Session method and session device

Abstract

The invention discloses a session method and a session device, and belongs to the technical field of communication. The session method is applied to the electronic device, the electronic device is in communication connection with an open wearable earphone (OWS), and the session method comprises the following steps: receiving session information sent by the OWS earphone, the session information being session information in a session scene collected by the OWS earphone, and the session information comprising at least one of the following items: voice information of a first user and voice information of a second user, the first user and the second user are users in the session scene, and the first user wears an OWS earphone; determining a target session scene type of the session scene and role information of the user according to the session information; determining target reply information corresponding to the target session scene type and the role information; and sending the target reply information to the OWS earphone for playing, so that the first user performs a session with the second user based on the target reply information.

Description

Technical Field

[0001] This application belongs to the field of communication technologies, and particularly relates to a conversation method and a conversation device. Background Art

[0002] With the development of Artificial Intelligence (AI) technology, the application of AI models has become increasingly widespread. For example, users can use the AI models in electronic devices to meet needs such as life assistance, dining recommendations, and oral practice.

[0003] Currently, users mainly interact with the AI models in electronic devices by actively asking questions to obtain the information replied by the AI models. When a user is in a scenario of having a conversation with others, it is not convenient to directly ask the AI model, thus unable to obtain the information replied by the AI model in a timely manner. For example, when parents are educating their children, when they want to use the AI model to answer the questions raised by their children, due to the inconvenience of frequently using electronic devices, parents are unable to give reasonable explanations or answers when facing some questions raised by their children. Therefore, the current use effect of electronic devices is poor when the user is in a scenario of having a conversation with others. Summary of the Invention

[0004] The purpose of the embodiments of this application is to provide a conversation method and a conversation device, enabling users to interact with the AI models in electronic devices in a timely manner, obtain the information related to the current chat scenario feedback by the AI models, improve the use effect of electronic devices when the user is in a scenario of having a conversation with others, and enhance the conversation effect.

[0005] In a first aspect, the embodiments of this application provide a conversation method, which is applied to an electronic device that communicates with an Open Wearable Stereo (OWS) headset. The conversation method includes:

[0006] Receiving the conversation information sent by the OWS headset, where the conversation information is the conversation information in the conversation scenario collected by the OWS headset, and the conversation information includes at least one of the following:

[0007] The voice information of the first user and the voice information of the second user;

[0008] Wherein, the first user and the second user are the users in the conversation scenario, and the first user wears the OWS headset;

[0009] Determining the target conversation scenario type of the conversation scenario and the role information of the user according to the conversation information;

[0010] Determining the target reply information corresponding to the target conversation scenario type and the role information;

[0011] Send the target reply information to the OWS headset for playback, so that the first user can have a conversation with the second user based on the target reply information.

[0012] In a second aspect, an embodiment of the present application provides a conversation device, which is applied to an electronic device. The electronic device communicates with an open wearable headset (OWS). The conversation device includes:

[0013] A receiving module, configured to receive the conversation information sent by the OWS headset. The conversation information is the conversation information in the conversation scenario collected by the OWS headset, and the conversation information includes at least one of the following:

[0014] The voice information of the first user and the voice information of the second user;

[0015] Wherein, the first user and the second user are users in the conversation scenario, and the first user wears the OWS headset;

[0016] A determining module, configured to determine the target conversation scenario type of the conversation scenario and the role information of the user according to the conversation information; determine the target reply information corresponding to the target conversation scenario type and the role information;

[0017] A sending module, configured to send the target reply information to the OWS headset for playback, so that the first user can have a conversation with the second user based on the target reply information.

[0018] In a third aspect, an embodiment of the present application provides an electronic device, which includes a processor and a memory. The memory stores a program or instruction that can run on the processor. When the program or instruction is executed by the processor, the steps of the method described in the first aspect are implemented.

[0019] In a fourth aspect, an embodiment of the present application provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps of the method described in the first aspect are implemented.

[0020] In a fifth aspect, an embodiment of the present application provides a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor, and the processor is configured to run a program or instruction to implement the steps of the method described in the first aspect.

[0021] In a sixth aspect, an embodiment of the present application provides a computer program product, which is stored in a storage medium and is executed by at least one processor to implement the steps of the method described in the first aspect.

[0022] In an embodiment of the present application, an electronic device receives session information sent by an OWS headset. The session information is the session information in a session scenario collected by the OWS headset. The session information includes at least one of the following: the voice information of a first user, the voice information of a second user. The first user and the second user are users in the session scenario, and the first user wears the OWS headset. Determine the target session scenario type and the role information of the user according to the session information; determine the target reply information corresponding to the target session scenario type and the role information; send the target reply information to the OWS headset for playback, so that the first user can have a conversation with the second user based on the target reply information. That is, in this embodiment, the OWS headset can be used to automatically collect the session information between users and send it to the electronic device. The electronic device determines the target session scenario type and the role information of the user in the session scenario based on the session information, generates the target reply information corresponding to the target session scenario type and the role information, and then the OWS headset plays it. There is no need for the user to actively initiate an inquiry to the electronic device. Therefore, the user can obtain the reply information corresponding to the target session scenario type feedback by the electronic device in a timely manner. At the same time, playing the target reply information through the OWS headset is neither easily detected by the other party nor will it interfere with the chat between users. Moreover, the generated reply information can change dynamically according to the type of the session scenario and the role information of the user, thereby helping the user to have a good conversation with others, improving the session effect, and enhancing the use effect of the electronic device when the user is in a scenario of having a conversation with others. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 FIG. is a schematic diagram of an application scenario of a session method provided by an embodiment of the present application;

[0024] Figure 2 FIG. is a schematic diagram of another application scenario of a session method provided by an embodiment of the present application;

[0025] Figure 3 FIG. is a flowchart of a session method provided by an embodiment of the present application;

[0026] Figure 4 FIG. is a flowchart of another session method provided by an embodiment of the present application;

[0027] Figure 5 FIG. is a schematic diagram of the display process of a scene interface provided by an embodiment of the present application;

[0028] Figure 6 FIG. is a flowchart of another session method provided by an embodiment of the present application;

[0029] Figure 7 FIG. is a schematic diagram of a target window provided by an embodiment of the present application;

[0030] Figure 8A flowchart of another conversation method provided in an embodiment of the present application;

[0031] Figure 9 A schematic diagram of the structure of a conversation device provided in an embodiment of the present application;

[0032] Figure 10 A schematic diagram of the structure of another conversation device provided in an embodiment of the present application;

[0033] Figure 11 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application;

[0034] Figure 12 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0035] The following will be combined with the drawings in the embodiments of the present application to clearly describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments in the present application belong to the scope of protection of this application.

