other devices wirelessly or by wire to exchange data. Although Fig.12 The electronic device 120 is shown with various devices, but it should be understood that it is not required to implement or have all the devices shown. More or fewer devices may be implemented or have instead.

[0092] 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 contains 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 129, or installed from the storage device 128, or installed from the ROM 122. When the computer program is executed by the processing device 121, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

[0093] 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 above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with 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), 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 above. 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 combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. Computer readable signal media may also be any computer readable medium other than computer readable storage media, which may send, propagate or transmit 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 appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0094] In some embodiments, any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol) can be used for communication, 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 future developed network.

[0095] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0096] 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 an intelligent interaction page, where the intelligent interaction page is used for users to interact with intelligent objects, and the intelligent object is used to generate reply content according to the user's input content through an associated machine learning model; in the process of interaction with the intelligent object, in response to the configuration operation of the machine learning model associated with the intelligent object, determine the target machine learning model associated with the intelligent object according to the configuration operation; in response to the content input operation on the intelligent interaction page, determine the target input content corresponding to the content input operation, and display the reply content generated by the target machine learning model according to the target input content.

[0097] 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 separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0098] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square 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 square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0099] The modules involved in the embodiments described in the present disclosure may be implemented by software or hardware, wherein the name of a module does not, in some cases, limit the module itself.

[0100] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, 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 chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0101] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may 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.

[0102] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. 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 a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other to form a technical solution.

[0103] 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 are 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.

[0104] Although the subject matter has been described in language specific to structural features and / or method logic actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims. Regarding the device in the above embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.

Claims

1. A content display method, characterized in that: The content display method comprises: Displaying a smart interaction page, wherein the smart interaction page is used for a user to interact with a smart object, and the smart object is used to generate reply content according to the user's input content through an associated machine learning model; In an interaction process with the smart object, in response to a configuration operation on a machine learning model associated with the smart object, determining a target machine learning model associated with the smart object according to the configuration operation; In response to a content input operation on the intelligent interaction page, the target input content corresponding to the content input operation is determined, and the reply content generated by the target machine learning model based on the target input content is displayed.

2. The content display method according to claim 1, characterized in that: The display of the intelligent interaction page includes: Displaying a model selection page, wherein the model selection page displays a target interaction entrance corresponding to the machine learning model, and the target interaction entrance is used to trigger a smart interaction page corresponding to a smart object associated with multiple machine learning models; In response to a triggering operation on the target interaction portal, displaying the smart interaction page; The displaying of the reply content generated by the target machine learning model according to the target input content includes: Display response content generated by each of the multiple machine learning models based on the target input content.

3. The content display method according to claim 1, characterized in that: There are multiple target machine learning models, and displaying the reply content generated by the target machine learning model according to the target input content includes: Determine the reply content generated by each target machine learning model according to the target input content, obtain multiple reply contents, and display the multiple reply contents in different areas on the intelligent interaction page.

4. The content display method according to claim 3, characterized in that: The intelligent interaction page displays model identifiers corresponding to the multiple target machine learning models one by one, and the multiple reply contents are displayed in different regions on the intelligent interaction page, including: Displaying the multiple reply contents in columns or rows in the intelligent interaction page; or, In response to a triggering operation on a first model identifier on the smart interaction page, displaying on the smart interaction page a first reply content generated by a target machine learning model corresponding to the first model identifier according to the target input content; In response to a triggering operation on a second model identifier on the smart interaction page, a second reply content generated by a target machine learning model corresponding to the second model identifier based on the target input content is displayed at a preset position around the first reply content displayed on the smart interaction page.

5. The content display method according to claim 4, characterized in that: The content display method further includes: Displaying model identifiers corresponding to the multiple target machine learning models one by one at the top of the intelligent interaction page; or, Displaying model identifiers corresponding to the multiple target machine learning models at the bottom of the intelligent interaction page; or, An expansion control is displayed on the intelligent interaction page, and in response to a triggering operation on the expansion control, model identifiers corresponding one-to-one to the multiple target machine learning models are displayed.

6. The content display method according to claim 1, characterized in that: There are multiple target machine learning models, and displaying the reply content generated by the target machine learning model according to the target input content includes: Displaying a third reply content generated by a first machine learning model among the multiple target machine learning models according to the target input content; In response to a content switching operation, the third reply content is switched to a fourth reply content generated by a second machine learning model among the multiple target machine learning models based on the target input content.

