Method for interface interaction and electronic device

Abstract

Methods and electronic devices for interface interaction are provided. The method includes displaying a first prompt word in a plaintext state, the first prompt word being used by an intelligent system, the plaintext state indicating that the first prompt word is visible to a user; in response to receiving a first instruction, converting the first prompt word from the plaintext state to a ciphertext state, the ciphertext state indicating that the first prompt word is not visible to the user; and presenting a conversion result, the conversion result including the first prompt word in the ciphertext state.

Description

Technical Field

[0001] The examples in this article generally relate to the field of computers, and in particular to methods, apparatuses, electronic devices, computer-readable storage media, and computer program products for user interface interaction. Background Technology

[0002] With the development of artificial intelligence-related technologies, more and more platforms are leveraging intelligent systems to edit media. For example, custom generation rules (such as prompts) can guide intelligent systems to automate media editing, thereby improving editing efficiency. Summary of the Invention

[0003] In a first aspect, a method for user interface interaction is provided. The method includes: displaying a first prompt word in plaintext, the first prompt word being used by an intelligent system, the plaintext state indicating that the first prompt word is visible to a user; in response to receiving a first instruction, converting the first prompt word from the plaintext state to an encrypted state, the encrypted state indicating that the first prompt word is not visible to the user; and presenting a conversion result, the conversion result including the first prompt word in the encrypted state.

[0004] In a second aspect, an electronic device is provided. The device includes at least one processor; and at least one memory coupled to the at least one processor and storing instructions for execution by the at least one processor. When executed by the at least one processor, the instructions cause the device to perform the method of the first aspect.

[0005] In this way, the first prompt can be called by the intelligent system without disclosing the specific content of the prompt to the user. This not only allows the prompt to be reused across users, but also protects the content of the prompt and can, to some extent, prevent the prompt from being directly viewed during transmission and reuse.

[0006] It should be understood that the content described in this section is not intended to limit the key or important features of the examples in this article, nor is it intended to restrict the scope of the solution. Other features will become readily apparent from the following description. Attached Figure Description

[0007] The above and other features, advantages, and aspects of the various examples herein will become more apparent when taken in conjunction with the accompanying drawings and the following detailed description. In the accompanying drawings, the same or similar reference numerals denote the same or similar elements, wherein: Figure 1 The diagram shows example environments for some scenarios; Figures 2A to 2H The diagram shows sample interfaces for some scenarios; Figures 3A to 3BA schematic diagram of example interfaces for other scenarios is shown; Figures 4A to 4B A schematic diagram of example interfaces for several other scenarios is shown; Figure 5 and Figure 6 A schematic diagram of example interfaces in some other scenarios is shown; Figure 7 Flowcharts are shown for methods used in interface interaction in some scenarios; Figure 8 Block diagrams of devices for interface interaction in several scenarios are shown; and Figure 9 A block diagram of an electronic device capable of implementing multiple illustrative scenarios is shown. Detailed Implementation

[0008] The examples in this document will now be described in more detail with reference to the accompanying drawings. While some examples are shown in the drawings, it should be understood that solutions can be implemented in various forms and should not be construed as limited to the examples presented herein. Rather, these examples are provided to provide a more thorough and complete understanding of the solutions. It should be understood that the drawings and examples in this document are for illustrative purposes only and are not intended to limit the scope of protection of the solutions.

[0009] It should be noted that the headings of any section / subsection provided herein are not restrictive. Various examples are described throughout this document, and examples of any type may be included under any section / subsection. Furthermore, examples described in any section / subsection may be combined in any way with any other examples described in the same section / subsection and / or different sections / subsections.

[0010] In the description of the examples in this document, the term "including" and similar terms should be understood as open inclusion, i.e., "including but not limited to". The term "based on" should be understood as "at least partially based on". The term "an example" or "the example" should be understood as "at least one example". The term "some examples" should be understood as "at least some examples". Other explicit and implicit definitions may also be included below. The terms "first", "second", etc., may refer to different or the same objects. Other explicit and implicit definitions may also be included below.

[0011] The examples in this document may involve user data, data acquisition, and / or use. All of these aspects comply with relevant laws, regulations, and rules. In the examples, all data collection, acquisition, processing, manipulation, forwarding, and use are conducted with the user's knowledge and confirmation. Accordingly, when implementing each example, the type, scope of use, and usage scenarios of any data or information that may be involved should be communicated to the user and their authorization obtained through appropriate means, in accordance with relevant laws and regulations. The specific methods of notification and / or authorization can vary depending on the actual situation and application scenario; the scope of the solution is not limited in this regard.

[0012] The example solutions in this manual, if involving personal interface interactions, will be processed under the premise of a legal basis (such as obtaining the consent of the personal information subject, or being necessary for the performance of a contract), and will only be processed within the scope stipulated or agreed upon. A user's refusal to process personal information beyond what is necessary for basic functions will not affect the user's use of basic functions.

[0013] In one context, an intelligent system is an information processing system. This intelligent system uses at least one or more models to process one or more inputs. The intelligent system may include the one or more models as components, or it may use models external to the system for processing. Those skilled in the art will recognize that there are various implementations of intelligent systems in the industry, including but not limited to agents, artificial intelligence (AI) assistants, AI workers, copilot systems, and chatbots. The inputs include data in one or more modalities. The modal data includes, but is not limited to, text, audio, images, video, application-specific data, or scientific computing data. The models include, but are not limited to, one or more combinations of the following: large-scale parametric models, deep learning models, neural network models, machine learning models, statistical models, rule-based models, or other models capable of processing the inputs. The specific implementation of the models can employ various existing or improved models. The intelligent system may involve one or more of the following operations: receiving single-round or multi-round input; recognizing and / or understanding the input; generating answers, decisions, or processing results using one or more models; invoking one or more external tools, interfaces, knowledge bases, or other systems to obtain information or perform operations; processing in a self-decision-making or human-machine collaborative manner, or transferring tasks to human or other systems for processing. Self-decision-making refers to execution without human intervention. Human-machine collaboration refers to partial human participation or confirmation. The above explanation of "intelligent system" is illustrative, and each description is an example, not necessarily necessary, and does not constitute an exhaustive list.

[0014] In this article, the term "machine learning model" can refer to a computational model that performs tasks by learning patterns and rules from data. Machine learning models can include, but are not limited to, neural network models, deep learning models, and large language models. In some cases, large language models are an example of machine learning models that can understand and generate natural language text and can be used to perform tasks such as task decomposition, tool invocation, and content generation.

[0015] As mentioned above, in some video editing clients, custom generation rules (such as prompts) used to guide the intelligent system in generating copy or editing are usually transmitted between users in plain text. In this case, the recipient can directly view the specific content while using the rule, making the rule content easy to reuse. Furthermore, if fixed preset tags are used to limit the generation style, it is difficult to support long and detailed custom rules. On the other hand, when a single general workflow is used without distinguishing between scenarios, mismatches can easily occur between the default loaded components and the target editing effect, and the output efficiency of long media under a single result is relatively low. The following will describe an example solution that can alleviate at least some of the above problems, with reference to the accompanying diagrams.

[0016] A scheme for interface interaction is proposed. According to this scheme, an electronic device can display a first prompt word used by an intelligent system in plaintext (also known as a user-visible state), where the first prompt word is visible to the user. In response to receiving a first instruction, the electronic device can convert the first prompt word from the plaintext state to an encrypted state (also known as a user-invisible state). In the encrypted state, the first prompt word is not visible to the user. The electronic device can then present the conversion result, which includes the first prompt word in the encrypted state.

[0017] Through the above scheme, the first prompt word, even after being converted to ciphertext, can still be invoked by the intelligent system to generate corresponding content, while its specific content remains invisible to the user. This allows custom generation rules to be reused across users while being protected at the content level, reducing the chances of the rules being directly viewed. Furthermore, since the rules are carried in ciphertext, there is no need to repeatedly perform plaintext comparisons or manual verification to hide their content, thereby reducing related processing overhead.

