Interaction method and electronic equipment

Abstract

The invention provides an interaction method and electronic equipment, relates to the technical field of terminals, and aims at an instruction of a user to obtain a response operation which is easier to match a user demand so as to bring better interaction experience to the user. In the method, the electronic equipment receives a first instruction input by a user; afterwards, the electronic device obtains the current scene, and the scene is determined according to at least one of the position of the electronic device in the real world, the time of the real world, the weather condition of the real world or the state of the mobile phone. And finally, the electronic equipment executes a first response operation corresponding to the first instruction in the current scene, and the first response operation is determined according to the current scene of the electronic equipment and the first instruction.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of terminal, and in particular, to an interaction method and an electronic device. BACKGROUND

[0002] A voice assistant is usually arranged in an electronic device, and a user can interact with the electronic device by using the voice assistant to meet some demands. At present, the voice assistant usually identifies a voice instruction of the user based on a model and outputs related information. In order to improve the experience of the user interacting with the voice assistant and improve the accuracy of the information output by the voice assistant, a large amount of training data, such as a corpus of the user and information corresponding to the corpus, needs to be obtained, and the model is trained offline based on the large amount of training data, and after training, the model is used online.

[0003] However, although the information output in this way is all corresponding to the voice instruction of the user, when the voice instruction of the user does not change but the actual demand changes, the information output by the voice assistant is difficult to meet the demand of the user, thereby affecting the use experience of the user. SUMMARY

[0004] Embodiments of the present application provide an interaction method and an electronic device, which can obtain response information that is more easily matched to the demand of the user for the instruction of the user, and bring a better interaction experience to the user.

[0005] In a first aspect, an interaction method is provided, applied to an electronic device. In the method, the electronic device receives a first instruction input by a user. Then, the electronic device obtains a scene in which the electronic device is located, wherein the scene is determined according to at least one of a position of the electronic device in a real world, a time of the real world, a weather condition of the real world, or a state of the electronic device. The electronic device performs a first response operation corresponding to the first instruction in the scene in which the electronic device is located. The first response operation is determined according to the scene and the first instruction.

[0006] In this implementation manner, the scene in which the electronic device is located and the instruction can reflect the demand of the user to some extent, and the method can perform a corresponding response operation in combination with the scene in which the electronic device is located for the instruction input by the user, so that the response operation can more easily match the demand of the user in the current scene, and a better interaction experience is brought to the user.

[0007] In an implementable manner of the first aspect, the electronic device performing the first response operation corresponding to the first instruction in the scene in which the electronic device is located includes: outputting first response information corresponding to the first instruction in the scene in which the electronic device is located; or performing an operation indicated by the first instruction in the scene in which the electronic device is located.

[0008] In this implementation, the electronic device can interact with the user and respond to the user's instructions, reply to the user with information, or perform corresponding operations.

[0009] In an implementation of the first aspect, after the user performs the first operation on the first response information, if the electronic device receives a second instruction identical to the content of the first instruction in the scenario, the electronic device outputs second response information identical to the first response information, where the first operation indicates that the user approves the first response information.

[0010] In this implementation, if the user approves the first response information, when the electronic device receives the same instruction again in the same scenario, the electronic device can directly output second response information identical to the first response information. It can be seen that the above interaction method has a certain scenario generalization capability. For the same scenario or the same user demand, the electronic device can give information satisfactory or approved by the user without repeated feedback from the user, and the user can have a better experience on the electronic device.

[0011] In an implementation of the first aspect, after the user performs the first operation on the first response information, if the electronic device receives a third instruction identical to the sentence pattern of the first instruction in the scenario, the electronic device outputs third response information identical to the sentence pattern of the first response information or identical to the content type of the first response information; or, after the user performs the first operation on the first response information, if the electronic device receives a third instruction identical to the content type of the first instruction in the scenario, the electronic device outputs third response information identical to the content type of the first response information.

[0012] In this implementation, if the user approves the first response information, the electronic device can also learn the user's historical language preference and spoken habit of issuing the first instruction in the current scenario according to the first response information. In this way, when the electronic device receives a third instruction identical to the sentence pattern of the first instruction or identical to the content type of the first instruction again, the electronic device can also give third response information according to the user's historical language preference and spoken habit. It can be seen that the above interaction method has a certain scenario generalization capability. For the same scenario and the user's language preference and spoken habit, the electronic device can give information satisfactory or approved by the user without repeated feedback from the user, and the user can have a better experience on the electronic device.

[0013] In an implementation form of the first aspect, after the user performs a second operation on the first response information, the electronic device obtains first indication information input by the user, wherein the second operation indicates that the user does not approve the first response information, and the first indication information is used to indicate content expected by the user. Then, the electronic device obtains fourth response information corresponding to the first instruction in the scene according to the first indication information, wherein the fourth response information is different from the content of the first response information. The electronic device outputs the fourth response information.

[0014] This implementation form can be regarded as a process in which the electronic device optimizes response information in real time according to feedback information of the user. If the user still does not approve the fourth response information, the electronic device can continue to provide new response information for the user until the user approves, thereby optimizing the relationship among the scene, the instruction and the response information, i.e., optimizing the interaction process between the electronic device and the user, so that the response information given by the electronic device can be more in line with the needs of the user, and the user's interaction experience is improved.

[0015] In an implementation form of the first aspect, the electronic device performs the operation indicated by the first instruction in the scene in which the electronic device is located, including: obtaining a first application corresponding to the first instruction in the scene of the electronic device, wherein the first application is determined according to the scene and the first instruction. Finally, the electronic device starts the first application to perform the operation indicated by the first instruction in the scene.

[0016] In this implementation form, the electronic device can start a corresponding application according to the first instruction input by the user in combination with different scenes, so that the starting of the application can meet the needs of the user in different scenes to some extent, reduce the situation that the user is not satisfied with the started application, and bring a better interaction experience to the user.

[0017] In an implementation form of the first aspect, after the user performs a third operation on the first application, if the electronic device receives a fourth instruction with the same content as the first instruction in the current scene, the electronic device starts the first application to perform the operation indicated by the fourth instruction in the current scene, wherein the third operation indicates that the user approves to use the first application to respond to the first instruction.

[0018] In this implementation form, if the user approves to start the above first application, when the electronic device receives the same instruction in the same scene again, the electronic device can directly start the first application. It can be seen that the above interaction method has a certain scene generalization ability. For the same scene or the same user needs, the electronic device can start the application that is satisfactory or approved by the user without repeated feedback of the user, and the user can obtain a better experience on the electronic device.

[0019] In an implementation form of the first aspect, after the user performs a fourth operation on the first application, the electronic device obtains second indication information input by the user, wherein the fourth operation indicates that the user does not approve using the first application to respond to the first instruction, and the second indication information is used to indicate an application expected to be started by the user. Then, the electronic device starts a second application according to the second indication information to perform an operation indicated by the first instruction in a current scenario of the electronic device, wherein the second application is of the same type as the first application and / or implements the same function.

[0020] This implementation form can be regarded as a process in which the electronic device optimizes the functions that can be implemented in real time according to the feedback information of the user. If the user still does not approve the second application, the electronic device can continue to provide a new application for the user until the user approves, thereby optimizing the relationship among the scenario, the instruction and the application, i.e., optimizing the interaction process between the electronic device and the user, so that the application started by the electronic device can be more in line with the needs of the user, and the user's interaction experience is improved.

[0021] In an implementation form of the first aspect, the first response operation is further determined according to historical preference information of the user.

[0022] The historical preference information can be determined according to historical instructions input by the user in the current scenario and response operations corresponding to the historical instructions. The historical preference information of the user can be analyzed according to the historical instructions and the corresponding response operations.

[0023] In an implementation form of the first aspect, the first instruction is a voice instruction or a text instruction; and the first response information is one or more of voice information, text information and image information.

[0024] In an implementation form of the first aspect, the first instruction is any one of the following instructions: a question type instruction, a creative generation type instruction, an indication type instruction or a task type instruction.

[0025] In an implementation form of the first aspect, in a case where the first instruction is a first location and the scenario of the electronic device is that the user is in a resting state, the output first response information is food introduction information or scenic spot introduction information of the first location; and in a case where the first instruction is the first location and the scenario of the electronic device is that the user is on a trip, the output first response information is navigation route information from a location of the user to the first location.

