A method, system, and related devices for generating a podcast

Abstract

Embodiments of the present application provide a method, system and related device for generating a podcast. In the method, an application for generating a podcast in an electronic device is a system application. When generating a podcast, the application can obtain user private domain data and generate a podcast based on the user private domain data. Alternatively, when listening to a podcast, a user can obtain a question answer corresponding to user question information based on user private domain data. Furthermore, the electronic device can upload the podcast and user private domain data related to the podcast to a server or share the podcast with another electronic device. When listening to the podcast, a user of the other electronic device can also interact with the podcast. In this way, when asking a question, a user can obtain an answer that is more matched to the user's own situation. Furthermore, a user of an electronic device receiving a podcast can also interact with the podcast when playing the podcast, which can improve the user experience.

Description

Technical Field

[0001] This application relates to the field of terminal and electronic technology, and in particular to a method, system and related apparatus for generating podcasts. Background Technology

[0002] Currently, electronic devices can generate audio similar to a radio program based on user-selected documents, web pages, images, or input text; this audio can be called a podcast. When the electronic device plays the podcast, the content can be read by one or more virtual characters. Users can also ask questions to the virtual characters reading the podcast, and the virtual characters will answer the user's questions. Currently, the answers received by the user are difficult to match with their own situation. This affects the user's interactive experience when playing podcasts. Summary of the Invention

[0003] This application provides a method, system, and related apparatus for generating podcasts. Using the method provided, when a user asks questions to the podcaster during podcast playback, they can receive answers that match their own situation. This improves the user's interactive experience when playing podcasts.

[0004] In a first aspect, this application provides a method for generating podcasts, which can be applied to a first electronic device. The method may include: receiving input from a user, the input indicating target content selected by the user for generating the podcast, the target content including one or more of web pages, text, videos, and images; and generating a first podcast based on the target content selected by the user and first private domain data associated with the target content on the first electronic device.

[0005] The target content may include the user-selected content involved in the embodiments. The first private domain data may include the user private domain data 1 involved in the embodiments. The first podcast may include the podcast 1 involved in the embodiments.

[0006] In some feasible examples, the first electronic device may be a terminal device, for example, the first electronic device may be electronic device 100 or electronic device 200 involved in the embodiment.

[0007] In some other feasible examples, the first electronic device can also be a server; for example, the first electronic device can be the server side involved in the embodiment.

[0008] Using the method provided in this first aspect, a first electronic device can generate a podcast based on user private domain data (i.e., the first private domain data) within the first electronic device. In this way, the content of the podcast can be tailored to the user's individual circumstances. Subsequently, when the user interacts with the podcast during playback, the answers to their questions can also be derived from this user's private domain data. This results in answers that are more closely matched to the user's own situation, thereby enhancing the user's interactive experience.

[0009] In one possible implementation, the method may further include sending the first podcast and the first private domain data to a second electronic device, which may be a terminal device or a server.

[0010] In some examples, the second electronic device may include the electronic device 200 involved in the embodiments. In other examples, the second electronic device may include the server side included in the embodiments.

[0011] In this way, the first electronic device can share the first podcast and the first private domain data with another device or upload them to the server.

[0012] In one possible implementation, sending the first podcast and the first private domain data to the second electronic device may include: uploading the first podcast and the first private domain data to a server and setting access permissions for the first private domain data; or, sharing the first podcast and the first private domain data with a terminal device.

[0013] In this way, the first electronic device can distribute podcasts generated by the first device by sharing the first podcast and first private domain data with another device or uploading them to a server. Furthermore, access permissions for the first private domain data can be set, thus preventing the leakage of local privacy or sensitive data.

[0014] In one possible implementation, the method may further include: providing a user with a question-and-answer control about the first podcast; receiving a first question input by the user based on the question-and-answer control; and providing the user with an answer to the first question based on first private domain data.

[0015] In some examples, the first question may include the question information 1 involved in the embodiment, and the answer to the first question may include the question answer 1 involved in the embodiment.

[0016] In this way, users can interact with the first podcast while playing it, that is, ask questions. Furthermore, users can receive answers that match their own situation.

[0017] In one possible implementation, the method may further include: displaying multiple private domain data on a first electronic device; and receiving a first private domain data selected by a user from the multiple private domain data.

[0018] In this way, users can see private domain data associated with the first podcast on the first electronic device.

[0019] In one possible implementation, multiple private domain data are displayed on a first electronic device, which may specifically include: the first electronic device displays first private domain data, a first control, and a second control, wherein the first control is used to modify the first private domain data, and the second control is used to delete the first private domain data.

[0020] In some feasible examples, the first private domain data may include any one of user private domain data 821, user private domain data 822, user private domain data 823, user private domain data 824, and user private domain data 825 involved in the embodiments. The first control may include any one of controls 8211, 8221, 8231, 8241, and 8251 involved in the embodiments. The second control may include any one of controls 8212, 8222, 8232, 8242, and 8252 involved in the embodiments.

[0021] In this way, users can modify the private domain data related to podcast 1 themselves through the first control, making the private domain data more consistent with the user's current situation. When a user does not want to display a user's private domain data in podcast 1, the user can also delete that user's private domain data through the second control.

[0022] In one possible implementation, after receiving a question input by the user based on a question-and-answer control, the method may include: sending a first question to a server; receiving an answer to the first question corresponding to the first question, wherein the answer to the first question is obtained by the server based on the first question and first private domain data.

[0023] In this way, the server's computing resources can be utilized, that is, the answer to the first question can be obtained through the server based on the first question and the first private domain data.

[0024] In one possible implementation, after providing the user with an answer to a question based on first private domain data, the method may include: saving the first question and the answer to the first question; uploading the first question and the answer to the first question to the server; or sharing the first question and the answer to the first question with a terminal device.

[0025] In this way, the first electronic device can share or upload the first question and its answer. This allows other users who subsequently listen to the first podcast and ask the same or related questions to directly refer to the answer to the first question.

[0026] In one possible implementation, the method may further include: receiving a second podcast sent by a second electronic device and second private domain data associated with the second podcast on the second electronic device; and acquiring third private domain data associated with the second podcast on a first electronic device.

[0027] In some feasible examples, when the first electronic device includes the electronic device 200 involved in the embodiment, the second podcast may include the podcast 1 involved in the embodiment, the second private domain data may include the user private domain data 1 involved in the embodiment, and the third private domain data may include the user private domain data 2 involved in the embodiment.

[0028] In some other examples, when the first electronic device includes the electronic device 100 involved in the embodiment, the second podcast may include the podcast 2 involved in the embodiment, the second private domain data may include the user private domain data 3 involved in the embodiment, and the third private domain data may include the user private domain data 4 involved in the embodiment.

[0029] In this way, the first electronic device can also receive podcasts shared by other devices and obtain the user's private domain data associated with that podcast on its local machine.

[0030] In one possible implementation, after receiving the second podcast sent by the second electronic device and the second private domain data associated with the second podcast on the second electronic device, the method may further include: displaying an identifier of the second podcast; receiving and responding to the user's identifier of the second podcast, displaying a first option box, the first option box being used by the user to select to download the second podcast and the second private domain data; receiving and responding to the user's operation of selecting to download the second podcast and the second private domain data, and downloading the second podcast and the second private domain data.

[0031] In some feasible examples, the first option box may include window 1210 as described in the embodiment.

[0032] In this way, the first electronic device can display a second podcast and second private domain data shared by another device. An option box is provided allowing the user to choose whether to download the second podcast and second private domain data. This improves the user experience.

[0033] In one possible implementation, after receiving a second podcast sent by a second electronic device and second private domain data associated with the second podcast on the second electronic device, the method may include: receiving a second question input by a user based on a question-and-answer control during the playback of the second podcast; and providing the user with an answer to the second question based on the second private domain data and third private domain data.

[0034] In some examples, the second question may include the question information 2 involved in the embodiment, and the answer to the second question may include the question answer 2 involved in the embodiment.

[0035] In this way, the first electronic device receives podcasts shared by other devices, and the user can interact with the podcast while it is being played on the first electronic device. This improves the user experience.

[0036] In one possible implementation, the answer to the first question is provided to the user based on the first private domain data. Specifically, this may include: searching for first public network knowledge based on the first question; and obtaining the answer to the first question based on the first public network knowledge and the first user's private domain data.

[0037] In some examples, the first public network knowledge may include the public network knowledge 1 involved in the embodiment.

[0038] In this way, the first electronic device can combine public network knowledge with the user's private domain data to obtain the answer to the first question. This achieves a deep integration of professional knowledge and personal preferences, making the answer to the first question not only professional but also more closely matched to the user's own situation.

[0039] In one possible implementation, the answer to the second question is provided to the user based on the second private domain data and the third private domain data. Specifically, this may include: searching for second public network knowledge based on the second question; and providing the answer to the second question to the user based on the second public network knowledge, the second private domain data, and the third private domain data.

[0040] In some examples, the second public network knowledge may include the public network knowledge 2 involved in the embodiment.

[0041] In this way, answers to questions can be obtained by combining private domain data from multiple users and public network knowledge.

[0042] Secondly, a method for generating podcasts is provided, which can be applied to a second electronic device. The method may include: receiving a first podcast sent by a first electronic device and first private domain data associated with the first podcast on the first electronic device; and obtaining fourth private domain data associated with the first podcast on the second electronic device.

[0043] In some examples, the second electronic device may include electronic device 200 as described in the embodiments, and the first electronic device may include electronic device 100 as described in the embodiments. The first podcast may include podcast 1 as described in the embodiments, the first private domain data may include user private domain data 1 as described in the embodiments, and the fourth private domain data may include user private domain data 2 as described in the embodiments.

[0044] Using the method provided in the second aspect, the second electronic device can also receive podcasts shared by other devices and obtain user private domain data associated with the podcast on its local machine.

[0045] In one possible implementation, after receiving the first podcast sent by the first electronic device and the first private domain data associated with the first podcast on the first electronic device, the method may further include: displaying an identifier of the first podcast; receiving and responding to the user's identifier of the first podcast, displaying a first option box, the first option box being used by the user to select to download the first podcast and the first private domain data; receiving and responding to the user's operation of selecting to download the first podcast and the first private domain data, and downloading the first podcast and the first private domain data.

[0046] In some feasible examples, the first option box may include window 1210 as described in the embodiment.

[0047] In this way, the second electronic device can display second podcasts and second private domain data shared by another device. An option box is provided allowing the user to choose whether to download the second podcasts and second private domain data. This improves the user experience.

[0048] In one possible implementation, after receiving a first podcast sent by a first electronic device and first private domain data associated with the first podcast on the first electronic device, the method may include: receiving a second question input by a user based on a question-and-answer control during the playback of the first podcast; and providing the user with an answer to the second question based on the first private domain data and the fourth private domain data.

[0049] In some examples, the second question may include the question information 2 involved in the embodiment, and the answer to the second question may include the question answer 2 involved in the embodiment.

[0050] In this way, the second electronic device can receive podcasts shared by other devices, and the user can interact with the podcast while it is being played. This improves the user experience.

[0051] In one possible implementation, providing the user with an answer to the second question based on the first private domain data and the fourth private domain data can specifically include: sending the second question to the server; receiving second public network knowledge obtained by the server based on the second question; and providing the user with an answer to the second question based on the second public network knowledge, the first private domain data, and the fourth private domain data.

[0052] In this way, the second electronic device can leverage the server-side computing resources to search for professional knowledge related to the second question. It then combines this professional knowledge with the user's personalized private domain data to arrive at the answer to the second question. Thus, the answer to the second question can not only integrate professional knowledge but also incorporate personalized information from multiple users.

[0053] Thirdly, a method for generating podcasts is provided. This method can be applied to a server and may include: receiving user-selected target content for generating the podcast and first private domain data associated with the target content sent by a first electronic device; generating a first podcast based on the target content and the first private domain data; and sending the first podcast to the first electronic device. The target content may include one or more of web pages, text, videos, and images.

[0054] In some examples, the target content may include user-selected content as described in the embodiments. The first private domain data may include user private domain data 1 as described in the embodiments. The first podcast may include podcast 1 as described in the embodiments.

[0055] In some examples, the server may include the server side involved in the embodiments, and the first electronic device may include the electronic device 100 involved in the embodiments.

[0056] The methods provided in the third aspect can deeply integrate expertise (e.g., target content) with personal preferences (e.g., first-hand private domain data) when generating the first podcast, thereby improving the quality of podcast generation and enhancing the multi-dimensional adaptability of podcast content.

[0057] In one possible implementation, the method may further include: receiving a first question sent by a first electronic device during the playback of a first podcast; searching for first public network knowledge based on the first question; and obtaining an answer to the first question based on the first public network knowledge and the first user's private domain data.

[0058] In some examples, the first question may include the question information 1 involved in the embodiment, and the answer to the first question may include the question answer 1 involved in the embodiment.

[0059] In this way, the first electronic device can utilize the server's computing power to obtain the answer to the user's question. The server can combine public network knowledge with the user's private domain data to obtain the answer to the first question. This achieves a deep integration of professional knowledge and personal preferences, making the answer to the first question not only professional but also more closely matched to the user's specific situation.

[0060] Fourthly, a system for generating podcasts is provided, the system comprising a first electronic device, a second electronic device, and a server, wherein: the first electronic device can be used to execute any possible implementation of the method in the first aspect; the second electronic device can be used to execute any possible implementation of the method in the second aspect; and the server can be used to execute any possible implementation of the method in the third aspect.

[0061] In some feasible examples, the first electronic device may include the electronic device 100 involved in the embodiment, the second electronic device may include the electronic device 200 involved in the embodiment, and the server may include the server side involved in the embodiment.

[0062] Fifthly, an electronic device is provided, characterized in that it includes one or more processors; one or more memories; the one or more memories storing one or more computer programs, the one or more computer programs including instructions that, when executed by the one or more processors, cause the electronic device to perform the method described in any possible implementation of the first aspect above.

[0063] A sixth aspect provides an electronic device, characterized in that it includes one or more processors; one or more memories; the one or more memories storing one or more computer programs, the one or more computer programs including instructions that, when executed by the one or more processors, cause the electronic device to perform the method described in any possible implementation of the second aspect above.

[0064] A seventh aspect provides a server, characterized in that it includes one or more processors; one or more memories; the one or more memories store one or more computer programs, the one or more computer programs including instructions that, when executed by the one or more processors, cause the server to perform the method described in any possible implementation of the third aspect above.

[0065] Eighthly, a chip is provided, the chip including a processor and a communication interface, the communication interface being used to receive a signal and transmit the signal to the processor, the processor processing the signal, causing the chip to perform the method described in any possible implementation of the first, second, or third aspect above.

[0066] Ninthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a computer, causes the computer to implement the method described in any possible implementation of the first, second, or third aspect above.