[0018] The following describes various examples of this scheme in further detail with reference to the accompanying drawings.

[0019] Figure 1 A schematic diagram of example environment 100 is shown. (e.g.) Figure 1 As shown, example environment 100 may include electronic device 110.

[0020] In this example environment 100, electronic device 110 can run an application 120 that supports user interface interaction. Application 120 can be any suitable type of application for user interface interaction, including but not limited to video editing applications or other suitable applications. User 140 can interact with application 120 via electronic device 110 and / or its attached devices.

[0021] exist Figure 1In environment 100, if application 120 is active, electronic device 110 can use application 120 to present interface 150 for supporting interface interaction.

[0022] In some cases, electronic device 110 communicates with server 130 to provide services to application 120. Electronic device 110 can be any type of mobile terminal, fixed terminal, or portable terminal, including mobile phones, desktop computers, laptop computers, notebook computers, netbook computers, tablet computers, media computers, multimedia tablets, handheld computers, portable gaming terminals, virtual reality (VR) / augmented reality (AR) devices, personal communication system (PCS) devices, personal navigation devices, personal digital assistants (PDAs), audio / video players, digital cameras / camcorders, positioning devices, television receivers, radio receivers, e-book devices, gaming devices, or any combination of the foregoing, including accessories and peripherals of these devices or any combination thereof. In some cases, electronic device 110 can also support any type of user-facing interface (such as "wearable" circuitry).

[0023] Server 130 can be a single physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks, and artificial intelligence platforms. Server 130 may include, for example, computing systems / servers such as mainframes, edge computing nodes, computing devices in a cloud environment, etc. Server 130 can provide backend services for applications 120 that support user interface interaction in electronic devices 110.

[0024] A communication connection can be established between server 130 and electronic device 110. This communication connection can be established via wired or wireless means. The communication connection can include, but is not limited to, Bluetooth, mobile network, Universal Serial Bus (USB), and Wireless Fidelity (WiFi) connections. In some cases, server 130 and electronic device 110 can exchange signaling information through their communication connection.

[0025] It should be understood that the structure and function of the various elements in environment 100 are described for illustrative purposes only and do not imply any limitation on the scope of the scheme.

[0026] The examples described herein can be implemented on electronic device 110. It should be noted that the operations described relative to electronic device 110 can be performed by a related application 120 running on electronic device 110. The interface described relative to electronic device 110 can be provided by application 120; for example, electronic device 110 presents the corresponding interface by running application 120. Furthermore, some operations described relative to electronic device 110 may require the assistance of server 130 to complete.

[0027] The following description of the example will continue with reference to the accompanying drawings.

[0028] Figures 2A to 2H Schematic diagrams of example interfaces 200A to 200H are shown according to some scenarios. Interfaces 200A to 200H can be, for example, by... Figure 1 The electronic device 110 shown is provided.

[0029] like Figure 2A As shown, the electronic device 110 can display a first media 202 and a editing control 204 on the editing interface 200A. The first media 202 represents the media to be edited, such as a video before editing. The editing control 204 is used to receive editing operations from the user 140 on the first media 202. The media mentioned herein can refer to multimedia content including video, audio, images, or any combination of the foregoing.

[0030] In one scenario, in response to receiving a third operation instructing the editing of the first media 202, the electronic device 110 can use an intelligent system to edit the first media 202, thereby displaying a second media, such as a edited video, obtained by editing the first media 202 using the intelligent system. In this way, the user 140 can obtain the editing result without manually editing frame by frame, reducing the number of steps the user 140 takes during the editing process. Correspondingly, the editing process is automatically completed in the background by the intelligent system, and the electronic device 110 does not need to perform frame-by-frame editing and preview calculations on the front end, thus reducing the front-end computing overhead and memory usage of the electronic device 110. In some scenarios, the electronic device 110 can also minimize the ongoing editing task and start a new editing task, thereby supporting the parallel execution of multiple tasks. The user 140 does not need to wait for the current task to complete before performing other operations, improving the overall efficiency of task processing.

[0031] like Figure 2BAs shown, the electronic device 110 can present a smart editing interface 200B (sometimes referred to herein as a second component), which may be, for example, an "input editing requirements" interface. The second component may include multiple elements 206 to 214, each corresponding to a different editing mode. The multiple elements 206 to 214 may include a first element, corresponding to a first editing mode, such as a voice-over / narration mode. In one scenario, in response to receiving a third trigger operation on the first element, the electronic device 110 may enter the first editing mode. As an example, the multiple editing modes may include a live-streaming segment mode, a voice-over / narration mode, a spoken word retouching mode, a narrative recording mode, and a music beat mode. The editing modes mentioned herein may refer to processing methods corresponding to specific editing scenarios; different editing modes may correspond to different default editing strategies, configuration items, and generation rules. In this way, the user 140 can directly select the desired editing mode within the same interface, reducing the number of jumps between different functional pages. Accordingly, the electronic device 110 only needs to load the corresponding configuration items and processing flow for the selected first editing mode, without having to preload resources for all editing modes, thereby reducing interface rendering overhead and memory usage, and reducing the number of resource requests sent to the server 130.

[0032] In some cases, electronic device 110 can receive a fourth operation, which instructs a first editing mode. In response to the fourth operation, electronic device 110 can use the intelligent system to edit the first media 202 in the first editing mode to obtain the second media. Afterwards, electronic device 110 can display the second media. The first editing mode corresponds to one of several sub-scenes, such as the voice-over narration scene described above. In this way, user 140 can select a matching editing mode for different creative goals, reducing the number of repeated adjustments needed to achieve the desired effect. Accordingly, the intelligent system performs editing within the processing flow corresponding to the selected first editing mode, avoiding invalid processing under mismatched flows, thereby reducing unnecessary computation by server 130 and the corresponding amount of end-to-cloud communication data.

[0033] In some cases, the electronic device 110 may receive first configuration information via a first configuration panel. The first configuration information may include third explanatory text used to explain the first media 202. Alternatively and / or additionally, the first configuration information may include first voice used to explain the first media 202. For example, the first configuration panel may include... Figure 2BThe diagram shows an input box 216 for inputting or presenting narration text and a control 218 for inputting narration audio. The third narration text can be received via input box 216, and the first audio can be received via control 218. The narration text mentioned herein can refer to text used for explaining, narrating, or describing media, such as scripts automatically generated by an intelligent system. In this way, user 140 can provide narration material via both text and audio, covering more input types. Correspondingly, electronic device 110 can directly reuse the narration material provided by user 140, reducing the number of inferences required for the intelligent system to regenerate the narration content, thereby reducing the computational overhead of the intelligent system.

[0034] In some cases, electronic device 110 can use an intelligent system to edit first media based on third narration text (or first speech). Furthermore, during the editing process, electronic device 110 also uses the intelligent system to acquire second speech based on the third narration text. The resulting second media contains the second speech to achieve the purpose of dubbing. In this way, the edited second media carries dubbing corresponding to the narration material, enabling the solution to directly produce media with dubbing. Accordingly, the dubbing synthesis is completed by the intelligent system in the background, eliminating the need for additional speech processing at the front end for electronic device 110, thereby reducing the computational overhead of electronic device 110.