[0026] In this implementation form, the electronic device can give different response information for the same instruction in different scenarios, thereby providing information that is more in line with the needs of the user in the current scenario.

[0027] In an implementation form of the first aspect, the third instruction is a query instruction about the second location, and the third response information is food introduction information or attraction introduction information of the second location if the electronic device receives the third instruction when the user is in the resting state after the user performs the first operation on the first response information; and the third response information is navigation route information from a current location of the user to the second location if the electronic device receives the third instruction when the user is in the traveling state after the user performs the first operation on the first response information.

[0028] In this implementation form, the electronic device can output response information of the same content type after receiving instructions about different locations in the same scenario.

[0029] In an implementation form of the first aspect, the first instruction is a query instruction about related content of the first location, and the first response information is food introduction information or attraction introduction information of the first location if the electronic device is in the scenario where the user is in the resting state.

[0030] In this implementation form, for a specific scenario, if the electronic device receives a query instruction about related content of the first location, such as "how is location A?", the electronic device can provide food introduction information or attraction introduction information of location A, thereby providing information that is more in line with the user's needs in the current scenario.

[0031] In an implementation form of the first aspect, the third instruction is a query instruction about related content of the second location, and the third response information is food introduction information or attraction introduction information of the second location if the electronic device receives the third instruction when the user is in the resting state after the user performs the first operation on the first response information.

[0032] In this implementation form, the third instruction is an instruction with the same sentence pattern as the first instruction, and the electronic device can output response information about recommended locations with the same sentence pattern or the same content type if the electronic device receives query instructions about related content of locations with the same sentence pattern in the same scenario. For example, the first instruction is "how is location A?", the first response information is "food introduction information of location A", the third instruction is "how is location B?", the third instruction has the same sentence pattern as the first instruction, and the third response information is "food introduction information of location B", and the third response information has the same content type or the same sentence pattern as the first response information.

[0033] In a second aspect, an electronic device is provided, comprising a memory, one or more processors; the memory is coupled to the processors; wherein the memory stores computer program codes, the computer program codes comprising computer instructions which, when executed by the processors, cause the electronic device to perform the interaction method according to the first aspect and any one of the implementation manners thereof.

[0034] In a third aspect, a computer-readable storage medium is provided, comprising computer instructions which, when executed on an electronic device, cause the electronic device to perform the interaction method according to the first aspect and any one of the implementation manners thereof.

[0035] In a fourth aspect, a computer program product is provided, which, when executed on a computer, causes the computer to perform the interaction method according to the first aspect and any one of the implementation manners thereof.

[0036] The electronic device provided by the second aspect, the computer-readable storage medium of the third aspect, and the computer program product of the fourth aspect can achieve the beneficial effects as described with reference to the first aspect and any one of the implementation manners thereof, which will not be described herein again. BRIEF DESCRIPTION OF DRAWINGS

[0037] Figure 1 A structure diagram of an electronic device provided by an embodiment of the present application is shown Figure 1 ;

[0038] Figure 2 A structure diagram of an electronic device provided by an embodiment of the present application is shown Figure 2 ;

[0039] Figure 3 A structure diagram of an electronic device provided by an embodiment of the present application is shown Figure 3 ;

[0040] Figure 4 A structure diagram of an electronic device provided by an embodiment of the present application is shown Figure 4 ;

[0041] Figure 5 A structure diagram of an electronic device provided by an embodiment of the present application is shown Figure 1 ;

[0042] Figure 6 A structure diagram of an electronic device provided by an embodiment of the present application is shown

[0043] Figure 7 A structure diagram of an electronic device provided by an embodiment of the present application is shown Figure 1 ;

[0044] Figure 8 A structure diagram of an electronic device provided by an embodiment of the present application is shownFigure 2 ;

[0045] Figure 9 A schematic diagram of the first prompt information provided in an embodiment of this application is shown;

[0046] Figure 10 This illustration shows the interactive process provided in an embodiment of this application. Figure 3 ;

[0047] Figure 11 This illustration shows an interaction method provided in an embodiment of this application. Figure 2 ;

[0048] Figure 12 This illustration shows the interactive process provided in an embodiment of this application. Figure 4 ;

[0049] Figure 13 This illustration shows the interactive process provided in an embodiment of this application. Figure 5 ;

[0050] Figure 14 This illustration shows the interactive process provided in an embodiment of this application. Figure 6 ;

[0051] Figure 15 A schematic diagram of the structure of the electronic device provided in the embodiments of this application is shown. Figure 5 . Detailed Implementation

[0052] The technical solutions in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application. In the description of the present application, unless otherwise specified, " / " represents an "or" relationship between the objects before and after it, for example, A / B can represent A or B; "and / or" in the present application is only a description of the relationship between the associated objects, which means that there can be three relationships, for example, A and / or B, which can represent: A alone, A and B together, and B alone, where A and B can be singular or plural. In the description of the present application, unless otherwise specified, "multiple" means two or more than two. "At least one of the following" or similar expressions means any combination of the items, including any combination of single or multiple items. For example, at least one of a, b, or c can mean a, b, c, a-b, a-c, b-c, or a-b-c, where a, b, and c can be single or multiple. In addition, in order to clearly describe the technical solutions of the embodiments of the present application, in the embodiments of the present application, "first", "second", etc. are used to distinguish the same items or similar items with basically the same function and role. Those skilled in the art can understand that "first", "second", etc. do not limit the quantity and execution order, and "first", "second", etc. also do not necessarily mean different. At the same time, in the embodiments of the present application, "exemplary" or "for example" means to serve as an example, illustration or explanation. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as more preferred or more advantageous than other embodiments or design schemes. Rather, the use of "exemplary" or "for example" is intended to present the relevant concept in a specific manner, for understanding.

[0053] In addition, the business scenarios described in the embodiments of the present application are used to more clearly illustrate the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided by the embodiments of the present application. Those skilled in the art can know that as new business scenarios appear, the technical solutions provided by the embodiments of the present application are also applicable to similar technical problems.

[0054] Currently, in the dialog interaction experience between the user and the voice assistant, the type of the dialog can usually include question and answer type, creative generation type, task type, etc. Among them, the question and answer type dialog is, for example, the user asks "Xiao Yi, how is place A?", and the voice assistant replies the relevant introduction of place A; the creative generation type dialog is, for example, the user says to the voice assistant "Xiao Yi, help me write an introduction of place A", and the voice assistant replies the introduction of place A; the task type dialog is, for example, the user says to the voice assistant "Xiao Yi, open application A", and the voice assistant will start the application A on the mobile phone.

[0055] In many cases, the content obtained by the user through the voice assistant in the above dialogue interaction process is short or ambiguous, and sometimes the content is not accurate and cannot meet the real needs of the user.

[0056] For example, the user says "place A" to the voice assistant, and the real needs of the user can be to know the route to place A, but the voice assistant can reply to the introduction of place A.

[0057] In the dialogue interaction process between the user and the voice assistant, in order to make the content replied by the voice assistant more accurate, some current solutions can obtain the interaction data of the user and the voice assistant, and use the interaction data to perform offline analysis and offline labeling, associate the instruction issued by the user with the content expected (or satisfied) by the voice assistant in reply to the user, and then use the associated dialogue content to perform offline training on the large language model (LLM) used by the voice assistant. After training, the large language model can learn which question to ask the user and which reply to give, which also optimizes the voice assistant.

[0058] However, the needs of the user can change, for example, the user at home says "place A" to the voice assistant, which can be to ask the voice assistant to reply to the relevant introduction of place A; and the user in the process of walking says "place A" to the voice assistant, which can be to ask the voice assistant to reply to the route to place A. The above optimized voice assistant will give the same reply to "place A" said by the user in different situations, and will not consider that the user can need different replies in different situations. It can be seen that even if the voice assistant can be optimized by the above method, it cannot better meet the needs of the user, thereby affecting the interactive experience of the user.

[0059] In addition, the training model has a long cycle and low efficiency, and the voice assistant cannot timely make the user perceive the reply after optimization.

