CN115208976B - Processing method and device for call channel switching, call equipment and storage medium - Google Patents

Abstract

The application relates to the technical field of call processing, and provides a call channel switching processing method, a call device and a storage medium. In the application, in the process of providing the call service for the user by utilizing the first call channel, the audio input active state of the second call channel is detected, if the audio input active state is enhanced, the user possibly wants to use the second call channel for call, at the moment, the using intention degree of the user to the second call channel is further analyzed, and whether the user switches or not is determined based on the using intention degree, so that the automatic switching of the call channel in the call process can be realized, the user is not required to intervene, and the call efficiency is improved; compared with the detection of the first call channel used by the user, the detection of the second call channel which is not used by the user can respond to the wish of the user to switch the call channel more quickly, and the call efficiency is further improved.

Description

Method, device, communication equipment and storage medium for processing call channel switching

Technical Field

The present application relates to the technical field of call processing, and in particular to a method, apparatus, call device and storage medium for processing call channel switching.

Background Art

With the development of voice communication technology, a technology for making calls using a call device has emerged. Among them, a call device can have multiple call channels, and a user can make a call using any call channel. When a user makes a call using one call channel, if he wants to make a call using another call channel, he needs to manually switch the call channel, which is inconvenient.

Summary of the invention

The embodiments of the present application provide a method, apparatus, call device and storage medium for processing call channel switching, which realize automatic switching of call channels during a call without user intervention, thereby improving the switching efficiency of call channels.

A method for processing call channel switching, the method comprising:

In the process of providing a call service to a user through a first call channel of a call device, detecting an audio input activity state of a second call channel of the call device;

If it is detected that the audio input activity state of the second call channel is enhanced, determining the user's intention to use the second call channel;

Based on the user's intention to use the second call channel, it is determined whether to switch to the second call channel providing the call service.

In one embodiment, determining the user's intention to use the second call channel includes:

Obtaining the second input audio of the second call channel;

Detecting the confidence that the second input audio is user input audio;

If the confidence level is greater than the target confidence level, determining that the user's intention to use the second call channel is high;

If the confidence level is less than the target confidence level, it is determined that the user's intention to use the second call channel is low.

In one embodiment, the method further comprises:

Determine the time when the second call channel receives the second input audio;

Obtaining a first input audio received by the first call channel at the time;

The confidence level that the first input audio is user input audio is used as the target confidence level.

In one embodiment, the determining whether to switch to the second call channel providing the call service based on the user's intention to use the second call channel includes:

If the user's intention to use the second call channel is high, determining to switch to the second call channel providing the call service;

If the user's intention to use the second call channel is low, it is determined not to switch to the second call channel to provide the call service.

In one embodiment, before detecting the audio input activity state of the second call channel of the call device, the method further includes:

Determining a plurality of candidate call channels associated with the first call channel;

Obtaining the usage frequency of each candidate call channel within a preset historical period; the usage frequency is the frequency at which the candidate call channel is used to provide call services;

Based on the relative size of the usage frequency of each candidate call channel and a preset usage frequency threshold, the second call channel is determined from the candidate call channels.

In one embodiment, the determining the second call channel from among the candidate call channels based on the relative magnitude of the usage frequency of the candidate call channels and a preset usage frequency threshold comprises:

Determine, among the candidate call channels, a target call channel whose usage frequency is greater than or equal to the preset usage frequency threshold;

If each target communication channel is set on a different sub-communication device, determining the distance between each sub-communication device and the user;

Determine, among the sub-communication devices, a target sub-communication device whose distance is less than a preset distance threshold;

The target call channel set in the target sub-call device is used as the second call channel.

In one embodiment, detecting the audio input activity state of the second call channel of the call device includes:

Get the preset detection interval duration;

The audio input activity state of the second call channel of the call device is detected at intervals according to the detection interval duration.