[0067] In a tenth aspect, embodiments of this application provide a computer program product that, when run on an electronic device, causes the electronic device to perform the method described in any possible implementation of the first, second, or third aspect.

[0068] It is understood that the beneficial effects of aspects four through ten above can be found in the relevant descriptions of aspects one through three above, and will not be repeated here. Attached Figure Description

[0069] Figure 1 This is a schematic diagram of a system provided in an embodiment of this application;

[0070] Figure 2 This is a schematic diagram of the structure of the electronic device 100 provided in the embodiments of this application;

[0071] Figure 3 This is a schematic diagram of the structure of the electronic device 200 provided in the embodiments of this application;

[0072] Figure 4 This is a schematic diagram of the server-side structure provided in an embodiment of this application;

[0073] Figure 5 This is a software structure block diagram of the electronic device 100 according to an embodiment of this application;

[0074] Figure 6 This is a software structure block diagram of the electronic device 200 according to an embodiment of this application;

[0075] Figure 7 This is a software structure block diagram of the server side according to an embodiment of this application;

[0076] Figure 8A This is a schematic diagram of a user interface provided in an embodiment of this application;

[0077] Figure 8B This is a schematic diagram of a user interface provided in an embodiment of this application;

[0078] Figure 8C This is a schematic diagram of a user interface provided in an embodiment of this application;

[0079] Figure 9A This is a schematic diagram of a user interface provided in an embodiment of this application;

[0080] Figure 9B This is a schematic diagram of a user interface provided in an embodiment of this application;

[0081] Figure 9C This is a schematic diagram of a user interface provided in an embodiment of this application;

[0082] Figure 9DThis is a schematic diagram of a user interface provided in an embodiment of this application;

[0083] Figure 9E This is a schematic diagram of a user interface provided in an embodiment of this application;

[0084] Figure 9F This is a schematic diagram of a user interface provided in an embodiment of this application;

[0085] Figure 9G This is a schematic diagram of a user interface provided in an embodiment of this application;

[0086] Figure 10A This is a schematic diagram of a user interface provided in an embodiment of this application;

[0087] Figure 10B This is a schematic diagram of a user interface provided in an embodiment of this application;

[0088] Figure 10C This is a schematic diagram of a user interface provided in an embodiment of this application;

[0089] Figure 11A This is a schematic diagram of a user interface provided in an embodiment of this application;

[0090] Figure 11B This is a schematic diagram of a user interface provided in an embodiment of this application;

[0091] Figure 11C This is a schematic diagram of a user interface provided in an embodiment of this application;

[0092] Figure 12A This is a schematic diagram of a user interface provided in an embodiment of this application;

[0093] Figure 12B This is a schematic diagram of a user interface provided in an embodiment of this application;

[0094] Figure 12C This is a schematic diagram of a user interface provided in an embodiment of this application;

[0095] Figure 12D This is a schematic diagram of a user interface provided in an embodiment of this application;

[0096] Figure 13 This is a flowchart illustrating a method for generating podcasts provided in an embodiment of this application;

[0097] Figure 14 This is a schematic diagram illustrating the process of an electronic device 100 sharing a podcast with an electronic device 200, the electronic device 200 playing the podcast, and interacting with the podcast, as provided in this embodiment of the application. Detailed Implementation

[0098] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0099] The terminology used in the following embodiments of this application is for the purpose of describing particular embodiments only and is not intended to be limiting of this application. As used in the specification and appended claims of this application, the singular expressions “a,” “an,” “the,” “the,” “the,” and “this” are intended to include the plural expressions as well, unless the context clearly indicates otherwise. The terms “first” and “second” are used for descriptive purposes only and should not be construed as implying or suggesting relative importance or implicitly indicating the number of indicated technical features. Thus, a feature defined as “first” or “second” may explicitly or implicitly include one or more of that feature. “First” and “second,” etc., are used to distinguish different objects, not to describe a particular order of objects. For example, a first object and a second object are used to distinguish different objects, not to describe a particular order of objects.

[0100] In the description of the embodiments in this application, unless otherwise stated, "multiple" means two or more. For example, multiple processing units refer to two or more processing units; multiple systems refer to two or more systems.

[0101] In the embodiments of this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or related scheme described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design schemes. Specifically, the use of the terms "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0102] The term "and / or" in this application is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent three cases: A existing alone, A and B existing simultaneously, and B existing alone.

[0103] The term "user interface (UI)" used in the following embodiments of this application refers to the medium interface through which an application or operating system interacts and exchanges information with the user. It realizes the conversion between the internal form of information and the form that the user can accept. The user interface is source code written in a specific computer language such as Java or Extensible Markup Language (XML). The interface source code is parsed and rendered on the electronic device, ultimately presenting content that the user can recognize. A common form of user interface is the graphical user interface (GUI), which refers to a user interface related to computer operation displayed graphically. It can be visible interface elements such as text, icons, buttons, menus, tabs, text boxes, dialog boxes, status bars, navigation bars, and widgets displayed on the screen of an electronic device.

[0104] Currently, electronic devices can summarize and extract user-selected content (such as documents, web pages, videos, images, etc.) to generate podcasts. This allows users to understand the selected content simply by listening to the podcast, without needing to spend additional time reading or listening to all the content. During podcast playback, users can also ask questions, and the electronic device can provide answers based on those questions.

[0105] In one possible implementation, when a user inputs a voice question, the electronic device can recognize the user's voice question based on a preset automatic speech recognition algorithm to obtain interactive information. Then, based on the interactive information and the podcast's original topic, it performs a matching search in a preset knowledge base to obtain feedback information (also known as the question answer) that matches the interactive information. In this way, the user can engage in question-and-answer interaction with the podcast.

[0106] However, currently, when users ask questions, the answers they receive may not match their individual circumstances. For example, a user's chat history might contain information such as disliking lamb or spicy food. When a user asks for "Xi'an food recommendations" while listening to a podcast, the cloud can only search for Xi'an food recommendations from the public internet and obtain the answer. The recommended dishes in the cloud's answers might all be spicy, which doesn't match the user's personal dietary habits. This negatively impacts the user experience.

[0107] In this application embodiment, user private domain data includes, but is not limited to: search history, shopping information, shopping cart information, and favorited items in the user's shopping application; chat information in the chat software; ticket purchase information in the ticketing software (departure time, departure location, arrival time, and arrival location of train tickets, high-speed rail tickets, air tickets, etc., as well as attraction ticket information (e.g., attraction entry time, location, etc.)); schedule reminder information; ticket purchase SMS messages; call record information; sports and health information, etc.

[0108] This application provides a method for generating podcasts. In this method, the application used to generate podcasts in the electronic device 100 is a system application. When generating podcasts, this application can obtain user private data and generate podcasts based on the user's private data. Alternatively, when a user listens to a podcast, the application can obtain answers to user questions based on the user's private data. In this way, when a user asks a question, the answer may be more relevant to the user's situation, thus improving the user experience.

[0109] Furthermore, in this embodiment, the podcast generated by electronic device 100 and the user's private domain data related to the podcast can not only be uploaded to the cloud but also shared with electronic device 200. Electronic device 200 can receive the podcast and the user's private domain data related to the podcast. Then, electronic device 200 can also obtain the user's private domain data related to the podcast within electronic device 200. Next, electronic device 200 can play the podcast. During the playback, the user can interact with the podcast; for example, the user can input a question (voice or text), and then electronic device 200 can provide the user with the answer. This answer can be obtained by electronic device 200 based on the user's private domain data sent by electronic device 100 and the private domain data related to the podcast within electronic device 200.

[0110] It is understood that the applications capable of generating podcasts in this application are not limited to system applications, but can also be third-party applications. The method for generating podcasts provided in this application is applicable to both system applications and third-party applications capable of obtaining user private data.

[0111] To better understand the technical solutions provided in this application, a podcast generation system provided in an embodiment of this application will be described below. Exemplarily, this podcast generation system can be as follows: Figure 1 System 10 is shown in the figure. Figure 1 An exemplary system 10 provided in an embodiment of this application is illustrated. For example... Figure 1 As shown, the system 10 may include electronic device 100, electronic device 200, and a cloud server. Wherein:

[0112] Electronic device 100 can be used to perform one or more of the following functions:

[0113] Function 1A: Generate podcast 1 and obtain user private domain data 1 related to podcast 1.

[0114] In this embodiment, a user can select content on an electronic device 100. The electronic device 100 can generate podcast 1 based on the user-selected content. During the generation of podcast 1, user private domain data 1 related to podcast 1 can also be obtained. For details on how a user selects content on the electronic device 100 to generate podcast 1, please refer to the following description. Figures 8A-8C The description will not be repeated here.

[0115] In one possible implementation, electronic device 100 contains a large model for generating podcasts. Electronic device 100 can input user-selected content into this large model, which can then summarize and refine the user-selected content to obtain podcast text 1. The large model can then generate podcast 1 from podcast text 1 according to the user-selected host.

[0116] Alternatively, electronic device 100 can input the user-selected content and user private domain data 1 into the large model. Then, the large model can summarize and refine the user-selected content and user private domain data 1 to obtain podcast text 1. Then, the large model can also generate podcast 1 from the podcast text 1 according to the user-selected host.

[0117] Regarding how electronic device 100 generates podcast 1 using the large model for generating podcasts, please refer to the existing descriptions of how large models generate podcasts from input content; these will not be repeated here.

[0118] Function 1B: Send the user-selected content and user private domain data 1 to the server side, and receive podcast 1 sent by the server side, which is generated by the server side based on the user-selected content and user private domain data 1.

[0119] Electronic device 100 can send user-selected content and user private domain data 1 to the server side based on the user's podcast generation operation. The server side can generate podcast 1 from the user-selected content and user private domain data 1 using a large model. Regarding how the server side generates podcast 1 using the large model for podcast generation, please refer to existing descriptions of large models for generating podcasts from input content; these will not be repeated here. The specific large model for generating podcasts involved in this application embodiment is not limited.

[0120] That is, when electronic device 100 implements function 1B, electronic device 100 can send interactive information ① to the server side. For example... Figure 1As shown, the interactive information ① may include user-selected content and user private domain data 1. The electronic device 100 can also receive interactive information ② received from the server side. For example... Figure 1 As shown, the interactive information ② may also include podcast 1.

[0121] Optionally, in some feasible examples, electronic device 100 may also send only user-selected content to the server side. The server side may generate podcast 1 based on the received user-selected content.

[0122] Function 1C: Upload podcast 1 and user private domain data 1 to the server side and provide a user interface for setting permissions for user private domain data 1.

[0123] Electronic device 100 can upload podcast 1 and user private data 1 to the server based on user operation. When uploading podcast 1 and user private data 1, the user can also set permissions for user private data 1 on electronic device 100. For example, the user can also set permissions to allow user B's electronic device (e.g., electronic device 200) to access user private data 1. Electronic devices that do not have permission to access user private data 1 cannot access user private data 1 on the server side. Electronic device 100 can also send the user's permission settings for user private data 1 to the server side.

[0124] In other words, when implementing this function 1C, the electronic device 100 can send interactive information ③ to the server side. This interactive information ③ may include podcast 1 and user private domain data 1.

[0125] For details on how users operate on electronic device 100, including uploading podcast 1 and user private data 1, please refer to the following section. Figures 10A-10C The description will not be repeated here.

[0126] Function 1D: Send podcast 1 and user private data 1 to electronic device 200.

[0127] Electronic device 100 can receive the user's action to share podcast 1 and send podcast 1 and user private data 1 to electronic device 200. For details on how the user operates the sharing of podcast 1 and user private data 1 on electronic device 100, please refer to the following section. Figures 11A-11C The description will not be repeated here.

[0128] When electronic device 100 performs this function 1D, it can send interactive information ⑥ to electronic device 200, such as Figure 1 As shown, the interactive information ⑥ may include podcast 1 and user private domain data 1.

[0129] Function 1E: Play podcast 1 and receive user-input question information 1 during the playback of podcast 1.

[0130] Electronic device 100 can play podcast 1 based on user operation. During the playback of podcast 1, electronic device 100 can receive user question information 1. This question information 1 can be identified from the user's voice input or text input by the user. This embodiment does not limit the input method or specific content of the question information 1. For details on how the user operates electronic device 100 to play the podcast, and how the user asks questions during podcast 1 playback, please refer to the following description. Figures 9A-9E The description will not be repeated here.

[0131] Function 1F: Send question information 1 to the server side and receive the question answer 1 corresponding to question information 1 sent by the server side.

[0132] When implementing this function 1E, electronic device 100 can send interactive information ④ to the server side, such as... Figure 1 As shown, the interactive information ④ may include the aforementioned question information 1. The electronic device 100 can receive the interactive information ⑤ sent by the server side, such as... Figure 1 As shown, the interactive information ⑤ may include the question answer 1.

[0133] Electronic device 200 can be used to perform one or more of the following functions:

[0134] Function 2A: Select to receive podcast 1 and user private domain data 1, and obtain user private domain data 1 related to podcast 1 from electronic device 200.

[0135] Electronic device 200 can receive podcast 1 and user private data 1 sent by electronic device 100. After receiving podcast 1, electronic device 200 can search for user private data 2 within electronic device 200. Electronic device 200 can search for user shopping application search history, shopping information, shopping cart information, favorited items, chat information in chat software, ticket purchase information (departure time, departure location, arrival time, arrival location, etc. of train tickets, high-speed rail tickets, air tickets, etc., and attraction ticket information (e.g., attraction entry time, location, etc.)), schedule reminders, ticket purchase SMS messages, call records, etc. as user private data 2.

[0136] In other examples, the user private data 2 may also include user health information (e.g., blood sugar, blood pressure, heart rate, etc.) stored in the electronic device 200.

[0137] This application does not limit the specific nature of the user's private domain data 2 in the embodiments.

[0138] When implementing function 2A, electronic device 200 can receive interactive information ⑥ sent by electronic device 100. For example... Figure 1 As shown, the interactive information ⑥ may include podcast 1 and user private domain data 1.

[0139] Function 2B: Provides users with a Q&A control for podcast 1, and receives questions 2 entered by users during the playback of podcast 1.

[0140] While playing podcast 1, electronic device 200 can also receive question information 2 entered by the user when interacting with the question-and-answer control. Then, electronic device 200 can send question information 2 to the server side.

[0141] The question information 2 can be recognized from the user's voice input or from the user's text input. This application embodiment does not limit the input method or specific content of the question information 2.

[0142] Question information 2 may be the same as or different from question information 1. This application embodiment does not impose any specific limitations on question information 1 and question information 2.

[0143] Function 2C: Send question information 2 to the server and obtain public network knowledge 2 obtained by the server based on question information 2. Based on user private domain data 1, user private domain data 2 and public network knowledge 2, obtain the question answer 2 corresponding to question information 2.