[0035] like Figure 2CAs shown, electronic device 110 can display control 222 on the smart editing interface 200C. If a trigger operation is received on control 222, electronic device 110 can present control 220. If a trigger operation is received on control 220, electronic device 110 can display configuration panel 228 (e.g., "Select Helper Preset" panel) on the smart editing interface 200C. Configuration panel 228 (sometimes referred to herein as the "first configuration panel") is associated with a first editing mode. In configuration panel 228, electronic device 110 can display first configuration parameters associated with the first editing mode, such as text style parameter 230, narrative angle parameter 232, and narration duration parameter 234, and can present corresponding parameter value options 240, 242 for each first configuration parameter. As an example, parameter value options for text style parameter 230 may include straightforward, conversational, etc. Parameter value options for narrative angle parameter 232 may include third person and first person, etc. The narration duration parameter 234 can include options such as unlimited, less than 1 minute, 1 to 3 minutes, and more than 3 minutes. The electronic device 110 can also receive a second input, which is a parameter value for the first configuration parameter. The electronic device 110 can display an input box 236 and a control 238 on the configuration panel 228, allowing the user to input supplementary information via the input box 236. After completing the input of the configuration parameter, the user can trigger the control 238. In response to the triggering operation of the control 238, the electronic device 110 uses the intelligent system to generate narration text based on the first configuration parameter. The electronic device 110 can present the narration text in the input box 216. In this way, the user 140 can select preset parameter values ​​to quickly express narration style requirements, reducing the amount of input required for the user 140 to describe the requirements word by word, and also allowing for the input of supplementary information to express personalized needs.

[0036] like Figure 2D and Figure 2E As shown, the electronic device 110 can display a first component 246, which may be, for example, a "custom prompt word" component. In response to a switch control 244 (such as...) Figure 2C(As shown) Upon triggering an operation, electronic device 110 can present first component 246. Electronic device 110 can display first component 246. A first input is received in first component 246, the first input including a first prompt word. Electronic device 110 can display the first prompt word in plaintext in first component 246. For example, the first prompt word 260 in plaintext can be presented in first area 254. At this time, the first prompt word 260 is visible to user 140, and the intelligent system can recognize the first prompt word 260 in plaintext. The prompt word mentioned herein can refer to input information used to guide the intelligent system in content generation or processing, such as descriptive text on generation style, generation rules, constraints, or output format. The prompt word can be input by user 140 or from an imported file. The plaintext state mentioned herein can refer to a state where the prompt word is visible to the user, and the ciphertext state can refer to a state where the prompt word is not visible to the user; the prompt word can switch between plaintext and ciphertext states. In this way, user 140 can directly view and modify the first prompt word during the editing stage, reducing the number of times user 140 switches between editing and previewing.

[0037] In some cases, electronic device 110 may display a first area 254 in the first component 246. The first area 254 displays a first control 250 (e.g., a control for importing a first prompt word) and guidance information 252, which guides the user to input a custom prompt word into the first area, such as "Enter a custom prompt word…". If a first trigger operation is received on the first control 250, electronic device 110 may receive a first input, which may include the first prompt word. Electronic device 110 may display the first prompt word in plaintext in the first area 254. In this way, user 140 can directly import existing prompt words, reducing the amount of re-entering prompt words.

[0038] Alternatively, electronic device 110 may display an input box in the first area 254. Electronic device 110 may receive the first input in the input box. In this way, user 140 can directly enter custom prompts in the input box, overriding input methods that do not rely on preset labels.

[0039] In some scenarios, electronic device 110 may receive a first instruction in response to a trigger operation on control 256 (such as the export and encryption control described above). Electronic device 110 may, in response to the first instruction, convert the first prompt word 260 from a plaintext state to an ciphertext state and present the conversion result, which includes the first prompt word in the ciphertext state. In this example, the trigger operation on control 256 is an example of receiving the first instruction. For example, the conversion result may be encapsulated as a local encrypted file, the filename of which can be modified without changing the first prompt word contained in the encrypted file. In this way, user 140 can complete the conversion of the prompt word from a plaintext state to an ciphertext state with a single trigger operation, reducing the additional operations required by user 140 to protect the prompt word content.

[0040] In some cases, such as Figure 2D As shown, the electronic device 110 can display control 248 in the first component 246. If a trigger operation is received on control 248, the electronic device 110 can display configuration panel 228. In this way, the user can switch between the first component 246 and configuration panel 228 as needed.

[0041] In some cases, the third explanatory text can be obtained by the intelligent system based on at least one of the first prompt word or the transformation result. In this way, the rules used to generate the explanatory text can come from either the first prompt word in plaintext or the transformation result in ciphertext, allowing the scheme to generate explanatory text while protecting the rule content. Correspondingly, regardless of the rule's state, the intelligent system can reuse the same generation process, avoiding the need to maintain different processing paths for rules from different sources, thereby reducing the system's processing branches and corresponding computational overhead. For example, the third explanatory text can be obtained by the intelligent system based on... Figure 2D The first prompt word received by the first component 246 shown can also be generated by the intelligent system based on the exported conversion results (e.g., an encrypted prompt word file).

[0042] In some cases, electronic device 110 can save the conversion result as a first file containing a first prompt word in an encrypted state, for example, by saving the conversion result as a local file in response to a triggering operation of the export and encryption control 256. In this way, user 140 can persistently save the first prompt word in an encrypted state as a file, facilitating its subsequent transmission and reuse. Accordingly, since the first prompt word is encapsulated in an encrypted state within the file, electronic device 110 does not need to maintain additional protection logic for its content during transmission, thereby reducing the corresponding processing overhead and the residence time of plaintext data.

[0043] like Figure 2F As shown, the electronic device 110 can respond to a second trigger operation on the first prompt word by displaying second explanatory text, which is obtained by the intelligent system based on the first prompt word. For example, the second trigger operation could be performed when the first prompt word is in plaintext. Figure 2E The explanatory text 262 generated by the triggering operation of the control 258 shown can be filled back into the input box 216 as the second explanatory text. In this way, the user 140 can obtain the explanatory text generated based on the first prompt word in the same interface, reducing the number of jumps between the generation interface and the main input interface. Correspondingly, the electronic device 110 directly fills the generated explanatory text back into the input box 216 without loading a new page for the explanatory text, thereby reducing the interface rendering overhead and the number of page requests sent to the server 130.

[0044] like Figure 2G As shown, in some cases, electronic device 110 can receive a first operation, which instructs the import of a second prompt word. The second prompt word is in an encrypted state, invisible to the user but visible to the intelligent system. Electronic device 110 can display a first identifier to identify the second prompt word. For example, as... Figure 2D and Figure 2G As shown, the user can trigger control 250. The electronic device 110 can respond to the triggering of control 250 by displaying the system's file manager. The user can select an encrypted prompt word file via the system's file manager, and the electronic device 110 can import the encrypted prompt word file in response to the selection. Afterwards, the electronic device 110 can display the first identifier 264 in the first area 254. In this way, the user cannot view the specific content of the second prompt word while using it, reducing the opportunity for the rule content to be directly viewed.

[0045] In some cases, electronic device 110 may present a delete control 268 in the first area 254. The user can select the delete control 268 if they wish to remove the second prompt word. Electronic device 110 may remove the second prompt word (e.g., an encrypted prompt word file) in response to a triggering action on the delete control 268.

[0046] In some cases, electronic device 110 can receive a second operation, which instructs the intelligent system to generate explanatory text. In response to the second operation, electronic device 110 can utilize the intelligent system to generate first explanatory text based on a second prompt. Afterward, electronic device 110 can display the first explanatory text. As an example, such as... Figure 2F As shown, in response to Figure 2GThe triggering operation of control 258 shown (as an example of the second operation) allows the intelligent system to generate first explanatory text 262 based on the second prompt word in an encrypted state. The electronic device 110 can then display the first explanatory text 262 in the input box 216. In this way, the user can obtain the explanatory text generated based on the rule without viewing the content of the second prompt word, reducing the user's operational steps before obtaining the explanatory text. Correspondingly, the intelligent system generates the explanatory text directly in the background based on the second prompt word in an encrypted state. The electronic device 110 does not need to decrypt and display the rule content or perform manual verification, thereby reducing the processing overhead of the electronic device 110 and the exposure of sensitive content.