[0036] The terms "first", "second", etc. in the specification of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second", etc. are usually a class, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0037] As mentioned above, in order to take advantage of the convenience brought by the AI model, users currently mainly interact with electronic devices that integrate AI models by actively asking questions, so as to obtain the reply information of the AI model. However, in some scenarios, such as scenarios where users are conversing with others, it is inconvenient for users to directly ask the AI model, resulting in the inability to obtain the information replied by the AI model in a timely manner, affecting the effect of the conversation. For example, when parents are educating their children, when parents want to use AI models to answer questions raised by their children, because it is inconvenient for parents to use electronic devices frequently, parents are unable to give reasonable explanations or answers when facing some questions raised by their children, which in turn affects the educational effect. Therefore, the current use effect of electronic devices when users are in a conversation with others is poor, and it is difficult to meet the needs of users in a timely manner.

[0038] In order to solve the above technical problems, the embodiments of the present application provide a conversation method and a conversation device, so that users can interact with the AI model in the electronic device in a timely manner, obtain information related to the current chat scene fed back by the AI model, improve the use effect of the electronic device when the user is in a conversation with others, and improve the conversation effect.

[0039] The conversation method and conversation device provided in the embodiments of the present application are described in detail below through specific embodiments and their application scenarios in conjunction with the accompanying drawings.

[0040] Figure 1 A schematic diagram of an application scenario of a conversation method provided in an embodiment of the present application, the application scenario may include a headset 101 and an electronic device 102, and the application scenario includes two users, user A and user B, for example, and user A may wear the headset 101. The headset 101 communicates with the electronic device 102.

[0041] In this application scenario, the electronic device 102 can integrate an AI model, and user A can use the AI model in the electronic device 102 to meet different needs.

[0042] The earphone 101 here can be an earphone that can perceive the ambient sound in real time and will not affect the user's conversation with others after the user wears it. For example, the earphone 101 can be an open wearable stereo (OWS). User A can wear the OWS earphone to talk with user B. The OWS earphone can collect the conversation information between user A and user B in real time.

[0043] The electronic device 102 may be a device capable of communicating with the OWS headset, such as a mobile phone, a tablet computer, a laptop computer, etc. The electronic device 102 may generate reply information based on the conversation information collected by the OWS headset, and feed it back to the OWS headset for playback, thereby assisting the conversation between user A and user B.

[0044] Figure 2 A schematic diagram of an application scenario of another conversation method provided in an embodiment of the present application, the application scenario may include a headset 101, an electronic device 102, and a server 103. The application scenario includes two users, user A and user B, for example, and user A may wear the headset 101. The electronic device 102 communicates with the headset 101 and the server 103, respectively.

[0045] In this application scenario, the server 103 can integrate the AI model, and the electronic device 102 can simply process the conversation information collected by the OWS headset and send the processed results to the server 103. The server 103 generates reply information corresponding to the conversation information and sends it to the OWS headset through the electronic device 102 for playback, thereby assisting the conversation between user A and user B.

[0046] Based on the above application scenarios, an embodiment of the present application provides a session method, as Figure 3 shown, this session method can be applied to an electronic device, and the electronic device can be Figure 1 the electronic device in the scenario shown, or can also be Figure 2 the electronic device in the scenario shown.

[0047] As Figure 3 shown, this session method may include the following steps:

[0048] S310. Receive the session information sent by the OWS headset.

[0049] Among them, the session information is the session information in the session scenario collected by the OWS headset, and the session information includes at least one of the following: the voice information of the first user, the voice information of the second user. The first user and the second user are users in the session scenario, and the first user wears the OWS headset.

[0050] S320. Determine the target session scenario type of the session scenario and the role information of the user according to the session information.

[0051] S330. Determine the target reply information corresponding to the target session scenario type and role information.

[0052] S340. Send the target reply information to the open wearable headset for playing, so that the first user can conduct a session with the second user based on the target reply information.

[0053] This embodiment can automatically collect the session information between users by using the OWS headset and send it to the electronic device. The electronic device determines the target session scenario type of the session scenario and the role information of the user based on the session information, and generates the target reply information corresponding to the target session scenario type and role information, and then plays it through the open wearable headset. There is no need for the user to actively initiate an inquiry to the electronic device. Thus, the user can timely obtain the reply information corresponding to the target session scenario type feedback by the electronic device. At the same time, playing the target reply information through the open wearable headset is neither easily noticed by the other party nor interferes with the chat between users. Moreover, the generated reply information can dynamically change with the type of the session scenario and the role information of the user, thereby helping the user to conduct a good session with others, improving the session effect, and enhancing the usage effect of the electronic device when the user is in a scenario of having a conversation with others.

[0054] The above steps are described in detail below, as specifically shown below:

[0055] In S310, the above-mentioned open wearable headset can be an OWS headset. The OWS headset can collect ambient sounds in real time. For example, it can collect conversation information in a conversation scenario in real time. The conversation scenario can be any type of scenario, such as including but not limited to shopping scenarios, blind date scenarios, children's education scenarios, work scenarios, etc.

[0056] The conversation scenario can include at least two users. In this embodiment, taking the example of including a first user and a second user, there can be multiple second users. The first user can be the user wearing the OWS headset, and the second user can be the user other than the first user in the conversation scenario. When the first user has a conversation with the second user, there is no need to remove the OWS headset.

[0057] The OWS headset can collect the voice information of any user in the conversation scenario in real time. For example, if the first user is speaking currently, the OWS headset can collect the voice information of the first user in real time. Then, when the second user speaks, the OWS headset can collect the voice information of the second user in real time.

[0058] The OWS headset can send the conversation information collected in real time to the electronic device. In practical applications, the first user can first wake up the OWS headset to enable the OWS headset to establish a communication connection with the electronic device, providing a basis for subsequent interactions between the OWS headset and the electronic device.

[0059] This embodiment does not limit the wake-up method of the OWS headset. Exemplarily, the first user can wake up the OWS headset by touching a physical button of the OWS headset. For example, the first user can wake up the OWS headset by long pressing the button on the left earphone or the right earphone.

[0060] Exemplarily, the first user can also wake up the OWS headset by voice. Different wake-up methods can be applied to different scenarios, thus improving the flexibility of the wake-up method.

[0061] Exemplarily, after the OWS headset is woken up, it can prompt the first user that the assisted chat function has been enabled and establish a communication connection with the electronic device. Exemplarily, the OWS headset can broadcast "The assisted chat function has been enabled".

[0062] In S320, the electronic device can dynamically determine the scenario type of the conversation scenario based on the conversation information sent by the OWS headset, improving the intelligence of the electronic device. In this embodiment, the scenario type automatically determined by the electronic device is determined as the target conversation scenario type.