[0144] Electronic device 200 can summarize and extract information from public network knowledge 2, user private domain data 1, and user private domain data 2 to obtain question answer 2 related to question information 2. Question answer 2 may include information such as the names and locations of one or more attractions. For example, if user private domain data 1 includes ticket purchase information for attraction 1, and user private domain data 2 includes chat history information about "wanting to visit attraction 2," then question answer 2 may include attraction 2 and its ticket purchase method, attraction 1 and its ticket purchase method, etc.

[0145] This application embodiment does not limit the specific content of the answer to question 2.

[0146] That is, when electronic device 200 implements this function 2C, electronic device 200 can send interactive information to the server side. For example... Figure 1As shown, the interactive information ⑦ may include question information 2. The electronic device 200 can also receive interactive information ⑧ sent from the server side. For example... Figure 1 As shown, the interactive information ⑧ may include public network knowledge 2.

[0147] Function 2D: Sends question information 2 and user private domain data 2 to the server side, and receives the question answer 2 corresponding to the question information 2 sent by the server side.

[0148] The electronic device 100 can also send a question message 2 and user private data 2 to the server. The server receives the question message 2 and user private data 2. The server can obtain the question answer 2 based on the question message 2 and user private data 2.

[0149] Optionally, in some feasible examples, if the server side determines that the electronic device 100 has permission to access the user's private domain data 1, the server side can obtain the question answer 2 corresponding to the question information 2 based on the user's private domain data 1, the user's private domain data 2, and the question information 2.

[0150] That is, when the electronic device 200 implements this function 2D, it can send interactive information ⑨ to the server side. For example... Figure 1 As shown, the interactive information ⑨ may include the question information 2 and the user's private domain data 2. The electronic device 200 can also receive interactive information ⑩ sent from the server side. For example... Figure 1 As shown, the interactive information ⑩ may include the question and answer 2.

[0151] The server side can be used to implement one or more of the following functions:

[0152] Function 3A: Receive user-selected content and user private domain data 1, generate podcast 1 based on user-selected content and user private domain data 1, and send podcast 1 to electronic device 100.

[0153] The server can receive user-selected content and user private data 1 sent by electronic device 100, and generate podcast 1 based on the user-selected content and user private data 1. The server can also send podcast 1 to electronic device 100.

[0154] Function 3B: Receive and store podcasts 1 and user private data 1 sent by electronic device 100.

[0155] The server can receive podcast 1 and user private data 1, along with related permission settings information, sent by electronic device 100. The server can store podcast 1 and user private data 1, and can set permissions for user private data 1 according to its permission settings. For example, the server can configure user private data 1 to be accessible by electronic device 200.

[0156] Function 3C: Receives question information 1 sent by electronic device 100, and searches for public network knowledge 1 based on question information 1.

[0157] The server can search for public internet knowledge 1 related to question information 1. For example, if question information 1 is "Xi'an food recommendations", then the server can search for "Xi'an food recommendations" on the globally accessible internet and obtain knowledge related to Xi'an food and Xi'an food recommendations, which is the aforementioned public internet knowledge 1. For example, public internet knowledge 1 may include multiple web pages introducing Xi'an food, Xi'an food ranking web pages, videos and audio related to Xi'an food introductions, etc.

[0158] In this embodiment of the application, content and knowledge searchable on the Internet that are publicly accessible globally can be referred to as public network knowledge. That is, when the server side implements this function 3C, the server side can receive the interactive information ④ sent by the electronic device 100. For example... Figure 1 As shown, the interactive information ④ may include the question information 1.

[0159] Function 3D: Generates answer 1 based on public network knowledge 1 related to question information 1 and user private domain data 1, and sends answer 1 to electronic device 100.

[0160] The server can obtain the question answer 1 based on public network knowledge 1 and user private domain data 1. For example, the server can have a model 1, into which public network knowledge 1 and user private domain data 1 can be input, and model 1 can output the question answer 1. This model 1 can summarize and refine public network knowledge 1 and user private domain data 1 to obtain the question answer 1 related to the question information 1. For example, the question answer 1 may include multiple food names and the names and addresses of one or more restaurants that offer these foods. If user private domain data 1 includes "the child likes to eat mutton," the question answer 1 may include one or more of the following: mutton soup, mutton stew, roasted mutton, etc. The question answer 1 may also include the names and addresses of restaurants that offer mutton soup, mutton stew, roasted mutton, etc.

[0161] This application embodiment does not limit the specific content included in the answer to the question 1.

[0162] The server can send the answer to the question 1 to the electronic device 100. That is, when implementing this 3D function, the server can send interactive information ⑤ to the electronic device 100. For example... Figure 1 As shown, the interactive information ⑤ may include the question answer 1.

[0163] Alternatively, in one possible implementation, the electronic device 100 may not upload the user's private domain data 1 to the server. The electronic device 100 can send the question information 1 to the server. The server obtains public network knowledge 1 based on the question information 1 and sends the public network knowledge 1 to the electronic device 100. The electronic device 100 obtains the question answer 1 based on the public network knowledge 1 and the user's private domain data 1.

[0164] Function 3E: Receives question information 2 sent by electronic device 200, searches for public network knowledge 2 based on question information 2, and sends public network knowledge 2 to electronic device 200.

[0165] The server can search for public internet knowledge 2 related to question information 2 based on question information 2. For example, if question information 2 is "Recommended attractions in Xi'an", then the server can search for "Recommended attractions in Xi'an" on the globally accessible internet and obtain knowledge related to recommended attractions in Xi'an, which is the aforementioned public internet knowledge 2. For example, public internet knowledge 2 may include multiple web pages introducing Xi'an attractions, web pages ranking Xi'an attractions, videos and audio recordings related to Xi'an attractions, etc.

[0166] That is, when the server implements this function 3E, the server can receive interactive information ⑦, such as Figure 1 As shown, the interactive information ⑦ may include the question information 2. The server can also send interactive information ⑧ to the electronic device 200. For example... Figure 1 As shown, the interactive information ⑧ may include public network knowledge 2.

[0167] Function 3F: Receives question information 2 and user private domain data 2 sent by electronic device 200, searches for public network knowledge 2 based on question information 2, obtains question answer 2 based on public network knowledge 2, user private domain data 1, and user private domain data 2, and sends question answer 2 to electronic device 200.

[0168] The server can receive the question information 2 and user private domain data 2 sent by electronic device 200. The server can also search for public network knowledge 2 based on the question information 2. The server can summarize and refine the public network knowledge 2 and user private domain data 2 to obtain the question answer 2 corresponding to the question information 2. Question answer 2 may include information such as the names and locations of one or more attractions. For example, if user private domain data 1 includes ticketing information for attraction 1, and user private domain data 2 includes chat logs stating "I want to go to attraction 2," then question answer 2 may include attraction 2 and its ticketing method, attraction 1 and its ticketing method, etc.

[0169] This application embodiment does not limit the specific content of the answer to question 2.

[0170] Optionally, in some possible implementations, after the server side determines that the electronic device 200 has permission to access the user's private domain data 1, the server side can obtain the question answer 2 corresponding to the question information 2 based on public network knowledge 2, user's private domain data 1, and user's private domain data 2.

[0171] Based on system 10, the podcast generation method provided in this application embodiment may include the following parallel schemes:

[0172] Option 1:

[0173] Electronic device 100 can be used to implement functions 1A, 1C, 1D, 1E, and 1F. Electronic device 200 can be used to implement functions 2A, 2B, and 2C. The server side can be used to implement functions 3A, 3B, 3C, 3D, and 3E.

[0174] In the implementation of Scheme 1, electronic device 100 interacts with the server through information flows including interactive information ③, interactive information ④, and interactive information ⑤. Electronic device 100 interacts with electronic device 200 through interactive information ⑥. Electronic device 200 interacts with the server through information flows including interactive information ⑦ and interactive information ⑧.

[0175] Option 2:

[0176] Electronic device 100 can be used to implement functions 1A, 1C, 1D, 1E, and 1F. Electronic device 200 can be used to implement functions 2A, 2B, and 2D. The server side can be used to implement functions 3A, 3B, 3C, 3D, and 3F.

[0177] In the implementation of Scheme 1, electronic device 100 interacts with the server through information flows including interactive information ③, interactive information ④, and interactive information ⑤. Electronic device 100 interacts with electronic device 200 through interactive information ⑥. Electronic device 200 interacts with the server through information flows including interactive information ⑨ and interactive information ⑩.

[0178] Option 3:

[0179] Electronic device 100 can be used to implement functions 1B, 1C, 1D, 1E, and 1F. Electronic device 200 can be used to implement functions 2A, 2B, and 2C. The server side can be used to implement functions 3A, 3B, 3C, 3D, and 3E.

[0180] In the implementation of Scheme 1, electronic device 100 interacts with the server through information flows including interactive information ①, interactive information ②, interactive information ③, interactive information ④, and interactive information ⑤. Electronic device 100 interacts with electronic device 200 through interactive information ⑥. Electronic device 200 interacts with the server through information flows including interactive information ⑦ and interactive information ⑧.

[0181] Option 4:

[0182] Electronic device 100 can be used to implement functions 1B, 1C, 1D, 1E, and 1F. Electronic device 200 can be used to implement functions 2A, 2B, and 2D. The server side can be used to implement functions 3A, 3B, 3C, 3D, and 3F.

[0183] In the implementation of Scheme 1, electronic device 100 interacts with the server through information flows including interactive information ①, interactive information ②, interactive information ③, interactive information ④, and interactive information ⑤. Electronic device 100 interacts with electronic device 200 through interactive information ⑥. Electronic device 200 interacts with the server through information flows including interactive information ⑨ and interactive information ⑩.

[0184] In another possible implementation, the server side can simultaneously implement functions 3A and 3B. That is, the server side will not actively save podcast 1 and user private data 1 after generating podcast 1. Only after electronic device 100 actively chooses to upload podcast 1 and user private data 1 will the server side save podcast 1 and user private data 1.

[0185] Alternatively, in another possible implementation, the server side may include multiple servers, where one server can be used to implement function 3A and another server can be used to implement function 3B. That is, the server that generates podcast 1 may not be the same server that stores podcast 1.

[0186] It is understood that the functions that electronic device 100, electronic device 200, and the server can implement can be combined arbitrarily, and the solutions formed by their combinations are all within the protection scope of this application.

[0187] In this application embodiment, the electronic device 100 may include, but is not limited to: mobile phones, tablet computers, desktop computers, laptop computers, handheld computers, laptops, ultra-mobile personal computers (UMPCs), netbooks, cellular phones, personal digital assistants (PDAs), augmented reality (AR) devices, virtual reality (VR) devices, artificial intelligence (AI) devices, wearable devices (e.g., smartwatches, smart bracelets, etc.), in-vehicle devices, and smart home devices (e.g., smart TVs, smart screens, large-screen devices, etc.). This application embodiment does not limit the specific form or type of the electronic device 100.

[0188] Electronic device 200 may include, but is not limited to: mobile phones, tablets, desktop computers, laptops, handheld computers, ultra-mobile personal computers (UMPCs), netbooks, cellular phones, personal digital assistants (PDAs), augmented reality (AR) devices, virtual reality (VR) devices, artificial intelligence (AI) devices, wearable devices (e.g., smartwatches, smart bracelets), in-vehicle devices, and smart home devices (e.g., smart TVs, smart screens, large-screen devices). This application does not limit the specific form or type of electronic device 200.

[0189] The server side can be a single server, a server cluster consisting of multiple servers, or a cloud computing center. This application does not limit the specific type of server in this embodiment.

[0190] The hardware and software structures of the electronic devices 100 and 200, and the server side involved in the embodiments of this application will be described below.

[0191] Figure 2 This is a schematic diagram of the structure of the electronic device 100 provided in the embodiments of this application.

[0192] The following detailed description uses electronic device 100 as an example. It should be understood that electronic device 100 may have more or fewer components than shown in the figures, may combine two or more components, or may have different component configurations. The various components shown in the figures can be implemented in hardware, software, or a combination of hardware and software, including one or more signal processing and / or application-specific integrated circuits.

[0193] Electronic device 100 may include: processor 110, external memory interface 120, internal memory 121, universal serial bus (USB) interface 130, charging management module 140, power management module 141, battery 142, antenna 1, antenna 2, mobile communication module 150, wireless communication module 160, audio module 170, speaker 170A, receiver 170B, microphone 170C, headphone jack 170D, sensor module 180, button 190, motor 191, indicator 192, camera 193, display screen 194, etc.

[0194] It is understood that the structures illustrated in the embodiments of this application do not constitute a specific limitation on the electronic device 100. In other embodiments of this application, the electronic device 100 may include more or fewer components than illustrated, or combine some components, or split some components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0195] Processor 110 may include one or more processing units, such as: application processor (AP), modem processor, graphics processing unit (GPU), image signal processor (ISP), controller, memory, video codec, digital signal processor (DSP), baseband processor, and / or neural network processing unit (NPU), etc. Different processing units may be independent devices or integrated into one or more processors.

[0196] The controller can be the nerve center and command center of the electronic device 100. The controller can generate operation control signals according to the instruction opcode and timing signals to complete the control of fetching and executing instructions.

[0197] The processor 110 may also include a memory for storing instructions and data. In some embodiments, the memory in the processor 110 is a cache memory. This memory can store instructions or data that the processor 110 has just used or that are used repeatedly. If the processor 110 needs to use the instruction or data again, it can retrieve it directly from the memory. This avoids repeated accesses, reduces the waiting time of the processor 110, and thus improves the efficiency of the system.

[0198] USB port 130 is a USB standard compliant interface, specifically a Mini USB port, Micro USB port, USB Type-C port, etc. USB port 130 can be used to connect a charger to charge electronic device 100, and can also be used for data transfer between electronic device 100 and peripheral devices. It can also be used to connect headphones for audio playback. This interface can also be used to connect other electronic devices, such as AR devices.

[0199] It is understood that the interface connection relationships between the modules illustrated in the embodiments of this application are merely illustrative and do not constitute a structural limitation on the electronic device 100. In other embodiments of this application, the electronic device 100 may also employ different interface connection methods or combinations of multiple interface connection methods as described in the above embodiments.

[0200] The charging management module 140 receives charging input from a charger, which can be a wireless charger or a wired charger. While charging the battery 142, the charging management module 140 can also supply power to the electronic device via the power management module 141.

[0201] The power management module 141 is used to connect the battery 142, the charging management module 140, and the processor 110. The power management module 141 receives input from the battery 142 and / or the charging management module 140 to power the processor 110, internal memory 121, external memory, display 194, camera 193, and wireless communication module 160, etc.