[0060] Based on the above, the embodiment of the present application provides an interaction method, which can be applied to an electronic device. When the method is executed, the electronic device can give a corresponding reply according to the current scene and the instruction input by the user. The scene in which the electronic device is located and the instruction can reflect the demand of the user to some extent, for example, the scene in which the electronic device is located indicates that the electronic device is stationary, and the user inputs "place A" to the electronic device, so that the electronic device can determine that the demand of the user is to obtain introduction information of place A; for another example, the scene in which the electronic device is located indicates that the electronic device is moving, and the user inputs "place A" to the electronic device, so that the electronic device can determine that the demand of the user is to obtain a route to place A. It can be seen that the above method can give a corresponding reply according to the instruction input by the user in combination with the scene in which the electronic device is located, so that the reply content can more easily match the demand of the user in the current scene, thereby bringing a better interaction experience for the user.

[0061] For example, when the above method is applied to an electronic device, the electronic device can receive a first instruction input by a user and obtain a scene in which the electronic device is located. Then, the electronic device executes a first response operation corresponding to the first instruction in the current scene. The scene in which the electronic device is located can be determined according to at least one of a position of the electronic device in a real world, a time of the real world, a weather condition of the real world or a state of the electronic device, and the first response operation is determined according to the scene in which the electronic device is located and the first instruction.

[0062] In some embodiments, a voice assistant can be included in the electronic device, and the voice assistant can give corresponding information or execute corresponding operations in response to the instruction of the user based on the LLM model.

[0063] For example, as shown in Figure 1 As shown, the voice assistant can input the instruction of the user, the position of the electronic device in the real world, the time of the real world, the weather condition of the real world or the state of the electronic device and the like into the LLM model as multi-dimensional (or multi-modal) information, the LLM model determines the scene in which the electronic device is located according to the position of the electronic device in the real world, the time of the real world, the weather condition of the real world or the state of the electronic device and the like, and outputs a response operation corresponding to the instruction of the user in the scene, and the electronic device executes the response operation. The execution of the response operation by the electronic device can include outputting response information corresponding to the instruction in the current scene, executing an operation indicated by the instruction in the current scene and the like, thereby realizing the scene-based information output or operation execution.

[0064] For example, the LLM model can output the response information, and then the voice assistant can play the response information to the user. The voice assistant can also collect feedback information of the user on the response information, such as approval of the response information, disapproval of the response information, and the like.

[0065] The voice assistant can also input the feedback information of the user as one of the multi-dimensional information into the LLM model. The LLM model can optimize the response information according to the feedback information of the user. For example, if the user does not approve the response information, the LLM model can output other response information in the current scene until the user approves the response information. In this way, the LLM model can have a scenario-based and accurate reply capability.

[0066] It can be understood that the voice assistant can prompt the user to give feedback information, which can prompt the user that the voice assistant has real-time self-optimization capability and will continuously provide the user with experience meeting different scenarios based on the feedback of the user.

[0067] In addition, the voice assistant can also adapt to the implicit preference or historical preference of the user, such as the way the user speaks, the speaking habit, the spoken habit, and the like. When receiving the historical input instruction of the user, the voice assistant can analyze the historical preference information of the user. Then, when the user inputs the instruction again in the same scene, the voice assistant can analyze what response information the user wants according to the historical preference information of the user. In this way, the user does not need to adapt to the standard dialogue mode of the voice assistant, which makes the interaction of the user more convenient, and can also enhance the user stickiness and make the user full of expectation for the assistant.

[0068] Alternatively, in some examples, the LLM model can also directly obtain the predetermined implicit preference or historical preference of the user (i.e., the implicit preference or historical preference of the user can be input as one dimension of information into the LLM model), and output the response information meeting the needs of the user in the current scene by combining the information of the instruction of the user, the position of the electronic device in the real world, the time of the real world, the weather condition of the real world, or the state of the electronic device.

[0069] For example, the LLM model can output the response information, and then the voice assistant can play the response information to the user. The voice assistant can also collect feedback information of the user on the response information, such as approval of the response information, disapproval of the response information, and the like.

[0070] In some embodiments, referring to Figure 2As shown in (a), the aforementioned voice assistant can also respond to user commands and provide corresponding information or perform corresponding functions based on the real-time closed-loop module. The real-time closed-loop module can be equivalent to an LLM model. For example, the user can provide feedback on the response information provided by the voice assistant. If the user disagrees, the voice assistant can input the user's feedback, the user's command, the location of the electronic device in the real world, the real-world time, the real-world weather conditions, or the status of the electronic device as multi-dimensional (or multi-modal) information into the real-time closed-loop module. The real-time closed-loop module can determine the current scene of the electronic device and provide response information that matches the scene. The voice assistant outputs this response information to the user. If the user agrees, the real-time closed-loop module completes the optimization of the response information.

[0071] See some examples. Figure 2 As shown in (b), the real-time closed-loop module can construct multiple preset scenarios and determine the current scenario of the electronic device based on the multi-dimensional input information. The real-time closed-loop module can also construct new scenarios based on newly added information, thereby obtaining more scenarios, and provides corresponding response information for different scenarios, giving users a contextualized interactive experience.

[0072] Furthermore, the real-time closed-loop module can learn the user's implicit or historical preferences, such as the user's speaking style, habits, and speech patterns, and analyze the user's historical preference information based on the multi-dimensional input information. Combining the current scenario of the electronic device and the user's historical preference information, the real-time closed-loop module outputs response information that meets the user's needs in the current scenario. The real-time closed-loop module can also learn or update newly added user preferences. Alternatively, in some examples, the real-time closed-loop module can directly obtain pre-determined implicit or historical preferences of the user, and combine this information with multi-dimensional information such as the user's instructions, the electronic device's location in the real world, the real-world time, real-world weather conditions, or the electronic device's status to output response information that meets the user's needs in the current scenario.

[0073] The aforementioned electronic devices can optimize their responses in real time based on user feedback, making users feel that the voice assistant becomes smarter with use, thus providing a better interactive experience. Similarly, users can provide feedback on the operations indicated by the commands executed by the electronic devices in the current scenario. The electronic devices can also optimize their operations or the way they are executed based on user feedback, again making users feel that the voice assistant becomes smarter with use, thus providing a better interactive experience.

[0074] Furthermore, the optimization effects of response information and operation are not limited to the current interaction between the user and the voice assistant. In some cases, a user can experience a better interaction effect over a long period of time after providing feedback only once.

[0075] The aforementioned electronic devices can be mobile phones, in-vehicle terminals, tablet computers, personal computers, laptops, or other terminal devices that can interact with users.

[0076] Taking a mobile phone as an example, in some embodiments, the structure of the electronic device can be found in [reference needed]. Figure 3 As shown. The electronic device 100 may include a processor 110, an external memory interface 120, an internal memory 121, a universal serial bus (USB) interface 130, a charging management module 140, a power management module 141, a battery 142, antenna 1, antenna 2, a mobile communication module 150, a wireless communication module 160, an audio module 170, a sensor module 180, buttons 190, a motor 191, an indicator 192, a camera 193, a display screen 194, and a user identification module (SIM) card interface 195, etc.

[0077] It is understood that the structures illustrated in the embodiments of this application do not constitute a specific limitation on the electronic device 100. In other embodiments of this application, the electronic device 100 may include more or fewer components than illustrated, or combine some components, or split some components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0078] Processor 110 may include one or more processing units ( Figure 3 (Not shown in the image), for example, processor 110 may include an application processor (AP), a modem processor, an image signal processor (ISP), a controller, memory, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural network processing unit (NPU), etc. Different processing units may be independent devices or integrated into one or more processors.

[0079] The controller can be the nerve center and command center of the electronic device 100. The controller can generate operation control signals according to the instruction opcode and timing signals to complete the control of fetching and executing instructions.

[0080] The processor 110 may also include a memory for storing instructions and data.

[0081] In some examples, processor 110 may include one or more interfaces ( Figure 3 (Not shown in the image). Interfaces may include inter-integrated circuit (I2C) interfaces, inter-integrated circuit sound (I2S) interfaces, pulse code modulation (PCM) interfaces, universal asynchronous receiver / transmitter (UART) interfaces, mobile industry processor interfaces (MIPI), general-purpose input / output (GPIO) interfaces, subscribing identity modules (SIM) interfaces, and / or universal serial bus (USB) interfaces, etc.

[0082] The charging management module 140 receives charging input from a charger, which can be a wireless charger or a wired charger. While charging the battery 142, the charging management module 140 can also supply power to the electronic device via the power management module 141.