[0063] In actual application, the first user can also select the scene type of the current conversation scene by themselves. For example, after the OWS headset is awakened, the electronic device can display a scene interface, which can include multiple candidate scene types for the first user to select. These candidate scene types are the scene types preset by the first user. Based on the input of the first user, the electronic device can determine the scene type of the current conversation scene, providing a more accurate basis for determining the target reply information subsequently.

[0064] The role information here is used to represent the identity information of different users in this conversation scene. For example, in an educational scene, it can include the parent role and the child role. In a blind date scene, it can include the male blind date object role and the female blind date object role. In a work scene, it can include the ordinary employee role and the leader role.

[0065] For the same scene, even for the same question, the target reply information corresponding to different roles can be different. This can make the target reply information more in line with the user's role, thereby enhancing the conversation effect. For example, for the same question "Why does the sky turn black", if the question is asked by a child, the target reply information can be more colloquial and story-like to facilitate the child's understanding. If the question is asked by an adult, the terms used in the target reply information are more rigorous.

[0066] Exemplarily, the electronic device can determine the target conversation scene type based on the conversation keywords in the conversation information, and determine the role information of the user in the conversation information based on the role determination model. The role determination model can be, for example, a machine learning model or a deep learning model.

[0067] Exemplarily, the electronic device can also determine the role information of the user based on the voiceprint feature of the conversation information.

[0068] In S330, the target reply information can be information used to assist the conversation between the first user and the second user. The target reply information can be the reply information provided by the electronic device based on the question of the first user, or the information provided by the electronic device based on the question of the second user. That is to say, the target reply information can be the response information corresponding to the inquiry.

[0069] Exemplarily, the electronic device can use the locally configured AI model to determine the target reply information corresponding to the target conversation scene type and role information. Exemplarily, the electronic device can also send the target conversation scene type and role information to the server, and the server determines the target reply information based on the target conversation scene type and role information.

[0070] In S340, the electronic device may send the target reply information to the OWS headset for playback. Exemplarily, the electronic device may first convert the target reply information into voice information and then send the voice information to the OES headset for playback. Exemplarily, the electronic device may also directly send the target reply information to the OWS headset. After receiving the target reply information, the OWS headset converts it into voice information first and then plays it.

[0071] Exemplarily, the first user may have a conversation with the second user based on the target reply information played by the OWS headset. For example, in the case where the second user asks a question to the first user, the first user may relay the target reply information played by the OWS headset to the second user, or may adjust the target reply information played by the OWS headset and then reply to the second user. For example, in the scenario of children's education, the child asks a question to the parent, and the parent may give a reasonable explanation or answer to the child based on the target reply information corresponding to the question played by the OWS headset.

[0072] Again, in the case where the first user asks a question to the second user, the first user may determine whether the answer of the second user is accurate based on the target reply information played by the OWS headset.

[0073] This embodiment can automatically collect conversation information with the help of the OWS headset. Without affecting the user's conversation, the OWS headset can communicate with the electronic device, timely obtain and play the reply information corresponding to the conversation information, assist the conversation between the first user and the second user, and improve the conversation effect. Moreover, by playing the target reply information through the OWS headset, it is neither easy to be noticed by the other party nor interfere with the conversation between users, thus improving the conversation effect.

[0074] Figure 4 This is a flowchart of another conversation method provided by the embodiment of the present application. Figure 4 Different from Figure 3 is that Figure 3 S320 in Figure 4 can be refined into S410 - S420 in

[0075] S410. Determine the target conversation scenario type between the first user and the second user according to the conversation keywords of the conversation information.

[0076] Different types of conversation scenarios can correspond to different conversation keywords. For example, for a blind date scenario, the conversation keywords can include blind date, self-introduction, hobbies, family members, etc. Another example is for the scenario of educating children, the conversation keywords can include dad or mom, baby, ask, tell, why, etc.

[0077] The conversation keywords here can be keywords directly included in the conversation information or keywords obtained by analyzing the conversation information. Exemplarily, the electronic device can perform semantic analysis and language understanding on the conversation information to obtain conversation keywords, and determine the conversation scenario type of the current conversation scenario based on the conversation keywords. This embodiment can dynamically determine the scenario type of the conversation scenario based on the conversation information between users, providing a more accurate basis for determining the corresponding reply information subsequently.

[0078] Exemplarily, the conversation keywords of the current conversation scenario can be matched with the reference conversation keywords by means of keyword matching to obtain the conversation scenario type of the current conversation scenario. The reference conversation keywords are the conversation keywords corresponding to different conversation scenario types.

[0079] Exemplarily, the conversation scenario type of the current conversation scenario can also be obtained through a machine learning model or a deep learning model based on the conversation keywords. For example, the conversation keywords can be input into the deep learning model to obtain the conversation scenario type of the current conversation scenario.

[0080] S420. Determine the role information of the user corresponding to the conversation information according to the voiceprint feature of the conversation information.

[0081] Exemplarily, the electronic device can extract the voiceprint feature of the conversation information and match the extracted voiceprint feature with the voiceprint feature of the first user pre-stored locally to judge the first user and the second user. For example, for the conversation information, two voiceprint features are extracted, namely the first voiceprint feature (corresponding to user A) and the second voiceprint feature (corresponding to user B). Among them, the first voiceprint feature matches the voiceprint feature of the first user stored locally. Therefore, it can be determined that user A is the first user and user B is the second user, and thus the owner of the electronic device and the other party can be distinguished.

[0082] Among them, the voiceprint of the first user can be input in advance. The electronic device can extract the feature of the voiceprint input by the first user to obtain the voiceprint feature of the first user and store the voiceprint feature of the first user for subsequent identity recognition.

[0083] In addition, factors such as gender and age also affect the voiceprint characteristics of users. For example, there are significant differences in the voiceprint characteristics between men and women, and between adults and children. Based on this, the role information of the first user and the second user can be further determined. The role information here can include, for example, children, adults, men, women, etc.

[0084] Exemplarily, the voiceprint characteristics of the extracted session information can be input into a role determination model to obtain the role information output by the role determination model.

[0085] This embodiment can determine the session scene type of the current session scene and the role information of the session user based on the real-time obtained session information, providing a more accurate basis for subsequent determination of the reply information, enabling the generated reply information to fit the current session scene and the role of the session user as much as possible, and helping to improve the session effect.

[0086] To ensure the accuracy of the session scene type, in some embodiments, after S410, the session method may further include the following steps:

[0087] Display the target session scene type;

[0088] In response to the first input of the first user to the target session scene type, display a scene interface, where the scene interface includes at least two candidate session scene types pre-configured by the first user;

[0089] In response to the second input of the first user to the target candidate session scene type, update the target session scene type to the target candidate session scene type, where the target candidate session scene type is any one of the at least two candidate session scene types other than the target session scene type.