[0047] In some scenarios, electronic device 110 can send the conversion result to the first object. For example, the conversion result can be sent to the first object in the form of an encrypted file via an external transmission method other than application 120 (such as an instant messaging application or a mobile storage device). In this way, user 140 can share the first prompt in an encrypted state with the first object, expanding the reuse path of the rule among multiple users. Accordingly, since the conversion result is carried in an encrypted state, electronic device 110 does not require additional content protection processing during sharing, thereby reducing the number of times sensitive data is transmitted and the data exposure surface.

[0048] like Figure 2H As shown, electronic device 110 can display a second configuration item 224 on the configuration panel. If a fourth trigger operation is received on the second configuration item 224, electronic device 110 can display a first label, which identifies a first character. If a fifth trigger operation is received on the first label, electronic device 110 can receive a first instruction, which indicates the first character, wherein the second media includes a second voice, which is produced in the voice of the first character. For example, electronic device 110 can present multiple labels (such as a first label 274 and a second label 276) on panel 272 (also called a voice-over character panel), where the first label 274 is used to identify the first character and the second label 276 is used to identify the second character; interface 200H can also present a third narration text 270. In this way, user 140 can select the desired voice for voice-over, reducing the repeated listening and adjustment required by user 140 to obtain the target voice. Accordingly, electronic device 110 submits the selected first character identifier to the intelligent system for speech synthesis, avoiding the need to synthesize multiple candidate voices separately, thereby reducing the number of synthesis operations and corresponding computational overhead of the intelligent system.

[0049] Figures 3A to 3B Schematic diagrams of example interfaces 300A to 300B according to other scenarios are shown below. (Refer to the following...) Figures 3A to 3B To describe the corresponding interface interaction process. For example... Figure 3A As shown, the electronic device 110 can display a smart music configuration item 302 (i.e., the first configuration parameter) on the smart editing interface 300A. The user 140 can turn the smart music function on or off through the smart music configuration item 302. For example, as shown... Figure 3A As shown, electronic device 110 can display control 222 on the intelligent editing interface 300A. If a trigger operation is received on control 222, electronic device 110 can present intelligent background music configuration item 302. In some cases, electronic device 110 can match background music for media with the help of an intelligent system when intelligent background music is enabled. For example, the intelligent system can first parse the prompt words entered by user 140. If the prompt words explicitly mention a music style or music name, the intelligent system can directly search the music library based on that style or name. If the prompt words do not explicitly mention it, the intelligent system can further perform a fallback match based on the understanding of the media's visuals. In addition, for editing modes that are not based on music beats, the loudness of the background music can be maintained within an appropriate range. The loudness mentioned in this article can refer to the strength of the audio signal, for example, it can be expressed in decibels (dB). In this way, user 140 can obtain background music that matches the content without manually selecting background music, reducing the selection steps for user 140. Correspondingly, the intelligent system eliminates the need for calculations related to image understanding when the prompt word provides a clear indication, thereby reducing the number of inferences and lowering the computational overhead of the server 130.

[0050] like Figure 3BAs shown, in some scenarios, electronic device 110 can acquire at least one third media segment, which is selected from multiple third media segments obtained by an intelligent system editing first media 202 based on a first editing strategy. Electronic device 110 can also acquire at least one fourth media segment, which is selected from multiple fourth media segments obtained by an intelligent system editing first media 202 based on a second editing strategy. Subsequently, electronic device 110 can display second media, which comprises a combination of at least one third media segment and at least one fourth media segment. For example, multiple second media 304, 306, and 308 (representing media A, media B, and media C, respectively) can be presented in the editing interface 300B. As an example, the first editing strategy can be a complete content recall strategy, which tends to retain segments with complete content. The second editing strategy can be a popular content recall strategy, which tends to recall segments of popular content. The two selection results can be merged and sorted to retain multiple candidate segments. In this way, by selecting and merging clips based on two complementary editing strategies, the number of manual selection operations required by the user (140) due to content omissions caused by a single strategy is reduced. Correspondingly, the two selection results are generated and merged by the intelligent system in the background at once, avoiding the need for the user (140) to re-trigger editing after discovering omissions, thereby reducing the amount of redundant editing calculations on the server (130) and the corresponding end-to-cloud communication data.

[0051] like Figure 3B As shown, in some cases, electronic device 110 can receive first text content, which includes the speech recognition result of first media 202. Electronic device 110 can also receive second text content, which is obtained by removing a portion of the first text content. Electronic device 110 can then use an intelligent system to edit first media 202 based on the second text content to obtain second media. Afterwards, electronic device 110 can present the second media. For example, the intelligent system can output a simplified text result based on word-level speech recognition results, constrained by prompt words, and then perform content matching mapping on each sentence of speech results to determine the time range of each retained speech. In this way, editing is performed after removing slips of the tongue, repetitions, etc., reducing the manual deletion steps of user 140. Correspondingly, the simplification process is completed by the intelligent system in the background based on the text, avoiding trial editing of each segment of the media, thereby reducing the front-end computing overhead of electronic device 110.

[0052] like Figure 3BAs shown, in some cases, electronic device 110 can use an intelligent system to edit first media 202 to obtain a first media segment and a second media segment. Electronic device 110 can acquire a first loudness and a second loudness, where the first loudness indicates the loudness of a first portion, which is the end of the first media segment, and the second loudness indicates the loudness of a second portion, which is the beginning of the second media segment. Electronic device 110 can determine whether the difference between the first loudness and the second loudness is less than a first threshold. If the difference between the first loudness and the second loudness is less than the first threshold, electronic device 110 can splice the first media segment and the second media segment to form at least a portion of the second media. In some cases, if there is a silent segment in the audio that meets a first condition (e.g., loudness below a preset threshold and duration reaching a preset lower limit), electronic device 110 can select a cut point from that silent segment to create a pause at the splicing point. If the duration of the resulting pause is less than the target duration, the electronic device 110 can move the editing point to the side of the silent segment where the loudness change is smaller (e.g., a smaller loudness slope or variance) to extend the pause, thereby avoiding loudness peaks. If no silent segment meets the first condition, the position with the smallest difference between the previous and subsequent loudness within a predetermined range is selected as the editing point. In this way, a more natural pause is preferentially formed at the splicing point, reducing the number of manual adjustments made by the user 140 to correct abrupt transitions. Accordingly, the selection of the splicing point is automatically completed in the background based on loudness differences, avoiding erroneous re-editing caused by relying solely on speech recognition results without considering audio features, thereby reducing the processing overhead of the electronic device 110 and improving output stability.

[0053] Figures 4A to 4B Schematic diagrams of example interfaces 400A to 400B according to certain scenarios are shown below. (Refer to the following...) Figures 4A to 4B This describes the user interface interaction process in the editing mode of live streaming or long media clips. For example... Figure 4AAs shown, electronic device 110 can display a first configuration panel 402, which is associated with a first editing mode. For example, electronic device 110 can display control 222 on example interface 400A. If a trigger operation is received on control 222, electronic device 110 can display the first configuration panel 402. Electronic device 110 can receive first configuration information in the first configuration panel 402. Electronic device 110 can use the intelligent system to edit the first media 202 based on the first configuration information to obtain the second media. Then, electronic device 110 can present the second media. For example, the first configuration panel 402 may include a second media quantity configuration item 404, an input box 406, a toggle control 410, and configuration items 412 for turning the intelligent background music function on or off and 414 for turning the subtitle highlighting function on or off. In this way, user 140 can complete the configuration for the selected editing mode on the spot, reducing the number of operations to adjust the configuration before and after editing. Accordingly, the electronic device 110 only needs to load the configuration items associated with the first editing mode, without loading configurations unrelated to the current mode, thereby reducing interface rendering overhead and memory usage.

