Data processing method and device

Abstract

The invention discloses a data processing method and device, and the method is applied to second electronic equipment, and comprises the steps: obtaining first interaction data corresponding to at least one piece of first electronic equipment; the second electronic device has a communication relationship with the at least one first electronic device; responding to the condition that the first interaction data meets a first condition, and obtaining second interaction data corresponding to the second electronic equipment; the second interaction data comprises audio data with audio features matched with a second object of the second electronic equipment, and the audio data is obtained in a generation mode; and sending the second interaction data to the at least one first electronic device.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a data processing method and device. Background Art

[0002] Currently, users may be unable to attend scheduled meetings due to travel conflicts, resulting in missed meetings. Summary of the invention

[0003] In view of this, the present application provides a data processing method and device as follows:

[0004] A data processing method, applied to a second electronic device, comprising:

[0005] Obtaining first interaction data corresponding to at least one first electronic device; the second electronic device has a communication relationship with the at least one first electronic device;

[0006] In response to the first interaction data satisfying the first condition, obtaining second interaction data corresponding to the second electronic device; the second interaction data includes audio data whose audio features match the second object of the second electronic device, and the audio data is obtained by generating;

[0007] The second interaction data is sent to the at least one first electronic device.

[0008] Preferably, the method of obtaining the second interaction data corresponding to the second electronic device includes:

[0009] searching for first information matching the first interaction data;

[0010] Obtaining second interaction data according to second information corresponding to first information matching the first interaction data;

[0011] The first information and the second information are related to an application scenario in which the communication relationship exists, and the first information and the second information are obtained based on a preset operation of the second object.

[0012] The above method preferably obtains the second interaction data according to the second information corresponding to the first information matching the first interaction data, including:

[0013] According to the second information corresponding to the first information matching the first interaction data, corresponding audio data is generated to obtain second interaction data.

[0014] The above method preferably obtains the second interaction data according to the second information corresponding to the first information matching the first interaction data, including:

[0015] According to the first interaction data, adjusting the second information corresponding to the first information matching the first interaction data to obtain third information;

[0016] According to the third information, corresponding audio data is generated to obtain second interaction data.

[0017] In the above method, preferably, the tone feature corresponding to the audio data in the second interaction data matches the tone feature of the first interaction data.

[0018] The above method preferably adjusts the second information corresponding to the first information matching the first interaction data according to the first interaction data to obtain the third information, including:

[0019] Obtaining target content related to the application scenario in the first interaction data; the target content is related to first information matching the first interaction data;

[0020] Corresponding third information is generated according to the target content and the second information corresponding to the first information matching the first interaction data.

[0021] In the above method, preferably, when no first information matching the first interaction data is found, the method further comprises:

[0022] outputting an input prompt interface for the second object;

[0023] receiving input text input by the second object through the input prompt interface;

[0024] According to the input text, corresponding audio data is generated to obtain second interaction data.

[0025] In the above method, preferably, the second interaction data further includes: at least one of text data and picture data matching the first interaction data.

[0026] In the above method, preferably, when obtaining the second interaction data, the target icon is in a state indicating that voice input is turned on, and / or the physical audio collection device of the second electronic device is in a turned off state;

[0027] Wherein, the target icon is displayed on the output interface of the electronic device.

[0028] A data processing device, comprising:

[0029] A first obtaining unit is used to obtain first interaction data corresponding to at least one first electronic device; the second electronic device has a communication relationship with the at least one first electronic device;

[0030] A second obtaining unit, configured to obtain second interaction data corresponding to the second electronic device in response to the first interaction data satisfying a first condition; the second interaction data includes audio data whose audio features match a second object of the second electronic device, and the audio data is obtained by generating;

[0031] An interaction sending unit is used to send the second interaction data to the at least one first electronic device.

[0032] An electronic device, serving as a second electronic device, comprises:

[0033] A communication device, used to establish a communication relationship with at least one first electronic device;

[0034] a processor, configured to obtain first interaction data corresponding to at least one first electronic device, obtain second interaction data corresponding to the second electronic device in response to the first interaction data satisfying a first condition, and send the second interaction data to the at least one first electronic device;

[0035] The second interaction data includes audio data whose audio features match the second object of the second electronic device, and the audio data is obtained by generating.