[0202] The wireless communication function of electronic device 100 can be realized through antenna 1, antenna 2, mobile communication module 150, wireless communication module 160, modem processor and baseband processor, etc.

[0203] Antenna 1 and antenna 2 are used to transmit and receive electromagnetic wave signals. Each antenna in electronic device 100 can be used to cover one or more communication frequency bands. Different antennas can also be multiplexed to improve antenna utilization. For example, antenna 1 can be multiplexed as a diversity antenna for a wireless local area network. In some other embodiments, the antennas can be used in conjunction with tuning switches.

[0204] The mobile communication module 150 can provide solutions for wireless communication, including 2G / 3G / 4G / 5G, applied to the electronic device 100. The mobile communication module 150 may include at least one filter, switch, power amplifier, low noise amplifier (LNA), etc.

[0205] The wireless communication module 160 can provide solutions for wireless communication applications on the electronic device 100, including wireless local area networks (WLAN) (such as wireless fidelity (Wi-Fi) networks), Bluetooth (BT), global navigation satellite system (GNSS), frequency modulation (FM), near field communication (NFC), infrared (IR) technology, etc.

[0206] Electronic device 100 implements display functions through a GPU, a display screen 194, and an application processor. The GPU is a microprocessor for image processing, connecting the display screen 194 and the application processor. The GPU is used to perform mathematical and geometric calculations and for graphics rendering.

[0207] The display screen 194 is used to display images, videos, etc. The display screen 194 can be a liquid crystal display (LCD), an OLED display, etc. This application embodiment does not limit the material of the display screen 194. In some embodiments, the display screen 194 may also include a flexible foldable screen. In some embodiments, the electronic device 100 may include one or N display screens 194, where N is a positive integer greater than 1.

[0208] Electronic device 100 can perform shooting functions through ISP, camera 193, video codec, GPU, display 194 and application processor.

[0209] The ISP is used to process data fed back from the camera 193. For example, when taking a picture, the shutter is opened, and light is transmitted through the lens to the camera's photosensitive element. The light signal is converted into an electrical signal, and the camera's photosensitive element transmits the electrical signal to the ISP for processing, converting it into an image visible to the naked eye.

[0210] Camera 193 is used to capture still images or videos. In some embodiments, electronic device 100 may include one or N cameras 193, where N is a positive integer greater than 1.

[0211] Digital signal processors (DSPs) are used to process digital signals. Besides digital image signals, they can also process other digital signals. For example, when electronic device 100 selects a frequency, the DSP can perform Fourier transforms on the frequency energy.

[0212] NPU stands for Neural Network (NN) Computing Processor. By borrowing the structure of biological neural networks, such as the transmission patterns between neurons in the human brain, it can rapidly process input information and continuously learn on its own. NPUs enable intelligent cognitive applications in electronic devices, such as AI image generation, image fusion, image recognition, facial recognition, speech recognition, and text understanding.

[0213] The external storage interface 120 can be used to connect an external memory card, such as a Micro SD card, to expand the storage capacity of the electronic device 100. The external memory card communicates with the processor 110 through the external storage interface 120 to perform data storage functions. For example, music, video, and other files can be saved on the external memory card.

[0214] Internal memory 121 can be used to store computer executable program code, which includes instructions. Processor 110 executes various functional applications and data processing of electronic device 100 by running the instructions stored in internal memory 121. Internal memory 121 may include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as sound playback, image playback, etc.), etc. The data storage area may store data created during the use of electronic device 100 (such as audio data, phonebook, etc.). Furthermore, internal memory 121 may include high-speed random access memory and may also include non-volatile memory, such as at least one disk storage device, flash memory device, universal flash storage (UFS), etc.

[0215] Electronic device 100 can implement audio functions, such as music playback and recording, through audio module 170, speaker 170A, receiver 170B, microphone 170C, headphone jack 170D, and application processor.

[0216] Audio module 170 is used to convert digital audio information into analog audio signal output, and also to convert analog audio input into digital audio signal. Audio module 170 can also be used for encoding and decoding audio signals.

[0217] The sensor module 180 may include pressure sensors, gyroscope sensors, barometric pressure sensors, magnetic sensors, accelerometers, gravity sensors, distance sensors, proximity sensors, fingerprint sensors, temperature sensors, touch sensors, ambient light sensors, bone conduction sensors, angle sensors, etc.

[0218] The gyroscope sensor can be used to determine the motion attitude of the electronic device 100. In some embodiments, the angular velocity of the electronic device 100 about three axes (i.e., the x, y, and z axes) can be determined by the gyroscope sensor. The offset angle of the electronic device 100 can also be determined by the gyroscope sensor.

[0219] An accelerometer can detect the magnitude of acceleration of an electronic device 100 in various directions (typically three axes). In some embodiments, the accelerometer can be used to identify the posture of the electronic device 100, and can be applied to applications such as screen orientation switching and pedometers.

[0220] Magnetic sensors can include Hall effect sensors, magnetometers, and so on.

[0221] Angle sensors can be used to detect the folding angle of a 100° foldable screen in electronic devices.

[0222] Buttons 190 include a power button, volume buttons, etc. Motor 191 can generate vibration feedback. Indicator 192 can be an indicator light, used to indicate charging status, battery level changes, and also to indicate messages, missed calls, notifications, etc.

[0223] Figure 3 This is a schematic diagram of the structure of the electronic device 200 provided in the embodiments of this application.

[0224] The following detailed description uses electronic device 200 as an example. It should be understood that electronic device 200 may have more or fewer components than shown in the figures, may combine two or more components, or may have different component configurations. The various components shown in the figures can be implemented in hardware, software, or a combination of hardware and software, including one or more signal processing and / or application-specific integrated circuits.

[0225] Electronic device 200 may include: processor 210, external memory interface 220, internal memory 221, universal serial bus (USB) interface 230, charging management module 240, power management module 241, battery 242, antenna 1, antenna 2, mobile communication module 250, wireless communication module 260, audio module 270, speaker 270A, receiver 270B, microphone 270C, headphone jack 270D, sensor module 280, button 290, motor 291, indicator 292, camera 293, display screen 294, etc.

[0226] It is understood that the structures illustrated in the embodiments of this application do not constitute a specific limitation on the electronic device 200. In other embodiments of this application, the electronic device 200 may include more or fewer components than illustrated, or combine some components, or split some components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0227] Processor 210 may include one or more processing units, such as application processor (AP), modem processor, graphics processing unit (GPU), image signal processor (ISP), controller, memory, video codec, digital signal processor (DSP), baseband processor, and / or neural network processing unit (NPU). Different processing units may be independent devices or integrated into one or more processors.

[0228] The controller can be the nerve center and command center of the electronic device 200. The controller can generate operation control signals based on the instruction opcode and timing signals to control the fetching and execution of instructions.

[0229] The processor 210 may also include a memory for storing instructions and data. In some embodiments, the memory in the processor 210 is a cache memory. This memory can store instructions or data that the processor 210 has just used or that are used repeatedly. If the processor 210 needs to use the instruction or data again, it can directly retrieve it from the memory. This avoids repeated accesses, reduces the waiting time of the processor 210, and thus improves the efficiency of the system.

[0230] USB port 230 is a USB standard compliant interface, specifically a Mini USB port, Micro USB port, or USB Type-C port. USB port 230 can be used to connect a charger to charge electronic device 200, and can also be used for data transfer between electronic device 200 and peripheral devices. It can also be used to connect headphones for audio playback. This interface can also be used to connect other electronic devices, such as AR devices.

[0231] It is understood that the interface connection relationships between the modules illustrated in the embodiments of this application are merely illustrative and do not constitute a structural limitation on the electronic device 200. In other embodiments of this application, the electronic device 200 may also employ different interface connection methods or combinations of multiple interface connection methods as described in the above embodiments.

[0232] The charging management module 240 receives charging input from a charger, which can be a wireless charger or a wired charger. While charging the battery 242, the charging management module 240 can also supply power to the electronic device via the power management module 241.

[0233] The power management module 241 is used to connect the battery 242, the charging management module 240, and the processor 210. The power management module 241 receives input from the battery 242 and / or the charging management module 240 to power the processor 210, internal memory 221, external memory, display 294, camera 293, and wireless communication module 260, etc.

[0234] The wireless communication function of electronic device 200 can be implemented through antenna 1, antenna 2, mobile communication module 250, wireless communication module 260, modem processor, and baseband processor.

[0235] Antenna 1 and antenna 2 are used to transmit and receive electromagnetic wave signals. Each antenna in electronic device 200 can be used to cover one or more communication frequency bands. Different antennas can also be multiplexed to improve antenna utilization. For example, antenna 1 can be multiplexed as a diversity antenna for a wireless local area network. In some other embodiments, the antennas can be used in conjunction with a tuning switch.

[0236] The mobile communication module 250 can provide solutions for wireless communication, including 2G / 3G / 4G / 5G, applied to the electronic device 200. The mobile communication module 250 may include at least one filter, switch, power amplifier, low noise amplifier (LNA), etc.

[0237] The wireless communication module 260 can provide solutions for wireless communication applications on the electronic device 200, including wireless local area networks (WLAN) (such as wireless fidelity (Wi-Fi) networks), Bluetooth (BT), global navigation satellite system (GNSS), frequency modulation (FM), near field communication (NFC), infrared (IR) technology, etc.

[0238] Electronic device 200 implements display functions through a GPU, a display screen 294, and an application processor. The GPU is a microprocessor for image processing, connecting the display screen 294 and the application processor. The GPU is used to perform mathematical and geometric calculations and for graphics rendering.

[0239] The display screen 294 is used to display images, videos, etc. The display screen 294 can be a liquid crystal display (LCD), an OLED display, etc. This application embodiment does not limit the material of the display screen 294. In some embodiments, the display screen 294 may also include a flexible foldable screen. In some embodiments, the electronic device 200 may include one or N display screens 294, where N is a positive integer greater than 1.

[0240] Electronic device 200 can perform shooting functions through ISP, camera 293, video codec, GPU, display screen 294 and application processor.

[0241] The ISP is used to process data fed back from the camera 293. For example, when taking a picture, the shutter is opened, and light is transmitted through the lens to the camera's photosensitive element. The light signal is converted into an electrical signal, and the camera's photosensitive element transmits the electrical signal to the ISP for processing, converting it into an image visible to the naked eye.

[0242] Camera 293 is used to capture still images or videos. In some embodiments, electronic device 200 may include one or N cameras 293, where N is a positive integer greater than 1.

[0243] Digital signal processors (DSPs) are used to process digital signals. Besides digital image signals, they can also process other digital signals. For example, when electronic device 200 selects a frequency, the DSP is used to perform Fourier transforms on the frequency energy.

[0244] NPU stands for Neural Network (NN) Computing Processor. By borrowing the structure of biological neural networks, such as the transmission patterns between neurons in the human brain, it can rapidly process input information and continuously learn on its own. NPUs enable intelligent cognitive applications in electronic devices, such as AI image generation, image fusion, image recognition, facial recognition, speech recognition, and text understanding.

[0245] The external storage interface 220 can be used to connect an external memory card, such as a Micro SD card, to expand the storage capacity of the electronic device 200. The external memory card communicates with the processor 210 through the external storage interface 220 to perform data storage functions. For example, music, video, and other files can be saved on the external memory card.

[0246] Internal memory 221 can be used to store computer executable program code, which includes instructions. Processor 210 executes various functional applications and data processing of electronic device 200 by running the instructions stored in internal memory 221. Internal memory 221 may include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as sound playback, image playback, etc.), etc. The data storage area may store data created during the use of electronic device 200 (such as audio data, phonebook, etc.). Furthermore, internal memory 221 may include high-speed random access memory and may also include non-volatile memory, such as at least one disk storage device, flash memory device, universal flash storage (UFS), etc.

[0247] Electronic device 200 can implement audio functions such as music playback and recording through audio module 270, speaker 270A, receiver 270B, microphone 270C, headphone jack 270D, and application processor.

[0248] Audio module 270 is used to convert digital audio information into analog audio signal output, and also to convert analog audio input into digital audio signal. Audio module 270 can also be used for encoding and decoding audio signals.

[0249] The sensor module 280 may include pressure sensors, gyroscope sensors, barometric pressure sensors, magnetic sensors, accelerometers, gravity sensors, distance sensors, proximity sensors, fingerprint sensors, temperature sensors, touch sensors, ambient light sensors, bone conduction sensors, angle sensors, etc.

[0250] The gyroscope sensor can be used to determine the motion attitude of the electronic device 200. In some embodiments, the angular velocity of the electronic device 200 about three axes (i.e., the x, y, and z axes) can be determined by the gyroscope sensor. The offset angle of the electronic device 200 can also be determined by the gyroscope sensor.

[0251] An accelerometer can detect the magnitude of acceleration of an electronic device 200 in various directions (typically three axes). In some embodiments, the accelerometer can be used to identify the posture of the electronic device 200, and can be applied to applications such as screen orientation switching and pedometers.

[0252] Magnetic sensors can include Hall effect sensors, magnetometers, and so on.

[0253] Angle sensors can be used to detect the folding angle of a 200° foldable screen in electronic devices.

[0254] Buttons 290 include a power button, volume buttons, etc. Motor 291 can generate vibration feedback. Indicator 292 can be an indicator light, used to indicate charging status, battery level changes, and also to indicate messages, missed calls, notifications, etc.

[0255] Figure 4 This is a schematic diagram of the server-side structure provided in an embodiment of this application.

[0256] The following description uses the server side as an example to illustrate the embodiment. It should be understood that the server side may have more or fewer components than shown in the figures, may combine two or more components, or may have different component configurations. The various components shown in the figures can be implemented in hardware, software, or a combination of hardware and software, including one or more signal processing and / or application-specific integrated circuits.

[0257] The server side may include: processor 301, internal memory 302, communication module 303, power supply unit 304, etc.

[0258] It is understood that the structures illustrated in the embodiments of this application do not constitute a specific limitation on the server side. In other embodiments of this application, the server side may include more or fewer components than illustrated, or combine some components, or split some components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0259] Processor 301 may include one or more processing units, such as: application processor (AP), modem processor, graphics processing unit (GPU), image signal processor (ISP), controller, memory, video codec, digital signal processor (DSP), baseband processor, and / or neural network processing unit (NPU), etc. The different processing units may be independent devices or integrated into one or more processors.

[0260] The controller can serve as the central nervous system and command center on the server side. Based on the instruction opcode and timing signals, the controller generates operation control signals to control the fetching and execution of instructions.

[0261] The processor 301 may also include a memory for storing instructions and data. In some embodiments, the memory in the processor 301 is a cache memory. This memory can store instructions or data that the processor 301 has just used or that are used repeatedly. If the processor 301 needs to use the instruction or data again, it can directly retrieve it from the memory. This avoids repeated accesses, reduces the waiting time of the processor 301, and thus improves the efficiency of the system.

