Interaction method of artificial intelligence application and electronic device

Abstract

The application provides an interaction method of an artificial intelligence application and an electronic device. The interaction method of the artificial intelligence application is applied to an electronic device, the electronic device comprises a first display component arranged on a first surface of the electronic device, and the method comprises the following steps: when an artificial intelligence application in the electronic device is started, a continuous interaction mode is entered; when a first application different from the artificial intelligence application is displayed on the first display component, the first display component displays first display content; the artificial intelligence application receives a first instruction input by a user, processes first target content data according to the received first instruction, to generate second target content data, wherein the first target content data comprises data extracted from the first display content by the artificial intelligence application; and the second target content data is output in a first mode. The application achieves the technical effect that the artificial intelligence application and the user interact in real time, and improves the accuracy of the generated second target content data.

Description

Technical Field

[0001] This application relates to the field of electronic device technology, and more particularly to an interactive method and electronic device for artificial intelligence applications. Background Technology

[0002] With the rapid development of technology, smartphones and other electronic devices are widely used in people's work and life. As the demand for intelligent electronic devices gradually increases, artificial intelligence (AI) applications have emerged and are being used by customers to process various types of information. However, existing AI applications cannot proactively extract and analyze content. Instead, users need to actively input content information (such as text, voice, photos, screenshots, etc.) into the AI ​​application before it can analyze and process it. This process involves multiple steps, wasting user time and reducing the efficiency of obtaining the target content data. Furthermore, the setting that AI applications only analyze and process input information prevents real-time analysis. This means the AI ​​application cannot analyze and process the required content data immediately, and the analysis results are entirely dependent on the user's input. When users input fragmented information, the analysis may be incomplete or inaccurate, thus degrading the user experience. Summary of the Invention

[0003] Therefore, this application provides an interaction method and electronic device for artificial intelligence applications, which can solve at least some of the above-mentioned technical problems.

[0004] The first aspect of this application provides an interaction method for an artificial intelligence application, the method being applied to an electronic device, the electronic device including a first display component disposed on a first surface of the electronic device, the method comprising: Once the artificial intelligence application in the electronic device is activated, it enters a continuous interaction mode; When the first display component displays a first application that is different from the artificial intelligence application, the first display component displays the first display content; The artificial intelligence application receives a first instruction input by the user and processes the first target content data according to the received first instruction to generate second target content data, wherein the first target content data includes data extracted by the artificial intelligence application from the first displayed content; The second target content data is output in the first mode.

[0005] A second aspect of this application provides an electronic device, comprising: Applications of artificial intelligence; A first display component disposed on the first side of the electronic device; When the artificial intelligence application in the electronic device is activated, it enters a continuous interaction mode. When the first display component displays a first application that is different from the artificial intelligence application, the first display component displays first display content. The artificial intelligence application receives a first instruction input by the user and processes the first target content data according to the received first instruction to generate second target content data. The second target content data is then output in a first mode. The first target content data is data extracted by the artificial intelligence application from the first display content.

[0006] A third aspect of this application provides an electronic device, comprising: a processor and a memory, the memory being connected to the processor, the memory storing a computer program, and the processor executing the interaction method of the artificial intelligence application as described above.

[0007] A fourth aspect of this application provides a computer-readable storage medium storing a computer program, which, when invoked by a processor, executes the interactive method of the artificial intelligence application described above.

[0008] This application provides an interactive method and electronic device for an artificial intelligence application. The AI ​​application of this application can actively extract first target content data from the first displayed content, without requiring the user to actively input content information (such as text, voice, photos, screenshots, etc.) into the AI ​​application. This process reduces user operation steps, thereby reducing user operation time and improving the efficiency of user acquisition of target content data. Furthermore, the AI ​​application of this application can be kept running for extended periods in continuous interaction mode to achieve the technical effect of real-time extraction of the first displayed content and real-time processing of the first target data content. The AI ​​application can then process the first displayed content and the first target data content instantly, improving the continuity of use of the AI ​​application and achieving the technical effect of real-time interaction between the AI ​​application and the user. Moreover, this setting also makes the AI ​​application independent of user-input content information, thus minimizing the possibility of incomplete or erroneous processing due to overly partial or incomplete content information, thereby improving the accuracy of the generated second target content data and further enhancing the user experience. Attached Figure Description