In one embodiment, if it is detected that the audio input activity state of the second call channel is enhanced, before determining the user's intention to use the second call channel, the method further includes:

If the input audio of the second call channel changes from non-existent to present, determining that the audio input activity state of the second call channel is enhanced;

and/or,

If the categories of the input audio of the second call channel increase, it is determined that the audio input activity state of the second call channel is enhanced.

A processing device for switching a call channel, the device comprising:

An activity status detection module, used for detecting the audio input activity status of a second call channel of a call device during the process of providing a call service to a user through a first call channel of the call device;

A usage intention acquisition module, configured to determine the user's usage intention for the second call channel if it is detected that the audio input activity state of the second call channel is enhanced;

The channel switching processing module is used to determine whether to switch to the second call channel to provide the call service based on the user's intention to use the second call channel.

A communication device includes a memory and a processor, wherein the memory stores a computer program and the processor executes the following method:

In the process of providing a call service to a user through a first call channel of a call device, detecting an audio input activity state of a second call channel of the call device;

If it is detected that the audio input activity state of the second call channel is enhanced, determining the user's intention to use the second call channel;

Based on the user's intention to use the second call channel, it is determined whether to switch to the second call channel providing the call service.

A computer-readable storage medium stores a computer program, wherein the computer program is executed by a processor as follows:

In the process of providing a call service to a user through a first call channel of a call device, detecting an audio input activity state of a second call channel of the call device;

If it is detected that the audio input activity state of the second call channel is enhanced, determining the user's intention to use the second call channel;

Based on the user's intention to use the second call channel, it is determined whether to switch to the second call channel providing the call service.

In the above-mentioned processing method, device, call device and storage medium for switching call channels, in the process of providing call services to users by the first call channel of the call device, the audio input activity state of the second call channel of the call device is detected; if it is detected that the audio input activity state of the second call channel is enhanced, the user's intention to use the second call channel is determined; based on the user's intention to use the second call channel, it is determined whether to switch to the second call channel to provide the call service. In the above-mentioned method, in the process of providing call services to users by using the first call channel, the audio input activity state of the second call channel is detected. If the audio input activity state is enhanced, it means that the user may want to use the second call channel for calls. At this time, the user's intention to use the second call channel is further analyzed, and it is determined whether to switch based on the intention to use. The automatic switching of the call channel during the call process can be realized without user intervention, thereby improving the call efficiency; and compared with detecting the first call channel used by the user, the present application detects the second call channel that the user does not use, which can respond more quickly to the user's willingness to switch the call channel, further improving the call efficiency.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG1 is an application environment diagram of a method for processing call channel switching in one embodiment;

FIG2 is a flow chart of a method for processing call channel switching in one embodiment;

FIG3 is a flow chart of a method for processing call channel switching in one embodiment;

FIG4 is a structural block diagram of a processing device for switching a call channel in one embodiment;

FIG. 5 is a diagram showing the internal structure of a communication device in one embodiment.

DETAILED DESCRIPTION

In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

Reference to "embodiments" in this application means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described in this application may be combined with other embodiments.

The processing method for call channel switching provided in the present application can be applied to the application environment shown in FIG1. The call device has multiple call channels, and the call device can use any call channel to provide call services to the user. If the call device is a cluster composed of multiple sub-call devices, then the multiple call channels can be set on each sub-call device, such as a mobile phone, a headset, a watch, and a computer.

In one embodiment, as shown in FIG. 2 , a method for processing call channel switching is provided, which is described by taking the method applied to the call device in FIG. 1 as an example, and includes the following steps:

Step S201, in the process of providing a call service to a user through a first call channel of a call device, detecting an audio input activity state of a second call channel of the call device;

The call channel may include an audio input channel and an audio playback channel, wherein the audio input channel is used to pick up the user's audio, and the audio playback channel is used to play the audio of other users who are talking to the user. The audio input channel may be implemented using a microphone, and the audio playback channel may be implemented using a speaker.