[0262] In this embodiment of the application, processor 301 can generate podcasts based on user-selected content sent by electronic device 100.

[0263] In this embodiment, the processor 301 can search for relevant public network knowledge 1 based on the question information 1 sent by the electronic device 100. The processor 301 can also obtain the question answer 1 corresponding to the question information 1 based on the public network knowledge 1 and the user's private domain data 1 uploaded by the electronic device 100. For details on the question information 1, public network knowledge 1, and question answer 1, please refer to the above description. Figure 1 The description will not be repeated here.

[0264] In this embodiment, the processor 301 can search for relevant public network knowledge 2 based on the query information 2 sent by the electronic device 200. For details on query information 2 and public network knowledge 2, please refer to the above description. Figure 1 The description will not be repeated here.

[0265] Internal memory 302 can be used to store computer executable program code, which includes instructions. Processor 301 executes various server-side functional applications and data processing by running the instructions stored in internal memory 302. Internal memory 302 may include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as sound playback, image playback, etc.), etc. The data storage area may store data created during server-side use (such as audio data, phonebook, etc.). Furthermore, internal memory 302 may include high-speed random access memory and may also include non-volatile memory, such as at least one disk storage device, flash memory device, universal flash storage (UFS), etc.

[0266] In this embodiment, the internal memory 302 can also be used to store podcasts uploaded by the electronic device 100, as well as user private domain data related to the podcasts.

[0267] The communication module 303 enables the server to communicate with other devices (e.g., electronic device 100, electronic device 200). The server can receive user-selected content uploaded by electronic device 100 through the communication module 303, and send podcasts generated based on the user-selected content to electronic device 100 through the same module.

[0268] In some examples, the server can also receive the question information 1 sent by the electronic device 100 through the communication module 303, and send the question answer 1 corresponding to the obtained question information 1 to the electronic device 100 through the communication module 303.

[0269] In some other examples, the server can also receive the question information 2 sent by the electronic device 200 through the communication module 303, and send the public network knowledge 2 related to the obtained question information 2 to the electronic device 200 through the communication module 303.

[0270] The power supply unit 304 can be used to supply power to components such as the processor 301, internal memory 302, and communication module 303 on the server side.

[0271] Figure 5 This is a software structure block diagram of an electronic device 100 according to an embodiment of this application. The operating system of the electronic device 100 may include multiple software structures. For example... Figure 5The electronic device 100 may include a device-side intelligent agent module 500, a knowledge base 504, and inAPP behavior data 505. The device-side intelligent agent module 500 may include a podcast generation module 501, a podcast management module 502, and a device-side data acquisition module 503.

[0272] The podcast generation module 501 provides a user interface for generating podcasts. Users can select relevant content for podcast generation, as well as set the podcast title and cover image, within this user interface. For details on the podcast generation user interface, please refer to the section below. Figures 8A-8C The description will not be repeated here.

[0273] The podcast management module 502 may include a storage submodule 5021, a sharing submodule 5022, and a playback submodule 5023. The storage submodule 5021 can be used to store podcasts and related user private data. The sharing submodule 5022 provides the functionality for sharing podcasts and a user interface for doing so. Users can select to share podcasts and related user private data within the user interface. For details on the user interface for sharing podcasts, please refer to the section below. Figures 11A-11C The description in [the documentation] will not be repeated here. The playback submodule 5023 provides the functionality to play podcasts and a related user interface for podcast playback. Users can select to play podcasts and ask questions about them in the user interface. For more information on the podcast playback user interface, please refer to the section below. Figures 9A-9E The description will not be repeated here.

[0274] The edge data acquisition module 503 can be used to collect local data 5041 and linked data 5042 stored in the knowledge base 504. Local data 5041 includes, but is not limited to, local files, images, videos, audio, etc., stored locally on the electronic device 100. Linked data 5042 includes, but is not limited to, web links, video links, etc.

[0275] The edge data acquisition module 503 can also be used to collect inAPP behavior data 505.

[0276] In this embodiment, inAPP behavioral data can refer to data generated by user operations in various applications installed on the electronic device 100. Examples include search records, shopping information, shopping cart information, and favorited items in a shopping application; chat information in a chat application; ticketing information (departure time, departure location, arrival time, and arrival location for train tickets, high-speed rail tickets, and airline tickets, etc.) and attraction ticket information (e.g., entry time and location of attractions) in a ticketing application; schedule reminders; ticketing SMS messages; call logs; and sports and health information. User private domain data can include this inAPP behavioral data. For example, inAPP behavioral data 505 can include favorites 5051, search records 5052, shopping cart 5053 in a shopping application, chat records 5054 in a chat application, and schedule information 5055 in a schedule application, etc.

[0277] It is understood that the operating system of electronic device 100 may include more software structures, and this application embodiment does not limit this.

[0278] Figure 6 This is a software structure block diagram of an electronic device 200 according to an embodiment of this application. The operating system of the electronic device 200 may include multiple software structures. For example... Figure 6 The electronic device 200 may include a device-side intelligent agent module 600, a knowledge base 604, and in-APP behavioral data 605. The device-side intelligent agent module 500 may include a podcast management module 601, a device-side large model 602, and a device-side data acquisition module 603.

[0279] The podcast management module 601 may include a storage submodule 6011, a sharing submodule 6012, and a playback submodule 6013. The storage submodule 6011 stores podcasts and related user private data (including user private data shared by other devices and user private data within the device itself). The sharing submodule 6012 provides the functionality to receive podcasts shared by other electronic devices and provides a related interface for receiving podcasts shared by other electronic devices. Users can select to receive podcasts shared by other electronic devices and related user private data in the interface for receiving podcasts shared by other electronic devices. For details on the interface for receiving podcasts shared by other electronic devices, please refer to the following section. Figures 12A-12C The description in [the documentation] will not be repeated here. The playback submodule 6013 can be used to provide the functionality to play podcasts and the related user interface for playing podcasts. Users can select to play podcasts and ask questions about podcasts in the related user interface. For details on the related user interface for playing podcasts, please refer to the section below. Figures 9A-9E The description will not be repeated here.

[0280] The edge-side large model 602 can be used to: obtain the answer corresponding to the user's question information based on public network knowledge related to the user's question information, user private domain data shared by other devices, and user private domain data in this device.

[0281] The edge data acquisition module 603 can be used to collect local data 6041 and linked data 6042 stored in the knowledge base 604. Local data 6041 includes, but is not limited to, local files, images, videos, audio, etc., stored locally on the electronic device 100. Linked data 6042 includes, but is not limited to, web page links, video links, etc.

[0282] The edge data acquisition module 603 can also be used to collect inAPP behavior data 605.

[0283] In this embodiment, inAPP behavioral data can refer to data generated by user operations in various applications installed on the electronic device 100. Examples include search records, shopping information, shopping cart information, and favorited items in a shopping application; chat information in a chat application; ticketing information (departure time, departure location, arrival time, and arrival location for train tickets, high-speed rail tickets, and airline tickets, etc.) and attraction ticket information (e.g., entry time and location of attractions) in a ticketing application; schedule reminders; ticketing SMS messages; call logs; and sports and health information. User private data can include this inAPP behavioral data. For example, inAPP behavioral data 605 can include favorites 6051, search records 6052, shopping cart 6053 in a shopping application, chat records 6054 in a chat application, and schedule information 6055 in a schedule application, etc.

[0284] It is understood that the operating system of electronic device 200 may include more software structures, and this application embodiment does not limit this.

[0285] Figure 7 This is a software architecture block diagram of the server side according to an embodiment of this application. The server-side operating system may include multiple software structures. For example... Figure 7 The server side may include a webpage link content parsing module 701, a video link content parsing module 702, a podcast generation module 703, and a public network knowledge retrieval module 704. Among them:

[0286] The webpage link content parsing module 701 can be used to extract valid links from the webpage links selected by the user for generating podcasts sent by the electronic device 100, verify the validity of the links, and find the corresponding webpages based on the webpage links. Furthermore, the webpage link content parsing module 701 can also be used to summarize and extract knowledge from the content of the webpages.

[0287] The video link content parsing module 702 can be used to extract valid links from the video links selected by the user for generating podcasts sent by the electronic device 100, verify the validity of the links, and find the corresponding video content based on the video links. Then, the video link content parsing module 702 can also be used to extract subtitle information from the video content and parse the video content in conjunction with the subtitle information to obtain parsed information. Finally, the video link content parsing module can also be used to summarize and extract knowledge from the parsed content.

[0288] The podcast generation module 703 can generate podcasts from the knowledge extracted from web pages by the web page link content parsing module 701, and / or the knowledge extracted from video content by the video link content parsing module 702, as well as the public network knowledge retrieval module 704 based on the public network knowledge searched for in the podcast topic.

[0289] The public network knowledge retrieval module 704 can be used to retrieve public network knowledge related to podcast topics. The public network knowledge retrieval module 704 can also be used to retrieve public network knowledge related to questions sent by electronic devices 100 or 200.

[0290] It is understood that the operating system on the server side may include more software structures, and the embodiments of this application do not limit this.

[0291] The following section introduces the user interface for generating, uploading, and sharing podcasts on electronic devices 100.

[0292] In this embodiment, the electronic device 100 can be configured with podcast generation functionality and controls for podcast generation in different application scenarios. In some scenarios, the electronic device 100 can configure podcast generation functionality and controls within a knowledge space. This knowledge space is a system function of the electronic device, which can collect content viewed by the user in other applications, such as web page links, video links, documents, etc. The user interface of this knowledge space can also display content that the user has selected to collect in the knowledge space.

[0293] Figures 8A-8C An example is shown of an electronic device 100 generating a podcast based on content that the user has viewed in other applications and which is collected in a knowledge space.

[0294] Figure 8A An exemplary embodiment of this application provides a user interface 800. This user interface 800 may be a user interface for the knowledge space mentioned above. This user interface 800 can be used to display multiple saved content items by a user, and to generate podcasts from one or more saved content items. For example... Figure 8AAs shown, the user interface 800 may include multiple collections of content that the user has saved, such as collection content 801, collection content 802, and collection content 803.

[0295] The title of the collection content 801 can be title 1, the application providing the collection content 801 can be application 1, the content contained in the collection content 801 can be content 1, the cover image of the collection content 801 can be image 1, and the collection date of the collection content 801 can be March 5.

[0296] The title of the collection content 802 can be title 2, the application providing the collection content 802 can be application 2, and the content contained in the collection content 802 can be content 2, the cover image of the collection content 802 can be image 2, and the collection date of the collection content 802 can be March 5.

[0297] The title of the collection content 803 can be title 3, the application providing the collection content 803 can be application 3, and the content contained in the collection content 803 can be content 3, the cover image of the collection content 803 can be image 3, and the collection date of the collection content 803 can be March 5.

[0298] The collected content 801, collected content 802, and collected content 803 can be any of the following: web page link, video link, document, image, etc. This application embodiment does not limit this.

[0299] like Figure 8A As shown, the user interface 800 may also include controls 804 and 805. Control 804 can be used to instruct the electronic device 100 to generate a podcast from content selected by the user. Control 805 can be used to add other content to the user interface 800 for generating the podcast.

[0300] After a user selects one or more favorite items, they can click control 804. In response to the user's action, electronic device 100 can display window 810.

[0301] Figure 8B A window 810 provided in an embodiment of this application is illustrated as an example. This window 810 can be used to display or set relevant information about the podcast to be generated (e.g., podcast title, cover image, reference sources, etc.). Optionally, this window 810 can be displayed over the user interface 800.

[0302] like Figure 8BAs shown, the window 810 may include a settings box 811, an option box 812, a settings box 813, a cover image display area 814, and controls 815. The settings box 811 can be used to display the reference source for generating the podcast (i.e., the content selected by the user). The option box 812 can be used to set the length of the podcast to be generated. For example, the user can select a concise version (podcast playback length of 5 minutes) or a detailed version (podcast playback length of 10 minutes) in the option box 812. It is understood that the above length setting options are only examples, and this application embodiment may have more or fewer length options, and the playback length of the podcast is not limited.

[0303] The settings box 813 can be used to display the podcast title generated by the electronic device 100 based on the reference source. Users can also enter the podcast title in the settings box 813, which is not limited in this embodiment.

[0304] The cover image display area 814 can be used to display the cover image of the podcast to be generated. This cover image can be intelligently generated by the electronic device 100 based on the podcast title and / or reference sources, or it can be an image uploaded by the user. Users can also edit the cover image displayed in the cover image display area 814, for example, by cropping, adding filters, etc. This application embodiment does not limit how the user specifically edits the cover image.

[0305] The user can click on control 815, and in response to the user's operation, electronic device 100 can display window 820.

[0306] Figure 8C A window 820 provided in an embodiment of this application is illustrated as an example. This window 820 can be used to display user private domain data related to the podcast to be generated in the electronic device 100. For example... Figure 8C As shown, window 820 may include user private data 821, control 8211, and control 8212. User private data 821 may come from call logs in a calling application; for example, user private data 821 could be "I'm going to Xi'an for tourism next week." This embodiment does not limit the specific content of user private data 821. Control 8211 can be used to modify user private data 821. When a user does not want user private data 821 to be used to generate the podcast or for the podcast's interactive process, the user can delete user private data 821 through control 8212.

[0307] like Figure 8CAs shown, the window 820 may also include user private data 823, control 8231, and control 8232. The user private data 823 may come from a calendar application; for example, the user private data 823 could be "Next Wednesday 15:00-17:00 Hangzhou Xiaoshan Airport T3 - Xi'an Xianyang Airport T1". This embodiment does not limit the specific content of the user private data 823. Control 8231 can be used to modify the user private data 823. When the user does not want the user private data 823 to be used to generate the podcast or for the podcast's interactive process, the user can delete the user private data 823 through control 8232.

[0308] like Figure 8C As shown, the window 820 may also include user private data 824, control 8241, and control 8242. The user private data 824 may originate from a communication application; for example, the user private data 824 may be "My child likes to eat lamb and barbecue." This embodiment of the application does not limit the specific content of the user private data 824. Control 8241 can be used to modify the user private data 824. When the user does not want the user private data 824 to be used to generate the podcast or for the interactive process of the podcast, the user can delete the user private data 824 through control 8242.

[0309] like Figure 8C As shown, the window 820 may also include user private data 825, control 8251, and control 8252. The user private data 825 may come from a sports and health application; for example, the user private data 825 may be "Your blood sugar is 160 mg / dL". This embodiment does not limit the specific content of the user private data 825. Control 8251 can be used to modify the user private data 825. When the user does not want the user private data 825 to be used to generate the podcast or for the podcast's interactive process, the user can delete the user private data 825 through control 8252.