[0009] To more clearly illustrate the technical solution of this application, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0010] Figure 1 This is a flowchart of an interaction method for an artificial intelligence application in one embodiment of this application; Figure 2 A flowchart illustrating an interaction method for an artificial intelligence application in another embodiment of this application; Figure 3 A flowchart illustrating an interaction method for an artificial intelligence application in yet another embodiment of this application; Figure 4 This is a schematic block diagram of an electronic device according to an embodiment of this application; Figure 5 This is a schematic diagram of a first display component of an electronic device according to an embodiment of this application; Figure 6 This is a schematic diagram of the first display content of an electronic device in one embodiment of this application; Figure 7 This is a schematic diagram of a second display component of an electronic device according to an embodiment of this application; Figure 8 This is a schematic block diagram of an electronic device according to another embodiment of this application.

[0011] Icon labels: Electronic device - 100; Artificial intelligence application - 200; First side - 300; First display component - 400; First display content - 401; First application - 500; Button - 600; Second side - 700; Second display component - 800; Processor - 900; Memory - 1000. Detailed Implementation

[0012] 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, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0013] In the description of the embodiments of this application, it should be understood that the terms "upper," "lower," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. The term "connection" in this application, unless otherwise specified, primarily refers to a physical structural connection; however, if specified, it may also include direct or indirect connections. The terms "first" and "second" in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the term "comprising" and any variations thereof are intended to cover non-exclusive inclusion.

[0014] Please see Figure 1 , Figure 1 This is a flowchart of an interaction method for an artificial intelligence application according to an embodiment of this application. The interaction method of the artificial intelligence application is applied to an electronic device, the electronic device including a first display component disposed on a first surface of the electronic device, the method including: S1: When the artificial intelligence application in the electronic device is activated, it enters the continuous interaction mode; S2: When the first display component displays a first application that is different from the artificial intelligence application, the first display component displays the first display content; S3: The artificial intelligence application receives a first instruction input by the user and processes the first target content data according to the received first instruction to generate second target content data, wherein the first target content data includes data extracted by the artificial intelligence application from the first displayed content; S4: Output the second target content data in the first mode.

[0015] Specifically, after the user activates the artificial intelligence application in the electronic device, it enters its own continuous interaction mode. At this time, the artificial intelligence application is always on and obtains the first display content displayed by the first display component in real time. In other words, it can extract the first display content in real time to obtain the first target content data. When the user inputs a first command, the artificial intelligence application will process the first target content data according to the first command to generate the second target content required by the user at this time, and output the second target content data in the first mode.

[0016] Therefore, the artificial intelligence application of this application can actively extract the first target content data from the first displayed content. This allows the application to obtain the first target content data without requiring the user to actively input content information (such as text, voice, photos, screenshots, etc.). This process reduces the user's operation steps, thereby reducing user operation time and improving the efficiency of obtaining target content data. Furthermore, the artificial intelligence application of this application can be kept running for extended periods in continuous interaction mode to achieve the technical effect of real-time extraction of the first displayed content and real-time processing of the first target data content. This allows the artificial intelligence application to process the first displayed content and the first target data content instantly, improving the continuity of use of the artificial intelligence application and achieving the technical effect of real-time interaction between the artificial intelligence application and the user. Moreover, this setting also makes the artificial intelligence application independent of the content information input by the user, thus minimizing the possibility of incomplete or erroneous processing due to overly partial or incomplete content information. This improves the accuracy of the generated second target content data and further enhances the user experience.

[0017] The electronic device may be a mobile phone, or it may be a watch, smart glasses, earphones, earphone case, voice recorder, ring, or other device capable of executing the interactive methods of the artificial intelligence application. The first display component is the display screen of the aforementioned electronic device that can display content information.

[0018] In some embodiments, the first application may be a user-operable application such as a memo app, a health monitoring app, a news website, or a browser. In this case, the first displayed content may be memo content data, health monitoring data, news content, content searched by the browser, etc. The first application and the first displayed content can be selected according to actual needs and are not limited to the above-mentioned applications and content.

[0019] In this application, the artificial intelligence application is an application with artificial intelligence processing capabilities, that is, an application with the ability to analyze and process content information to obtain analysis results, such as existing artificial intelligence applications such as Gemini and ChatGPT.

[0020] In some embodiments, the first displayed content includes one or more of the following: input information, information obtained through the first application, and historical content data of the first application.