[0036] The above electronic device preferably further includes:

[0037] Display device and / or physical audio acquisition device;

[0038] When the processor obtains the second interaction data, the display device is used to display a target icon, where the target icon is in a state indicating that the voice input is turned on;

[0039] When the processor obtains the second interaction data, the physical audio collection device is in a closed state. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0041] Figure 1 A flowchart of a data processing method provided in an embodiment of the present application;

[0042] Figure 2 This is an example diagram of a first electronic device and a second electronic device in an embodiment of the present application;

[0043] Figure 3This is an example diagram of device 1, device 2, device 3 and device 4 in a conference scenario applicable to an embodiment of the present application;

[0044] Figure 4 This is an example diagram of device 1 and device 2 in a conference scenario applicable to an embodiment of the present application;

[0045] Figure 5 A partial flow chart of a data processing method provided in an embodiment of the present application;

[0046] Figure 6 Another partial flow chart of a data processing method provided in an embodiment of the present application;

[0047] Figure 7 This is an example diagram of the input prompt interface in the embodiment of the present application;

[0048] Figure 8 This is an example diagram of the output interface of the conference participant device in the embodiment of the present application;

[0049] Fig. 9 A schematic diagram of the structure of a data processing device provided in an embodiment of the present application;

[0050] Fig.10 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application;

[0051] Fig.11 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application;

[0052] Fig.12 This is an example diagram of a scenario where this application is applicable to voice conference participation on a mobile phone;

[0053] Fig.13 This is a data processing diagram for voice conference participation using a mobile phone applicable to this application. DETAILED DESCRIPTION

[0054] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0055] refer to Figure 1 , is a flowchart of a data processing method provided in an embodiment of the present application, which can be applied to an electronic device that can process data and establish a communication connection with other electronic devices. Figure 2The second electronic device shown. The second electronic device has a communication relationship with at least one first electronic device. The corresponding application scenarios, such as conference scenarios or game scenarios, are realized through the communication relationship between multiple electronic devices. The communication relationship between electronic devices can be established based on the local area network in which the electronic devices are located. The technical solution in this embodiment is mainly used to realize the interaction between the interactive objects of electronic devices.

[0056] Specifically, the method in this embodiment may include the following steps:

[0057] Step 101: Obtain first interaction data corresponding to at least one first electronic device.

[0058] The first electronic device and the second electronic device may be devices such as mobile phones, tablet devices or notebooks that can collect and output data.

[0059] like Figure 3 As shown in , device 1, device 2, device 3 and device 4 respectively install conference applications, and device 1, device 2, device 3 and device 4 establish communication relationships in the Internet through the conference application. Device 1, device 2, device 3 and device 4 each have one or more interactive objects, i.e., participants. Therefore, the interactive objects of device 1, device 2, device 3 and device 4 each participate in the meeting through online applications. The theme of the meeting is A. The second electronic device in this embodiment can be any device among device 1, device 2, device 3 and device 4, and the first electronic device is other devices among device 1, device 2, device 3 and device 4 except the second electronic device.

[0060] like Figure 4 As shown in , device 1 and device 2 are respectively installed with conference applications, and device 1 and device 2 establish a communication relationship in the Internet through the conference application. Device 1 has multiple interaction objects such as b1, and device 2 has one interaction object such as b2. The multiple interaction objects of device 1 are real people attending the meeting, and the interaction objects of device 2 attend the meeting through online applications. The theme of the meeting is B. The second electronic device in this embodiment can be device 2, and the first electronic device is device 1.

[0061] It should be noted that the interactive object of the electronic device can be a real person or a digital person. The digital person is a virtual object built based on the real person. An electronic device can have one or more interactive objects.

[0062] For example, Figure 4For example, on the conference interface of the conference application of device 1, the video image of the real person b2 of the interactive object of device 2 can be output, and b2 is participating in the conference in real person; or, on the conference interface of the conference application of device 1, the video image of the digital person of b2 can be output, and b2 is participating in the conference through the digital person; or, on the conference interface of the conference application of device 1, the default image corresponding to b2 can be output to indicate that b2 is participating in the conference through audio. In this way, participants can participate in the conference through real people, digital people or audio data.

[0063] Specifically, the first interaction data may include voice data of the first object (interaction object) of the first electronic device, action data of the interaction object, text data provided by the interaction object, image data provided by the interaction object, video data provided by the interaction object, and other interaction data.

[0064] For example, Figure 4 For example, device 1 is a first electronic device, and device 2 is a second electronic device. On device 2, the microphone of device 1 collects voice data input by a participant of device 1 through a conference application, the camera of device 1 collects motion data of the participant of device 1, and the conference content provided by the participant of device 1, such as text, images, and videos, is obtained through the conference application.

[0065] Step 102: In response to the first interaction data satisfying the first condition, obtaining second interaction data corresponding to the second electronic device.

[0066] The second interaction data includes audio data whose audio features match the second object (interaction object) of the second electronic device.