[0310] The user private domain data related to the podcast to be generated shown in window 820 is merely an example. In this embodiment, the electronic device 100 may contain more or less user private domain data related to the podcast to be generated. Furthermore, the user private domain data related to the podcast to be generated contained in the electronic device 100 may also be different when the reference source and title of the podcast to be generated are different. This embodiment does not limit this.

[0311] In some examples, window 820 may also include controls 826, 827, and 828. Users can click control 826 to add user private domain data related to the podcast to be generated. Users can click control 827 to return to the previous screen, for example, to return to... Figure 8B The user interface shown is the display window 810 of the electronic device 100. The user can click control 828, and in response to this user action, the electronic device 100 can generate a podcast file based on the user-selected content, user private data related to the podcast to be generated, the podcast title, cover image, etc. Alternatively, the electronic device 100 can send the user-selected content, user private data related to the podcast to be generated, the podcast title, cover image, etc., to the server. Then, the server generates the podcast file based on the user-selected content, user private data related to the podcast to be generated, the podcast title, cover image, etc., and sends the podcast file to the electronic device 100. This podcast file can be an audio file.

[0312] Once a podcast is generated, users can play it on electronic devices 100 and interact with it. Figures 9A-9E An example is shown of an electronic device 100 playing a podcast and the related user interface for users to interact with the podcast.

[0313] Figure 9A An exemplary user interface 900 provided in an embodiment of this application is illustrated. This user interface 900 can be used to display podcast cards in an electronic device 100. For example... Figure 9A The user interface 900 may include a card 901. The card 901 may also include a control 902, a title 903, a cover image 904, and a control 905. A user can click the control 902, and in response to this user action, the electronic device 100 can directly play the podcast corresponding to the card 901. The title 903 is the title of the podcast corresponding to the card 901. The cover image 904 is the cover image of the podcast corresponding to the card 901. The control 905 can be used to view more operations related to the podcast corresponding to the card 901.

[0314] The user can operate on the card 901. For example, the user can click or double-click an area of ​​the card 901 other than the control 902, or click the control 902, etc. In response to the user's operation, the electronic device 100 displays the user interface 910.

[0315] Figure 9B An exemplary user interface 910 provided in an embodiment of this application is illustrated. This user interface 910 can be the playback interface for the podcast corresponding to the card 901. For example... Figure 9BAs shown, the user interface 900 may include control 911, cover image 912, title 913, control 914, anchor image 915a, anchor image 915b, playback progress bar 916, control 917a, control 917b, control 917c, control 917d, control 917e, and control 918.

[0316] Control 911 can hide or exit the user interface 900. The cover image 912 is the cover image of the podcast that is about to play or is currently playing (that is, the cover image of the podcast corresponding to card 901 above). The title 903 is the title of the podcast that is about to play or is currently playing. Control 914 can be used to view the reference sources of the podcast that is about to play or is currently playing.

[0317] The present invention includes images 915a and 915b, which are images of the podcast host about to play or currently playing. Images 915a and 915b can be used to indicate whether the host currently reading content from the podcast or answering user questions is the host corresponding to image 915a. For example, if the host corresponding to image 915a is currently reading the podcast, then image 915a can be highlighted (e.g., image 915a becomes larger, or its color is darkened). Similarly, if the host corresponding to image 915b is currently reading the podcast, then image 915b can be highlighted (e.g., image 915b becomes larger, or its color is darkened). This embodiment does not limit the method of highlighting images 915a and 915b.

[0318] The playback progress bar 916 can be used to indicate the playback progress of the podcast that is to be played or is currently playing in the current user interface 910, the total playback time (e.g., 5 minutes), etc.

[0319] Control 917a can be used to download the podcast currently playing or waiting to be played. Control 917b can be used to rewind the podcast currently playing in the user interface 910 by 10 seconds. Control 917c can be used to start or pause the podcast. Control 917d can be used to fast forward the podcast currently playing in the user interface 910 by 10 seconds. Control 917e can be used to set the playback speed of the podcast currently playing in the user interface 910 (e.g., 1x).

[0320] Users can interact with the podcast waiting to be played or currently playing on the user interface 910 through the control 918. Users can click the control 918 and input voice input into the electronic device 100. In response to this user action, the electronic device 100 can display, as shown below... Figure 9CThe voiceprint waveform 920 shown is the user-input voice collected by the electronic device 100. Optionally, the electronic device 100 may also display, for example, the voiceprint waveform 920. Figure 9C Controls 921 and 922 are shown. Control 921 can be used to trigger the electronic device 100 to display an input box and an input keyboard. The user can enter text information in the input box using the input keyboard. Control 922 can be used to delete voice input by the user.

[0321] After the user finishes inputting their voice, the electronic device 100 can recognize the user's voice input and display it as shown below. Figure 9D The icon 930 and text 931 are shown. The icon 930 and text 931 can be used to prompt the user that the electronic device 100 is processing the user's voice input (e.g., recognizing it, and providing a corresponding answer (or response text) based on the user's voice input).

[0322] After the electronic device 100 obtains the user's voice input and provides the corresponding answer, it can, for example... Figure 9E The user interface 910 shows answer 940. For example, answer 940 could be something like, "I recommend you go to restaurant xx at xx address for dinner next Wednesday. xx restaurant has lamb and barbecue, which your child likes, and they also have whole-grain staples like buckwheat noodles, which can help you control your blood sugar." The content of answer 940 relates to the user's private domain data in electronic device 100 (e.g., the aforementioned...). Figure 8C The answer 940 includes user private domain data 821, 823, 824, and 825. This data not only covers the user's arrival time in Xi'an, but also the child's dietary preferences mentioned in the chat, and the user's abnormal blood sugar levels recorded in the fitness app. This ensures that the answers received during the interaction with the podcast are more closely aligned with the user's own situation.

[0323] In some examples, when electronic device 100 recognizes the user's voice input, it obtains corresponding semantic information (e.g., recommendations for Xi'an cuisine). Electronic device 100 can then send this semantic information to the server. The server can then search for public internet knowledge related to this semantic information. The server can then obtain the answer corresponding to the semantic information based on the public internet knowledge and the user's private domain data. The server can then send this answer to electronic device 100. That is, the... Figure 9E The answer 940 shown in the image could be obtained from the server and then sent to the electronic device 100.

[0324] In other examples, when electronic device 100 recognizes the user's voice input and obtains corresponding semantic information (e.g., recommendations for Xi'an cuisine), it can then send this semantic information to a server. The server can then search for public internet knowledge related to this semantic information. The server can then send this public internet knowledge to electronic device 100. Finally, electronic device 100 can obtain the answer corresponding to the semantic information based on this public internet knowledge and the user's private domain data.

[0325] In other scenarios, electronic device 100 can configure the podcast generation function and related controls on the AI ​​search function on the negative one screen. When a user inputs a document question or summary using the AI ​​search function, electronic device 100 can search locally for files related to the input. The user can then choose to generate a podcast from the files found by electronic device 100. Electronic device 100 can generate podcasts based on user actions. Figures 9F-9G An exemplary illustration shows the relevant user interface for generating podcasts on the negative one screen of the electronic device 100 provided in this application embodiment.

[0326] Figure 9F An exemplary user interface 950 provided in an embodiment of this application is illustrated. In some examples, this user interface 950 may be referred to as the negative one screen of an electronic device 100. Figure 9F As shown, the user interface 950 may include an input box 951. The input box 951 may include a control 952 and text information 953 entered by the user. The control 952 is used to instruct the electronic device 100 to be in AI search mode, that is, to search for documents, videos, etc. related to the text information 953 in the local storage of the electronic device 100 based on the text information 953 entered by the user. For example, the text information 953 may be "Introduce Deepseek". This application embodiment does not limit the specific content of the text information 953.

[0327] Optionally, the user interface 950 may also include instruction information 954. The instruction information 954 may be used to indicate that the electronic device 100 is loading documents, videos, etc., related to the text information 953.

[0328] After the electronic device 100 finds a document and / or video related to the text information 953, the electronic device 100 can display, as follows: Figure 9GThe search results box 960 shown may include search results 961 and 962. Search result 961 may include the document "deepseek introduction document 1" related to text information 953, along with the document's size and whether it is a local file, etc. Search result 962 may include the document "deepseek introduction document 2" related to text information 953, along with the document's size and whether it is a local file, etc.

[0329] like Figure 9G As shown, the electronic device 100 can also display controls 963 and 964. Control 963 can be used to trigger the electronic device 100 to summarize and refine the search results to obtain the answer text. Control 964 is used to generate a podcast based on the search results displayed in the current user interface. The user can click on control 964, and in response to this user action, the electronic device 100 can display a podcast generation window for generating the podcast. For more information on the podcast generation window, please refer to [link to relevant documentation]. Figure 8B The window 810 shown in the image. For information on how electronic device 100 generates podcasts from search results, please refer to [link / reference]. Figures 8B-8C The descriptions shown in the document regarding generating podcasts from user-selected reference sources are not repeated here.

[0330] In other words, this application embodiment does not limit the scenarios in which the electronic device 100 can generate podcasts. The electronic device 100 can also set controls for generating podcasts on the document content display interface, video playback interface, or gallery display interface. Based on user operations, the displayed document content, videos, gallery, etc., can be used to generate podcasts.

[0331] Although the current document display interface may contain controls for reading the document, and the electronic device 100 can read the document content aloud in response to these controls, it does not summarize or extract the content. Furthermore, the user cannot interact with the document while it is being read aloud, negatively impacting the user experience.

[0332] While the video itself can be played, the generated podcast is a distillation of the video's content. Listening to a podcast is shorter than watching the entire video. Furthermore, users can interact with the generated podcast, adding to its engaging experience.

[0333] While the current electronic device 100 can generate videos from certain types of photos in its gallery or photos selected by the user, the generated videos lack accompanying descriptions. To address this, when a user wants to listen to the electronic device 100's descriptions of the photos and interact with them, the device can generate podcasts from those photos. This allows the user to listen to the descriptions by playing the podcast. Users can also interact with the podcast, increasing engagement and improving the user experience.

[0334] In some examples, users can also choose to upload podcasts generated on electronic device 100 to the server side. Figures 10A-10C An example is shown of the user interface for uploading podcasts on an electronic device 100.

[0335] Figure 10A An exemplary user interface 900 provided in an embodiment of this application is illustrated. For more information on this user interface 900, please refer to... Figure 9A The description in [the original text] will not be repeated here. For example... Figure 10A As described above, the user can click on control 905 in the user interface 900. In response to this user action, the electronic device 100 can display, as shown below. Figure 10B The menu bar 1000 shown is included. This menu bar 1000 may include multiple function options for the podcast corresponding to card 901.

[0336] For example, such as Figure 10B As shown, the menu bar 1000 may include function options 1001, 1002, 1003, 1004, 1005, and 1006. Function option 1001 can be used to upload the podcast corresponding to card 901 to the server. Function option 1002 can be used to share the podcast corresponding to card 901. Function option 1003 can be used to delete the podcast corresponding to card 901. Function option 1004 can be used to edit the podcast corresponding to card 901. Function option 1005 can be used to change the host in the podcast corresponding to card 901. It is understood that different hosts have different voices. Option 1006 can be used to display more podcast-related function options.

[0337] Understandably, Figure 10B The menu bar 1000 shown is merely an example; the electronic device 100 may display more or fewer podcast-related function options, and this application embodiment does not limit this.

[0338] The user can click on function option 1001, and in response to the user's operation, electronic device 100 can display as follows: Figure 10C The window shown is 1010. (As shown...) Figure 10CAs shown, window 1010 may include settings panel 1011, settings panel 1012, and settings panel 1013. Among them:

[0339] Settings bar 1011 can be used to set permissions for podcast 1 and select whether to upload podcast 1. For example, settings bar 1011 may include controls 10111 and 10112. Control 10111 can be used to set permissions for podcast 1 (e.g., all users can access or download, or access or download can be specified to certain users, or access or download can be specified to electronic device 100, etc.). Control 10112 can delete podcast 1; that is, the user can use control 10112 to choose not to upload podcast 1 this time.

[0340] It is understandable that "Podcast 1" here could be the podcast mentioned above with the title "Xi'an Travel Guide". For ease of description, this podcast will be referred to as "Podcast 1".

[0341] Settings bar 1012 can be used to set permissions for user private data related to podcast 1, and to select whether to upload such user private data. For example, settings bar 1012 may include controls 10121 and 10122. Control 10121 can be used to set permissions for user private data related to podcast 1 (e.g., all users can access it, or access can be specified to certain users, or access can be limited to electronic device 100, etc.). Control 10112 can delete user private data related to podcast 1; that is, the user can use control 10112 to select not to upload user private data related to podcast 1 this time.

[0342] Settings bar 1013 can be used to set permissions for the Q&A text generated when a user plays podcast 1, and to select whether to upload the Q&A text. For example, settings bar 1013 may include controls 10131 and 10132. Control 10131 can be used to set permissions for the Q&A text (e.g., all users can access it, or access can be specified to certain users, or access can be limited to electronic device 100, etc.). Control 10112 can delete the Q&A text; that is, the user can use control 10112 to select not to upload the Q&A text this time.

[0343] It is understood that during the playback of podcast 1, the electronic device 100 can save the user-inputted question information and the corresponding answer obtained based on that question information as a question-and-answer text. This question-and-answer text is merely an example, and this application embodiment does not limit the form in which the electronic device 100 saves the user-inputted question information and the corresponding answer obtained based on that question information.

[0344] In some examples, users can also choose to share electronic device 100 with other electronic devices. Figures 11A-11C An example is shown of the user interface for sharing podcasts on electronic device 100.

[0345] Figure 11A An exemplary user interface 900 provided in an embodiment of this application is illustrated. Reference can be made to the above description of this user interface 900. Figure 9A and Figure 10A The details described in the text will not be repeated here. Figure 11A As shown, the user can click on function option 1002. In response to this user action, the electronic device 100 can display as follows: Figure 11B The window shown is 1100.

[0346] like Figure 11B As shown, window 1100 may include settings panel 1101, settings panel 1102, and settings panel 1103. Wherein:

[0347] Settings bar 1101 can be used to choose whether to share podcast 1. For example, settings bar 1011 may include controls 11011 and 11012. Control 11011 allows you to choose whether to share podcast 1. Control 11012 allows you to choose whether to share podcast 1.

[0348] Settings bar 1102 can be used to select whether to share or not share user private domain data related to podcast 1. For example, settings bar 1102 may include controls 11021 and 11022. Control 11021 can select to share the user private domain data related to podcast 1. Control 11022 can select not to share the user private domain data related to podcast 1.