When the call device uses the first call channel to provide call services to the user, the user is talking on the first call channel, so the audio input activity state of the first call channel is relatively active; because the user is not talking on the second call channel, the audio input activity state of the second call channel is relatively inactive when there is no other sound source or the other sound source is relatively stable (such as continuously playing background music).

Furthermore, in order to reduce the power consumption of the call device, the detection of the audio input activity state of the second call channel of the call device is performed at intervals, for example, the audio input activity state of the second call channel is detected at intervals of 2 minutes. Specifically, the call device can perform the following steps to implement interval detection: obtain a preset detection interval; and detect the audio input activity state of the second call channel of the call device at intervals according to the detection interval.

Step S202: if it is detected that the audio input activity state of the second call channel is enhanced, determining the user's intention to use the second call channel;

In this step, if the distance between the user and the second call channel is shortened, or the user speaks into the second call channel, or the volume of the background music suddenly increases, the audio input activity state of the second call channel is relatively active and shows an enhanced phenomenon; at this time, the user's intention to use the second call channel for calls is further determined, that is, the user's intention to use the second call channel.

Step S203: determining whether to switch to the second call channel providing the call service based on the user's intention to use the second call channel.

Furthermore, if the user's intention to use the second call channel is high, it is determined to switch to the second call channel to provide the call service; if the user's intention to use the second call channel is low, it is determined not to switch to the second call channel to provide the call service.

That is to say, if the user has a high intention to use the second call channel, then the second call channel can be switched to for the user to make calls; if the user has a low intention to use the second call channel, then it is not necessary to switch to the second call channel and the first call channel can still be used for calls.

In the above-mentioned method for processing call channel switching, in the process of using the first call channel to provide call services to the user, the audio input activity status of the second call channel is detected. If the audio input activity status is enhanced, it means that the user may want to use the second call channel for calls. At this time, the user's intention to use the second call channel is further analyzed, and whether to switch is determined based on the intention to use. Automatic switching can be achieved without user intervention, thereby improving call efficiency. Moreover, compared with detecting the first call channel used by the user, the present application detects the second call channel that is not used by the user, which can respond more quickly to the user's desire to switch call channels, thereby further improving call efficiency.

Furthermore, in the above step S202, the call device may also perform the following steps: obtaining the second input audio of the second call channel; detecting the confidence that the second input audio is the user input audio; if the confidence is greater than the target confidence, determining that the user's intention to use the second call channel is high; if the confidence is less than the target confidence, determining that the user's intention to use the second call channel is low.

Furthermore, the target confidence level is the confidence level that the first input audio is the user input audio; the first input audio corresponds to the first call channel. When determining the confidence level that the first input audio is the user input audio, the call device may perform the following steps: determining the time when the second call channel receives the second input audio; obtaining the first input audio received by the first call channel at the time; and using the confidence level that the first input audio is the user input audio as the target confidence level.

Exemplarily, if the time when the second call channel receives the second input audio is 15:15, the call device can obtain the input audio (i.e., the first input audio) received by the first call channel at 15:15; then, the call device obtains the confidence that the first input audio is the user input audio (hereinafter referred to as the first confidence), and uses it as the target confidence to compare with the confidence that the second input audio is the user input audio (hereinafter referred to as the second confidence); if the call device determines that the first confidence is greater than the second confidence, it is considered that the user's intention to use the second call channel is low; if the call device determines that the first confidence is less than or equal to the second confidence, it is considered that the user's intention to use the second call channel is high.

It can be seen that in the above method, since the confidence corresponding to the first call channel is compared with the confidence corresponding to the second call channel, it is more in line with the actual situation compared to the comparison with a fixed confidence, and the detection result of the user intention is more accurate.

Furthermore, when the target confidence includes the first confidence, it may also include a preset confidence, so as to further improve the accuracy of the user intention detection result. That is to say, in this case, if the second confidence is greater than both the first confidence and the preset confidence, it is considered that the user has a high intention to use the second call channel, which can further improve the accuracy of the user intention detection result and the accuracy of call channel switching.