[0021] Therefore, the AI ​​application can acquire one or more types of information in real time and extract the first target content data from them in real time. This improves the continuity of the AI ​​application's use and achieves the technical effect of real-time interaction between the AI ​​application and the user. Furthermore, this setting allows the AI ​​application to be independent of user-inputted content information, thus minimizing the possibility of incomplete or erroneous processing due to overly partial or incomplete content information. This improves the accuracy of the generated second target content data, further enhancing the user experience. Moreover, the first target content data can be extracted from multiple types of information, improving not only the comprehensiveness of the first target content data but also the accuracy and comprehensiveness of the generated second target content data.

[0022] The input information can be information entered by the user in the first application through voice input, typing input, uploading pictures, taking photos, etc. This input information can ultimately be displayed on the first display component in modalities such as voice, text, and images to form at least a portion of the first displayed content. For example, when the first application is a memo app, the input information is the content information entered by the user in real time within the first application; when the first application is a health monitoring application, the information input by the electronic device is the health data information obtained and recorded in real time by the first application through its monitoring function, or the health data information (personal height, weight, exercise status, body dimensions, etc.) entered by the user within the health monitoring application.

[0023] The information obtained through the first application may be news content, entertainment videos, learning content, etc., obtained by searching through the first application. For example, when the first application is a browser, the required information can be obtained by searching through the first application to form at least part of the first displayed content.

[0024] The historical content data information of the first application can be the content information already stored in the first application. For example, when the first application is a memo app, the historical content data information is the content information already stored in the first application; when the first application is a health monitoring application, the historical content data information is the health data information already stored in the first application.

[0025] In some embodiments, the artificial intelligence application may also extract the first target content data by extracting historical usage data and / or other non-first display content of the electronic device. Here, the source of the first target content data is not restricted.

[0026] In some embodiments, the first instruction includes at least one of a voice input instruction and an operation instruction for the first display component.

[0027] Therefore, the artificial intelligence application can respond to the first instruction to process the first target content data based on the first instruction to generate the second target content data required by the user at this time, realizing the technical effect of real-time interaction between the artificial intelligence application and the user. Furthermore, this setting allows the artificial intelligence application to directly and selectively output the second target content data required by the user, without requiring the user to search for the desired content in the first target content data, thereby improving the efficiency and convenience for the user to obtain the second target content data and enhancing the user experience.

[0028] The operation instructions for the first display component can include typing, selecting an image, taking a photo, and paragraph marking.

[0029] Please see Figure 2 , Figure 2 This is a flowchart of an interaction method for an artificial intelligence application according to another embodiment of this application. The step of processing the first target content data according to the received first instruction to generate second target content data includes: S31: The artificial intelligence application analyzes the first target content data according to the received first instruction to obtain the second target content data, wherein the second target content data includes one or more types of data such as text, images, videos, and audio.

[0030] Therefore, after receiving the first instruction, the artificial intelligence application needs to continue analyzing the acquired first target content data to obtain the second target content data required by the user. This avoids the situation where there is too much first target content data and the user cannot quickly obtain the information they need. In other words, it improves the speed and efficiency of obtaining the information required by the user and improves the user's satisfaction.

[0031] In some embodiments, in order to further improve the response speed of the artificial intelligence application after the user issues the first command, during the period when the artificial intelligence application enters the continuous interaction mode and the first display component displays the first display content of the first application, the artificial intelligence application may perform preprocessing analysis based on the first display content acquired in real time before receiving the first command.

[0032] For example, the artificial intelligence application can perform segmented parsing, entity / key concept extraction, summary generation, difficult sentence identification, background knowledge retrieval and alignment related to the first displayed content, and write the corresponding analysis results, candidate answers, and / or intermediate results of model inference into the context cache or data space to form the first target content data.

[0033] In some embodiments, the context cache may be further associated with the user's current reading position, selected area, cursor focus control, scroll position, and / or the page structure information of the first application, so that the user does not need to repeat the specific content when issuing the first command. When the AI ​​application receives the user's voice command or the first command generated by a trigger operation such as pressing a button, the AI ​​application can directly call the first target content data in the context cache and generate the second target content data corresponding to the first command. This moves the analysis that originally needed to be completed after receiving the first command to the period when the user is reading the first displayed content, thereby reducing the response latency perceived by the user and improving the response speed of the AI ​​application after the user issues the first command.

[0034] Furthermore, since the preprocessing analysis can be performed continuously while the user is reading the first displayed content, the artificial intelligence application can directly select a model with a longer reasoning time but stronger capabilities or a processing strategy with higher reasoning depth to more fully understand and analyze the first displayed content. At the same time, it can still quickly output the second target content data after the user issues the first command, so as to achieve an interactive experience of "reading, asking and answering at the same time".