[0083] The power management module 141 connects the battery 142, the charging management module 140, and the processor 110. The power management module 141 receives input from the battery 142 and / or the charging management module 140, providing power to the processor 110, internal memory 121, external memory, display screen 194, camera 193, and wireless communication module 160, etc. The power management module 141 can also be used to monitor parameters such as battery capacity, battery cycle count, and battery health status (leakage current, impedance).

[0084] The wireless communication function of electronic device 100 can be realized through antenna 1, antenna 2, mobile communication module 150, wireless communication module 160, modem processor and baseband processor, etc.

[0085] The antenna 1 and the antenna 2 are used to transmit and receive electromagnetic wave signals.

[0086] The mobile communication module 150 can provide a solution for wireless communication including 2G / 3G / 4G / 5G, etc. applied to the electronic device 100. The mobile communication module 150 can receive electromagnetic waves by the antenna 1, and perform filtering, amplification, etc. on the received electromagnetic waves, and transfer the processed signals to the modem processor for demodulation. The mobile communication module 150 can also amplify the signals modulated by the modem processor, and radiate the signals as electromagnetic waves through the antenna 1.

[0087] The modem processor can include a modulator and a demodulator. The modulator is used to modulate a low-frequency baseband signal to be transmitted into a medium-high frequency signal. The demodulator is used to demodulate a received electromagnetic wave signal into a low-frequency baseband signal. The demodulator then transmits the demodulated low-frequency baseband signal to the baseband processor for processing. The low-frequency baseband signal processed by the baseband processor is transmitted to the application processor. The application processor outputs a sound signal through an audio device, or displays an image or a video through the display screen 194.

[0088] The wireless communication module 160 can provide a solution for wireless communication including wireless local area networks (WLAN) (such as wireless fidelity (Wi-Fi) networks), Bluetooth (BT), global navigation satellite system (GNSS), frequency modulation (FM), near field communication (NFC), infrared (IR) technology, etc. applied to the electronic device 100. The wireless communication module 160 receives electromagnetic waves via the antenna 2, performs frequency modulation and filtering processing on the electromagnetic wave signals, and transmits the processed signals to the processor 110. The wireless communication module 160 can also receive signals to be transmitted from the processor 110, perform frequency modulation and amplification on the signals, and radiate the signals as electromagnetic waves through the antenna 2.

[0089] In some examples, the antenna 1 and the mobile communication module 150 of the electronic device 100 are coupled, and the antenna 2 and the wireless communication module 160 are coupled, so that the electronic device 100 can communicate with a network and other devices through wireless communication technology.

[0090] The electronic device 100 implements display functions through a GPU, a display screen 194, and an application processor, etc. The GPU is a microprocessor for image processing, and is connected to the display screen 194 and the application processor. The GPU is used to perform mathematical and geometric calculations for graphics rendering.

[0091] The display screen 194 is used to display images, videos, etc. The display screen 194 includes a display panel. In some examples, the electronic device 100 can include 1 or N display screens 194, N being a positive integer greater than 1.

[0092] For example, the electronic device 100 outputs response information in response to a user's instruction, which can be displayed to the user through the display screen 194. Alternatively, the electronic device 100 displays a process of performing an operation in response to a user's instruction to the user through the display screen 194.

[0093] For example, the display screen 194 can also display a function page, so that the user can input a text instruction or text content on the function page to control the electronic device 100 to implement a corresponding function.

[0094] The electronic device 100 can implement a shooting function through an ISP, a camera 193, a video codec, a GPU, a display screen 194, and an application processor, etc. The ISP is used to process data fed back by the camera 193. The camera 193 is used to capture still images or videos. In some examples, the electronic device 100 can include 1 or N cameras 193, N being a positive integer greater than 1.

[0095] The digital signal processor is used to process digital signals, which can process not only digital image signals but also other digital signals. The video codec is used to compress or decompress digital videos. The electronic device 100 can support one or more video codecs.

[0096] The NPU is a neural network (NN) computing processor, which is used to quickly process input information by referring to the structure of a biological neural network, such as the transmission mode between human brain neurons, and can also continuously self-learn.

[0097] The external memory interface 120 can be used to connect an external memory card, such as a Micro SD card, to expand the storage capacity of the electronic device 100. The external memory card communicates with the processor 110 through the external memory interface 120 to implement a data storage function.

[0098] The internal memory 121 can be used to store computer executable program codes, which include instructions. The processor 110 executes various function applications and data processing of the electronic device 100 by running the instructions stored in the internal memory 121.

[0099] Exemplarily, after the electronic device 100 receives the first instruction, the processor 110 can acquire the current scene in which the electronic device 100 is located by running the instruction stored in the internal memory 121, and then the electronic device 100 acquires the first operation corresponding to the first instruction in the current scene and executes the first response operation. Wherein, the electronic device 100 executing the first response operation can include outputting the first response information corresponding to the first instruction in the current scene; or the electronic device 100 executing the operation indicated by the first instruction in the current scene.

[0100] Wherein, the scene in which the electronic device 100 is located can be determined by the processor 110 running the instruction stored in the internal memory 121 according to at least one of the position of the electronic device 100 in the real world, the time of the real world, the weather condition of the real world or the state of the electronic device, and the first response information and the operation indicated by the instruction can be determined by the processor 110 running the instruction stored in the internal memory 121 according to the scene in which the electronic device 100 is located and the first instruction.

[0101] The electronic device 100 can realize audio function through the audio module 170 and the application processor, etc. For example, music playing, recording, etc.

[0102] The audio module 170 is used to convert digital audio information into analog audio signal output, and is also used to convert analog audio input into digital audio signal. The audio module 170 can also be used to encode and decode audio signals.

[0103] Exemplarily, the electronic device 100 outputs the response information in response to the user's instruction, which can be played to the user through the audio module 170.

[0104] The key 190 includes the power-on key, the volume key, etc. The key 190 can be a mechanical key. It can also be a touch key.

[0105] The motor 191 can generate vibration prompt. The motor 191 can be used for incoming call vibration prompt, and can also be used for touch vibration feedback.

[0106] The indicator 192 can be an indicator light, which can be used to indicate the charging state, the power change, and can also be used to indicate the message, the missed call, the notification, etc.

[0107] The SIM card interface 195 is used to connect the SIM card.

[0108] The scene in which the electronic device is located and the instruction can reflect the user's demand to some extent, based on the above Figure 3When the electronic device shown in the figure implements the interaction method in the embodiments of the present application, the electronic device can execute a corresponding response operation in combination with the scene in which the electronic device is located, for the instruction input by the user, so that the response operation can more easily match the needs of the user in the current scene, and bring a better interaction experience for the user.

[0109] In some embodiments, the software system of the electronic device 100 described above can adopt a layered architecture, an event-driven architecture, a microkernel architecture, a microservice architecture, or a cloud architecture. The embodiments of the present application take a mobile operating system with a layered architecture as an example to exemplarily illustrate the software structure of the electronic device 100. The layered architecture divides the software into several layers, each layer has a clear role and division of labor. The layers communicate with each other through software interfaces. For example, see Figure 4 As shown, the layered architecture of the electronic device 100 described above divides the mobile operating system into four layers, from top to bottom, the application program layer, the application program framework layer, the system service layer, and the kernel layer.

[0110] The application program layer can include a series of application program packages.

[0111] As Figure 4 shown, the application program package can include camera, gallery, calendar, call, map, navigation, WLAN, Bluetooth, music, video, short message, and the like.

[0112] The application program framework layer provides the application program layer with application programming interfaces (application programming interface, API) and programming frameworks. The application program framework layer includes some pre-defined functions.

[0113] As Figure 4 shown, the application program framework layer can include a window manager, a content provider, a view system, a phone manager, a resource manager, a notification manager, and the like.