[0090] The first input is used to indicate that the first user does not agree with the target session scene type determined by the electronic device, that is, the first user believes that the target session scene type determined by the electronic device does not match the current actual session scene. Exemplarily, the first input may include voice input, gesture input, touch input, etc.

[0091] Exemplarily, as Figure 5 shown, when the electronic device displays the target session scene type, it can simultaneously display a "confirm" control 501 and a "cancel" control 502. Figure 5 Taking the shopping scene as the target session scene type as an example, when the first user clicks the "confirm" control 501, it means that the target session scene type determined by the electronic device matches the current session scene. When the first user clicks the "cancel" control 502, it means that the target session scene type determined by the electronic device does not match the current session scene.

[0092] Exemplarily, after the electronic device receives a first input from a first user to the "Cancel" control 502, it may display a scene interface 503. The scene interface 503 may be an atomic component interface, and the scene interface 503 may include multiple atomic components. Each atomic component may correspond to a session scene type. Figure 5 Taking the example of including 5 atomic components, they are atomic component 504 - atomic component 508 respectively, and the corresponding session scene types are shopping session scene, elder session scene, educating children scene, work scene, and blind date scene.

[0093] The scenes in the scene interface 503 may be pre-configured by the first user. In actual application, the scene interface 503 may further include an "Other" control 509. When the first user clicks the "Other" control 509, the scene interface 503 may change the currently displayed session scene type. For example, if the currently displayed session scene type in the scene interface 503 does not meet the needs of the first user, the first user may click the "Other" control 509.

[0094] The second input is used to determine a target candidate session scene type that conforms to the current session scene from the candidate session scene types. Exemplarily, the second input may include inputs such as clicking and long-pressing on the target candidate session scene type.

[0095] Taking the example that the target session scene type determined by the electronic device is a shopping session scene, exemplarily, the second input may include an input to any one of the elder session scene, educating children scene, work scene, and blind date scene.

[0096] Based on the received second input, the electronic device may update the target session scene type to the target candidate session scene type, and subsequently may determine the corresponding target reply information based on the target candidate session scene type and the user's role information.

[0097] The electronic device in this embodiment may automatically determine the scene type of the session scene based on the session information and display it to the first user for confirmation. When receiving the first input from the first user, it may display multiple candidate session scene types for the first user to select, thereby ensuring the accuracy of the session scene type, and further improving the accuracy of the target reply information.

[0098] Figure 6 It is a flowchart of another session method provided by an embodiment of this application. Figure 6 Different from Figure 3 is that Figure 3 S330 in Figure 6 can be refined into S610 - S620 in

[0099] S610. Determine the corresponding reply keyword according to the session information.

[0100] Reply keywords are used to generate target reply information corresponding to the conversation information, assisting the conversation between the first user and the second user. Exemplarily, a large language model can be used to perform language understanding on the conversation information to obtain reply keywords corresponding to the conversation information. For example, for the question "Why does the sky turn black?", through language understanding, it can be determined that the reply keywords include the earth, rotation, sun, etc.

[0101] S620. Generate target reply information corresponding to the role information and the target conversation scenario type according to the reply keywords.

[0102] For the same reply keywords, if the role information and the target conversation scenario type are different, the corresponding reply information is also different. In this embodiment, the reply information can be dynamically determined based on the reply keywords, the user's role information, and the conversation scenario type, thereby improving the accuracy of the reply information.

[0103] Exemplarily, for the question "Why does the sky turn black?", taking the reply keywords including the earth, rotation, and sun as an example, if the question is asked by a child, the generated target reply information is colloquial and easy for the child to understand. If the question is asked by an adult, the generated target reply information is more professional.

[0104] Exemplarily, the target reply information for a child can be, for example, "The sky gets dark because the earth is playing a 'turning in circles' game! The sun is like a big flashlight, but its light can only illuminate half of the earth. When we turn to the side facing away from the sun, the sunlight can't shine on us, and that's when the sky gets dark and becomes night."

[0105] The target reply information for an adult can be, for example, "The sky turns black because the earth is constantly rotating. It takes about 24 hours for the earth to rotate once. When our location turns to the side facing away from the sun, the sunlight can't directly shine on this area, and the sky will gradually get dark."

[0106] This embodiment can dynamically determine the reply information corresponding to the conversation information according to the user's role information and the conversation scenario type, making the reply information more suitable for the current conversation scenario and the user's role, improving the accuracy of the reply information, and achieving a smoother effect of communicating with people.

[0107] To save the memory and power consumption of the electronic device, exemplarily, the above S330 may include the following steps:

[0108] Send the target conversation scenario type and role information to the server so that the server generates corresponding target reply information according to the target conversation scenario type and role information;

[0109] Receive the target reply information sent by the server.

[0110] The server here can be a cloud server or a physical server. This server has characteristics such as a large amount of memory, high computing power, and support for concurrent requests from multiple electronic devices. Considering that the AI model requires a large amount of memory and high power consumption, in order not to affect other functions of the user using the electronic device, in this embodiment, the AI model can be integrated into the server.

[0111] The electronic device can send the determined target session scenario type of the current session scenario and the corresponding user's role to the server, and the server uses the AI model to generate a target reply message corresponding to the target session scenario type and role information.

[0112] After the server generates the target reply message, it can send the target reply message to the electronic device, thereby reducing the power consumption of the electronic device, saving the memory of the electronic device, and avoiding affecting other functions of the first user using the electronic device.

[0113] In some embodiments, after S330, the session method may further include the following steps:

[0114] Display the target window;

[0115] In the target window, display the first reply message in the first display mode and display the second reply message in the second display mode;

[0116] Wherein, the first reply message is the target reply message played by the OWS headset, the second reply message is the target reply message not played by the OWS headset, and the first display mode is different from the second display mode.

[0117] The target window here can be a window on the lock screen interface, a window on the desktop, or a window on a specific application interface. That is, in this embodiment, the target reply message can be displayed when the electronic device is locked or unlocked, thereby improving the flexibility of the information display method.

[0118] In this embodiment, in addition to sending the target reply message to the OWS headset for playback, the electronic device can also display the target reply message in the target window for the convenience of the first user to view.

[0119] The electronic device can dynamically display the target reply message according to the playback progress of the OWS headset, so that the first user can more intuitively understand the playback progress of the OWS headset.