[0067] In one implementation, the first condition includes: the first interaction data is identified as a second object corresponding to the second electronic device. Figure 4 For example, on device 2, after receiving the first interaction data sent by device 1, it is recognized that the voice data of the first interaction data contains keywords that match the second object, such as "Zhang San, tell me what you think" matches the participant name "Zhang San" of the second object b2; for another example, it is recognized that the video data of the first interaction data contains a picture of the first object pointing to the second object, such as b1 of device 1 pointing to the screen in its video picture, and the default image of b2 is on the screen.

[0068] The audio data is obtained by generation. In a specific implementation, in this embodiment, the audio data can be generated by an intelligent model capable of realizing audio generation, and the audio features of the audio data match the second object of the second electronic device. The audio features of the audio data may include features such as voiceprint features that can uniquely characterize the interactive object.

[0069] For example, Figure 4 For example, on device 2, after recognizing that the voice data of the first interaction data "Zhang San, tell me what you think" matches b2 "Zhang San", the intelligent model is used to generate the audio data of the voiceprint matching "Zhang San".

[0070] Step 103: Send second interaction data to at least one first electronic device.

[0071] The first electronic device can output the audio data in the second interactive data, so that the first object of the first electronic device can listen to the audio data of the second object of the second device, thereby realizing the audio expression of the second object to the first object and realizing the interaction.

[0072] For example, Figure 4 For example, the audio data of the voiceprint matching "Zhang San" is generated on device 2. Then, the audio data is sent to device 1, and the audio data of the voiceprint matching "Zhang San" is output on device 1. For the participants of device 1, they can hear the voice expression of Zhang San, and the interaction between Zhang San and the participants of device 1 is realized.

[0073] In one implementation, the second interaction data may further include: at least one of text data and image data matching the first interaction data. For example, the text data may be bullet text, and the image data may be static images or dynamic images such as emoticon images.

[0074] For example, Figure 4 For example, after generating audio data of voiceprint matching "Zhang San" on device 2, the audio data is sent to device 1, and the emoticon package of "smiley face" can also be sent to device 1. Device 1 outputs the audio data of voiceprint matching "Zhang San". For the participants of device 1, they can listen to Zhang San's voice expression and see Zhang San's emoticon package, realizing the interaction between Zhang San and the participants of device 1.

[0075] It can be seen from the above technical scheme that in a data processing method provided by an embodiment of the present application, on any current electronic device among multiple electronic devices with a communication relationship, the interaction data corresponding to other electronic devices can be obtained, and then when the interaction data is in accordance with the first condition, the audio data corresponding to the audio characteristics of the current electronic device and matching the interaction object of the electronic device is obtained by generating, and it is sent to other electronic devices as interaction data. It can be seen that in the present application, even if the interaction object of the current electronic device cannot interact with the interaction object of other electronic devices through the electronic device, audio data matching the interaction object can be generated for the interaction object by generating, so that it is fed back to other electronic devices as interaction data, so that for the interaction objects of other electronic devices, the current interaction object can interact through audio participation, thereby achieving the purpose of the present application.

[0076] In one implementation, the second object may be pre-configured with first information and second information corresponding to the first information. The first information and the second information are related to an application scenario in which the communication relationship exists, and the first information and the second information are obtained based on a preset operation of the second object.

[0077] Specifically, the first information and the second information may be stored in the storage area corresponding to the second object. For example, taking the application scenario in which the communication relationship is located as a conference scenario as an example, the first information may be a preset question, and the second information may be a preset answer corresponding to the preset question. The preset question and the preset answer are both related to the conference theme of the current conference scenario. Taking the theme of "sales summary meeting" as an example, the preset question may be "total sales in December", and the corresponding preset answer may be "235,698 yuan". These preset questions and preset answers are stored in b2's private knowledge base, and b2's private knowledge base is in a specific folder corresponding to b2. The preset questions and preset answers in b2's private knowledge base are all set by b2 in advance for the conference theme. b2 can set the preset questions and corresponding preset answers before the conference scenario starts, so that the audio data in the second interactive data can be generated on device 2 according to these preset answers and preset questions. After outputting to device 1, b1 of device 1 can listen to the voice replied by b2 for the conference theme.

[0078] Based on the above implementation, when obtaining the second interaction data corresponding to the second electronic device in step 102, it can be implemented in the following manner: Figure 5 As shown in:

[0079] Step 501: Search for first information matching first interaction data.

[0080] For example, Figure 4 For example, in this embodiment, device 2 can search b2's private knowledge base for a preset question "Total sales in December" that matches b1's first interaction data "You said the total for last month".

[0081] For example, Figure 4 For example, in this embodiment, device 2 can search b2's private knowledge base for a preset question "total sales in December" that matches b1's first interaction data "what do you think of the sales changes in the past two months?".

[0082] Step 502: Obtain second interaction data according to second information corresponding to first information matching the first interaction data.