[0035] Specifically, the AI ​​application can directly extract the first displayed content, that is, perform operations such as analysis and summarization on the first displayed content. The extracted overall content and the content analyzed by the AI ​​application based on the first displayed content constitute the first target content data. When the user inputs the first instruction, the AI ​​application receives the first instruction and processes the first target content data based on the first instruction to generate second target content data related to the first instruction.

[0036] For example, when a user is browsing news or other information through the first application, the first displayed content is the news or other information that the user is browsing. The artificial intelligence application will obtain the first displayed content displayed by the first display component in real time, and perform processing such as summarizing, organizing, and automatically searching the network to supplement relevant background information and extended content to obtain the first target content data. The first target content data can be stored in the data space, local space, cloud storage space, etc. of the electronic device in data format such as cards and notes, so that it can be directly called when the first target content data is needed later.

[0037] The user can then input the first instruction. If the first instruction is a voice input instruction, it can specifically ask for the meaning of a paragraph, a sentence, or a technical term, or ask what the main content of this news or information is. If the first instruction is a selection and marking operation, it can specifically ask the user to select a part of the content they do not understand. The artificial intelligence application analyzes the received first instruction to understand the user's current needs, and then calls the first target content data based on the first instruction, processes it to obtain the second target content data, and outputs the second target content data in a first mode. This answers the user's questions and meets the user's needs, thus enabling real-time interaction between the user and the artificial intelligence application, and allowing for real-time learning and interaction.

[0038] In some embodiments, users can also engage in daily chat conversations with the AI ​​application. The AI ​​application records and / or replies to the chat conversations sent by the user. This operation enables the AI ​​application to better understand the user's actions, habits, current goals, preferences, daily routines, and other personal information. Consequently, during the processing of the first target content data based on the first instruction, the application can generate second target content data that is easier for the user to understand and / or more suitable for the user based on the user's personal information.

[0039] For example, the first instruction is to recommend suitable recreational activities (which can be input by voice or typing). The AI ​​application can recommend suitable recreational activities for the user based on the user's personal information, that is, to customize a list of recreational activities for the user. As another example, the first application is a health monitoring application. The AI ​​application obtains first target content data based on the user's personal information. The first target content data includes a customized exercise plan based on the user's personal information, and / or reminders based on the user's daily work to remind the user to take a rest or go for a walk, and / or reminders to adjust the user's exercise intensity.

[0040] In some embodiments, if a user is unable to look at the first display component in certain scenarios or is unable to look at the first display component for an extended period of time, the user may issue a voice input command to enable the artificial intelligence application to process the first target content data, thereby facilitating the user to obtain the required second target content data.

[0041] In some embodiments, the artificial intelligence application has a corresponding dynamic image, which functions similarly to an "assistant" or "pet companion." During the operation of the artificial intelligence application, the dynamic image of the application is displayed on the first display component. The user can clearly know the current state of the artificial intelligence application based on the dynamic image, specifically whether it is running or stopped. Furthermore, the dynamic image can interact with the user to increase the fun of intelligent interaction between the artificial intelligence application and the user.

[0042] Please see Figure 3 , Figure 3 This is a flowchart of an interaction method for an artificial intelligence application in another embodiment of this application. The step of processing the first target content data according to the received first instruction to generate second target content data includes: S32: Generate a first prompt message according to the first instruction, and the artificial intelligence application processes the first target content data according to the first prompt message to generate second target content data, wherein the first prompt message includes a processing scheme for the first target content data; The step of outputting the second target content data in a first mode includes: S41: Determine the corresponding first mode based on the first prompt information, and output the second target content data in the corresponding first mode, wherein the first mode includes one or more of audio, image, and text modes.

[0043] The first prompt information may be prompt statements, prompt words, or other information that has a prompting function.

[0044] Specifically, the user inputs the first instruction, the electronic device analyzes and processes the first instruction to generate the first prompt information, and the artificial intelligence application processes the first target content data according to the first prompt information to generate second target content data related to the first prompt information. After generating the second target content data, the electronic device continues to process the second target content data according to the first prompt information and outputs the second target content data in a first mode included in the first prompt information.