Furthermore, the confidence that the input audio is the user input audio is obtained using an audio classification detection model. That is, the first confidence and the second confidence can be obtained using a pre-built audio classification detection model to achieve accurate prediction of the user's use of the second call channel.

Furthermore, before the call device obtains the user's intention to use the second call channel if it is detected that the audio input activity state of the second call channel is enhanced, it may further perform the following steps: if the input audio of the second call channel increases from nothing to something, it is determined that the audio input activity state of the second call channel is enhanced; and/or, if the volume of the input audio of the second call channel increases, it is determined that the audio input activity state of the second call channel is enhanced.

For example, during a user call, if there is no interference from other background music or other noise, then there is no input audio on the second call channel; if it is detected that the second call channel has input audio, then it may be that the user is close to the second call channel, at this time, the audio input activity state of the second call channel is enhanced.

As another example, during a user call, if there is background music, the category of the input audio of the second call channel is background music; at this time, if the user approaches the second call channel, or a nearby audio playback device (such as a doorbell rings), the category of the input audio of the second call channel increases, which may be because the user approaches the second call channel and wants to use the second call channel. At this time, the audio input activity state of the second call channel is enhanced.

In the above manner, by determining whether the audio input activity state of the second call channel is enhanced by determining whether the second call channel has input audio or whether the types of input audio are increased, the accuracy of recognition can be improved.

In one embodiment, if the user has multiple unused call channels, the call device may perform the following steps to determine the second call channel from the multiple unused call channels. The steps performed by the call device include: determining multiple candidate call channels associated with the first call channel; obtaining the usage frequency of each candidate call channel within a preset historical period; the usage frequency is the frequency at which the candidate call channel is used to provide call services; based on the relative size of the usage frequency of each candidate call channel and the preset usage frequency threshold, determining the second call channel from the candidate call channels.

Since the call device may include multiple call channels, the call channel associated with the first call channel may be other call channels included in the call device except the first call channel; and, if the user is currently using the first call channel for a call, then other call channels (which may be referred to as candidate call channels) are in an unused state and are unused call channels.

Exemplarily, after the call device determines the call channels a, b and c associated with the first call channel, it obtains the usage frequency of call channels a, b and c for providing call services in the past week, which are 4 times, 3 times and 1 time respectively; if the preset usage frequency threshold is 3 times, then since the usage frequencies of call channels a and b are 4 times and 3 times respectively, both are greater than or equal to the preset usage frequency threshold, the call channel can use call channels a and b as the second call channel and detect the audio input activity status of call channels a and b.

It can be seen that in the above method, if there are multiple unused call channels, the call device can determine the second call channel from each unused call channel based on the usage frequency of each unused call channel, avoid detecting the audio input activity status of all unused call channels, reduce power consumption while ensuring the accuracy of detecting user usage intentions.

In some scenarios, if each call channel is set on a different sub-call device (such as a mobile phone, headset, watch and computer), in order to further reduce power consumption and ensure the accuracy of detecting the user's usage intention, the call device can also specifically perform the following steps when executing the step of determining the second call channel in each candidate call channel based on the relative size of the usage frequency of each candidate call channel and the preset usage frequency threshold: among the candidate call channels, determine the target call channel whose usage frequency is greater than or equal to the preset usage frequency threshold; if each target call channel is set on a different sub-call device, determine the distance between each sub-call device and the user; among the sub-call devices, determine the target sub-call device whose distance is less than the preset distance threshold; and use the target call channel set at the target sub-call device as the second call channel.