[0054] like Figure 4A and Figure 4B As shown, in some cases, the first configuration information may indicate one of the following: a specified number of second media; or a second instruction that instructs the intelligent system to automatically determine the number of second media. For example, user 140 may enter a specified number 408 in input box 406 (e.g., ...). Figure 4A As shown), the specified number can be determined, for example, according to the number of products involved in the first media 202. Alternatively, user 140 can also switch to the second instruction 416 (i.e., the instruction that automatically determines the number of the second media, as shown) via the toggle control 410. Figure 4B (As shown). In the case of automatic determination, the intelligent system automatically determines the number of second media based on the first media 202. In this way, the user 140 can either specify the number of slices or let the intelligent system determine it automatically, covering both explicit requirements and automatic analysis input methods. Accordingly, when a specified number is specified, the intelligent system does not need to perform additional media analysis to determine the number, thereby reducing the corresponding analysis and calculation; in the case of automatic determination, the intelligent system completes the analysis and segmentation in one go, reducing the repeated editing calculations caused by the user 140 repeatedly trying different numbers of slices.

[0055] Figure 5 A schematic diagram of an example interface 500 based on certain scenarios is shown. For example... Figure 5As shown, the electronic device 110 can display a configuration panel 502 on the intelligent editing interface 500. The configuration panel 502 can include a configuration item 504 for enabling or disabling the intelligent background music function and a configuration item 506 for enabling or disabling the subtitle highlighting function. In some cases, the default value of the same configuration item in the editing mode corresponding to the interface 500 may be different from its default value in other editing modes. For example, the configuration item 504 for enabling or disabling the intelligent background music function can be enabled by default in the live broadcast segment mode, while it can be disabled by default in other editing modes. For the configuration item 506 for enabling or disabling the subtitle highlighting function, when enabled, the subtitles are highlighted when the track is closed, while when disabled, only subtitle recognition is performed. In this way, the user 140 can see the default configuration that matches the corresponding editing mode after entering the corresponding editing mode, reducing the operation steps of the user 140 adjusting the configuration item by item. Accordingly, the electronic device 110 loads the configuration according to the default strategy of each mode, reducing the repeated editing processing and corresponding computational overhead triggered by the mismatch of the default configuration. In some cases, multiple editing modes can reuse the same configuration items, with each configuration item having its own default value in different editing modes. User 140's enabling or disabling of configuration items can be avoided between different editing modes, thus allowing each editing mode to maintain its own default strategy while sharing components.

[0056] Figure 6 A schematic diagram of an example interface 600 based on certain scenarios is shown. For example... Figure 6 As shown, electronic device 110 can respond to a fifth operation by displaying a first historical prompt. If a sixth trigger operation is received on the first historical prompt, electronic device 110 can utilize a smart system to clip first media 202 based on the first historical prompt to obtain at least one second media. As an example, such as Figure 6As shown, electronic device 110 can display control 610 on example interface 600. If the user wants to recall historical prompts, the user can trigger (e.g., single-click, double-click, long-press, etc.) control 610. In response to the trigger operation of control 610, electronic device 110 can present a historical prompt panel 602 on the smart editing interface 600 (i.e., example interface 600). The historical prompt panel 602 can display multiple historical prompts 604, 606, and 608. If the user selects one of the historical prompts, such as historical prompt 606, electronic device 110 can present historical prompt 606 in input box 216. Then, if the user triggers control 226, electronic device 110 can use the smart system to edit the first media based on the historical prompt 606 to obtain at least one second media. In this way, user 140 can directly reuse previously used historical prompts, reducing the amount of time user 140 needs to repeatedly input the same prompts. Correspondingly, electronic device 110 directly calls the saved historical prompts without needing to re-receive and parse the same input, thereby reducing the corresponding processing overhead.

[0057] In summary, the first prompt word can be input, viewed, and edited in plaintext, and can be converted to ciphertext for export, transmission, and import through a single trigger operation. This ensures that the same prompt word remains "accessible to the intelligent system without being displayed to the user" during cross-user reuse, thus protecting the content of the prompt word while preserving its reuse value. It also reduces the chance of the prompt word being directly viewed during transmission and reuse, and reduces the dwell time and data exposure of plaintext content on various devices.

[0058] Figure 7 A flowchart of an example process 700 for interface interaction is shown, based on some scenarios. Process 700 can be implemented at electronic device 110. See below for reference. Figure 7 To describe process 700.

[0059] like Figure 7 As shown in box 710, electronic device 110 displays a first prompt word in plaintext. The first prompt word is used by the intelligent system, and the plaintext state indicates that the first prompt word is visible to the user.

[0060] In box 720, in response to receiving a first instruction, electronic device 110 changes the first prompt word from plaintext to ciphertext, the ciphertext state indicating that the first prompt word is not visible to the user.

[0061] In box 730, electronic device 110 presents the conversion result, which includes the first prompt word in the encrypted state.

[0062] In this way, the first prompt word can still be invoked by the intelligent system after being converted to an encrypted state, while its specific content is not visible to the user. This protects the content while enabling the reuse of custom-generated rules across users and reduces the chance of the rules being directly viewed. Correspondingly, since the rules are carried in an encrypted state, the electronic device 110 does not need to repeatedly perform plaintext comparisons or manual verifications to hide its content, thereby reducing the corresponding processing overhead and the duration of plaintext rule content residing locally and data exposure.

[0063] In some scenarios, the electronic device 110 may display a first component; receive a first input in the first component, the first input including a first prompt word; and display the first prompt word in plaintext in the first component. For specific interactive presentation, please refer to the above. Figure 2E The example described illustrates this. In this way, user 140 can input and view the first prompt word within the same component, reducing the number of times switching between different interfaces. Correspondingly, electronic device 110 completes the reception and display of plaintext in a local component without interacting with server 130, thereby reducing the number of end-to-cloud interaction rounds and the corresponding bandwidth usage.

[0064] In some cases, the electronic device 110 may display a first area in a first component, the first area displaying a first control; and in response to a first trigger operation on the first control, receive a first input; and display a first prompt word in plaintext in the first area. For specific interactive presentation, please refer to the above. Figure 2D The example described illustrates this. In this way, user 140 can import existing prompts via controls, reducing the amount of re-entry required. Correspondingly, electronic device 110 directly reads the imported content without needing to re-identify or transcribe it, thus reducing computational overhead.

[0065] In some cases, the electronic device 110 may display an input box in the first area and receive the first input in the input box. For specific interactive presentation, please refer to the above. Figure 2E The example described illustrates this. In this way, user 140 can directly input custom prompts into the input box, overriding input methods that do not rely on preset tags. Accordingly, electronic device 110 directly uses the input as input to the intelligent system, reducing the matching and conversion processing of preset tags, thereby reducing the corresponding computational overhead.

[0066] In some scenarios, the electronic device 110 can receive a first operation, which instructs the import of a second prompt word, the second prompt word being in an encrypted state and invisible to the user; and display a first identifier, which is used to identify the second prompt word. For specific interaction details, please refer to the above. Figure 2GThe example described illustrates this. In this way, users cannot view the specific content of the second prompt word while using it, reducing the chance of the rule content being directly viewed. Correspondingly, electronic device 110 only presents the identifier without rendering the full text, thereby reducing interface rendering overhead and decreasing the dwell time and data exposure surface of the plaintext rule content.

[0067] In some cases, electronic device 110 can receive a second operation, which instructs the generation of explanatory text; and display the first explanatory text, which is obtained by the intelligent system based on the second prompt word. For specific interactive presentation, please refer to the above. Figure 2G The example described illustrates this. In this way, users can obtain the explanatory text without viewing the rules, reducing the steps required to access it. Correspondingly, the intelligent system directly generates a second prompt based on the encrypted state in the background, eliminating the need for electronic device 110 to decrypt and display it, thus reducing processing overhead and the exposure of sensitive content.