[0083] For example, Figure 4For example, in this embodiment, for the first interactive data "What do you think of last month's total", device 2 can generate audio data in the second interactive data, such as voice data of "235,698 yuan", based on the preset answer "235,698 yuan" corresponding to "total sales in December".

[0084] For example, Figure 4 For example, in this embodiment, for the first interactive data "What do you think of the sales changes in the past two months", device 2 can generate audio data in the second interactive data based on the preset answer "235,698 yuan" corresponding to the "total sales in December", such as the voice data of "December increased by 5,364 yuan compared to November".

[0085] In one implementation, step 502 may be implemented in the following manner:

[0086] According to the second information corresponding to the first information matching the first interaction data, corresponding audio data is generated to obtain the second interaction data.

[0087] For example, Figure 4 For example, in this embodiment, for the first interaction data "What do you think of last month's total?", device 2 can directly generate audio according to the preset answer "235,698 yuan" corresponding to "total sales in December" to obtain second interaction data, such as voice data of "235,698 yuan". After the second interaction data is transmitted to device 1, b1 of device 1 can hear the total sales of last month, i.e., December, expressed by b2 through voice.

[0088] In another implementation, step 502 may be implemented in the following manner:

[0089] First, based on the first interaction data, the second information corresponding to the first information matching the first interaction data is adjusted to obtain third information; then, based on the third information, corresponding audio data is generated, for example, by directly using an intelligent model to generate audio for the third information to obtain the second interaction data.

[0090] Among them, the tone feature corresponding to the audio data in the second interactive data matches the tone feature of the first interactive data. The tone feature can characterize the emotional type of the interactive object. For example, if the voice of b1 in the first interactive data transmitted by device 1, "Our company's performance has increased a lot", is in a happy tone, then device 2 generates the corresponding audio data "Yes, yes" in a happy tone and transmits it to device 1 to match the emotion of b1; for another example, if the voice of b1 in the first interactive data transmitted by device 1, "Our sales this month have dropped a lot", is in a happy tone, then the second electronic device such as device 2 generates the corresponding audio data "Indeed, it is" in a depressed tone and transmits it to device 1 to match the emotion of b1.

[0091] Based on the above implementation, when obtaining the third information in step 502, it can be specifically implemented in the following manner:

[0092] First, target content related to the application scenario is obtained in the first interaction data, where the target content is related to the first information matching the first interaction data; then, corresponding third information is generated using the target model based on the second information corresponding to the target content and the first information matching the first interaction data.

[0093] Among them, the target model can be a text generation model that can perform data processing. The target model generates third information for the target content and the second information. It should be noted that the target content is not only related to the first information that matches the first interactive data, but also related to the content corresponding to the second object in the first interactive data. The content corresponding to the second object in the first interactive data can be understood as the content of the question asked to the second object in the first interactive data. For example, the first interactive data contains "November total sales 230334" and "October total sales 204278", of which "November total sales 230334" is related to "What do you think of the sales changes in the previous two months?" At this time, "November total sales 230334" is the target content.

[0094] For example, for the first interactive data "What do you think about the sales changes in the past two months?", device 2 can extract target content such as "November sales total 230334" related to the meeting theme "sales summary meeting" and "What do you think about the sales changes in the past two months" from the first interactive data according to the preset answer "235698 yuan" corresponding to "December sales total". After that, the text generation model is used to generate text for "November sales total 230334" and the preset answer "235698 yuan" according to "What do you think about the sales changes in the past two months" to obtain third information such as "December increased by 5364 yuan compared to November". Then, the intelligent model is used to generate corresponding audio data based on "December increased by 5364 yuan compared to November", such as voice data of "December increased by 5364 yuan compared to November". After the second interactive data is transmitted to device 1, b1 of device 1 can listen to the sales change of 5364 yuan in December expressed by b2 through voice.

[0095] Based on the above implementation, when obtaining the second interaction data corresponding to the second electronic device in step 102, if the first information matching the first interaction data is not found, the following processing may be performed, such as Figure 6 As shown in:

[0096] Step 601: output an input prompt interface for the second object.

[0097] In this embodiment, an input prompt interface may be output on the second electronic device to prompt the second object to perform input in the input prompt interface.

[0098] For example, Figure 7 As shown in , if no preset answer matching "What about the sales changes in the past two months" is found in b2's private knowledge base, a prompt message "Please reply to the question in time" can be output on the input prompt interface of device 2, and b2 can enter the corresponding text for "What about the sales changes in the past two months", such as "December increased by 5,364 yuan compared to November".

[0099] Step 602: receiving input text input by the second object through the input prompt interface.

[0100] In this embodiment, the input text of the second object can be received through the transmission interface in the input prompt interface.