[0120] Exemplarily, the electronic device may display the first reply information that has been played by the OWS headset in a first display mode, and display the second reply information that has not been played by the OWS headset in a second display mode. In this embodiment, the specific forms of the first display mode and the second display mode are not limited. For example, the first display mode and the second display mode may be different colors, different font sizes, or other forms. For example, the first display mode is bold display, and the second display mode is non-bold display, or the first display mode is underlined display, and the second display mode is non-underlined display. Of course, the same display mode may also include multiple display forms. For example, the first display mode includes bold red display, and the second display mode includes non-bold black display.

[0121] Figure 7 Exemplarily, a schematic diagram of a target window is provided. The target window 701 may display target reply information. Figure 7 The target reply information that has been played by the OWS headset is represented in red font, and the target reply information that has not been played by the OWS headset is represented in black font. The electronic device may update the font color of the target reply information in the target window 701 in real time according to the playback progress of the OWS to keep in sync with the OWS headset.

[0122] To avoid affecting the use of the electronic device by the first user, exemplarily, the session method may further include the following steps:

[0123] When the playback of the target reply information is completed, hide the target window or shrink the target window.

[0124] By hiding or shrinking the target window, the occlusion of the interface content by the target window can be reduced, which affects the user's use. For example, when the target window is displayed on the specific display interface of an application, by hiding the target window or folding the target window, the occlusion of the display interface can be reduced, avoiding affecting the user's use of the display interface.

[0125] Exemplarily, when the first user wants to view the content in the target window again, the first user can click on the location of the target window. When the electronic device receives the input from the first user on the location of the target window, the target window can be completely displayed, and at this time, the first user can view the content in the target window again.

[0126] Exemplarily, the first user can also use voice or gestures or other means to make the electronic device display the content in the target window again.

[0127] In this embodiment, after the playback of the OWS headset ends, the target window can be dynamically adjusted, hidden or shrunk, to avoid the target window affecting the use of the electronic device by the first user.

[0128] To control the playback of the target reply information by the OWS headset, exemplarily, the session method may further include the following steps:

[0129] Receive a target input to the electronic device;

[0130] In response to the target input, control the OWS headset to perform an operation corresponding to the target input on the target reply information.

[0131] The target input here may be an input for controlling the OWS headset to play the target reply information. In some embodiments, the target input may include an input of a first user to a target window.

[0132] Exemplarily, when the first user long-presses the right half of the target window, the playback speed of the OWS headset can be controlled to increase. Each long-press doubles the playback speed, and so on. When the left half of the target window is long-pressed, the playback speed of the OWS headset can be controlled to decrease. Each long-press halves the speed, and so on.

[0133] Exemplarily, when the first user double-clicks the target window, the OWS headset can be controlled to pause playback. If it is already in the paused state, the OWS headset can continue to play after double-clicking.

[0134] Exemplarily, when the first user swipes up the target window, the OWS headset can be controlled to cancel the current playback, and the target window is hidden or reduced in display.

[0135] Exemplarily, when the first user clicks on the text in the target window, the OWS headset can be controlled to jump to the click position of the first user to start playing.

[0136] In some embodiments, the first user can also indicate whether they are satisfied with the target reply information by swiping the target window left or right. For example, when the first user swipes the target window to the left, it can indicate that the first user is not satisfied with the generated target reply information. At this time, the electronic device can adjust the parameters of the AI model, regenerate the target reply information and redisplay it. Again, when the first user swipes the target window to the right, it can indicate that the first user is satisfied with the generated target reply information, and the electronic device can continue to generate reply information using the current parameters of the AI model.

[0137] In some embodiments, the first user can also control the OWS headset through the physical keys of the electronic device.

[0138] Exemplarily, when the first user touches and holds the power key and the volume up key of the electronic device at the same time, the playback speed of the OWS headset can be controlled to increase. Each touch increases the playback speed by a factor of two, and so on. When the power key and the volume down key of the electronic device are touched and held at the same time, the playback speed of the OWS headset can be controlled to decrease. Each touch halves the speed, and so on.

[0139] Exemplarily, when the first user touches the volume up key and the volume down key of the electronic device simultaneously, the OWS headset can be controlled to cancel the current playback.

[0140] In some embodiments, the first user can also control the OWS headset by shaking the electronic device. For example, when the first user shakes the electronic device, the OWS headset can be controlled to pause the playback. If it is already in the paused state, the OWS headset can resume playback after shaking. Exemplarily, the first user can shake to the left, to the right, forward, backward, left and right, or forward and backward.

[0141] In some embodiments, the first user can also indicate whether they are satisfied with the target reply message by touching the volume button alone. For example, when the first user double-touches the volume down key, it can indicate that the first user is not satisfied with the generated target reply message. At this time, the electronic device can adjust the parameters of the AI model, regenerate the target reply message and redisplay it. For another example, when the first user double-touches the volume up key, it can indicate that the first user is satisfied with the generated target reply message, and the electronic device can continue to generate reply messages using the current parameters of the AI model.

[0142] This embodiment can control the electronic device through different control methods, and then control the OWS headset to perform different operations on the target reply message, improving the flexibility of the control method and meeting the control requirements of the OWS headset in different scenarios.

[0143] When the OWS headset is awakened, the first user can control the OWS headset to exit the auxiliary chat function by double-tapping the button on the left or right headset. At this time, the OWS headset no longer collects the sound in the environment and disconnects from the electronic device. Exemplarily, the first user can also control the OWS headset to exit the auxiliary chat function by voice. For example, the first user can issue a voice command "exit the auxiliary chat function". At this time, the OWS headset no longer collects the sound in the environment and disconnects from the electronic device.

[0144] This embodiment can assist the chat between users with the OWS headset, automatically collect the conversation information by the OWS headset and send it to the electronic device, and the electronic device returns the corresponding reply information to the OWS headset based on the conversation information, without interfering with the chat between users and without the user asking actively, enabling the user to enjoy the convenience of the AI model. While achieving good communication with others, it is not easily noticed by the other party.

[0145] Figure 8 The flowchart of another conversation method provided by the embodiment of the present application, this conversation method can be applied to the OWS headset, as Figure 8 shown, this conversation method can include the following steps:

[0146] S810. Collect the conversation information in the conversation scenario.

[0147] Among them, the conversation information includes at least one of the following: the voice information of the first user, the voice information of the second user. The first user and the second user are users in the conversation scenario, and the first user wears an open - type wearable headset.

[0148] S820. Send the conversation information to the electronic device so that the electronic device determines the target conversation scenario type and the role information of the corresponding user according to the conversation information, and determines the target reply information corresponding to the target conversation scenario type and role information.

[0149] S830. Receive the target reply information sent by the electronic device.

[0150] S840. Play the target reply information.