[0114] The window manager is used to manage windows programs. The content provider is used to store and retrieve data and make the data accessible to the application programs. The view system includes visual controls, such as a control for displaying text, a control for displaying pictures, etc. The telephony manager is used to provide the communication function of the electronic device 100. For example, the management of the call state (including the connection, hang-up, etc.). The resource manager provides various resources for the application programs, such as localized strings, icons, pictures, layout files, video files, etc. The notification manager enables the application programs to display notification information in the status bar, which can be used to convey the type of message, which can automatically disappear after a short stay, without user interaction. The notification manager can also be a notification in the form of a chart or a scroll bar text appearing in the system top status bar, such as the notification of the application program running in the background, and can also be a notification in the form of a dialogue window appearing on the screen. For example, prompting text information in the status bar, issuing a prompt sound, the electronic device vibrating, the indicator light flashing, etc.

[0115] The system service layer can include a plurality of functional modules. For example: a surface manager, media libraries, a three-dimensional graphics processing library (for example: OpenGL ES), a two-dimensional graphics engine (for example: SGL, Vulkan), etc.

[0116] The surface manager is used to manage the display subsystem and provides a fusion of 2D and 3D layers for a plurality of application programs.

[0117] The media library supports a plurality of commonly used audio, video format playback and recording, and static image files, etc.

[0118] The three-dimensional graphics processing library is used to realize three-dimensional graphics drawing, image rendering, synthesis, and layer processing, etc.

[0119] The 2D graphics engine is a drawing engine for 2D drawing.

[0120] The kernel layer is the layer between the hardware and the software. The kernel layer at least includes a display driver, a camera driver, an audio driver, and a sensor driver.

[0121] Based on the above Figure 4 When the electronic device implements the interaction method in the embodiments of the present application, similarly, the electronic device can execute the corresponding response operation in combination with the scene in which the electronic device is located, in response to the instruction input by the user, so that the response operation can more easily match the needs of the user in the current scene, thereby bringing a better interaction experience to the user.

[0122] The above-mentioned interaction method is further described below by taking the case of applying the interaction method to a mobile phone. The interaction method can correspond to various interaction purposes, such as a user participating in interaction to obtain information or a user participating in interaction to experience a certain function. The following content of the embodiments of the present application describes the above-mentioned interaction method by using different embodiments for different interaction purposes.

[0123] Embodiment one

[0124] Referring to FIG. 1, the above-mentioned interaction method can include the following steps S501-S504. Figure 5

[0125] S501, the mobile phone receives an instruction A input by a user.

[0126] The above-mentioned instruction A can be a voice instruction or a text instruction. For example, the user can speak voice content to the mobile phone or input text content on the mobile phone.

[0127] In addition, the above-mentioned instruction A also has a type of instruction. For example, the type of instruction can be used to indicate that the instruction A is a question-type instruction, a creative generation-type instruction, or an indication-type instruction.

[0128] For example, the question-type instruction can be “How is XX?”, “What is XX?”, “How to go to XX?”, and the like. The question-type instruction is used to ask the mobile phone a question in order to obtain information given by the mobile phone as a reply.

[0129] For example, the creative generation-type instruction can be “Help me make a resume”, “Help me write an introduction about XX”, and the like. The creative generation-type instruction is used to ask the mobile phone a request in order to obtain information generated by the mobile phone.

[0130] For example, the indication-type instruction can be a place name, a book title, a person name, and the like. The indication-type instruction can not explicitly ask the mobile phone a question or a request, but it is also expected to obtain information replied by the mobile phone.

[0131] In the embodiments of the present application, the type of instruction A can be various, that is, the user can control the mobile phone by using various types of instructions, and the user can operate the mobile phone in various ways, thereby improving the user experience.

[0132] S502, the mobile phone obtains a scene in which the mobile phone is located.

[0133] The scene in which the mobile phone is located can be determined according to first information obtained by the mobile phone. The first information can include at least one of the following different types of information: a position of the mobile phone in the real world, a time in the real world, a weather condition in the real world, or a state of the mobile phone.

[0134] ​In some examples, the mobile phone can first acquire the first information after receiving the instruction A input by the user, and then determine the current scenario according to the first information.

[0135] According to different information types and / or information contents included in the first information, the mobile phone can determine different scenarios.

[0136] For example, as shown in (a) of FIG. 1, the first information includes that the state of the mobile phone is static, the location of the mobile phone in the real world is in the user's home, and the time in the real world is the weekend. Then the mobile phone can determine that the current scenario is the first scenario. As shown in (b) of FIG. 1, the first information includes that the state of the mobile phone is static, the location of the mobile phone in the real world is in the user's car, and the time in the real world is the weekend. Then the mobile phone can determine that the current scenario is the second scenario. As shown in (c) of FIG. 1, the first information includes that the state of the mobile phone is dynamic, the location of the mobile phone in the real world is in the XX highway, and the time in the real world is the weekend. Then the mobile phone can determine that the current scenario is the third scenario. As shown in (d) of FIG. 1, the first information includes that the weather in the real world is moderate rain, and the state of the mobile phone is dynamic. Then the mobile phone can determine that the current scenario is the fourth scenario. As shown in (e) of FIG. 1, the first information includes that the state of the mobile phone is dynamic. Then the mobile phone can determine that the current scenario is the fifth scenario. Figure 6 Figure 6 Figure 6 Figure 6 Figure 6

[0137] In some examples, the location of the mobile phone in the real world can be determined according to the positioning information of the mobile phone, or the mobile phone can first capture an environment image of the environment in which the mobile phone is located through the camera, and then identify the environment image to determine the location of the mobile phone in the real world.

[0138] In some examples, the time in the real world can be determined according to the standard time in a certain time zone displayed on the mobile phone, or the mobile phone can acquire the time in a certain time zone from the server as the time in the real world.

[0139] In some examples, the weather in the real world can be determined according to the weather in a certain region displayed on the mobile phone, or the mobile phone can acquire the weather in a certain region from the server as the weather in the real world.

[0140] In some examples, the state of the mobile phone can be determined according to the change of the location of the mobile phone in the real world within a period of time, or the state of the mobile phone can be detected by the sensor set by the mobile phone, wherein the state of the mobile phone can include static state, dynamic state, etc.

[0141] ​​​​​The scenario in which the mobile phone is located can reflect the state of the user or the demand of the user. For example, the mobile phone is in the first scenario, and the user can be on vacation at home; the mobile phone is in the second scenario, and the user can be about to go on a trip; the mobile phone is in the third scenario, and the user can be on the way to a trip; and the mobile phone is in the fourth scenario, and the user can be walking in the rain.

[0142] S503, the mobile phone acquires first response information corresponding to the instruction A in the scenario in which the mobile phone is located.

[0143] The first response information is determined according to the scenario in which the mobile phone is located and the instruction A.

[0144] Since the scenario in which the mobile phone is located can reflect the state of the user or the demand of the user, the first response information can also be determined according to the state (or demand) of the user and the instruction A.

[0145] For example, the mobile phone is in the first scenario, and in this scenario, the user can be resting at home. If the instruction A input by the user to the mobile phone is "location A", the mobile phone can determine that the demand of the user is to understand what is delicious at location A, and thus to prepare for a trip to location A, since the user is in a resting state. After determining the demand of the user, the mobile phone can acquire food introduction information of location A as the first response information, as shown in (a) of FIG. 1. Figure 7

[0146] For example, the mobile phone is in the second scenario, and in this scenario, the user can be about to go on a trip. If the instruction A input by the user to the mobile phone is "location A", the mobile phone can determine that the demand of the user is to understand the navigation route to location A, since the user is in a state of about to go on a trip. After determining the demand of the user, the mobile phone can acquire navigation route information from the location of the user to location A as the first response information, as shown in (b) of FIG. 1. Figure 7

[0147] For example, the mobile phone is in the third scenario, and in this scenario, the user can be on the way to a trip. If the instruction A input by the user to the mobile phone is "location A", the mobile phone can determine that the demand of the user is to understand how far location A is, since the user is on the way to a trip. After determining the demand of the user, the mobile phone can acquire distance information from the location of the user to location A as the first response information, as shown in (c) of FIG. 1. Figure 7

[0148] It can be understood that the first response information can be determined not only according to the instruction A input by the user, but also according to the scenario in which the mobile phone is located. Since the scenario in which the mobile phone is located can reflect the demand of the user to a certain extent, the first response information determined can also meet the demand of the user to a certain extent. ​​​

[0149] S504, the mobile phone outputs the first response information.

[0150] The first response information can be one or more of voice information, text information, and image information. For example, the food introduction information of the location A can also be played in the form of voice to the user, or displayed to the user in the form of text or image. In this way, the user has multiple ways to output the instruction A, and the mobile phone has multiple ways to output the first response information, thereby providing the user with a more abundant interactive experience.