[0101] For example, device 2 receives the text "December increased by 5364 yuan compared to November" input by b2 on the input prompt interface.

[0102] Step 603: Generate corresponding audio data according to the input text to obtain second interaction data.

[0103] Among them, in this embodiment, the audio can be directly generated from the input text through the intelligent model to obtain the audio data in the second interactive data.

[0104] For example, in this embodiment, the intelligent model is used to generate corresponding audio data based on "December increased by 5,364 yuan compared to November", such as voice data of "December increased by 5,364 yuan compared to November". After the second interactive data is transmitted to device 1, b1 of device 1 can hear the sales change of 5,364 yuan in December compared to November expressed by b2 through voice.

[0105] Therefore, in this embodiment, when the first information matching the first interaction data is not found, the user is promptly reminded to input the content manually, so as to avoid the situation in which the second object in the application scenario cannot interact.

[0106] In another implementation, when obtaining the second interaction data corresponding to the second electronic device in step 102, if the first information matching the first interaction data is not found, the preset audio data may also be used as the audio data in the second interaction data.

[0107] For example, if no preset answer matching "What about the sales changes in the past two months" is found in b2's private knowledge base, the threshold audio data "I have recorded this question and will answer you after the meeting" can be used as the audio data in the second interaction data. In this way, after the second interaction data is transmitted to device 1, b1 of device 1 can hear the voice of b2 expressing his reply to the question after the meeting.

[0108] In one implementation, when the second interaction data is obtained in step 102, the target icon presented on the electronic device, such as the first electronic device and the second electronic device, is in a state where voice input is turned on, and / or the physical audio collection device of the second electronic device is in a turned off state. The target icon is an icon representing whether the second object of the second electronic device performs voice input.

[0109] The target icon is displayed on the output interface of the electronic device, and the target icon can be used to prompt the second object whether to perform voice input. When the target icon is in the voice input on state, it can prompt the second object that voice input can be performed. Further, the target icon can flash or otherwise prompt the second object that voice input is currently being performed or that the second object is not currently performing voice input; when the target icon is in the voice input off state, it can prompt the second object that voice input cannot be performed.

[0110] The physical audio collection device of the second electronic device refers to a physical device capable of audio collection, such as a physical microphone. A virtual audio collection device, such as a virtual microphone, may also be deployed in the second electronic device for the physical audio collection device.

[0111] It should be noted that the target icon corresponding to the second electronic device can be associated with a physical audio acquisition device to indicate whether the physical audio acquisition device performs audio acquisition, that is, whether the second object performs voice input. Alternatively, the target icon corresponding to the second electronic device can also be associated with a virtual audio acquisition device to indicate whether the virtual audio acquisition device performs audio acquisition, that is, whether the second object performs voice input. In this embodiment, in response to the second electronic device being in the first mode, the target icon can be controlled to be associated with the virtual audio acquisition device, and the target icon indicates whether the second object performs voice input. The first mode is a mode corresponding to the application scenario in which the communication relationship is located, and the first mode can be set by the second object. If the second object does not set the second electronic device to be in the first mode, then the second electronic device is in the second mode. At this time, the target icon is associated with the physical audio acquisition device. At this time, the target icon also indicates whether the second object performs voice input.

[0112] In one case, the target icon is in a state indicating that voice input is turned on, the second electronic device sends the second interaction data to the first electronic device, and the first electronic device outputs the audio data therein, thereby realizing audio interaction between the first object and the second object;

[0113] In another case, the physical audio collection device of the second electronic device is in a closed state, so as to avoid transmitting the audio data in the environment where the second electronic device is located to the first electronic device for output;

[0114] In another case, the target icon is in a state representing that voice input is turned on, and at the same time, the physical audio acquisition device of the second electronic device is in a turned off state. In this way, the second electronic device sends the second interaction data to the first electronic device, and the first electronic device outputs the audio data but does not output the audio data in the environment where the second electronic device is located, thereby realizing audio interaction between the second object and the first object.

[0115] For example, Figure 8 As shown in , each output interface of device 1 and device 2 has a microphone icon corresponding to device 1 and device 2, and the icon status of the microphone icon of device 2 is used to prompt b2 whether to perform voice input. In one case, the microphone icon is in a state indicating that voice input is turned on, and device 2 sends the voice data of "December increased by 5,364 yuan compared to November" to device 1, and device 1 outputs the voice data to achieve interaction between b2 and b1; in another case, the physical microphone of device 2 is in a closed state to avoid outputting the voice in the environment where device 2 is located in device 1; in another case, the microphone icon is in a state indicating that voice input is turned on, and at the same time, the physical microphone of device 2 is in a closed state, so that device 2 sends the voice data of "December increased by 5,364 yuan compared to November" to device 1, and device 1 outputs the voice data and does not output the voice in the environment where device 2 is located, to achieve interaction between b2 and b1.