Taking the target call channels as call channels a and b and call channels a and b being respectively set in the headset and the computer as an example, the above method is introduced: the call device determines the above call channels a and b from multiple unused call channels based on the frequency of use of the call channels for providing call services; since call channel a is set in the headset and call channel b is set in the computer, the distance between the user and the headset (referred to as the first distance) and the distance between the user and the computer (referred to as the second distance) can be determined; if the first distance is less than the preset distance threshold and the second distance is greater than the preset distance threshold, it means that the current user is close to the headset and may want to use the headset to make a call; at this time, the call device can use the call channel a set in the headset as the second call channel, and detect the audio input activity status of the call channel a.

It can be seen that in the above implementation, when the call channels are set on different sub-call devices, further determining the second call channel in combination with the distance between the sub-call device and the user can further reduce power consumption and ensure the accuracy of detecting the user's usage intention.

In order to better understand the above method, an application example of the processing method for switching call channels of the present application is described in detail below in conjunction with Figure 3. Among them, the first call channel is set on the mobile phone (the mobile phone can be regarded as a user device, so the first call channel is called a UD call channel), and the second call channel is set on the headset (if the headset is an audio device wirelessly connected to the mobile phone, then the second call channel can be called a WAD call channel).

During the process of the call device using the UD call channel to provide call services to the user, if the audio input activity status of the WAD call channel is enhanced, then the call device can input both the input audio of the UD call channel and the input audio of the WAD call channel into the audio classification detection model (step S301), and use the audio classification detection model to detect whether each input audio belongs to user input audio or noise input audio; during the process of the audio classification detection model detecting each input audio, if the input audio is more likely to belong to user input audio, then the corresponding confidence is larger; if the input audio is more likely to belong to noise input audio, then the confidence output by the audio classification detection model is smaller.

After the audio classification detection model detects the input audio, it outputs the corresponding confidence level to the call device, where the confidence level corresponding to the input audio of the UD call channel is recorded as C(UD), and the confidence level corresponding to the input audio of the WAD call channel is recorded as C(WAD). The call device compares C(UD) and C(WAD) (step S302).

If C(UD) is less than C(WAD), the calling device can further determine whether C(WAD) is greater than the confidence threshold. If so, the initial call channel is a UD call channel and not a WAD call channel. Then, the calling device switches to the WAD call channel to provide call services to the user (step S303-step S304). Similarly, if the initial call channel is a WAD call channel, since C(WAD) is greater than C(WAD) and the confidence threshold, the calling device may not switch to the WAD call channel and still use the WAD call channel to provide call services to the user (step S307).

If C(UD) is greater than C(WAD), the calling device can further determine whether C(UD) is greater than the confidence threshold. If so, and because the initial call channel is the UD call channel, the calling device does not switch the call channel and still uses the UD call channel to provide call services to the user (step S307). Similarly, if the initial call channel is the WAD call channel, since C(UD) is greater than C(WAD) and the C(UD) confidence threshold, the calling device can switch to the UD call channel to provide call services to the user (steps S305-S306).

The call channel switching situation of this application example can be referred to Table 1.

Table 1

In the method provided by this application example, in the process of using the initial call channel to provide call services to the user, the audio input activity status of other call channels not used by the user is detected. If the audio input activity status is enhanced, it means that the user may want to use other call channels for calls. At this time, the user's intention to use other call channels is further analyzed, and whether to switch is determined based on the intention to use. Automatic switching can be achieved without user intervention, thereby improving call efficiency. Moreover, compared with the method of detecting the call channels used by the user, the present application detects other call channels not used by the user, which can respond more quickly to the user's desire to switch call channels, thereby further improving call efficiency.

It should be understood that, although the various steps in the flowcharts of Figures 1 to 3 are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a portion of the steps in Figures 1 to 3 may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of the steps or stages in other steps.

In one embodiment, as shown in FIG4 , a processing device for switching a call channel is provided, including:

An activity state detection module 401 is used to detect the audio input activity state of a second call channel of a call device during the process of providing a call service to a user through a first call channel of the call device;

A usage intention acquisition module 402 is configured to determine the user's usage intention for the second call channel if it is detected that the audio input activity state of the second call channel is enhanced;

The channel switching processing module 403 is used to determine whether to switch to the second call channel to provide the call service based on the user's intention to use the second call channel.