[0045] Therefore, by processing the first target content data according to the first prompt information, the second target content data required by the user can be obtained. This avoids the situation where the first target content data is too large and the user cannot quickly obtain the information they need, thus improving the speed and efficiency of obtaining the information required by the user. Furthermore, the second target content data can be output in the first mode required by the user according to the first prompt information, so that the user can obtain the second target content information instantly and conveniently in the current scenario, thereby improving the user's satisfaction and user experience.

[0046] The first prompt information includes not only the processing scheme for the first target content data (e.g., what content to extract, what answer to find, what question to answer), but also information on the specific first mode, so that the obtained second target content data can be output in the mode required by the user.

[0047] In some embodiments, the electronic device presets the first mode, and if the user does not specify which first mode the second target content should be output in, then the preset first mode is used for output.

[0048] In some embodiments, the method further includes: When a preset operation command is received, the AI ​​application is controlled to exit the continuous interaction mode.

[0049] Therefore, upon receiving a preset operation command, the artificial intelligence will exit the continuous interaction mode to close the continuous interaction mode of the artificial intelligence, thereby improving the controllability of the continuous interaction mode of the artificial intelligence, enhancing the user experience, and the existence of the preset operation command can be distinguished from other commands to avoid the situation where the artificial intelligence application is mistakenly exited from the continuous interaction mode.

[0050] The preset operation commands include flipping the electronic device in a preset posture, exiting by voice input, and pressing the buttons on the electronic device with preset pressing parameters.

[0051] In some embodiments, the method further includes: The artificial intelligence application obtains a cognitive set based on the first displayed content, and generates second target content data according to the first instruction input by the user and the cognitive set when it receives the first instruction input by the user.

[0052] Therefore, upon receiving the first instruction input by the user, the AI ​​application responds to the first instruction while also referencing the cognitive set to generate the second target content data required by the user, so as to provide targeted answers to the questions raised by the user, thereby providing the content required by the user more accurately and improving the user experience.

[0053] The cognitive set can also be regarded as the content information included in the first target content data.

[0054] In some embodiments, the first displayed content may include multiple types of information. For example, a user may display and play a video while browsing text information, or perform a split-screen search operation on the current page at the same time. In this case, the artificial intelligence application will acquire multiple types of information in real time, and summarize and analyze the multiple types of information to obtain the user's current cognitive level information. Based on the acquired cognitive level information, a cognitive set is generated. Then, when the artificial intelligence application responds to the first instruction, the artificial intelligence application will generate second target content data that the user can understand and currently needs based on the user's current cognitive level and multiple types of information, thereby achieving the technical effect of providing targeted answers to the user's questions.

[0055] In some embodiments, the electronic device is also used to display second display content, which is information that cannot be monitored by the artificial intelligence application.

[0056] Therefore, the electronic device also includes information that cannot be eavesdropped on or obtained by artificial intelligence applications, such as users' chat logs, payment records and other important private information, thereby ensuring the security of user privacy and preventing important private information from being obtained and leaked.

[0057] In some embodiments, users can set information that the AI ​​application cannot access in the settings interface of the electronic device before the continuous interaction mode of the AI ​​application is turned on, so as to ensure the security of user privacy.

[0058] In some embodiments, the electronic device includes a second display component disposed on a second surface opposite to the first surface, and the method further includes: In response to a trigger operation, the electronic device is controlled to launch the artificial intelligence application, and the first display component and / or the second display component is controlled to display status effects related to the working state of the artificial intelligence application, so as to indicate the current working state of the artificial intelligence application.

[0059] Therefore, by displaying status effects related to the working status of the artificial intelligence application through the first display component and / or the second display component, the current working status of the artificial intelligence application can be clearly identified. Users can clearly see the current working status of the artificial intelligence application through the first display component and / or the second display component, which facilitates subsequent operations by the user.

[0060] In some embodiments, the first display component is a display screen or other component with a display function of the electronic device, and the second display component may be another display screen or a light array or other component with a display function of the electronic device.

[0061] Specifically, when the second display component is another display screen, the second display component can display the current working status of the AI ​​application in text form, and / or, the second display component can display the current working status of the AI ​​application with corresponding dynamic effects and / or static images, etc.; when the second display component is a display component that mainly displays light, such as a light array, the second display component can display the current working status of the AI ​​application with the corresponding light color, and / or, the second display component can display the current working status of the AI ​​application with the corresponding light brightness, and / or, the second display component can display the current working status of the AI ​​application with the corresponding light dynamic effects, etc. The specific status effects can be set according to the type and needs of the second display component. Here, the status effects related to the working status of the AI ​​application displayed by the first display component and the second display component are not limited.