[0151] In this embodiment, the OWS headset can automatically collect conversation information. Without affecting the user's conversation, the OWS headset can communicate with the electronic device, timely obtain and play the reply information corresponding to the conversation information, assist the conversation between the first user and the second user, and improve the conversation effect. Moreover, playing the target reply information through the OWS headset is neither easily noticed by the other party nor interferes with the conversation between users, improving the use effect of the electronic device when the user is in a scenario of having a conversation with others and enhancing the conversation effect.

[0152] For specific details, reference can be made to the above - mentioned embodiments. For the sake of brevity, it will not be elaborated here.

[0153] In some embodiments, before S810, the conversation method may further include the following steps:

[0154] Receive a third input to the OWS headset;

[0155] In response to the third input, establish a communication connection between the OWS headset and the electronic device.

[0156] The third input is used to wake up the OWS headset. Exemplarily, the third input may include a long - press input by the first user on the left earphone or the right earphone of the OWS headset. When the OWS headset receives the third input, it can turn on the auxiliary chat function and establish a communication connection with the electronic device, providing a basis for subsequent assisting the user in chatting.

[0157] In this embodiment, by touching the left earphone or the right earphone of the OWS headset, the OWS headset can be quickly woken up, enabling the OWS headset to timely assist the user in chatting and improving the chatting effect.

[0158] It should be noted that for the conversation method provided in the embodiments of the present application, the execution subject can be a conversation device, or a processing module in the conversation device for executing the conversation method. In the embodiments of the present application, taking the conversation device as an example to execute the conversation method, the conversation device provided in the embodiments of the present application is described.

[0159] Figure 9 It is a schematic structural diagram of a conversation device provided in an embodiment of the present application. The conversation device 900 is applied to an electronic device, and the electronic device is communicatively connected to an OWS headset.

[0160] As Figure 9 shown, the conversation device 900 may include:

[0161] A receiving module 901, configured to receive conversation information sent by the OWS headset. The conversation information is the conversation information in the conversation scenario collected by the OWS headset, and the conversation information includes at least one of the following: voice information of the first user, voice information of the second user. The first user and the second user are users in the conversation scenario, and the first user wears the OWS headset;

[0162] A determining module 902, configured to determine the target conversation scenario type of the conversation scenario and the role information of the user according to the conversation information; determine the target reply information corresponding to the target conversation scenario type and role information;

[0163] A sending module 903, configured to send the target reply information to the OWS headset for playing, so that the first user can have a conversation with the second user based on the target reply information played by the OWS headset.

[0164] In this embodiment, the OWS headset can be used to automatically collect the conversation information between users and send it to the electronic device. The electronic device determines the target conversation scenario type of the conversation scenario and the role information of the user based on the conversation information, and generates the target reply information corresponding to the target conversation scenario type and role information, and then plays it through the OWS headset. There is no need for the user to actively initiate an inquiry to the electronic device. Thus, the user can timely obtain the reply information corresponding to the target conversation scenario type feedback by the electronic device. At the same time, playing the target reply information through the OWS headset is neither easily noticed by the other party nor will it interfere with the chat between users. Moreover, the generated reply information can change dynamically according to the type of the conversation scenario and the role information of the user, thereby helping the user to have a good conversation with others, improving the usage effect of the electronic device when the user is in a scenario of having a conversation with others, and improving the conversation effect.

[0165] In some possible implementations of the embodiments of the present application, the determining module 902 is specifically configured to:

[0166] Determine the target conversation scenario type between the first user and the second user according to the conversation keywords in the conversation information;

[0167] Determine the role information of the user corresponding to the session information according to the voiceprint feature of the session information.

[0168] In some possible implementations of the embodiments of the present application, the session device 900 may further include:

[0169] A display module, configured to display the target session scenario type after the determination module 902 determines the target session scenario type of the first user and the second user according to the session keywords of the session information; in response to a first input of the first user to the target session scenario type, display a scenario interface, where the scenario interface includes at least two candidate session scenario types pre-configured by the first user;

[0170] An update module, configured to update the target session scenario type to the target candidate session scenario type in response to a second input of the first user to the target candidate session scenario type, where the target candidate session scenario type is any one of the at least two candidate session scenario types other than the target session scenario type.

[0171] In some possible implementations of the embodiments of the present application, the determination module 902 is specifically configured to:

[0172] Determine the corresponding reply keyword according to the session information;

[0173] Generate a target reply information corresponding to the role information and the target session scenario type according to the reply keyword.

[0174] In some possible implementations of the embodiments of the present application, the display module is further configured to display a target window after the determination module 902 determines the target reply information corresponding to the target session scenario type and the role information; in the target window, display the first reply information in a first display manner and display the second reply information in a second display manner;

[0175] Wherein, the first reply information is the target reply information played by the OWS earphone, the second reply information is the target reply information not played by the OWS earphone, and the first display manner is different from the second display manner.

[0176] The session device in the embodiments of the present application can be a device or a component in an electronic device, such as an integrated circuit or a chip. Exemplarily, the electronic device can be a mobile phone, a tablet computer, a laptop computer, a handheld computer, a vehicle-mounted electronic device, a Mobile Internet Device (MID), an augmented reality (AR) / virtual reality (VR) device, a robot, a wearable device, an ultra-mobile personal computer (UMPC), a netbook, or a personal digital assistant (PDA), etc. It can also be a server, a Network Attached Storage (NAS), a personal computer (PC), a television (TV), a teller machine, or a self-service machine, etc. The embodiments of the present application do not make specific limitations.

[0177] The electronic device in the embodiments of the present application can be a terminal with an operating system. The operating system can be an Android operating system, an iOS operating system, or other possible operating systems. The embodiments of the present application do not make specific limitations.

[0178] The session device provided in the embodiments of the present application can implement Figures 1 to 7 each process in the session method embodiments and can achieve the same technical effects. To avoid repetition, it will not be elaborated here.

[0179] Figure 10 It is a schematic structural diagram of another session device provided in the embodiments of the present application. The session device 1000 is applied to an open-type wearable earphone. The session device 1000 can include:

[0180] An acquisition module 1001, configured to acquire session information in a session scenario. The session information includes at least one of the following: voice information of a first user, voice information of a second user. The first user and the second user are users in the session scenario, and the first user wears an OWS earphone;

[0181] A sending module 1002, configured to send the session information to an electronic device, so that the electronic device determines a target session scenario type and corresponding user role information according to the session information, and determines a target reply information corresponding to the target session scenario type and role information;

[0182] A receiving module 1003, configured to receive the target reply information sent by the electronic device;

[0183] A playback module 1004 for playing the target reply information.