In one embodiment, the usage intention acquisition module 402 is also used to obtain the second input audio of the second call channel; detect the confidence that the second input audio is the user input audio; if the confidence is greater than the target confidence, determine that the user's usage intention for the second call channel is high; if the confidence is less than the target confidence, determine that the user's usage intention for the second call channel is low.

In one embodiment, the device also includes a target confidence determination module, which is used to determine the moment when the second call channel receives the second input audio; obtain the first input audio received by the first call channel at the moment; and use the confidence that the first input audio is user input audio as the target confidence.

In one embodiment, the channel switching processing module 403 is also used to determine to switch to the second call channel to provide the call service if the user's intention to use the second call channel is high; and to determine not to switch to the second call channel to provide the call service if the user's intention to use the second call channel is low.

In one embodiment, the confidence that the input audio is user input audio is obtained using an audio classification detection model.

In one embodiment, the device also includes a second call channel determination module, which is used to determine multiple candidate call channels associated with the first call channel; obtain the usage frequency of each candidate call channel within a preset historical period; the usage frequency is the frequency at which the candidate call channel is used to provide call services; based on the relative size of the usage frequency of each candidate call channel and a preset usage frequency threshold, determine the second call channel among the candidate call channels.

In one embodiment, the second call channel determination module is further used to determine, among the candidate call channels, a target call channel whose usage frequency is greater than or equal to the preset usage frequency threshold; if the target call channels are set on different sub-call devices, determine the distance between each sub-call device and the user; among the sub-call devices, determine a target sub-call device whose distance is less than a preset distance threshold; and use the target call channel set on the target sub-call device as the second call channel.

In one embodiment, the activity status detection module 401 is further used to obtain a preset detection interval duration; and to detect the audio input activity status of the second call channel of the call device at intervals according to the detection interval duration.

In one embodiment, the device also includes a state enhancement determination module, which is used to determine that the audio input activity state of the second call channel is enhanced if the input audio of the second call channel changes from nothing to something; and/or, the state enhancement determination module is also used to determine that the audio input activity state of the second call channel is enhanced if the volume of the input audio of the second call channel increases.

For the specific definition of the processing device for call channel switching, please refer to the definition of the processing method for call channel switching in the above text, which will not be repeated here. Each module in the above-mentioned processing device for call channel switching can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the call device in the form of hardware, or can be stored in the memory of the call device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

In one embodiment, a call device is provided, which may be a terminal, and its internal structure diagram may be shown in FIG5. The call device includes a processor, a memory, a communication interface, a display screen, and an input device connected via a system bus. Among them, the processor of the call device is used to provide computing and control capabilities. The memory of the call device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the call device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner may be implemented through WIFI, an operator network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a method for processing call channel switching is implemented. The display screen of the call device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the call device may be a touch layer covered on the display screen, or a key, trackball or touchpad provided on the shell of the call device, or an external keyboard, touchpad or mouse, etc.

Those skilled in the art will understand that the structure shown in FIG5 is merely a block diagram of a partial structure related to the scheme of the present application, and does not constitute a limitation on the call device to which the scheme of the present application is applied. The specific call device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

In one embodiment, a communication device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the above-mentioned computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims (10)