[0116] In one implementation, the second electronic device may also send target audio data related to the application scenario corresponding to the communication relationship to the first electronic device when the interaction condition is met.

[0117] The interaction condition may be: no audio data of the first object is recognized in the first interaction data within the target duration.

[0118] For example, after the meeting starts, device 2 continues to receive the first interaction data of device 1, but does not recognize b1 speaking within 2 minutes. At this time, device 2 can send audio data of "I will tell you some news first" to device 1, so that b2 can actively share the message content with b1.

[0119] refer to Fig. 9 , is a schematic diagram of the structure of a data processing device provided in an embodiment of the present application, which can be deployed in an electronic device that can perform data processing and establish a communication connection with other electronic devices. Figure 2 The second electronic device shown. The second electronic device has a communication relationship with at least one first electronic device. The corresponding application scenarios, such as conference scenarios or game scenarios, are realized through the communication relationship between multiple electronic devices. The communication relationship between electronic devices can be established based on the local area network in which the electronic devices are located. The technical solution in this embodiment is mainly used to realize the interaction between the interactive objects of electronic devices.

[0120] Specifically, the device in this embodiment may include the following units:

[0121] The first obtaining unit 901 is used to obtain first interaction data corresponding to at least one first electronic device; the second electronic device has a communication relationship with the at least one first electronic device;

[0122] A second obtaining unit 902 is configured to obtain second interaction data corresponding to the second electronic device in response to the first interaction data satisfying the first condition; the second interaction data includes audio data whose audio features match the second object of the second electronic device, and the audio data is obtained by generating;

[0123] The interaction sending unit 903 is configured to send the second interaction data to the at least one first electronic device.

[0124] It can be seen from the above technical scheme that in a data processing device provided by an embodiment of the present application, on any current electronic device among multiple electronic devices with a communication relationship, the interaction data corresponding to other electronic devices can be obtained, and then when the interaction data is in accordance with the first condition, the audio data corresponding to the audio characteristics of the current electronic device and matching the interaction object of the electronic device is obtained by generating, and it is sent to other electronic devices as interaction data. It can be seen that in the present application, even if the interaction object of the current electronic device cannot interact with the interaction object of other electronic devices through the electronic device, audio data matching the interaction object can be generated for the interaction object by generating, so that it is fed back to other electronic devices as interaction data, so that for the interaction objects of other electronic devices, the current interaction object can interact through audio participation, thereby achieving the purpose of the present application.

[0125] In one implementation, the second obtaining unit 902 is specifically configured to: search for first information matching the first interaction data; obtain second interaction data according to second information corresponding to the first information matching the first interaction data;

[0126] The first information and the second information are related to an application scenario in which the communication relationship exists, and the first information and the second information are obtained based on a preset operation of the second object.

[0127] Among them, when the second obtaining unit 902 obtains the second interaction data according to the second information corresponding to the first information matching the first interaction data, it is specifically used to: generate corresponding audio data according to the second information corresponding to the first information matching the first interaction data to obtain the second interaction data.

[0128] In one implementation, when the second obtaining unit 902 obtains the second interaction data based on the second information corresponding to the first information matching the first interaction data, it is specifically used to: adjust the second information corresponding to the first information matching the first interaction data based on the first interaction data to obtain third information; and generate corresponding audio data based on the third information to obtain the second interaction data.

[0129] Among them, the tone feature corresponding to the audio data in the second interaction data matches the tone feature of the first interaction data.

[0130] In one implementation, when the second obtaining unit 902 adjusts the second information corresponding to the first information matching the first interaction data according to the first interaction data to obtain the third information, it is specifically used to: obtain target content related to the application scenario in the first interaction data; the target content is related to the first information matching the first interaction data; and generate corresponding third information based on the target content and the second information corresponding to the first information matching the first interaction data.

[0131] In one implementation, when the second obtaining unit 902 fails to find the first information matching the first interaction data, it is also used to: output an input prompt interface for the second object; receive input text input by the second object through the input prompt interface; and generate corresponding audio data based on the input text to obtain second interaction data.

[0132] The second interaction data further includes: at least one of text data and picture data matching the first interaction data.

[0133] In one implementation, when obtaining the second interaction data, the target icon is in a state representing that voice input is turned on, and / or the physical audio acquisition device of the second electronic device is in a turned off state; wherein the target icon is displayed on the output interface of the electronic device.

[0134] It should be noted that the specific implementation of each unit in this embodiment can refer to the corresponding content in the previous text and will not be described in detail here.