[0184] In this embodiment, the OWS headset can be used to automatically collect conversation information. Without affecting the user's conversation, the OWS headset can communicate with the electronic device to timely obtain and play the reply information corresponding to the conversation information, assisting the conversation between the first user and the second user and improving the conversation effect. Moreover, playing the target reply information through the OWS headset is neither easily noticed by the other party nor interferes with the conversation between users, improving the usage effect of the electronic device when the user is in a scenario of having a conversation with others and enhancing the conversation effect.

[0185] In some possible implementations of the embodiments of the present application, the receiving module 1003 is further configured to receive a third input to the OWS headset before the acquisition module 1001 acquires the voice information in the preset environment;

[0186] The conversation device 1000 may further include:

[0187] A establishing module for establishing a communication connection between the OWS headset and the electronic device in response to the third input.

[0188] The conversation device provided by the embodiments of the present application can implement Figure 8 each process in the conversation method embodiments and achieve the same technical effects. To avoid repetition, details are not described here again.

[0189] As Figure 11 shown, the embodiments of the present application further provide an electronic device 1100, including a processor 1101 and a memory 1102. The memory 1102 stores a program or instruction that can run on the processor 1101. When the program or instruction is executed by the processor 1101, it implements each step of the above-mentioned conversation method embodiments and achieves the same technical effects. To avoid repetition, details are not described here again.

[0190] It should be noted that the electronic devices in the embodiments of the present application include the above-mentioned mobile terminals and non-mobile terminals.

[0191] Figure 12 It is a schematic hardware structure diagram of an electronic device provided by the embodiments of the present application.

[0192] The electronic device 1200 includes, but is not limited to: a radio frequency unit 1201, a network module 1202, an audio output unit 1203, an input unit 1204, a sensor 1205, a display unit 1206, a user input unit 1207, an interface unit 1208, a memory 1209, and a processor 1210, etc.

[0193] Those skilled in the art can understand that the electronic device 1200 may further include a power source (such as a battery) for supplying power to each component. The power source can be logically connected to the processor 1210 through a power management system, so as to manage functions such as charging, discharging, and power consumption management through the power management system. Figure 12 The structure of the electronic device 1200 shown in Figure 12 does not limit the electronic device 1200. The electronic device 1200 may include more or fewer components than shown in the figure, or combine some components, or have different component arrangements, which will not be elaborated here.

[0194] When the electronic device 1200 is the electronic device in the above Figure 1 or Figure 2 scenario, the functions of each component are as follows:

[0195] The processor 1210 is configured to receive the session information sent by the OWS headset. The session information is the session information in the session scenario collected by the OWS headset, and the session information includes at least one of the following: the voice information of the first user, the voice information of the second user. The first user and the second user are users in the session scenario, and the first user wears the OWS headset;

[0196] Determine the target session scenario type of the session scenario and the role information of the user according to the session information;

[0197] Determine the target reply information corresponding to the target session scenario type and role information;

[0198] Send the target reply information to the OWS headset for playback, so that the first user can have a conversation with the second user based on the target reply information.

[0199] This embodiment can automatically collect the session information between users by using the OWS headset and send it to the electronic device. The electronic device determines the target session scenario type of the session scenario and the role information of the user based on the session information, and generates the target reply information corresponding to the target session scenario type and role information, and then plays it through the open wearable headset. There is no need for the user to actively initiate an inquiry to the electronic device. Thus, the user can timely obtain the reply information corresponding to the target session scenario type feedback by the electronic device. At the same time, playing the target reply information through the OWS headset is neither easily noticed by the other party nor will it interfere with the chat between users. Moreover, the generated reply information can dynamically change with the type of the session scenario and the role information of the user, thereby helping the user to have a good conversation with others and improving the use effect of the electronic device when the user is in the scenario of having a conversation with others, and improving the conversation effect.

[0200] In some possible implementations of the embodiments of the present application, the processor 1210 is specifically configured to:

[0201] Determine the target conversation scenario type of the first user and the second user according to the conversation keywords in the conversation information;

[0202] Determine the role information of the user corresponding to the conversation information according to the voiceprint characteristics of the conversation information.

[0203] In some possible implementations of the embodiments of the present application, the display unit 1206 is configured to display the target conversation scenario type after the processor 1210 determines the target conversation scenario type of the first user and the second user according to the conversation keywords in the conversation information; in response to the first input of the first user for the target conversation scenario type, display a scenario interface, and the scenario interface includes at least two candidate conversation scenario types pre-configured by the first user;

[0204] The processor 1210 is further configured to update the target conversation scenario type to the target candidate conversation scenario type in response to the second input of the first user for the target candidate conversation scenario type, and the target candidate conversation scenario type is any one of the at least two candidate conversation scenario types other than the target conversation scenario type.

[0205] In some possible implementations of the embodiments of the present application, the processor 1210 is specifically configured to:

[0206] Determine the corresponding reply keyword according to the conversation information;

[0207] Generate a target reply message corresponding to the role information and the target conversation scenario type according to the reply keyword.

[0208] In some possible implementations of the embodiments of the present application, the display unit 1206 is further configured to display a target window after the processor 1210 determines the target reply message corresponding to the target conversation scenario type and the role information; in the target window, display the first reply message in a first display manner and display the second reply message in a second display manner;

[0209] Wherein, the first reply message is the target reply message played by the OWS earphone, the second reply message is the target reply message not played by the OWS earphone, and the first display manner is different from the second display manner.

[0210] It should be understood that in the embodiments of the present application, the input unit 1204 may include a Graphics Processing Unit (GPU) 12041 and a microphone 12042. The graphics processor 12041 processes the image data of static pictures or videos obtained by an image capture device (such as a camera) in a video capture mode or an image capture mode. The display unit 1206 may include a display panel 12061, and the display panel 12061 may be configured in the form of a liquid crystal display, an organic light emitting diode, or the like. The user input unit 1207 includes at least one of a touch panel 12071 and other input devices 12072. The touch panel 12071 is also referred to as a touch screen. The touch panel 12071 may include two parts: a touch detection device and a touch controller. The other input devices 12072 may include, but are not limited to, a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, and a joystick, which will not be elaborated here.

[0211] The memory 1209 can be used to store software programs and various data. The memory 1209 may mainly include a first storage area for storing programs or instructions and a second storage area for storing data. Among them, the first storage area may store an operating system, application programs or instructions required for at least one function (such as a sound playback function, an image playback function, etc.). In addition, the memory 1209 may include a volatile memory or a non-volatile memory, or the memory 1209 may include both a volatile memory and a non-volatile memory. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), a static random access memory (SRAM), a dynamic random access memory (DRAM), a synchronous dynamic random access memory (SDRAM), a double data rate synchronous dynamic random access memory (DDR SDRAM), an enhanced synchronous dynamic random access memory (ESDRAM), a synchlink dynamic random access memory (SLDRAM), and a direct rambus random access memory (DRRAM). The memory 1209 in the embodiments of the present application includes but is not limited to these and any other suitable types of memories.