[0062] As mentioned above, when the artificial intelligence application has a corresponding dynamic image, the first display component and / or the second display component can combine the dynamic image to clearly define the current working status of the artificial intelligence application when the application is running.

[0063] In some embodiments, the triggering operation may be a pressing operation on a button of the electronic device, a touch operation on the first display component and / or the second display component, or a state triggering operation of the sensor of the electronic device.

[0064] In some embodiments, the method further includes: When a specific exit command is triggered, the first display component and / or the second display component are controlled to display status effects related to the exit of the AI ​​application from the continuous interaction mode.

[0065] Therefore, by displaying the status effect related to the AI ​​application exiting the continuous interaction mode through the first display component and / or the second display component, it can be clearly seen that the AI ​​application is currently exiting the continuous interaction mode, so as to facilitate the user's subsequent operations.

[0066] The specific exit instruction and the aforementioned preset operation instruction are the same concept, both being instructions that cause the artificial intelligence application to exit the continuous interaction mode.

[0067] In some embodiments, the triggering operation includes a first triggering operation and a second triggering operation, wherein the pressing parameters of the first triggering operation and the second triggering operation are different, which are used to characterize the different permissions granted by multiple first applications in the electronic device to the artificial intelligence application.

[0068] Therefore, users can determine the permissions that the first application grants to the AI ​​application based on different trigger operations, which simplifies the user's steps in setting the permissions that the first application grants to the AI ​​application, making it easier for users to operate.

[0069] In some embodiments, the triggering operation is a pressing operation, that is, pressing a button on the electronic device. The pressing operation includes a first pressing operation and a second pressing operation. At least one of the pressing parameters of the first pressing operation, the pressing force, the pressing duration, and the number of pressings is different between the second pressing operation and the first pressing operation. Furthermore, the first pressing operation and the second pressing operation can be operations performed separately for pressing different buttons on the electronic device.

[0070] Specifically, the different permissions granted by multiple first applications to the artificial intelligence application can be reflected in the different ways the artificial intelligence application reads the first display content of the first application. For example, granting full permissions means that the artificial intelligence application can obtain all the content information of the first display content, while granting partial permissions means that the artificial intelligence application can obtain only part of the content information of the first display content.

[0071] In some embodiments, the electronic device is communicatively connected to a second terminal, and the method further includes: When the artificial intelligence application is activated, it controls the electronic device to acquire information stored in the second terminal in real time. The artificial intelligence application analyzes and processes the acquired information stored in the second terminal to obtain the corresponding second target content data.

[0072] Therefore, after the artificial intelligence application is launched, it can also analyze and process the information stored in the second terminal to obtain the second target content data. This allows the artificial intelligence application to be free from the limitations of a fixed device, thereby expanding its application scope. Furthermore, since more information can be obtained, the comprehensiveness and credibility of the second target content data can be improved accordingly.

[0073] In some embodiments, the information stored in the second terminal is one or more of the following: parameter information, voice information, and image information.

[0074] Therefore, by obtaining more information, the comprehensiveness and credibility of the second target content data can be improved accordingly.

[0075] Please see Figure 4 and Figure 5 , Figure 4 This is a schematic block diagram of an electronic device 100 according to an embodiment of this application. Figure 5 This is a schematic diagram of the first display component 400 of an electronic device 100 according to an embodiment of this application. The electronic device 100 includes an artificial intelligence application 200 and a first display component 400 disposed on a first surface 300 of the electronic device 100. When the artificial intelligence application in the electronic device is activated, it enters a continuous interaction mode. Please refer to [link to relevant documentation]. Figure 6 , Figure 6 This is a schematic diagram of the first display content 401 of an electronic device 100 in one embodiment of this application. When the first display component 400 displays a first application 500 that is different from the artificial intelligence application 200, the first display component 400 displays the first display content 401. The artificial intelligence application 200 receives a first instruction input by the user and processes the first target content data according to the received first instruction to generate second target content data, and outputs the second target content data in a first mode. The first target content data is data extracted by the artificial intelligence application 200 from the first display content 401.