[0135] refer to Fig.10 , is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device may be a second electronic device such as a mobile phone, a tablet device or a notebook device that can establish a communication connection with at least one first electronic device, such as Figure 2 The technical solution in this embodiment is mainly used to realize the interaction between interactive objects of electronic devices.

[0136] Specifically, the electronic device in this embodiment as the second electronic device may include the following structure:

[0137] A communication device 1001, such as an antenna, is used to establish a communication relationship with at least one first electronic device;

[0138] Processor 1002 is used to obtain first interaction data corresponding to at least one first electronic device; the second electronic device has a communication relationship with the at least one first electronic device; in response to the first interaction data satisfying a first condition, second interaction data corresponding to the second electronic device is obtained; the second interaction data includes audio data whose audio features match the second object of the second electronic device, and the audio data is obtained by generating; and the second interaction data is sent to the at least one first electronic device through the communication module 1002.

[0139] It can be seen from the above technical solution that in an electronic device provided by an embodiment of the present application, on any current electronic device among multiple electronic devices with a communication relationship, the interaction data corresponding to other electronic devices can be obtained, and then when the interaction data is in accordance with the first condition, the audio data corresponding to the audio characteristics of the current electronic device and matching the interaction object of the electronic device is obtained by generating, and it is sent to other electronic devices as interaction data. It can be seen that in the present application, even if the interaction object of the current electronic device cannot interact with the interaction object of other electronic devices through the electronic device, audio data matching the interaction object can be generated for the interaction object by generating, so that it is fed back to other electronic devices as interaction data, so that for the interaction objects of other electronic devices, the current interaction object can interact through audio participation, thereby achieving the purpose of the present application.

[0140] In one implementation, the electronic device in this embodiment may further include at least one of the following structures: Fig.11 As shown in:

[0141] Display device 1003, such as a display screen;

[0142] A physical audio collection device 1004, such as a physical microphone;

[0143] When the processor 1002 obtains the second interaction data, the display device 1003 is used to display a target icon, where the target icon is in a state indicating that the voice input is turned on;

[0144] When the processor 1002 obtains the second interaction data, the physical audio collection device 1004 is in a closed state.

[0145] In addition, the processor 1002 also constructs a virtual audio collection device, such as a virtual microphone (a software module), for the physical audio collection device 1004 . The target image can be associated with the virtual audio collection device or the physical audio collection device 1004 .

[0146] Among them, in this embodiment, in response to the second electronic device being in the first mode, the target icon can be controlled to be associated with the virtual audio acquisition device, and the icon state of the target icon represents whether the second object performs voice input through the virtual audio acquisition device. The first mode is a mode corresponding to the application scenario in which the communication relationship is located, and the first mode can be set by the second object. If the second object does not set the second electronic device to be in the first mode, then the second electronic device is in the second mode. At this time, the target icon is associated with the physical audio acquisition device 1004. At this time, the icon state of the target icon represents whether the second object performs voice input through the physical audio acquisition device 1004.

[0147] Taking the second electronic device in the present application as a mobile phone as an example, the technical solution of the present application is described in detail below:

[0148] Based on the technical solution of the present application, when a user is unable to attend an online meeting due to something or there is a meeting conflict, an artificial intelligence (AI) meeting substitute (temporary meeting assistant) can be used to attend the meeting on behalf of the user. By temporarily presetting questions and answers related to the meeting topic before the meeting (i.e., the preset questions and preset answers in the previous text) combined with a large language model, the AI ​​can answer relevant questions on behalf of the user only when it analyzes that the user is asked a question, without the need for the user to actually attend the meeting.

[0149] like Fig.12 As shown in the figure, in the conference room, Jason, Peter and Tom participate in an online meeting, but Mike cannot participate in Jason and others' online meeting at the same time because he is participating in another offline meeting. At this time, Mike can use the conference application installed on his mobile phone to use the preset questions and answers to realize the online voice participation. Jason, Peter and Tom can output Mike's avatar image on the conference application. Based on this, the following example illustrates this application:

[0150] like Fig.13 As shown in, before the meeting starts, users such as Mike manually anticipate some questions that may be asked regarding the meeting topic and give possible answers to these questions. These questions and answers are added to a private local knowledge base to form a vector database for retrieval and call by large models such as the large language model LLM (Large Language Model).

[0151] For example, taking a progress discussion meeting for a product project as an example, users can preset the following questions and answers before the meeting:

[0152] Question 1: Has the product project passed the security review?

[0153] Answer: No, it is still waiting for the review stage. It is expected that there will be a conclusion at the project safety review meeting next Tuesday.

[0154] Question 2: Has the open source review of the product project passed?