[0349] Settings bar 1013 can be used to choose whether to share or not share the question and answer text generated when a user plays podcast 1. For example, settings bar 1103 may include controls 11031 and 11032. Control 11031 can choose to share the question and answer text. Control 11032 can choose not to share the question and answer text.

[0350] like Figure 11B As shown, the window 1100 may also include a control 1014. After the user selects to share podcast 1, user private data related to podcast 1, and Q&A text generated when the user plays podcast 1, the user can click the control 1014. In response to this user action, the electronic device 100 can display as follows: Figure 11C Option box 1110 is shown.

[0351] like Figure 11CAs shown, option box 1110 may include options 1111, 1112, 1113, and 1114. Option 1111 can be used to trigger electronic device 100 to share one or more of the following via application 1: podcast 1, user private data related to podcast 1, and question-and-answer text generated when the user plays podcast 1. Option 1112 can be used to trigger electronic device 100 to share podcast 1 via Bluetooth, user private data related to podcast 1, and question-and-answer text generated when the user plays podcast 1. Option 1113 can be used to trigger electronic device 100 to share podcast 1 via WiFi Direct, user private data related to podcast 1, and question-and-answer text generated when the user plays podcast 1. Option 1114 can trigger electronic device 100 to display more options that can be shared.

[0352] Users can select any option in option box 1110 to share, choosing to share podcast 1, user private data related to podcast 1, and the Q&A text generated when the user plays podcast 1 to electronic device 200. The user interface for sharing podcast 1, user private data related to podcast 1, and the Q&A text generated when the user plays podcast 1 after selecting option 1111, 1112, or 1113 to electronic device 200 is not shown here. Refer to the existing user interface for sharing files, videos, and images from electronic device 100 to electronic device 200. Further details are omitted here.

[0353] Electronic device 200 can receive podcast 1 shared by electronic device 100, user private data related to podcast 1, and question-and-answer text generated when the user plays podcast 1. For example, Figures 12A-12D An exemplary illustration shows an electronic device 200 receiving a podcast 1 shared by an electronic device 100, and the relevant user interface for playing the podcast 1.

[0354] Figure 12A An exemplary user interface 1200 provided in an embodiment of this application is illustrated. This user interface 1200 can be a user interface for an electronic device 200 to receive podcast 1 shared by an electronic device 100. For example... Figure 12A As shown, the user interface 1200 may include an identifier 1201 for podcast 1 shared by electronic device 100. Optionally, the identifier 1201 may include the title of podcast 1 (such as "Xi'an Travel Guide"), the cover image of podcast 1, and playback controls 1202. The playback controls 1202 can be used to play podcast 1.

[0355] like Figure 12A As shown, the user can click or long-press the icon 1201 of podcast 1. In response to this user action, the electronic device 200 can display as follows: Figure 12BThe window 1210 shown. Window 1210 is used by the user of electronic device 200 to select whether to download one or more of the following: podcast 1 shared by electronic device 100, user private data related to podcast 1, and question and answer text generated when the user plays podcast 1.

[0356] like Figure 12B As shown, window 1210 may include settings panel 1211, settings panel 1212, and settings panel 1213. Wherein:

[0357] Settings bar 1211 can be used to select whether or not to download podcast 1. For example, settings bar 1211 may include controls 12111 and 12112. Control 12111 allows selection to download podcast 1. Control 12112 allows selection not to download podcast 1.

[0358] Settings bar 1212 can be used to select whether to download user private domain data related to podcast 1. For example, settings bar 1212 may include controls 12121 and 12122. Control 12121 can select whether to download the user private domain data related to podcast 1. Control 12122 can select whether to download the user private domain data related to podcast 1.

[0359] Settings bar 1213 can be used to select whether to download the question and answer text generated when the user plays podcast 1. For example, settings bar 1213 may include controls 12131 and 12132. Control 12131 can select to download the question and answer text. Control 12132 can select not to download the question and answer text.

[0360] like Figure 12B As shown, window 1210 may also include control 1214. After the user selects to download podcast 1, user private data related to podcast 1, and Q&A text generated when the user plays podcast 1, the user can click control 1214. In response to this user action, electronic device 200 can download podcast 1, user private data related to podcast 1, and Q&A text generated when the user plays podcast 1. Electronic device 200 can also save podcast 1, user private data related to podcast 1, and Q&A text generated when the user plays podcast 1 locally.

[0361] Optionally, in some examples, electronic device 200 can also access user private domain data related to podcast 1 within electronic device 200.

[0362] Electronic device 200 can also play downloaded podcast 1. For example, such as... Figure 12C As shown, the user can click the control 1202, and in response to the user's operation, the electronic device 200 can display as shown. Figure 12DThe user interface shown is 1220.

[0363] Figure 12D An exemplary user interface 1220 provided in an embodiment of this application is illustrated. This user interface 1220 may be a podcast playback interface in an electronic device 200. For example... Figure 12D As shown, the user interface 1220 may include control 911, cover image 912, title 913, control 914, anchor image 915a, anchor image 915b, playback progress bar 916, control 917a, control 917b, control 917c, control 917d, control 917e, and control 918. For details regarding control 911, cover image 912, title 913, control 914, anchor image 915a, anchor image 915b, playback progress bar 916, control 917a, control 917b, control 917c, control 917d, control 917e, and control 918, please refer to the above description. Figure 9B The description will not be repeated here.

[0364] Users of electronic device 200 can interact with podcast 1 via control 918 in the user interface 1200. For details regarding user interaction between electronic device 200 and podcast 1, please refer to the above. Figures 9C-9E The relevant descriptions of the interaction between the user of the electronic device 100 and the podcast 1 are not repeated here.

[0365] Regarding how the electronic device 200 obtains the answer to a question after the user interface 1200 inputs a question, please refer to the above. Figure 1 The relevant descriptions of steps 8-10 in the previous section will not be repeated here.

[0366] Based on the above description of the hardware and software structures of electronic devices 100 and 200 and the server side, as well as the relevant user interfaces in electronic devices 100 and 200, the following describes a method for generating podcasts provided by an embodiment of this application in conjunction with the accompanying drawings. Figure 13 An exemplary flowchart illustrating a method for generating podcasts according to an embodiment of this application is shown. Figure 13 As shown in the embodiments of this application, a method for generating podcasts may include the following steps:

[0367] S1301. In response to the user's first operation, the electronic device 100 sends the user-selected content, podcast title, and user private domain data 1 related to the user-selected content and / or podcast title to the server side.

[0368] Electronic device 100 may have such Figure 5The podcast generation module 501 shown can generate podcast titles, podcast covers, etc., from user-selected content. For details on the specific functions of this podcast generation module 501, please refer to the above description. Figure 5 The details of that will not be repeated here.

[0369] In one possible implementation, the electronic device 100 can display, for example... Figure 8C The window 820 is shown. The first operation can be a user action on control 828 within window 820. For example, the user clicks control 828. For details regarding window 820 and control 828, please refer to the above description. Figure 8C The description will not be repeated here.

[0370] In one possible implementation, before receiving the user's first operation, the electronic device 100 may also display something like... Figure 8A The user interface 800 is shown in the image. When the user clicks control 804 on the user interface 800, the electronic device 100 can also display something like... Figure 8B The window 810 shown. The electronic device 100 is only displayed after the user clicks control 815 in this window 810. Figure 8C The window 820 is shown in the image. For information on the user interface 800 and controls 804, please refer to the above description. Figure 8A The description of 810 and 815 will not be repeated here. For information on window 810 and control 815, please refer to the above description. Figure 8B The description will not be repeated here.

[0371] In response to this first operation, the electronic device 100 may send the user-selected content, podcast title, and user private domain data 1 related to the user-selected content and / or podcast title to the server side.

[0372] The user's private domain data 1 may include search history, shopping information, shopping cart information, and favorited items in the user's shopping applications related to the user's selected content and / or podcast title in the electronic device 100; chat information in chat software; ticket information in ticketing software (departure time, departure location, arrival time, and arrival location of train tickets, high-speed rail tickets, air tickets, etc., and attraction ticket information (e.g., attraction entry time, location, etc.); schedule reminders; ticket purchase SMS messages; call records; sports and health information, etc.

[0373] For example, if the podcast title is "Xi'an Travel Guide," and the content selected by the user can be one or more of the following: web pages introducing Xi'an tourism, documents introducing Xi'an tourism, pictures and videos introducing Xi'an tourism, etc., then the user's private domain data 1 can include user behavior data related to Xi'an tourism generated within various applications of the electronic device 100, as well as data related to the user's and family's dietary preferences, accommodation requirements, health, etc. For example, the user's private domain data 1 can include, for example, Figure 8C The user private domain data 821, 822, 823, 824, and 825 shown herein may be one or more of these. For more information on user private domain data 821, 822, 823, 824, and 825, please refer to the above description. Figure 8C The description will not be repeated here.

[0374] This application does not limit the specific private data of the user.

[0375] S1302. The server generates a podcast file based on the user-selected content, podcast title, and user private domain data 1.

[0376] The server can receive user-selected content, podcast title, and user private domain data 1 from electronic device 100. Then, the server can search for other public internet knowledge related to the user-selected content and / or podcast title based on the user-selected content and / or podcast title. Next, the server can summarize and refine the public internet knowledge, user-selected content, and user private domain data 1 to obtain refined text information. The server can also generate a podcast script based on the number of hosts selected by the user. Finally, the server can generate a podcast file from the podcast script. This podcast file is a playable audio file. The playback format involves the hosts reading the podcast script aloud.

[0377] In some examples, when generating a podcast, the electronic device 100 may not upload the user's private domain data 1 to the server. The server can then generate the podcast file based on the user-selected content and public internet knowledge related to the user-selected content and / or the podcast title. This application embodiment does not limit this approach.

[0378] S1303. The server sends podcast files to electronic device 100.

[0379] The server can send the generated podcast file to electronic device 100.

[0380] Optionally, in some examples, after generating the podcast file, the server can delete the user-selected content, podcast title, user private data 1, etc., sent by the electronic device 100. This can save server-side storage resources and prevent the leakage of user private data 1.

[0381] S1304. Electronic device 100 receives podcast files and plays podcast files based on user operations.

[0382] Electronic device 100 can receive podcast files sent from the server and save the podcast files. Electronic device 100 can also play the podcast files based on user actions. For example, a user can click on... Figure 9A In the user interface 900 shown, control 902, or clicking or double-clicking an area of ​​card 901 other than control 902, in response to the user action, allows electronic device 100 to play the podcast file. For more information on user interface 900, control 902, and card 901, please refer to the above description. Figure 9A The description will not be repeated here.

[0383] S1305. Electronic device 100 responds to the user's click on the question control of the podcast playback interface 1 and receives the question information 1 input by the user.

[0384] When playing a podcast file, the electronic device 100 can also display a podcast playback interface 1 for that podcast file. This podcast playback interface 1 may also include a question / answer control. For example, the podcast playback interface 1 may be as follows: Figure 9B The user interface 900 is shown. The query control can be control 918 within this user interface 900. For details regarding this user interface 910 and control 918, please refer to the above description. Figure 9B The description of the content is omitted here. This application embodiment does not specifically limit the content included in the podcast playback interface 1, the shape of the question control, or its position within the podcast playback interface 1.

[0385] The electronic device 100 can receive user operations on the question control and receive question information 1 input by the user. Question information 1 can be identified from user-inputted voice information or user-inputted text information. This application embodiment does not limit the input method or specific content of the question information 1.

[0386] S1306. Electronic device 100 sends a query message 1 to the server side.

[0387] Electronic device 100 can send a question message 1 to the server.

[0388] In one possible implementation, if the electronic device 100 has not uploaded the user's private domain data 1 to the server before sending the query information 1, then the electronic device 100 can send the user's private domain data 1 along with the query information 1 to the server.

[0389] In another possible implementation, before sending the query message 1, the electronic device 100 can upload the user's private domain data 1 to the server and set permissions for that user's private domain data 1. For details regarding the electronic device 100 uploading the user's private domain data 1 and setting permissions, please refer to the above section. Figure 10C The description will not be repeated here.

[0390] S1307. The server receives the question information 1 and searches for public network knowledge 1 related to the question information 1.

[0391] The server can search for public internet knowledge 1 related to question information 1. For example, if question information 1 is "Xi'an food recommendations", then the server can search for "Xi'an food recommendations" on the globally accessible internet and obtain knowledge related to Xi'an food and Xi'an food recommendations, which is the aforementioned public internet knowledge 1. For example, public internet knowledge 1 may include multiple web pages introducing Xi'an food, Xi'an food ranking web pages, videos and audio related to Xi'an food introductions, etc.

[0392] In this application embodiment, content and knowledge that can be searched on the Internet and is publicly accessible globally can be referred to as public Internet knowledge.

[0393] S1308. The server side obtains the answer to the question based on public network knowledge 1 and user private domain data 1.

[0394] The server can obtain the question answer 1 based on public network knowledge 1 and user private domain data 1. For example, the server can have a model 1, into which public network knowledge 1 and user private domain data 1 can be input, and model 1 can output the question answer 1. This model 1 can summarize and refine public network knowledge 1 and user private domain data 1 to obtain the question answer 1 related to the question information 1. For example, the question answer 1 may include multiple food names and the names and addresses of one or more restaurants that offer these foods. If user private domain data 1 includes "the child likes to eat mutton," the question answer 1 may include one or more of the following: mutton soup, mutton stew, roasted mutton, etc. The question answer 1 may also include the names and addresses of restaurants that offer mutton soup, mutton stew, roasted mutton, etc.

[0395] This application embodiment does not limit the specific content included in the answer to the question 1.

[0396] S1309. The server sends a question and answer 1 to electronic device 100.

[0397] The server can send the answer to the question 1 to electronic device 100.

[0398] Steps S1307-S1309 above can be found in the above description. Figure 1 The description of step 5 in the text.

[0399] S1310. Electronic device 100 receives question answer 1 and plays and / or displays question answer 1 in playback interface 1.

[0400] The electronic device 100 can receive the question-and-answer 1 sent by the server and play and / or display the question-and-answer 1 on the playback interface 1. For example, the question-and-answer 1 may be as follows: Figure 9E The answer 940 is shown. Electronic device 100 can display the answer 940 and have it read aloud by the host in the podcast.

[0401] This application does not limit the specific answer to question 1 in this embodiment.

[0402] S1311. Electronic device 100 stores the question and answer information 1 obtained during podcast playback. The question and answer information 1 includes the obtained question information 1 and the corresponding question answer 1.

[0403] After the electronic device 100 finishes playing the podcast, it can also save the Q&A information 1 obtained during the podcast playback. This Q&A information 1 includes all the questions entered by the user during the podcast playback and the corresponding answers to all the questions obtained by the electronic device 100. This Q&A information 1 can include question information 1 and question answer 1.