[0068] In some cases, electronic device 110 can save the conversion result as a first file, which contains a first prompt word in an encrypted state. For specific interactive presentation, please refer to the above. Figure 2D The example described illustrates this. In this way, user 140 can persistently save the first prompt in an encrypted state as a file, facilitating its subsequent transmission and reuse. Accordingly, since the first prompt is encapsulated in an encrypted state in a file, electronic device 110 does not need to maintain additional content protection logic, thereby reducing processing overhead and the residence time of plaintext data.

[0069] In some cases, electronic device 110 can send the conversion result to the first object. For specific interaction details, please refer to the above text. Figure 2G The example described illustrates this. In this way, user 140 is able to share the first prompt word in an encrypted state with the first object, extending the rule's reuse path. Accordingly, the transformation result is carried in an encrypted state, requiring no additional content protection processing, thereby reducing the number of times sensitive data is transmitted and the data exposure surface.

[0070] In some cases, electronic device 110 can respond to a second trigger operation on the first prompt word by displaying second explanatory text, which is obtained by the intelligent system based on the first prompt word. For specific interactive presentation, please refer to the above. Figure 2F The example described illustrates this. In this way, user 140 can obtain explanatory text generated based on the first prompt word on the same interface, reducing the number of interface jumps. Correspondingly, electronic device 110 directly fills in the explanatory text without loading a separate page for it, thereby reducing interface rendering overhead and reducing the number of page requests sent to server 130.

[0071] In some scenarios, electronic device 110 can display a first medium; receive a third operation instructing the editing of the first medium; and display a second medium obtained by editing the first medium using an intelligent system. Specific interactive presentations can be found above. Figure 2A The example described illustrates this. In this way, user 140 can obtain the editing result without manually editing frame by frame, reducing the number of steps. Accordingly, the editing is completed in the background by the intelligent system, and electronic device 110 does not need to perform frame-by-frame editing and preview calculations on the front end, thereby reducing front-end computing overhead and memory usage.

[0072] In some cases, electronic device 110 can receive a fourth operation, which instructs a first editing mode; and display second media, which is obtained by editing the first media using the intelligent system in the first editing mode. Specific interactive presentations can be found above. Figure 2B The example described illustrates this. In this way, user 140 can select a matching editing mode for different creative goals, reducing the number of repeated adjustments. Accordingly, the intelligent system edits under the matching processing flow, avoiding invalid processing under mismatched flows, thereby reducing unnecessary computation on server 130 and the amount of data in edge-cloud communication.

[0073] In some scenarios, the electronic device 110 can display a second component, which includes multiple elements, each corresponding to a different clipping mode; and receive a third trigger operation, which is a trigger operation on a first element, including the first element, which corresponds to a first clipping mode. For specific interactive presentation, please refer to the above. Figure 2B The example described illustrates this. In this way, user 140 can directly select the desired clip mode on the same interface, reducing the number of interface jumps. Correspondingly, electronic device 110 loads resources only for the selected mode, without needing to preload for all modes, thereby reducing rendering overhead and memory usage and reducing the number of resource requests.

[0074] In some scenarios, the electronic device 110 may display a first configuration panel associated with a first editing mode; receive first configuration information in the first configuration panel; and display second media, which is obtained by editing the first media based on the first configuration information using an intelligent system. For specific interactive presentation, please refer to the above. Figure 4A The example described illustrates this. In this way, user 140 can complete the configuration for the selected clip mode in-situ, reducing the number of round trips to adjust the configuration. Accordingly, electronic device 110 only loads the configuration items associated with that mode, thereby reducing interface rendering overhead and memory usage.

[0075] In some cases, the first configuration information may indicate one of the following: a specified number of second media; or a second instruction that instructs the intelligent system to automatically determine the number of second media. See above for a detailed presentation. Figure 4B The example described illustrates this approach. In this way, the user can either specify the number or allow the intelligent system to determine it automatically, covering both explicit requirements and automated analysis. Accordingly, when specifying the number, the intelligent system does not need to perform additional media analysis, reducing corresponding calculations; when automatically determining the number, the segmentation is completed in one go, reducing repetitive editing calculations caused by repeated attempts.

[0076] In some scenarios, the electronic device 110 can receive third explanatory text on the first configuration panel, which is used to explain the first media; and receive first voice on the first configuration panel, which is used to explain the first media. For specific interactive presentation, please refer to the above. Figure 2B The example described illustrates this. In this way, user 140 can provide narration material via both text and voice, covering a wider range of input types. Correspondingly, electronic device 110 directly reuses the provided material, reducing the number of inferences regenerated by the intelligent system and thus lowering computational overhead.

[0077] In some cases, the second medium may include a second voice, which is obtained based on at least one of a third narration text and a first voice. Specific presentation details can be found above. Figure 2B and Figure 2H The example described illustrates this. In this way, the edited second media carries a corresponding voiceover, enabling the scheme to directly produce media with voiceover. Accordingly, the voiceover synthesis is completed in the background by the intelligent system, eliminating the need for additional voice processing at the front end for the electronic device 110, thereby reducing computational overhead.

[0078] In some cases, the third explanatory text can be obtained by the intelligent system based on at least one of the first prompt words or the transformation result. In this way, the rules used to generate the explanatory text can come from either the first prompt words in the plaintext or the transformation result in the ciphertext, generating the explanatory text while protecting the content of the rules. Accordingly, the intelligent system reuses the same generation process, avoiding the maintenance of different paths for different sources, thereby reducing processing branches and computational overhead.

[0079] In some scenarios, electronic device 110 may display a second configuration item on a first configuration panel; in response to a fourth trigger operation on the second configuration item, display a first label identifying a first role; and in response to a fifth trigger operation on the first label, receive a first instruction indicating the first role, wherein the second media includes a second voice, the second voice being delivered in the voice of the first role. Specific interactive presentations can be found above. Figure 2HThe example described illustrates this. In this way, user 140 is able to select the desired timbre for dubbing, reducing repeated listening and adjustments. Accordingly, electronic device 110 submits only the selected character identifier for synthesis, avoiding the separate synthesis of multiple candidate timbres, thereby reducing the number of synthesis attempts and computational overhead of the intelligent system.

[0080] In some scenarios, the electronic device 110 can display a first configuration parameter on a first configuration panel, the first configuration parameter being associated with a first clipping mode; and receive a second input, the second input being a parameter value for the first configuration parameter. For specific interactive presentation, please refer to the above. Figure 2C The example described illustrates this. In this way, user 140 can quickly express requirements by selecting preset parameter values, reducing the amount of input required for verbal descriptions. Correspondingly, electronic device 110 submits structured parameter values, reducing the computational load of free text parsing, thereby reducing the processing load on server 130 and the amount of data in edge-cloud communication.

[0081] In some scenarios, electronic device 110 may respond to a fifth operation by displaying a first historical prompt; and respond to a sixth trigger operation on the first historical prompt by displaying second media, the second media being obtained by the intelligent system by editing the first media based on the first historical prompt. Specific interactive presentations can be found above. Figure 6 The example described illustrates this. In this way, user 140 can directly reuse historical prompts, reducing the amount of repetitive input. Correspondingly, electronic device 110 directly calls up saved historical prompts without needing to re-receive and parse them, thereby reducing processing overhead.

[0082] In some scenarios, the electronic device 110 can receive first text content, which includes the speech recognition result of a first medium; receive second text content, which is obtained by removing a portion of the first text content; and present a second medium, which is obtained by the intelligent system editing the first medium based on the second text content. Specific interactive presentations can be found above. Figure 3B The example described illustrates how this method, by removing slips of the tongue, repetitions, and other errors during editing, reduces the number of manual deletion steps for users by 140. Correspondingly, the simplification process is completed in the background by the intelligent system based on text, avoiding the need for segment-by-segment trial editing of the media, thereby reducing front-end computational overhead.