7. The content display method according to claim 6, characterized in that: The intelligent interaction page displays model identifiers corresponding to the multiple target machine learning models one by one, and in response to the content switching operation, the third reply content is switched to a fourth reply content generated by a second machine learning model among the multiple target machine learning models according to the target input content, including: In response to a triggering operation on a model identifier corresponding to the second machine learning model, switching the third reply content to fourth reply content generated by the second machine learning model according to the target input content; or, In response to a content sliding operation on the third reply content, the third reply content is switched to a fourth reply content generated by the second machine learning model according to the target input content.

8. The content display method according to any one of claims 1 to 7, characterized in that: The target machine learning model is multiple, and the content display method further includes: In response to a deletion operation on a third machine learning model among the multiple target machine learning models, the reply content generated by the third machine learning model based on the target input content that has been displayed on the intelligent interaction page is cleared.

9. The content display method according to any one of claims 1 to 7, characterized in that: The content display method further includes: In response to a model adding operation in the smart interaction page, a fourth machine learning model corresponding to the model adding operation is determined, and a synchronization confirmation pop-up window is displayed, where the synchronization confirmation pop-up window is used for the user to determine whether to synchronize the historical interaction content in the smart interaction page to the fourth machine learning model; In response to the operation of synchronizing the historical interaction content in the synchronization confirmation pop-up window, the interaction areas corresponding to the target machine learning model and the fourth machine learning model are displayed in the smart interaction page, and the historical interaction content is synchronously displayed in the interaction area corresponding to the fourth machine learning model; or, In response to the operation of not synchronizing the historical interaction content in the synchronization confirmation pop-up window, the interaction areas corresponding to the target machine learning model and the fourth machine learning model are displayed in the smart interaction page, wherein the interaction area corresponding to the fourth machine learning model does not display the historical interaction content.

10. The content display method according to any one of claims 1 to 7, characterized in that: The smart interaction page displays a model switching control, and the response to the configuration operation of the machine learning model associated with the smart object, according to the configuration operation, determines the target machine learning model associated with the smart object, including: In response to a first trigger operation on the model switching control, displaying a model switching panel, wherein the model switching panel displays at least one candidate machine learning model for selection by the user; In response to a first selection operation among the at least one candidate machine learning model, the machine learning model corresponding to the first selection operation is determined as the target machine learning model associated with the smart object.

11. The content display method according to claim 10, characterized in that: The content display method further includes: After displaying the reply content generated by the target machine learning model according to the target input content, in response to a second trigger operation on the model switching control, displaying the model switching panel; In response to a second selection operation in the at least one candidate machine learning model, a fifth machine learning model corresponding to the second selection operation is determined, and a synchronization confirmation pop-up window is displayed, where the synchronization confirmation pop-up window is used for the user to determine whether to synchronize the historical interaction content in the smart interaction page to the fifth machine learning model; In response to the operation of synchronizing the historical interaction content in the synchronization confirmation pop-up window, synchronously displaying the historical interaction content on the smart interaction page; or, In response to an operation of not synchronizing the historical interaction content in the synchronization confirmation pop-up window, the historical interaction content is cleared on the smart interaction page.

12. The content display method according to any one of claims 1 to 7, characterized in that: The smart interaction page displays a model editing control, and the response to the configuration operation of the machine learning model associated with the smart object, according to the configuration operation, determines the target machine learning model associated with the smart object, including: In response to a triggering operation on the model editing control, a model editing panel is displayed, wherein the model editing panel is used to configure model parameters of the machine learning model associated with the smart object; In response to the parameter configuration operation in the model editing panel, based on the parameter configuration operation, the parameters of the machine learning model currently associated with the smart object in the smart interaction page are updated to obtain the target machine learning model associated with the smart object.

13. A content display device, characterized in that: The content display device comprises: A first display module, configured to display an intelligent interaction page, wherein the intelligent interaction page is configured to allow a user to interact with an intelligent object, and the intelligent object is configured to generate reply content according to input content of the user through an associated machine learning model; a determination module for determining, in response to a configuration operation on a machine learning model associated with the smart object during interaction with the smart object, a target machine learning model associated with the smart object according to the configuration operation; The second display module is used to respond to the content input operation on the intelligent interaction page, determine the target input content corresponding to the content input operation, and display the reply content generated by the target machine learning model according to the target input content.

14. A computer readable medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processing device, the steps of the method according to any one of claims 1 to 12 are implemented.

15. An electronic device, characterized in that: include: a storage device having a computer program stored thereon; A processing device, configured to execute the computer program in the storage device to implement the steps of the method according to any one of claims 1 to 12.

16. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 12 are implemented.

Images