[0151] In the above scheme S501-S504, the mobile phone can give corresponding first response information according to the instruction A input by the user in combination with different scenes, so that the first response information can meet the needs of the user in different scenes to some extent, reduce the situation that the user is not satisfied with the first response information, and bring a better interactive experience to the user.

[0152] In some examples, if the user approves the above first response information, the user can perform operation A on the first response information, so that the mobile phone can associate the first response information with the instruction A input by the user in the current scene of the mobile phone. In order to subsequently receive the same instruction again in the same scene, the mobile phone can directly output the second response information which is the same as the first response information. In this way, the above interactive method has a certain scene generalization ability, and for the same scene or the same user demand, the mobile phone can give information that the user is satisfied with or approves of without repeated feedback of the user, and the user can obtain a better experience on the mobile phone.

[0153] The same instruction can mean that the mobile phone receives the same instruction multiple times. For example, referring to (a) shown in Figure 8 , the mobile phone is in a first scene, the instruction A input by the user to the mobile phone is "location A", and the first response information output by the mobile phone is "food introduction information of location A". If the user inputs the instruction B "location A" again when the mobile phone is in the first scene, the second response information output by the mobile phone is still "food introduction information of location A".

[0154] In some examples, if the user approves the above first response information, the mobile phone can also learn the historical preference information of the user in the current scene for issuing the instruction A according to the first response information, such as language preference, spoken habit, etc. In this way, when the mobile phone subsequently receives the instruction C which is the same in sentence and / or the same in content type as the instruction A, the mobile phone can also give the third response information according to the historical preference information of the user. In this way, the above interactive method has a certain scene generalization ability, and for the same scene and the historical preference information of the user, the mobile phone can give information that the user is satisfied with or approves of without repeated feedback of the user, and the user can obtain a better experience on the mobile phone.

[0155] For example, see Figure 8 As shown in (b), the user inputs instruction A to the phone as "Location A", and the phone outputs the first response information as "Food information for Location A". The phone determines that the user's spoken language habit when issuing instruction A in the current scenario is: when inputting "location" to the phone, they want to know about the food in a certain place. In the same scenario, the user inputs instruction C to the phone as "Location B". Instruction C and instruction A have the same content type, both indicating a location. Therefore, based on the user's spoken language habit, the phone determines that the user may currently want to know more about the food in Location B. Thus, the phone obtains the food information for Location B and outputs it to the user as the third response information. The third response information has the same content type as the first response information, both indicating food information for a location.

[0156] For example, see Figure 8 As shown in (c), the user inputs instruction A to the phone as "How is location A?", and the phone outputs the first response information as "Introduction to attractions at location A". The phone determines that the user's spoken language habit when issuing instruction A in the current scenario is: when inputting "How is location A?", the user wants to know about the fun attractions in a certain place. In the same scenario, the user inputs instruction C as "How is location B?". Instruction C has the same sentence structure as instruction A, both used to inquire about relevant content about a location. Based on the user's spoken language habit, the phone determines that the user may currently want to know more about the attractions at location B. Thus, the phone obtains the introduction to the attractions at location B and outputs it to the user as the third response information. Furthermore, the content type of the third response information is the same as that of the first response information, both representing introduction to attractions at a location. Alternatively, the sentence structure of the third response information and the first response information can also be the same, both using the same language structure or expression to give the response information.

[0157] In some examples, operation A above can also be referred to as the first operation.

[0158] It is understood that the above-mentioned third response information has the same sentence structure and / or the same content type as the first response information. The content type can be, for example, an event, a place, a person, food, a building, etc., and the content type of instruction A can also be, for example, an event, a place, a person, food, a building, etc.

[0159] In some examples, when the phone outputs the initial response information, it can also simultaneously display a prompt message asking the user to provide feedback. For example, see [link to example]. Figure 9As shown, the first response information is "attraction introduction information of place A", and the first prompt information can include information such as "like", "dislike" and the like in the display control. If the user approves the first response information, the user can click the control 901 corresponding to "like". If the user does not approve the first response information, the user can click the control 902 corresponding to "dislike". Exemplarily, the operation A described above can be a confirmation operation of the user on the first prompt information, for example, clicking the control corresponding to "like".

[0160] Of course, the user may also be dissatisfied or disapprove of the first response information output by the mobile phone. In this case, the mobile phone can optimize the response information given by the mobile phone to the instruction A in the current scene in real time according to the feedback of the user on the first response information, so that the response information given can satisfy or be approved by the user.

[0161] In some examples, if the user does not approve the first response information, the user can perform operation B on the first response information and input first indication information of the content expected to be obtained to the mobile phone, so that the mobile phone re-acquires fourth response information corresponding to the instruction A in the current scene according to the first indication information input by the user, and outputs the fourth response information to the user. Exemplarily, the operation B can be a denial operation of the user on the first prompt information, for example, clicking the control corresponding to "dislike" described in the foregoing embodiments and the like. In this way, if the user does not approve the first response information, the mobile phone can continue to recommend new response information to the user, so that the user can obtain a better experience on the mobile phone.

[0162] For example, referring to (a) in FIG. 10, Figure 10 As shown, the mobile phone is in the first scene, the instruction A input by the user to the mobile phone is "how is place A", and the first response information output by the mobile phone is "history introduction information of place A". If the user does not approve the first response information, the user can input first indication information "I want to know what interesting places there are in place A" to the mobile phone, so that the mobile phone can give, for example, "attraction introduction information of place A" as the fourth response information.

[0163] Alternatively, referring to FIG. 11, Figure 10As shown in (b) of FIG. 10, the mobile phone is in the first scene, the instruction A input by the user to the mobile phone is "how is place A", and the first response information output by the mobile phone is "historical introduction information of place A". If the user does not approve the first response information, after the user clicks the "dislike" corresponding control, the mobile phone can continue to display some to-be-selected information, for example, display different types of to-be-selected information such as "offensive", "biased", "unprofessional", "irrelevant", "wrong value" and the like, and the user can input the first indication information by selecting the to-be-selected information. Alternatively, the mobile phone can also provide an input box 1001 for the user to input information, and the user can also input the first indication information in the input box 1001. Thus, the mobile phone can give the fourth response information more in line with the user's requirements.

[0164] If the user approves the fourth response information, the mobile phone can learn the historical preference information of the user in the current scene according to the fourth response information, such as language preference, oral habit and the like. For example, in the first scene, when the user inputs "how is the place" to the mobile phone, the user wants to know about the interesting scenic spots of a place. Then, when the user inputs "how is place B" in the first scene again, the mobile phone can give "scenic spot introduction information of place B".

[0165] In some examples, the operation B described above can also be referred to as a second operation.

[0166] The above process can be regarded as a process in which the mobile phone optimizes the response information in real time according to the feedback information of the user. If the user still does not approve the fourth response information, the mobile phone can continue to provide new response information for the user until the user approves, so as to optimize the relationship among the scene, the instruction and the response information, that is, to optimize the interaction process between the mobile phone and the user, so that the response information given by the mobile phone can be more in line with the user's requirements, and the user's interaction experience is improved.

[0167] Embodiment Two

[0168] Referring to FIG. 10, Figure 11 As shown in FIG. 10, the above-mentioned interaction method can further include the following steps S1101-S1104.

[0169] S1101, the mobile phone receives the instruction A input by the user.

[0170] For example, the type of the foregoing instruction can also be used to indicate that the instruction A is a task type instruction. For example, the task type instruction can be "open APP1", "play music", "call XX", "I want to watch a movie", "I want to listen to music", and the like. The task type instruction is used to make a request to the mobile phone, so as to control the mobile phone to implement corresponding functions or perform corresponding operations. In some examples, after the mobile phone performs the corresponding operation, the user can also be prompted that the corresponding operation has been completed or the corresponding function has been implemented.

[0171] S1102. The mobile phone obtains the scene in which the mobile phone is located.

[0172] The method by which the mobile phone determines the current scene can be referred to the content in the aforementioned embodiment S502, and will not be repeated here.

[0173] S1103, The mobile phone obtains the operation indicated by instruction A in the current scenario of the mobile phone.