[0076] Therefore, the AI ​​application 200 of this application can actively extract the first target content data from the first displayed content 401, without requiring the user to actively input content information into the AI ​​application 200. This process reduces the user's operation steps, thereby reducing the user's operation time and improving the efficiency of the user in obtaining the target content data. Furthermore, the AI ​​application 200 of this application can be kept running for a long time in continuous interaction mode to achieve the technical effect of real-time extraction of the first displayed content 401 and real-time processing of the first target data content. Thus, the AI ​​application 200 can process the first displayed content 401 and the first target data content in real time, improving the continuity of use of the AI ​​application 200 and achieving the technical effect of real-time interaction between the AI ​​application 200 and the user. Moreover, this setting also makes the AI ​​application 200 independent of the content information input by the user, thus avoiding situations where the content information is too partial or incomplete, resulting in incomplete processing or errors. This improves the accuracy of the generated second target content data and further enhances the user experience.

[0077] Please see Figure 7 , Figure 7This is a schematic diagram of a second display component 800 of an electronic device 100 according to one embodiment of this application. In some embodiments, the electronic device 100 further includes a second display component 800 disposed on a second surface 700 opposite to the first surface 300. The second display component 800 can be used to display status effects related to the working state of the artificial intelligence application 200 to indicate the current working state of the artificial intelligence application 200.

[0078] In some embodiments, the first display component 400 is a display screen or other component with display function of the electronic device 100, and the second display component 800 may be another display screen or light array or other component with display function of the electronic device 100.

[0079] In some embodiments, the electronic device 100 further includes a button 600 disposed on the side of the electronic device, the button 600 being used to respond to a pressing operation to cause the electronic device to perform a predetermined function.

[0080] In some embodiments, real-time acquisition of the first display content can be achieved through at least one of the following methods: ① under user authorization, calling the accessibility / accessibility interface provided by the operating system of the electronic device to obtain interface text and control hierarchy information; ② the first application providing the structured content of the current page to the artificial intelligence application through a preset content sharing interface; ③ under user authorization, capturing the content of the current display frame and performing text recognition / structured parsing; wherein, the second display content configured as unaccessible is not collected or is filtered / de-sensitized after collection.

[0081] Please see Figure 8 , Figure 8 This is a schematic block diagram of an electronic device 100 according to another embodiment of this application. The electronic device 100 includes a processor 900 and a memory 1000, the memory 1000 being connected to the processor 900, the memory 1000 storing a computer program, and the processor 900 executing the interaction method of the artificial intelligence application described above.

[0082] Therefore, the AI ​​application 200 of this application can actively extract the first target content data from the first displayed content 401, without requiring the user to actively input content information into the AI ​​application 200. This process reduces the user's operation steps, thereby reducing the user's operation time and improving the efficiency of the user in obtaining the target content data. Furthermore, the AI ​​application 200 of this application can be kept running for a long time in continuous interaction mode to achieve the technical effect of real-time extraction of the first displayed content 401 and real-time processing of the first target data content. Thus, the AI ​​application 200 can process the first displayed content 401 and the first target data content in real time, improving the continuity of use of the AI ​​application 200 and achieving the technical effect of real-time interaction between the AI ​​application 200 and the user. Moreover, this setting also makes the AI ​​application 200 independent of the content information input by the user, thus avoiding situations where the content information is too partial or incomplete, resulting in incomplete processing or errors. This improves the accuracy of the generated second target content data and further enhances the user experience.

[0083] In some embodiments, the electronic device 100 can be applied to the interaction method of the artificial intelligence application as described above, and the steps in the interaction method of the artificial intelligence application can be executed by the processor 900 and memory 1000 in the electronic device 100.

[0084] In some embodiments, the steps in the interaction method of the artificial intelligence application can be applied to the aforementioned electronic device 100, and the steps in the interaction method of the artificial intelligence application can be functional operations performed by the aforementioned electronic device 100. The interaction method of the artificial intelligence application and the content of the aforementioned electronic device 100 can be mutually referenced.

[0085] Furthermore, the processor 900 can be a general-purpose processor, a digital signal processor, an application-specific integrated circuit (ASIC), an off-the-shelf programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The processor can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this invention. The processor can be a graphics processor, a microprocessor, or any conventional processor. The steps of the methods disclosed in the embodiments of this invention can be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software modules can reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. This storage medium is located in the memory; for example, the processor 900 can read application programs, computer instructions, or data from the memory and, in conjunction with its hardware, complete the steps of the above methods.

[0086] This application also provides a computer-readable storage medium storing a computer program, which is invoked by a processor 900 to execute the above-described interactive method of artificial intelligence application.

[0087] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage device, which may include: a flash drive, a read-only memory, a random access memory, a magnetic disk, or an optical disk, etc.