1. A method for processing call channel switching, characterized in that the method comprises: In the process of providing a call service to a user through a first call channel of a call device, detecting an audio input activity state of a second call channel of the call device; If it is detected that the audio input activity state of the second call channel is enhanced, determining the user's intention to use the second call channel; wherein the intention to use is used to indicate the user's intention to use the second call channel for a call; If the user's intention to use the second call channel is high, determining to switch to the second call channel providing the call service; If the user's intention to use the second call channel is low, determining not to switch to the second call channel providing the call service; The determining of the user's intention to use the second call channel includes: Obtaining the second input audio of the second call channel; Detecting the confidence level that the category of the second input audio is the category of the user input audio; wherein the confidence level is obtained using a pre-built audio classification detection model; If the confidence is greater than the target confidence, it is determined that the user's intention to use the second call channel is high; wherein the target confidence is the confidence that the first input audio of the first call channel is the user input audio; If the confidence level is less than the target confidence level, it is determined that the user's intention to use the second call channel is low. 2. The method according to claim 1, characterized in that the method further comprises: Determine the time when the second call channel receives the second input audio; Obtaining a first input audio received by the first call channel at the time; The confidence that the category of the first input audio is the category of the user input audio is used as the target confidence. 3. The method according to claim 2, wherein the target confidence further includes a preset confidence, and if the confidence is greater than the target confidence, determining that the user's intention to use the second call channel is high, comprises: If the confidence is greater than both the confidence that the category of the first input audio is the category of the user input audio and the preset confidence, it is determined that the user's intention to use the second call channel is high. 4. The method according to claim 1, characterized in that before detecting the audio input activity state of the second call channel of the call device, the method further comprises: Determining a plurality of candidate call channels associated with the first call channel; Obtaining the usage frequency of each candidate call channel within a preset historical period; the usage frequency is the frequency at which the candidate call channel is used to provide call services; Based on the relative size of the usage frequency of each candidate call channel and a preset usage frequency threshold, the second call channel is determined from the candidate call channels. 5. The method according to claim 4, characterized in that the determining the second call channel from the candidate call channels based on the relative size of the usage frequency of the candidate call channels and a preset usage frequency threshold comprises: Determine, among the candidate call channels, a target call channel whose usage frequency is greater than or equal to the preset usage frequency threshold; If each target communication channel is set on a different sub-communication device, determining the distance between each sub-communication device and the user; Determine, among the sub-communication devices, a target sub-communication device whose distance is less than a preset distance threshold; The target call channel set in the target sub-call device is used as the second call channel. 6. The method according to claim 1, characterized in that the detecting the audio input activity state of the second call channel of the call device comprises: Get the preset detection interval duration; The audio input activity state of the second call channel of the call device is detected at intervals according to the detection interval duration. 7. The method according to claim 1, characterized in that before determining the user's intention to use the second call channel if the audio input activity state of the second call channel is detected to be enhanced, the method further comprises: If the input audio of the second call channel changes from non-existent to present, determining that the audio input activity state of the second call channel is enhanced; and/or, If the categories of the input audio of the second call channel increase, it is determined that the audio input activity state of the second call channel is enhanced. 8. A processing device for switching a call channel, characterized in that the device comprises: An activity status detection module, used for detecting the audio input activity status of a second call channel of a call device during the process of providing a call service to a user through a first call channel of the call device; A usage intention acquisition module, configured to determine the user's usage intention for the second call channel if it is detected that the audio input activity state of the second call channel is enhanced; wherein the usage intention is used to indicate the user's intention to use the second call channel for a call; a channel switching processing module, configured to determine to switch to the second call channel to provide the call service if the user's intention to use the second call channel is high; and to determine not to switch to the second call channel to provide the call service if the user's intention to use the second call channel is low; The usage intention acquisition module is specifically used for: Obtaining the second input audio of the second call channel; Detecting the confidence level that the category of the second input audio is the category of the user input audio; wherein the confidence level is obtained using a pre-built audio classification detection model; If the confidence is greater than the target confidence, it is determined that the user's intention to use the second call channel is high; wherein the target confidence is the confidence that the first input audio of the first call channel is the user input audio; If the confidence level is less than the target confidence level, it is determined that the user's intention to use the second call channel is low. 9. A communication device, comprising a memory and a processor, wherein the memory stores a computer program, and wherein the processor implements the method according to any one of claims 1 to 7 when executing the computer program. 10. A computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.