[0174] Since the context in which the mobile phone is located may reflect the user's state or needs, the operation indicated by instruction A in the context of the mobile phone can also be determined based on the user's state (or needs) and instruction A.

[0175] In this context, the operation indicated by instruction A in the context of the mobile phone can be, for example, playing music, playing video, displaying navigation routes, opening applications, making phone calls, or sending messages.

[0176] S1104. The mobile phone executes the operation indicated by instruction A in the current scenario of the mobile phone.

[0177] In some examples, during the execution of the above operations, the phone can first obtain the first application corresponding to instruction A in the current scenario. This first application can be determined based on the current scenario and instruction A. Then, the phone launches the first application to execute the operation specified by instruction A in that scenario.

[0178] For example, in scenario one, the user might be resting at home. If the user's input command A is "I want to watch a movie," then because the user is resting, the phone might determine that the user's need is to open a mobile app to watch a movie. After determining the user's need, see [further details omitted]. Figure 12 As shown in (a), the phone can identify the video application as the first application.

[0179] For example, in the second scenario, the user may be about to go out. If the user's input command A is "I want to watch a movie," then because the user is about to go out, the phone may determine that the user's need is to find navigation routes to the nearest movie theater. After determining the user's need, see... Figure 12 As shown in (b), the phone can identify the navigation app as the first app.

[0180] For example, in a third scenario, the user may already be out. If the user's input command A is "I want to watch a movie," then because the user is already out, the phone might determine that the user's need is to know how far away the nearest movie theater is. After determining the user's need, see [link to relevant documentation]. Figure 12As shown in (c), the phone can identify the navigation app as the first app.

[0181] It is understandable that the first application mentioned above can be determined not only based on the user's input instruction A, but also based on the scenario in which the mobile phone is located. Since the scenario in which the mobile phone is located can reflect the user's needs to a certain extent, the determined first application can also meet the user's needs to a certain extent.

[0182] In the above-mentioned solutions S1101-S1104, the mobile phone can execute the operation indicated by instruction A according to the user's input instruction A, combined with different scenarios, or launch the corresponding application to execute the operation indicated by instruction A. This allows the execution of the operation to meet the user's needs in different scenarios to a certain extent, reducing user dissatisfaction with the launched application and bringing a better interactive experience to the user.

[0183] In some examples, if the user approves launching the first application, they can perform operation C on it. This allows the phone to associate the first application, the current context, and the user's input command A. Consequently, when the same command is received again in the same context, the phone can directly launch the first application. This gives the interaction method a certain degree of scenario generalization capability. For the same scenario or the same user needs, the phone can launch the application that satisfies or satisfies the user without requiring repeated user feedback, resulting in a better user experience.

[0184] For example, see Figure 13 As shown in (a), the phone is in the first scenario, and the user inputs the instruction A to the phone as "I want to watch a movie". The first application launched by the phone is application 1. If the user inputs the instruction D "I want to watch a movie" again when the phone is in the first scenario, the content of instruction D is the same as that of instruction A, and the phone will still launch application 1.

[0185] In some examples, if the user approves launching the first application, the phone can also learn from the user's historical preferences for issuing command A in the current scenario, such as language preferences and spoken language habits. Thus, when the phone receives another command later, it can determine and launch the corresponding application based on the user's historical preferences. This gives the interaction method a certain degree of scenario generalization capability. For the same scenario and the user's historical preferences, the phone can launch the application that satisfies or satisfies the user without requiring repeated user feedback, resulting in a better user experience.

[0186] For example, see Figure 13In the first scenario, the instruction A inputted by the user to the mobile phone is "I want to watch a movie", and the first application started by the mobile phone is a video application. The mobile phone determines that the oral habit of the user in the current scenario is that when the user inputs a video demand to the mobile phone, the user wants to open a video application. In the same scenario, the instruction D inputted by the user to the mobile phone is "I want to listen to music", and the content type of the instruction D is the same as that of the instruction A, both of which indicate a video demand. Therefore, according to the oral habit of the user, the mobile phone determines that the user currently wants to open a music application more, and thus the mobile phone starts the music application.

[0187] In some examples, the operation C described above can also be referred to as a third operation.

[0188] It can be understood that the content type of the instruction A and the instruction D can be used to indicate a video demand, a shopping demand, a food demand, etc.

[0189] In some examples, when the mobile phone starts the first application, the mobile phone can also display second prompt information for prompting the user to give feedback. For example, the second prompt information can be "Are you satisfied with the application?", and the second prompt information can also include information such as "like" and "dislike" in a display control. If the user approves the starting of the first application, the user can click the control corresponding to "like". If the user does not approve the first application, the user can click the control corresponding to "dislike". For example, the operation C described above can be a confirmation operation of the user on the second prompt information, such as clicking the control corresponding to "like".

[0190] Of course, the user can also be dissatisfied or disapprove of the first application started by the mobile phone. In this case, the mobile phone can optimize the application started by the mobile phone in the current scenario according to the feedback of the user on the first application in real time, so that the started application can satisfy or be approved by the user.

[0191] In some examples, if the user does not approve the first application, the user can perform an operation D on the first application and input second indication information of an application expected to be started to the mobile phone, so that the mobile phone determines a second application corresponding to the instruction A in the current scenario according to the second indication information inputted by the user, and starts the second application. For example, the operation D can be a disapproval operation of the user on the first application, such as clicking the control corresponding to "dislike" described in the foregoing embodiments, etc. In this way, if the user does not approve the first application, the mobile phone can also recommend a new application to the user, so that the user can obtain a better experience on the mobile phone.

[0192] For example, referring to Figure 14As shown in (a), the mobile phone is in the first scenario. The user inputs the instruction A to the mobile phone as "I want to watch a movie". The mobile phone launches application 1, which provides audio and video functions. If the user does not approve of application 1, the user can input the second instruction information "I want to use application 2" to the mobile phone, so that the mobile phone launches application 2, which provides audio and video functions.

[0193] If the user approves of the second application, the phone can learn the user's historical preferences for issuing command A in the current scenario, such as language preferences and speaking habits. For example, in the first scenario, when the user enters "I want to watch a movie" into the phone, they want to use application 2. Later, when the user enters "I want to watch a movie" again in the first scenario, the phone can directly launch application 2.

[0194] For example, see Figure 14 As shown in (b), the mobile phone is in the first scenario. The user inputs the instruction A to the mobile phone as "I want to watch a movie". The mobile phone launches application 1, which provides audio and video functions. If the user does not approve of application 1, the user can input the second instruction information "I want to know how to get to the cinema" to the mobile phone, so that the mobile phone launches application 3, which provides navigation functions.

[0195] The above process can be seen as the phone optimizing its functionality in real time based on user feedback. If the user still does not approve of the second application, the phone can continue to provide new applications until the user approves, thereby optimizing the relationship between scenarios, commands, and applications, that is, optimizing the interaction process between the phone and the user, so that the applications launched by the phone can better meet the user's needs and improve the user's interactive experience.

[0196] It is understandable that the user commands, user feedback information, the phone's location in the real world, the real world time, the real world weather conditions, or the phone's status collected by the phone are all obtained with the user's authorization.

[0197] The foregoing embodiments all use mobile phones as examples to illustrate the interaction methods in the embodiments of this application. In other embodiments, the process of implementing the above interaction methods in vehicle terminals, tablet computers, personal computers, laptop computers, etc. can also refer to the process of the foregoing embodiments, and will not be repeated here.

[0198] In some scenarios, multiple embodiments of the present application can be combined, and the combined scenario can be implemented. Optionally, some operations in the flow of each method embodiment are optionally combined, and / or the order of some operations is optionally changed. Moreover, the execution order between the steps of each flow is only exemplary, and does not constitute a limitation on the execution order between the steps, and other execution orders between the steps can also be used. The described execution order is not intended to indicate that these operations can only be executed in this order. A person of ordinary skill in the art will think of various ways to reorder the operations described in the embodiments of the present application. In addition, it should be pointed out that the process details involved in a certain embodiment of the present application are also applicable in a similar manner to other embodiments, or different embodiments can be combined for use.

[0199] In addition, some steps in the method embodiments can be equivalently replaced by other possible steps. Alternatively, some steps in the method embodiments can be optional and can be deleted in some use scenarios. Alternatively, other possible steps can be added to the method embodiments.