[0212] The processor 1210 may include one or more processing units; optionally, the processor 1210 integrates an application processor and a modem processor. Among them, the application processor mainly processes operations related to the operating system, user interface, and application programs, etc., and the modem processor mainly processes wireless communication signals, such as a baseband processor. It can be understood that the above modem processor may not be integrated into the processor 1210.

[0213] The embodiments of the present application also provide a readable storage medium. A program or instruction is stored on the readable storage medium. When the program or instruction is executed by a processor, it implements each process of the above session method embodiment and can achieve the same technical effect. To avoid repetition, it will not be elaborated here.

[0214] Among them, the processor is the processor in the electronic device described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory ROM, random access memory RAM, magnetic disks, or optical discs, etc.

[0215] Another embodiment of the present application provides a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is used to run programs or instructions to implement each process of the above embodiment of the session method, and can achieve the same technical effects. To avoid repetition, it will not be elaborated here.

[0216] It should be understood that the chip mentioned in the embodiments of the present application may also be referred to as a system-on-chip, system chip, chip system, or system-on-chip, etc.

[0217] The embodiments of the present application provide a computer program product. The program product is stored in a storage medium and is executed by at least one processor to implement each process of the above embodiment of the session method, and can achieve the same technical effects. To avoid repetition, it will not be elaborated here.

[0218] It should be noted that in this article, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device. Without further limitations, an element defined by the statement "including a..." does not exclude the existence of additional identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in a reverse order according to the functions involved. For example, the described methods may be performed in an order different from that described, and various steps may be added, omitted, or combined. Additionally, the features described with reference to certain examples may be combined in other examples.

[0219] Through the description of the above embodiments, those skilled in the art can clearly understand that the above embodiment methods can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation. Based on such an understanding, the technical solution of the present application in essence or the part that contributes to the related technology can be embodied in the form of a computer software product. The computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disc) and includes several instructions to enable a terminal (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in various embodiments of the present application.

[0220] The embodiments of the present application have been described above in conjunction with the accompanying drawings. However, the present application is not limited to the above specific embodiments. The above specific embodiments are merely illustrative and not restrictive. Under the inspiration of the present application, those of ordinary skill in the art can also make many forms without departing from the purpose of the present application and the scope protected by the claims, and all of them fall within the protection scope of the present application.

Claims

1. A session method, applied to an electronic device, characterized in that, The electronic device is communicatively connected to an open wearable headphone (OWS), and the method includes: Receiving session information sent by the OWS headphone, where the session information is session information in a session scenario collected by the OWS headphone, and the session information includes at least one of the following: Voice information of a first user, voice information of a second user; Wherein, the first user and the second user are users in the session scenario, and the first user wears the OWS headphone; Determining a target session scenario type of the session scenario and role information of the user according to the session information; Determining target reply information corresponding to the target session scenario type and the role information; Sending the target reply information to the OWS headphone for playback, so that the first user can have a conversation with the second user based on the target reply information.

2. The method according to claim 1, characterized in that, The determining the target session scenario type of the session scenario and the role information of the user according to the session information includes: Determining the target session scenario type of the first user and the second user according to the session keywords of the session information; Determining role information of the user corresponding to the session information according to the voiceprint feature of the session information.

3. The method according to claim 2, wherein After determining the target session scenario type of the first user and the second user according to the session keywords of the session information, the method further includes: Displaying the target session scenario type; In response to a first input of the first user to the target session scenario type, displaying a scenario interface, where the scenario interface includes at least two candidate session scenario types pre-configured by the first user; In response to a second input of the first user to a target candidate session scenario type, updating the target session scenario type to the target candidate session scenario type, where the target candidate session scenario type is any one of the at least two candidate session scenario types other than the target session scenario type.

4. The method according to any one of claims 1 to 3, characterized in that, The determining the target reply information corresponding to the target session scenario type and the role information includes: Determining corresponding reply keywords according to the session information; Generating target reply information corresponding to the role information and the target session scenario type according to the reply keywords.

5. The method according to any one of claims 1 to 3, characterized in that, After determining the target reply information corresponding to the target session scenario type and the role information, the method further includes: Displaying a target window; In the target window, displaying first reply information in a first display manner and second reply information in a second display manner; Wherein, the first reply information is the target reply information that has been played by the OWS headphone, the second reply information is the target reply information that has not been played by the OWS headphone, and the first display manner is different from the second display manner.

6. A session device, applied to an electronic device, characterized in that The electronic device is communicatively connected to an open wearable headphone (OWS), and the apparatus includes: A receiving module, configured to receive session information sent by the OWS headphone, where the session information is session information in a session scenario collected by the OWS headphone, and the session information includes at least one of the following: Voice information of a first user, voice information of a second user; Wherein, the first user and the second user are users in the session scenario, and the first user wears the OWS headset; A determination module, configured to determine a target session scenario type of the session scenario and role information of the user according to the session information; determine target reply information corresponding to the target session scenario type and the role information; A sending module, configured to send the target reply information to the OWS headset for playing, so that the first user conducts a session with the second user based on the target reply information.

7. The device according to claim 6, characterized in that, The determination module is specifically configured to: Determine the target session scenario type of the first user and the second user according to the session keywords of the session information; Determine the role information of the user corresponding to the session information according to the voiceprint feature of the session information.

8. The device according to claim 7, characterized in that The device further includes: A display module, configured to display the target session scenario type after the determination module determines the target session scenario type of the first user and the second user according to the session keywords of the session information; in response to a first input of the first user to the target session scenario type, display a scenario interface, where the scenario interface includes at least two candidate session scenario types pre-configured by the first user; An update module, configured to update the target session scenario type to the target candidate session scenario type in response to a second input of the first user to the target candidate session scenario type, where the target candidate session scenario type is any one of the at least two candidate session scenario types other than the target session scenario type.

9. The device according to any one of claims 6 - 8, characterized in that, The determination module is specifically configured to: Determine corresponding reply keywords according to the session information; Generate target reply information corresponding to the role information and the target session scenario type according to the reply keywords.

10. The device according to any one of claims 6 - 8, characterized in that The display module in the device is configured to display a target window after the determination module determines the target reply information corresponding to the target session scenario type and the role information; in the target window, display first reply information in a first display manner and display second reply information in a second display manner; Wherein, the first reply information is the target reply information that has been played by the OWS headset, the second reply information is the target reply information that has not been played by the OWS headset, and the first display manner is different from the second display manner.

Images