[0083] In some scenarios, the electronic device 110 can receive a first media segment and a second media segment, which are obtained by editing the first media using an intelligent system; acquire a first loudness and a second loudness, where the first loudness indicates the loudness of a first portion, which is the end of the first media segment, and the second loudness indicates the loudness of a second portion, which is the beginning of the second media segment; and display the second media, which includes a splicing of the first and second media segments, based on the fact that the difference between the first and second loudnesses is less than a first threshold. Specific interactive presentations can be found above. Figure 3B The example described illustrates how this prioritizes creating natural pauses at splicing points, reducing the number of manual adjustments required by the user to correct abrupt transitions. Correspondingly, splicing points are automatically selected in the background based on loudness differences, avoiding accidental cuts and re-cuts, thereby reducing processing overhead and improving output stability.

[0084] In some scenarios, electronic device 110 can acquire at least one third media segment, which is selected from a plurality of third media segments obtained by an intelligent system editing a first media segment based on a first editing strategy; acquire at least one fourth media segment, which is selected from a plurality of fourth media segments obtained by an intelligent system editing a first media segment based on a second editing strategy; and display a second media segment comprising a splicing of at least one third media segment and at least one fourth media segment. Specific interactive presentations can be found above. Figure 3B The example described illustrates how selecting and merging clips based on two complementary strategies reduces the number of manual re-selections required due to missed clips. Correspondingly, the two results are generated and merged simultaneously, avoiding the need for user 140 to re-trigger editing, thereby reducing redundant editing calculations on server 130 and the amount of data exchanged between the end and cloud.

[0085] A corresponding apparatus for implementing the above methods or processes is also provided. Figure 8 Block diagrams of a device 800 for user interface interaction are shown in several scenarios. Device 800 can be implemented as or included in electronic device 110. The various modules / components in device 800 can be implemented by hardware, software, firmware, or any combination thereof.

[0086] like Figure 8As shown, the device 800 includes: a display module 810 configured to display a first prompt word in plaintext state, the first prompt word being used by an intelligent system, the plaintext state indicating that the first prompt word is visible to the user; a conversion module 820 configured to convert the first prompt word from plaintext state to ciphertext state in response to receiving a first instruction, the ciphertext state indicating that the first prompt word is not visible to the user; and a presentation module 830 configured to present the conversion result, the conversion result including the first prompt word in ciphertext state.

[0087] In some cases, the display module 810 may also be configured to display a first component; receive a first input in the first component, the first input including a first prompt word; and display the first prompt word in plaintext in the first component.

[0088] In some cases, the display module 810 may also be configured to display a first area in a first component, the first area displaying a first control; and to receive a first input in response to a first trigger operation on the first control; and to display a first prompt word in plaintext in the first area.

[0089] In some cases, the display module 810 can also be configured to display an input box in a first area; and to receive a first input in the input box.

[0090] In some cases, the display module 810 may also be configured to receive a first operation, the first operation instructing the import of a second prompt word, the second prompt word being in an encrypted state, in which the second prompt word is invisible to the user; and to display a first identifier, the first identifier being used to identify the second prompt word.

[0091] In some cases, the display module 810 may also be configured to receive a second operation, the second operation instructing the generation of the first explanatory text; and to display the first explanatory text, which is obtained by the intelligent system based on the second prompt word.

[0092] In some cases, the device 800 may further include a storage module configured to save the conversion result as a first file, the first file containing a first prompt word in an encrypted state.

[0093] In some cases, the device 800 may further include a sending module configured to send the conversion result to the first object.

[0094] In some cases, the display module 810 can also be configured to display second explanatory text in response to a second triggering operation on the first prompt word, the second explanatory text being obtained by the intelligent system based on the first prompt word.

[0095] In some cases, the display module 810 may also be configured to display a first medium; receive a third operation that instructs the editing of the first medium; and display a second medium that is obtained by editing the first medium using an intelligent system.

[0096] In some cases, the display module 810 may also be configured to receive a fourth operation, the fourth operation indicating a first editing mode; and to display a second medium, the second medium being obtained by editing the first medium using an intelligent system in the first editing mode.

[0097] In some cases, the display module 810 may also be configured to display a second component, the second component comprising multiple elements, each element corresponding to a multiple clipping mode, the multiple elements including a first element corresponding to a first clipping mode; and to receive a third trigger operation, the third trigger operation being a third trigger operation on the first element.

[0098] In some cases, the display module 810 may also be configured to display a first configuration panel associated with a first editing mode; receive first configuration information in the first configuration panel; and display a second medium obtained by editing the first medium using the intelligent system based on the first configuration information.

[0099] In some cases, the first configuration information may indicate one of the following: a specified number of second media; or a second instruction that instructs the intelligent system to automatically determine the number of second media.

[0100] In some cases, the display module 810 may also be configured to receive a third explanatory text on the first configuration panel, the third explanatory text being used to explain the first media; and to receive a first voice on the first configuration panel, the first voice being used to explain the first media.

[0101] In some cases, the second medium may include a second voice, which is obtained based on at least one of a third narration text and a first voice.

[0102] In some cases, the third explanatory text may be obtained by the intelligent system based on at least one of the first prompt words or the conversion result.

[0103] In some cases, the display module 810 may also be configured to display a second configuration item on a first configuration panel; display a first label identifying a first role in response to a fourth trigger operation on the second configuration item; and receive a first instruction indicating the first role in response to a fifth trigger operation on the first label, wherein the second media includes a second voice, the second voice being spoken in the voice of the first role.

[0104] In some cases, the display module 810 may also be configured to display a first configuration parameter on a first configuration panel, the first configuration parameter being associated with a first clipping mode; and to receive a second input, the second input being a parameter value for the first configuration parameter.

[0105] In some cases, the display module 810 may also be configured to display a first historical prompt in response to a fifth operation; and to display second media in response to a sixth trigger operation on the first historical prompt, the second media being obtained by the intelligent system by editing the first media based on the first historical prompt.

[0106] In some cases, the display module 810 may also be configured to receive first text content, which includes the speech recognition result of the first media; receive second text content, which is obtained by removing a portion of the first text content; and display a second media, which is obtained by the intelligent system by editing the first media based on the second text content.

[0107] In some cases, the display module 810 may also be configured to receive a first media segment and a second media segment, the first media segment and the second media segment being obtained by editing the first media using an intelligent system; acquire a first loudness and a second loudness, the first loudness indicating the loudness of a first portion, the first portion being the end portion of the first media segment, the second loudness indicating the loudness of a second portion, the second portion being the beginning portion of the second media segment; and display the second media, the second media comprising a splicing of the first media segment and the second media segment, based on the difference between the first loudness and the second loudness being less than a first threshold.

[0108] In some cases, the display module 810 may also be configured to acquire at least one third media segment, which is selected from a plurality of third media segments obtained by an intelligent system editing a first media based on a first editing strategy; acquire at least one fourth media segment, which is selected from a plurality of fourth media segments obtained by an intelligent system editing a first media based on a second editing strategy; and display a second media, which includes a splicing of at least one third media segment and at least one fourth media segment.

[0109] The modules included in device 800 can be implemented in various ways, including software, hardware, firmware, or any combination thereof. In some cases, one or more modules can be implemented using software and / or firmware, such as machine-executable instructions stored on a storage medium. In addition to or as an alternative to machine-executable instructions, some or all of the units in device 800 can be implemented at least partially by one or more hardware logic components. By way of example, and not limitation, exemplary types of hardware logic components that can be used include field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard parts (ASSPs), systems on a chip (SOCs), complex programmable logic devices (CPLDs), and so on.