[0200] Moreover, each method embodiment can be implemented individually or in combination.

[0201] It can be understood that, in order to achieve the above functions, the foregoing electronic device contains hardware and / or software modules corresponding to each function. The algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented in hardware or a combination of hardware and computer software. Whether a certain function is implemented in hardware or computer software driven hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application in combination with the embodiments, but such implementation should not be considered beyond the scope of the present application.

[0202] The present embodiment can divide the electronic device into functional modules according to the above method examples. For example, each functional module can be divided according to each function, or two or more functions can be integrated into one processing module. The integrated module can be implemented in the form of hardware. It should be noted that the division of modules in the present embodiment is illustrative, and is only a logical functional division. Actual implementation can have another division manner.

[0203] The present embodiment also provides an electronic device, as shown in the figure, which can include one or more processors 1501, a memory 1502, and a communication interface 1503. Figure 15

[0204] ​The memory 1502, the communication interface 1503, and the processor 1501 are coupled. For example, the memory 1502, the communication interface 1503, and the processor 1501 can be coupled together through a bus 1504.

[0205] The communication interface 1503 is configured to perform data transmission with other devices. The memory 1502 stores computer program code. The computer program code includes computer instructions, which, when executed by the processor 1501, cause the electronic device to perform the interaction method in the embodiments of the present application.

[0206] The processor 1501 can be a processor or a controller, for example, can be a CPU, a general-purpose processor, a digital signal processor (Digital Signal Processor, DSP), an application-specific integrated circuit (Application-Specific Integrated Circuit, ASIC), a field programmable gate array (Field Programmable Gate Array, FPGA), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute various exemplary logical blocks, modules, and circuits described in combination with the present disclosure. The processor can also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like.

[0207] The bus 1504 can be a peripheral component interconnect (Peripheral Component Interconnect, PCI) bus or an extended industry standard architecture (Extended Industry Standard Architecture, EISA) bus, etc. The above-mentioned bus 1504 can be divided into an address bus, a data bus, a control bus, etc. For the sake of convenience, Figure 15 Only one thick line is used in the above description, but it does not mean that there is only one bus or only one type of bus.

[0208] The embodiments of the present application also provide a computer readable storage medium, which includes computer instructions, when the computer instructions are run on an electronic device, the electronic device performs the related method steps in the above method embodiments.

[0209] The embodiments of the present application also provide a computer program product, when the computer program product is run on a computer, the computer executes the related method steps in the above method embodiments.

[0210] The electronic device, the computer readable storage medium or the computer program product provided in the application are used to execute the corresponding method provided above, and thus the beneficial effects achieved thereby can refer to the beneficial effects of the corresponding method provided above, which will not be described here again.

[0211] Through the description of the above embodiments, those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above functional modules is taken as an example, and in actual application, the above functions can be completed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above.

[0212] In several embodiments provided in the application, it should be understood that the disclosed device and method can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the modules or units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another device, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interface, device or unit, and can be electrical, mechanical or other forms.

[0213] The units described as separate components can or can not be physically separated, and the components shown as units can be one physical unit or multiple physical units, that is, can be located in one place, or can be distributed to multiple different places. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0214] In addition, each functional unit in each embodiment of the application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0215] The integrated unit, if implemented in the form of a software function unit and sold or used as an independent product, can be stored in a readable storage medium. Based on such understanding, the technical solutions of the embodiments of the present application can be embodied in the form of a software product in essence or in the part that contributes to the present application, or the whole or part of the technical solutions can be embodied in the form of a software product stored in a storage medium, including a plurality of instructions for causing an apparatus (which can be a single-chip microcomputer, a chip, etc.) or a processor to execute all or part of the steps of the method described in the embodiments of the present application. The foregoing storage medium includes a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0216] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto, and any change or replacement within the technical scope disclosed in the present application should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. An interaction method, characterized in that, Applied to electronic devices, the method includes: Receive the first instruction input by the user; The scene in which the electronic device is located is obtained; the scene is determined based on at least one of the following: the location of the electronic device in the real world, the time in the real world, the weather conditions in the real world, or the status of the mobile phone. Execute the first response operation corresponding to the first instruction in the scenario; the first response operation is determined based on the scenario and the first instruction.

2. The method according to claim 1, characterized in that, The execution of the first response operation corresponding to the first instruction in the scenario includes: outputting the first response information corresponding to the first instruction in the scenario; or, executing the operation indicated by the first instruction in the scenario.

3. The method according to claim 2, characterized in that, The method further includes: After the user performs a first operation on the first response information, if a second instruction with the same content as the first instruction is received in the scenario, then a second response information with the same content as the first response information is output; the first operation indicates that the user acknowledges the first response information.

4. The method according to claim 2 or 3, characterized in that, The method further includes: After the user performs a first operation on the first response information, if a third instruction with the same sentence structure as the first instruction is received in the scenario, then a third response information with the same sentence structure or content type as the first response information is output; or, After the user performs a first operation on the first response information, if a third instruction with the same content type as the first instruction is received in the scenario, then a third response information with the same content type as the first response information is output.

5. The method according to any one of claims 2-4, characterized in that, The method further includes: After the user performs a second operation on the first response information, first indication information input by the user is obtained; the second operation indicates that the user does not agree with the first response information, and the first indication information is used to indicate the content that the user expects to obtain; Based on the first instruction information, obtain the fourth response information corresponding to the first instruction in the scenario; the content of the fourth response information is different from that of the first response information. Output the fourth response information.

6. The method according to claim 2, characterized in that, The execution of the operation indicated by the first instruction in the scenario includes: Obtain the first application corresponding to the first instruction in the scenario; the first application is determined based on the scenario and the first instruction; The first application is launched to execute the operation indicated by the first instruction in the scenario.

7. The method according to claim 6, characterized in that, The method further includes: After the user performs a third operation on the first application, if a fourth instruction with the same content as the first instruction is received in the scenario, the first application is started to execute the operation indicated by the fourth instruction in the scenario; the third operation indicates that the user agrees to use the first application to respond to the first instruction.

8. The method according to claim 6 or 7, characterized in that, The method further includes: After the user performs the fourth operation on the first application, the second instruction information input by the user is obtained; the fourth operation indicates that the user does not agree to use the first application to respond to the first instruction, and the second instruction information is used to indicate the application that the user expects to launch; According to the second instruction information, in the current scenario of the electronic device, a second application is launched to execute the operation indicated by the first instruction in the scenario; the second application is of the same type as the first application and / or performs the same function.

9. The method according to any one of claims 1-8, characterized in that, The first response operation is also determined based on the user's historical preference information.

10. The method according to any one of claims 2-5, characterized in that, When the first instruction is a first location and the scenario is that the user is in a resting state, the first response information output is food information or attraction information for the first location; When the first instruction is a first location and the scenario is a user traveling, the first response information output is the navigation route information from the user's current location to the first location.

11. The method according to claim 10, characterized in that, The third instruction refers to the second location. After the user performs the first operation on the first response information, if the electronic device receives the third instruction while the user is in a resting state, the third response information is food information or attraction information for the second location; After the user performs the first operation on the first response information, if the electronic device receives the third instruction while the user is traveling, the third response information is the navigation route information from the user's location to the second location.

12. The method according to any one of claims 2-5, characterized in that, When the first instruction is an inquiry instruction about the first location, and the scenario is that the user is in a resting state, the first response information output is food information or attraction information for the first location.

13. The method according to claim 12, characterized in that, The third instruction is an inquiry instruction regarding information related to the second location. After the user performs the first operation on the first response information, if the electronic device receives the third instruction while the user is in a resting state, the third response information is food information or attraction information for the second location.

14. The method according to any one of claims 1-13, characterized in that, The first instruction is a voice instruction or a text instruction; the first response information is one or more of voice information, text information, and image information.

15. An electronic device, characterized in that, The device includes a memory and one or more processors; the memory is coupled to the processors; wherein the memory stores computer program code, the computer program code including computer instructions, which, when executed by the processor, cause the electronic device to perform the interaction method as described in any one of claims 1-14.

16. A computer-readable storage medium, characterized in that, Includes computer instructions that, when executed on an electronic device, cause the electronic device to perform the interaction method as described in any one of claims 1-14.

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

Images