[0155] Answer: The open source review has been passed and the tripartite statement is being integrated into the product project.

[0156] Question 3: Which version of the product supports multiple system architectures at the same time?

[0157] Answer: Since version 3.1, the product project has supported multiple system architectures simultaneously.

[0158] Among them, the large language model can recognize the names of preset alternative participants and questions containing names, so that the AI ​​will only retrieve answers from the private local knowledge base when it analyzes that a specific name is asked.

[0159] When the voice conference starts, the conference audio equipment in the conference room, such as an open microphone, collects the conference room's voice data. In this way, Mike's electronic devices, such as mobile phones, can receive multimedia data transmitted by the conference audio equipment in the conference room, such as the voice data of Jason and others. Then, the conference audio is converted into text content in real time using speech-to-text technology. Then, the conference text is analyzed in real time using a large language model. Specific names and questions containing the names are found in the text. The name of the alternative participant and the question containing this name are found, and the operation of analyzing the question is triggered. The LLM will only retrieve the answer from the private local knowledge base when a specific name is analyzed to be asked. The details are as follows:

[0160] When the large language model analyzes the question asked and finds a high degree of similarity with the preset question, that is, finds the answer, the answer text can be output. Specifically, the preset answer can be input into the virtual microphone through text-to-speech for answering.

[0161] If the large language model does not find a question with high similarity, it will output the preset text content (for example, telling the questioner that I have recorded this question and will answer it after the meeting). AI will collect these questions that have not found preset answers for answering after the meeting.

[0162] In addition, this AI conference stand-in can also actively share some preset content through text-to-speech when no one is talking after the meeting starts, such as telling everyone some news, etc.

[0163] In summary, even if users cannot attend the meeting, they can still express their thoughts about the meeting through voice and realize simulated meeting participation.

[0164] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0165] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0166] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0167] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A data processing method, applied to a second electronic device, comprising: Obtaining first interaction data corresponding to at least one first electronic device; The second electronic device has a communication relationship with the at least one first electronic device; In response to the first interaction data satisfying the first condition, obtaining second interaction data corresponding to the second electronic device; the second interaction data includes audio data whose audio features match the second object of the second electronic device, and the audio data is obtained by generating; The second interaction data is sent to the at least one first electronic device.

2. The method according to claim 1, obtaining second interaction data corresponding to the second electronic device, comprising: searching for first information matching the first interaction data; Obtaining second interaction data according to second information corresponding to first information matching the first interaction data; The first information and the second information are related to an application scenario in which the communication relationship exists, and the first information and the second information are obtained based on a preset operation of the second object.

3. The method according to claim 2, obtaining the second interaction data according to the second information corresponding to the first information matching the first interaction data, comprises: According to the second information corresponding to the first information matching the first interaction data, corresponding audio data is generated to obtain second interaction data.

4. The method according to claim 2, obtaining second interaction data according to second information corresponding to first information matching the first interaction data, comprises: According to the first interaction data, adjusting the second information corresponding to the first information matching the first interaction data to obtain third information; According to the third information, corresponding audio data is generated to obtain second interaction data.

5. According to the method of claim 4, the tone features corresponding to the audio data in the second interaction data match the tone features of the first interaction data.

6. The method according to claim 4, adjusting the second information corresponding to the first information matching the first interaction data according to the first interaction data to obtain the third information, comprising: Obtaining target content related to the application scenario in the first interaction data; The target content is related to first information matching the first interaction data; Corresponding third information is generated according to the target content and the second information corresponding to the first information matching the first interaction data.

7. The method according to claim 2, when no first information matching the first interaction data is found, the method further comprises: outputting an input prompt interface for the second object; receiving input text input by the second object through the input prompt interface; According to the input text, corresponding audio data is generated to obtain second interaction data.

8. The method according to claim 1 or 2, wherein when obtaining the second interaction data, the target icon is in a state indicating that voice input is turned on, and / or the physical audio collection device of the second electronic device is in a turned off state; in, The target icon is displayed on the output interface of the electronic device.

9. An electronic device, as a second electronic device, comprising: A communication device, used to establish a communication relationship with at least one first electronic device; a processor, configured to obtain first interaction data corresponding to at least one first electronic device, obtain second interaction data corresponding to the second electronic device in response to the first interaction data satisfying a first condition, and send the second interaction data to the at least one first electronic device; The second interaction data includes audio data whose audio features match the second object of the second electronic device, and the audio data is obtained by generating.

10. The electronic device according to claim 9, further comprising: Display device and / or physical audio acquisition device; When the processor obtains the second interaction data, the display device is used to display a target icon, where the target icon is in a state indicating that the voice input is turned on; When the processor obtains the second interaction data, the physical audio collection device is in a closed state.

Images