[0110] Figure 9 A block diagram of an electronic device 900 in which one or more examples may be implemented is shown. It should be understood that... Figure 9 The electronic device 900 shown is merely exemplary and should not be construed as limiting the functionality and scope of the examples described herein. Figure 9 The illustrated electronic device 900 can be used to implement the electronic device 110 discussed above.

[0111] like Figure 9 As shown, electronic device 900 is in the form of a general-purpose electronic device. Components of electronic device 900 may include, but are not limited to, one or more processing units or processors 910, memory 920, storage devices 930, one or more communication units 940, one or more input devices 950, and one or more output devices 960. Processor 910 may be a physical or virtual processor and is capable of performing various processes according to programs stored in memory 920. In a multiprocessor system, multiple processors execute computer-executable instructions in parallel to improve the parallel processing capability of electronic device 900.

[0112] Electronic device 900 typically includes multiple computer storage media. Such media can be any accessible media that is accessible to electronic device 900, including but not limited to volatile and non-volatile media, removable and non-removable media. Memory 920 can be volatile memory (e.g., registers, cache, random access memory (RAM)), non-volatile memory (e.g., read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof). Storage device 930 can be removable or non-removable media and can include machine-readable media, such as flash drives, disks, or any other media that can be used to store information and / or data and can be accessed within electronic device 900.

[0113] Electronic device 900 may further include additional removable / non-removable, volatile / non-volatile storage media. Although not explicitly stated... Figure 9 As shown, disk drives for reading from or writing to removable, non-volatile disks (e.g., "floppy disks") and optical disk drives for reading from or writing to removable, non-volatile optical disks can be provided. In these cases, each drive can be connected to a bus (not shown) via one or more data media interfaces. Memory 920 may include computer program product 925 having one or more program modules configured to perform various methods or actions of various examples.

[0114] The communication unit 940 enables communication with other electronic devices via a communication medium. Additionally, the functionality of the components of the electronic device 900 can be implemented using a single computing cluster or multiple computing machines capable of communicating via communication connections. Therefore, the electronic device 900 can operate in a networked environment using logical connections to one or more other servers, networked personal computers, or another network node.

[0115] Input device 950 can be one or more input devices, such as a mouse, keyboard, trackball, etc. Output device 960 can be one or more output devices, such as a monitor, speaker, printer, etc. Electronic device 900 can also communicate with one or more external devices (not shown) via communication unit 940 as needed. External devices include storage devices, display devices, etc., and can communicate with one or more devices that enable user interaction with electronic device 900, or with any device that enables electronic device 900 to communicate with one or more other electronic devices (e.g., network card, modem, etc.). Such communication can be performed via input / output (I / O) interface (not shown).

[0116] A computer-readable storage medium is provided that stores computer-executable instructions thereon, wherein the computer-executable instructions are executed by a processor to implement the methods described above. A computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, which are executed by a processor to implement the methods described above.

[0117] The flowcharts and / or block diagrams of the methods, apparatus, devices, and computer program products referred to herein describe various aspects. It should be understood that each block of the flowcharts and / or block diagrams, as well as combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer-readable program instructions.

[0118] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processor of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner; thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0119] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions that execute on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0120] The flowcharts and block diagrams in the accompanying figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products under various scenarios. In this respect, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction, which contains one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than those shown in the figures. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0121] Various examples have been described above. The foregoing descriptions are exemplary and not exhaustive, nor are they limited to the disclosed implementations. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described implementations. The terminology used herein is chosen to best explain the principles, practical applications, or improvements to technology in the market, or to enable others skilled in the art to understand the various implementations disclosed herein.

Claims

1. A method for interface interaction, comprising: The first prompt word is displayed in plaintext, the first prompt word is used by the intelligent system, and the plaintext state indicates that the first prompt word is visible to the user; In response to receiving a first instruction, the first prompt word is converted from the plaintext state to the ciphertext state, the ciphertext state indicating that the first prompt word is not visible to the user; as well as The conversion result is presented, and the conversion result includes the first prompt word in the encrypted state.

2. The method of claim 1, wherein displaying the first prompt word in plaintext includes: Display the first component; The first component receives a first input, the first input including the first prompt word; as well as In the first component, the first prompt word is displayed in plaintext.

3. The method of claim 2, wherein receiving the first input in the first component comprises: A first area is displayed in the first component, and a first control is displayed in the first area; as well as In response to a first trigger operation on the first control, the first input is received; and The first prompt word being displayed in plaintext in the first component includes: The first prompt word is displayed in plaintext in the first area.

4. The method of claim 2, wherein receiving the first input in the first component comprises: Display the input box in the first component; as well as The first input is received in the input box.

5. The method according to claim 1, further comprising: Receive a first operation, the first operation instructing the import of a second prompt word, the second prompt word being in the encrypted state, the second prompt word being invisible to the user in the encrypted state; as well as Display a first identifier, which is used to identify the second prompt word.

6. The method according to claim 5, further comprising: Receive a second operation, which instructs the generation of the first explanatory text; The first explanatory text is displayed, which is obtained by the intelligent system based on the second prompt word.

7. The method according to claim 1, further comprising: The conversion result is saved as a first file, which contains the first prompt word in the encrypted state.

8. The method according to claim 1, further comprising: The conversion result is sent to the first object.

9. The method according to claim 1, further comprising: In response to a second triggering operation on the first prompt word, a second explanatory text is displayed, which is obtained by the intelligent system based on the first prompt word.

10. The method of claim 1, further comprising: Displaying the primary media; Receive a third operation, the third operation instructing the editing of the first media; as well as The second media is displayed, which is obtained by editing the first media using the intelligent system.

11. The method of claim 10, wherein displaying the second media comprises: Receive a fourth operation, the fourth operation indicating a first editing mode; as well as The second media is displayed, which is obtained by editing the first media using the intelligent system in the first editing mode.

12. The method of claim 11, wherein receiving the fourth operation comprises: The second component is displayed, which includes multiple elements, each of which corresponds to a multiple clipping mode. The multiple elements include a first element, which corresponds to the first clipping mode. as well as Receive a third trigger operation, which is a trigger operation on the first element.

13. The method of claim 11, wherein displaying the second media comprises: Display a first configuration panel, which is associated with the first editing mode; Receive the first configuration information in the first configuration panel; as well as The second media is displayed, which is obtained by editing the first media based on the first configuration information using the intelligent system.

14. The method of claim 13, wherein the first configuration information indicates one of the following: The specified number of the second media; or The second instruction instructs the intelligent system to automatically determine the number of the second media.

15. The method of claim 13, wherein receiving the first configuration information in the first configuration panel includes at least one of the following: The first configuration panel receives a third explanatory text, which is used to explain the first media; The first voice is received on the first configuration panel, and the first voice is used to explain the first media.

16. The method of claim 15, wherein the second medium comprises a second speech, the second speech being obtained based on at least one of the third narration text and the first speech.

17. The method of claim 15, wherein the third explanatory text is obtained by the intelligent system based on at least one of the first prompt word or the conversion result.

18. The method of claim 13, wherein receiving the first configuration information in the first configuration panel includes: The second configuration item is displayed in the first configuration panel; In response to a fourth trigger operation on the second configuration item, a first label is displayed, the first label identifying the first role; as well as In response to a fifth trigger operation on the first tag, a first instruction is received, the first instruction indicating the first character, wherein the second medium includes a second voice, the second voice being uttered in the timbre of the first character.

19. The method of claim 13, wherein receiving the first configuration information in the first configuration panel includes: The first configuration parameter is displayed in the first configuration panel and is associated with the first editing mode. as well as Receive a second input, which is a parameter value for the first configuration parameter.

20. An electronic device, comprising: At least one processor; as well as At least one memory coupled to the at least one processor and storing instructions for execution by the at least one processor, the instructions causing the electronic device to perform the method according to any one of claims 1 to 19 when executed by the at least one processor.

Images