[0088] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0089] In the description of this application, unless otherwise expressly specified and limited, the term "connection" should be interpreted broadly. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a direct connection or an indirect connection through an intermediate medium; it can also refer to the internal connection of two components; it can be a communication connection; or it can be an electrical connection. Those skilled in the art can understand the specific meaning of the above terms in this application according to the specific circumstances.

[0090] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The presentation of this phrase in various locations throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0091] In the several embodiments provided in this application, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or modules may be electrical or other forms.

[0092] The modules described above as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0093] Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0094] If the integrated modules described above are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to related technologies, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0095] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage device, which may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, etc.

[0096] The above are the implementation methods of the embodiments of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the embodiments of this application, and these improvements and modifications are also considered to be within the protection scope of this application.

Claims

1. An interaction method for an artificial intelligence application, characterized in that, The method is applied to an electronic device, the electronic device including a first display component disposed on a first surface of the electronic device, the method comprising: Once the artificial intelligence application in the electronic device is activated, it enters a continuous interaction mode; When the first display component displays a first application that is different from the artificial intelligence application, the first display component displays the first display content; The artificial intelligence application receives a first instruction input by the user and processes the first target content data according to the received first instruction to generate second target content data, wherein the first target content data includes data extracted by the artificial intelligence application from the first displayed content; The second target content data is output in the first mode.

2. The method according to claim 1, characterized in that, The step of processing the first target content data according to the received first instruction to generate the second target content data includes: The artificial intelligence application analyzes the first target content data to obtain the second target content data, wherein the second target content data includes one or more types of data such as text, images, videos, and audio.

3. The method according to claim 1, characterized in that, The step of processing the first target content data according to the received first instruction to generate the second target content data includes: The first prompt information is generated according to the first instruction, and the artificial intelligence application processes the first target content data according to the first prompt information to generate second target content data. The first prompt information includes a processing scheme for the first target content data. The step of outputting the second target content data in a first mode includes: The first mode is determined according to the first prompt information, and the second target content data is output in the corresponding first mode, wherein the first mode includes one or more of audio, image and text modes.

4. The method according to claim 1, characterized in that, The method further includes: The artificial intelligence application obtains a cognitive set based on the first displayed content, and generates second target content data according to the first instruction input by the user and the cognitive set when it receives the first instruction input by the user.

5. The method according to claim 1, characterized in that, The electronic device is also used to display a second display content, which is information that cannot be listened to by the artificial intelligence application.

6. The method according to claim 1, characterized in that, The electronic device includes a second display component disposed on a second surface opposite to the first surface, and the method further includes: In response to a trigger operation, the electronic device is controlled to launch the artificial intelligence application, and the first display component and / or the second display component is controlled to display status effects related to the working state of the artificial intelligence application, so as to indicate the current working state of the artificial intelligence application.

7. The method according to claim 6, characterized in that, The method further includes: When a specific exit command is triggered, the first display component and / or the second display component are controlled to display status effects related to the exit of the AI ​​application from the continuous interaction mode.

8. The method according to claim 6, characterized in that, The triggering operation includes a first triggering operation and a second triggering operation, wherein the pressing parameters of the first triggering operation and the second triggering operation are different, which are used to characterize the different permissions that multiple first applications in the electronic device grant to the artificial intelligence application.

9. The method according to claim 1, characterized in that, The electronic device is communicatively connected to the second terminal, and the method further includes: When the artificial intelligence application is activated, it controls the electronic device to acquire information stored in the second terminal in real time. The artificial intelligence application analyzes and processes the acquired information stored in the second terminal to obtain the corresponding second target content data.

10. The method according to claim 9, characterized in that, The information stored in the second terminal is one or more of the following: parameter information, voice information, and image information.

11. An electronic device, characterized in that, include: Artificial intelligence applications; A first display component disposed on the first side of the electronic device; When the artificial intelligence application in the electronic device is activated, it enters a continuous interaction mode. When the first display component displays a first application that is different from the artificial intelligence application, the first display component displays first display content. The artificial intelligence application receives a first instruction input by the user and processes the first target content data according to the received first instruction to generate second target content data. The second target content data is then output in a first mode. The first target content data is data extracted by the artificial intelligence application from the first display content.

12. An electronic device, characterized in that, include: A processor and a memory, the memory being connected to the processor, the memory storing a computer program, the processor executing the interaction method of the artificial intelligence application as described in any one of claims 1-10.

13. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, which, when invoked by a processor, executes the interaction method of the artificial intelligence application as described in any one of claims 1-10.

Images