[0404] In some examples, the electronic device 100 can save the question-and-answer information 1 in text form. This question-and-answer information 1 can be the question-and-answer text mentioned above. This application embodiment does not limit the saving format or the specific content of the question-and-answer information 1.

[0405] In some examples, when the electronic device 100 plays the podcast again later, if the user's question information is included in the question-and-answer information 1, then the electronic device 100 can directly answer the user's question according to the question answer corresponding to the question information in the question-and-answer information 1.

[0406] In other examples, after the electronic device 100 plays the podcast again, it can save the questions and answers from the subsequent podcast playback in Question-Answer Information 1. That is, the electronic device 100 can update Question-Answer Information 1 after each podcast playback.

[0407] In one possible implementation, the electronic device 100 may also upload one or more of the following to the server: podcast file, user private data 1 related to the podcast file, and Q&A information 1.

[0408] The podcast generation method provided in this application allows the electronic device 100 to obtain user private domain data related to the podcast during the podcast generation process. This allows the electronic device 100 to generate podcasts based on this user private domain data, potentially resulting in podcast content that is more relevant to the user. Alternatively, after podcast generation, during podcast playback, when the user interacts with the podcast, the answer to the user's question can be obtained based on the user's private domain data. This means that when a user asks a question, the answer may be more relevant to the user's situation, improving the user experience.

[0409] In a method for generating a podcast provided in this application embodiment, after the electronic device 100 generates the podcast, the method may further include the electronic device 100 sharing the podcast with the electronic device 200, the electronic device 200 receiving the podcast shared by the electronic device 100 and playing the podcast, and the user of the electronic device 200 interacting with the podcast during the playback of the podcast by the electronic device 200, etc. Figure 14 This is a schematic diagram illustrating the process of an electronic device 100 sharing a podcast with an electronic device 200, the electronic device 200 playing the podcast, and interacting with the podcast, as provided in an embodiment of this application. Figure 14 As shown, electronic device 100 shares podcasts with electronic device 200, electronic device 200 plays podcasts, and interacts with podcasts, which may specifically include the following steps:

[0410] S1401. Electronic device 100 sends podcast files, user private domain data 1 and / or Q&A information 1 to electronic device 200.

[0411] Users can choose to share podcast files from electronic device 100, along with associated user private data 1 and / or Q&A information 1, to electronic device 200. For details on how users can operate on electronic device 100 to share podcast files and associated user private data 1 and / or Q&A information 1, please refer to the above section. Figures 11A-11C The description in the text will not be repeated here.

[0412] For information on user private domain data 1 and Q&A information 1, please refer to the above text. Figure 13 The description in the text will not be repeated here.

[0413] In response to a user's decision to share a podcast file from electronic device 100, along with user private data 1 and / or Q&A information 1 associated with that podcast file, with electronic device 200, electronic device 100 may send the podcast file, user private data 1, and / or Q&A information 1 to electronic device 200.

[0414] Understandably, when a user chooses to share a podcast file with electronic device 200, then electronic device 100 can send the podcast file to electronic device 200. Similarly, when a user chooses to share both a podcast file and user private data 1 with electronic device 200, then electronic device 100 can send both the podcast file and user private data 1 to electronic device 200. Likewise, when a user chooses to share both a podcast file and Q&A information 1 with electronic device 200, then electronic device 100 can send both the podcast file and Q&A information 1 to electronic device 200.

[0415] S1402. Electronic device 200 receives podcast files, user private data 1 and / or Q&A information 1, and obtains user private data 2 related to podcast files.

[0416] Electronic device 200 can receive podcast files, user private data 1, and / or Q&A information 1 sent by electronic device 100. When electronic device 100 sends podcast files, user private data 1, and Q&A information 1 to electronic device 200, the user of electronic device 200 can choose to receive and save one or more of the podcast files, user private data 1, and Q&A information 1. For details regarding electronic device 200 receiving podcast files, user private data 1, and Q&A information 1 shared by electronic device 100, and the user choosing to download podcast files, user private data 1, and Q&A information 1 on electronic device 200, please refer to the above description. Figure 12A , Figure 12B The description will not be repeated here.

[0417] After receiving the podcast file, the electronic device 200 can also obtain user private domain data 2 related to the podcast file. For example, if the podcast file is about a Xi'an travel guide, then user private domain data 2 may include user behavior data related to Xi'an travel generated in various applications within the electronic device 200, as well as data related to the user's and family's dietary preferences, accommodation requirements, health, etc. For a more detailed explanation of user private domain data 2, please refer to the definition of user private domain data and the description of user private domain data 1 above. This application embodiment does not limit the specific content included in user private domain data 2.

[0418] S1403. In response to the user's action of playing a podcast file, display playback interface 2, which includes a question control.

[0419] Users can also select to play received podcast files on the electronic device 200; for example, a user can click... Figure 12C The control 1202 is shown. In response to this user operation, the electronic device 200 can display a playback interface 2, which may also include a question control. For example, the playback interface 2 may be as follows: Figure 12D The user interface 1220 shown includes a query control via control 918. For more information on user interface 1220 and control 918, please refer to the above description. Figure 12D The description in the text will not be repeated here.

[0420] S1404. In response to the user clicking the question control in the playback interface 2, receive the question information 2 entered by the user.

[0421] The electronic device 200 can receive the user's click on the question control and receive the question information 2 input by the user. The question information 2 can be recognized from the user's voice input or text input by the user. This application embodiment does not limit the input method or specific content of the question information 2.

[0422] S1405. Electronic device 200 sends a query message 2 to the server side.

[0423] Electronic device 200 can also send a question message 2 to the server side.

[0424] S1406. The server receives question information 2 and searches for public network knowledge 2 related to question information 2.

[0425] The server can search for public internet knowledge 2 related to question information 2 based on question information 2. For example, if question information 2 is "Recommended attractions in Xi'an", then the server can search for "Recommended attractions in Xi'an" on the globally accessible internet and obtain knowledge related to recommended attractions in Xi'an, which is the aforementioned public internet knowledge 2. For example, public internet knowledge 2 may include multiple web pages introducing Xi'an attractions, web pages ranking Xi'an attractions, videos and audio recordings related to Xi'an attractions, etc.

[0426] S1407. Server-side electronic device 200 sends public network knowledge 2.

[0427] The server can send public network knowledge 2 to electronic device 200.

[0428] S1408. Electronic device 200 obtains the question answer 2 corresponding to question information 2 based on public network knowledge 2, user private domain data 1, and user private domain data 2.

[0429] Electronic device 200 can summarize and extract information from public network knowledge 2, user private domain data 1, and user private domain data 2 to obtain question answer 2 related to question information 2. Question answer 2 may include information such as the names and locations of one or more attractions. For example, if user private domain data 1 includes ticket purchase information for attraction 1, and user private domain data 2 includes chat history information about "wanting to visit attraction 2," then question answer 2 may include attraction 2 and its ticket purchase method, attraction 1 and its ticket purchase method, etc.

[0430] In another possible implementation, when the question-and-answer information 1 sent by electronic device 100 includes the question "Recommended attractions in Xi'an" and the corresponding answer, then electronic device 200 can obtain the answer 2 based on the question-and-answer information 1 and the user's private domain data 2.

[0431] This application embodiment does not limit the specific content of the answer to question 2.

[0432] S1409. Electronic device 200 plays and / or displays question and answer 2 in playback interface 2.

[0433] Electronic device 100 can play and / or display question and answer 2 in playback interface 2.

[0434] Step S1409 can be referred to the description in step S1310 above, and will not be repeated here.

[0435] According to the method for generating podcasts provided in this application embodiment, the podcast generated by electronic device 100 and the user's private domain data related to the podcast can be shared with electronic device 200. Electronic device 200 can receive the podcast and the user's private domain data related to the podcast. Then, electronic device 200 can also obtain the user's private domain data related to the podcast within electronic device 200. Next, electronic device 200 can play the podcast. During the playback, the user can interact with the podcast; for example, the user can input a question (voice question or text question), and then electronic device 200 can provide the user with the answer. This answer can be obtained by electronic device 200 based on the user's private domain data sent by electronic device 100 and the private domain data related to the podcast within electronic device 200.

[0436] Optionally, in this embodiment of the application, the electronic device 200 may also generate podcast 2 and obtain user private domain data 3 associated with podcast 2. The process of the electronic device 200 generating podcast 2 and obtaining user private domain data 3 can be referred to the above description of the electronic device 100 generating podcast 1 and obtaining user private domain data 1, and will not be repeated here.

[0437] In some feasible examples, electronic device 200 can also share podcast 2 and user private data 2 with electronic device 100 or upload them to the server. For details, please refer to the relevant descriptions of electronic device 100 sharing podcast 1 and user private data 1 with electronic device 100 and uploading them to the server, which will not be repeated here.

[0438] In some other feasible examples, after receiving the podcast 2 and user private domain data 3, electronic device 100 can also obtain user private domain data 4 associated with the podcast 2 on electronic device 100. For details, please refer to the above description of electronic device 200 obtaining user private domain data 2 associated with podcast 1 after receiving podcast 1 and user private domain data 1, which will not be repeated here.

[0439] In some other feasible examples, the electronic device 100 can play podcast 2 and display a question control. The user of the electronic device 100 can input a question based on this question control. That is, the user can interact with podcast 2 while the electronic device 100 is playing it. For details, please refer to the specific description of user interaction with podcast 1 while the electronic device 100 is playing podcast 1; it will not be repeated here.

[0440] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit it. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

[0441] As used in the above embodiments, depending on the context, the term "when..." can be interpreted as meaning "if...", "after...", "in response to determining...", or "in response to detecting...". Similarly, depending on the context, the phrase "when determining..." or "if (the stated condition or event) is interpreted as meaning "if determining...", "in response to determining...", "when (the stated condition or event) is detected", or "in response to detecting (the stated condition or event)".

[0442] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state drive), etc.

[0443] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. This program can be stored in a computer-readable storage medium, and when executed, it can include the processes described in the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM or random access memory (RAM), magnetic disks, or optical disks.

Claims

1. A method for generating podcasts, characterized in that, The method is applied to a first electronic device, and the method includes: Receive user input, which is used to indicate the target content selected by the user for generating the podcast, the target content including one or more of web pages, text, videos, and images; A first podcast is generated based on the target content selected by the user and the first private domain data associated with the target content on the first electronic device.

2. The method according to claim 1, characterized in that, The method further includes: The first podcast and the first private domain data are sent to a second electronic device, which is either a terminal device or a server.

3. The method according to claim 2, characterized in that, Sending the first podcast and the first private domain data to the second electronic device includes: Upload the first podcast and the first private domain data to the server, and set access permissions for the first private domain data; Alternatively, the first podcast and the first private domain data can be shared with the terminal device.

4. The method according to claim 3, characterized in that, The method further includes: Provide the user with a question-and-answer control about the first podcast; Receive the first question input by the user based on the question-and-answer control; The answer to the first question is provided to the user based on the first private domain data.

5. The method according to any one of claims 1-4, characterized in that, The method further includes: Display multiple private domain data items on the first electronic device; Receive the first private domain data selected by the user from the plurality of private domain data.

6. The method according to claim 5, characterized in that, Displaying multiple private domain data items on the first electronic device, specifically including: The first electronic device displays the first private domain data, a first control, and a second control. The first control is used to modify the first private domain data, and the second control is used to delete the first private domain data.

7. The method according to claim 4, characterized in that, After receiving the question input by the user based on the question-and-answer control, the method includes: Send the first question to the server; The server receives the answer to the first question corresponding to the first question, and the answer to the first question is obtained by the server based on the first question and the first private domain data.

8. The method according to claim 7, characterized in that, After providing the user with an answer to the question based on the first private domain data, the method includes: Save the first question and its answer; Upload the first question and its answer to the server; Alternatively, the first question and its answer can be shared with the terminal device.

9. The method according to any one of claims 2-8, characterized in that, The method further includes: Receive a second podcast sent by the second electronic device and second private domain data associated with the second podcast on the second electronic device; Obtain third private domain data associated with the second podcast on the first electronic device.

10. The method according to claim 9, characterized in that, After receiving the second podcast sent by the second electronic device and the second private domain data associated with the second podcast on the second electronic device, the method further includes: Display the identifier of the second podcast; Upon receiving and responding to the user's identifier for the second podcast, a first option box is displayed, which is used by the user to select to download the second podcast and the second private domain data; Receive and respond to the user's choice to download the second podcast and the second private domain data, and download the second podcast and the second private domain data.

11. The method according to claim 10, characterized in that, After receiving the second podcast sent by the second electronic device and the second private domain data associated with the second podcast on the second electronic device, the method includes: During the playback of the second podcast, a second question is received from the user based on the question-and-answer control; The answer to the second question is provided to the user based on the second private domain data and the third private domain data.

12. The method according to claim 4, characterized in that, Providing the user with an answer to the first question based on the first private domain data specifically includes: Based on the first question, the first public network knowledge was found; The answer to the first question is obtained based on the first public network knowledge and the first user's private domain data.

13. The method according to claim 11, characterized in that, Providing the user with an answer to the second question based on the second private domain data and the third private domain data specifically includes: Based on the second question, a second public network knowledge was found; Based on the second public network knowledge, the second private domain data, and the third private domain data, the answer to the second question is provided to the user.

14. A system for generating podcasts, characterized in that, The system includes a first electronic device, a second electronic device, and a server, wherein: The first electronic device is used to perform the method of any one of claims 1 to 8, the second electronic device is used to perform the method of any one of claims 9 to 11, and the server is used to perform the method of any one of claims 12 to 13.

15. An electronic device, characterized in that, It includes one or more processors; one or more memories; said one or more memories storing one or more computer programs, said one or more computer programs including instructions that, when executed by said one or more processors, cause the method of any one of claims 1 to 8 to be performed.

16. An electronic device, characterized in that, It includes one or more processors; one or more memories; said one or more memories storing one or more computer programs, said one or more computer programs including instructions that, when executed by said one or more processors, cause the method as described in any one of claims 9 to 11 to be performed.

17. A server, characterized in that, It includes one or more processors; one or more memories; said one or more memories storing one or more computer programs, said one or more computer programs including instructions that, when executed by said one or more processors, cause the method of any one of claims 12 to 13 to be performed.

18. A chip, characterized in that, The chip includes a processor and a communication interface, the communication interface being used to receive signals and transmit the signals to the processor, the processor processing the signals such that the method described in any one of claims 1 to 14 is executed.

19. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed on a computer, cause the method as described in any one of claims 1 to 14 to be performed.

20. A computer program product, characterized in that, When the computer program product is run on a computer, it causes the computer to perform the method as described in any one of claims 1 to 14.

Images