Intercom information processing method and system based on voice control function

Abstract

The application discloses a talkback information processing method and system based on a voice control function, belongs to the technical field of voice or sound processing of the Internet industry, or belongs to the technical field of mobile voice services of the next-generation information network industry, and the method comprises the following steps: acquiring first state data of a first user; identifying a talkback demand mode of the first user according to the first state data and a target sports scene, wherein the talkback demand mode comprises a cross-domain talkback demand mode, a public-domain talkback demand mode and a private-domain talkback demand mode; determining a talkback network to be used and talkback information to be transmitted according to the talkback demand mode; and transmitting the talkback information through the talkback network. The application scheme is favorable for improving the functional expansibility and scene applicability of the talkback machine in the team sports scene, and improving the intelligence, comprehensiveness, accuracy and success rate of the talkback machine in processing talkback information.

Description

Technical Field

[0001] The present application belongs to the field of voice or sound processing technology in the Internet industry, or to the field of mobile voice service technology in the next generation information network industry, and specifically relates to an intercom information processing method and system based on a voice control function. Background Art

[0002] In practical applications, voice control technology for intercoms demonstrates wide applicability. For example, traditional manual keystrokes can be inconvenient when the user is holding heavy objects or wearing gloves, but voice control technology easily solves this problem. Furthermore, manual keystrokes are prone to misoperation in noisy environments, while voice control technology accurately recognizes user commands, ensuring smooth communication.

[0003] The VOX currently used in walkie-talkies ) Voice control function, which can use sound to control the function of transmitting voice operations. When the VOX function is activated, the microphone of the walkie-talkie will be in a "standby" state, which means it is always listening to the user's voice. When you speak to the walkie-talkie, it will automatically detect the sound and automatically start transmitting the voice synchronously. At this time, you don't need to press the PTT button anymore. It relies directly on "voice control" to start the transmission operation. When the voice stops, the transmission operation will automatically end. The VOX voice control function controls whether to turn on the intercom by checking the sound volume, and avoids frequent triggering by setting the sensitivity. The main disadvantage of this method is that it is easy to trigger by mistake in a noisy environment. Even if the person is not speaking, the check will fail, resulting in continuous transmission and failure to stop automatically. At the same time, because it can only check the sound volume, it cannot complete other functions such as switching channels, resulting in insufficient practicality.

[0004] Currently, the latest intercom systems are able to activate the intercom function, record and transmit user voice functions based on user voice commands.

[0005] In actual application scenarios, R&D personnel found that smart voice walkie-talkies could hardly meet the real intercom call needs in team sports scenarios. For example, the huge engine noise in off-road motorcycle riding could completely drown out the user's voice, resulting in the failure of intercom paging in an emergency. For another example, the user's point-to-point intercom needs in team road cycling could not be realized. Summary of the Invention

[0006] The present application discloses an intercom information processing method and system based on voice control function, in order to improve the functional expandability and scene applicability of intercoms in team sports scenes, and to improve the intelligence, comprehensiveness, accuracy and success rate of intercom information processing by intercoms.

[0007] In a first aspect, an embodiment of the present application provides a method for processing intercom information based on a voice control function, comprising:

[0008] Acquiring first status data of a first user, where the first status data includes audio sampling data and motion sampling data, where the first intercom device of the first user is an intercom device in a first public intercom group, and where the service scenario to which the first public intercom group belongs is a target motion scenario;

[0009] identifying an intercom demand pattern of the first user according to the first status data and the target motion scene, the intercom demand pattern including a cross-domain intercom demand pattern, a public domain intercom demand pattern, and a private domain intercom demand pattern;

[0010] Determining the intercom network to be used and the intercom information to be transmitted according to the intercom demand mode;

[0011] The intercom information is transmitted through the intercom network.

[0012] In a second aspect, an embodiment of the present application provides an intercom information processing system based on a voice control function, comprising:

[0013] an acquiring unit, configured to acquire first status data of a first user, the first status data including audio sampling data and motion sampling data, the first intercom device of the first user being an intercom device in a first public intercom group, and the service scenario to which the first public intercom group belongs being a target motion scenario;

[0014] an identification unit, configured to identify an intercom demand pattern of the first user according to the first status data and the target motion scene, the intercom demand pattern including a cross-domain intercom demand pattern, a public domain intercom demand pattern, and a private domain intercom demand pattern;

[0015] A determination unit, configured to determine an intercom network to be used and intercom information to be transmitted according to the intercom demand mode;

[0016] A transmission unit is used to transmit the intercom information through the intercom network.

[0017] It can be seen that in the embodiment of the present application, compared with the existing solution based on voice control of the intercom function of the intercom, the device of the present application first obtains the user's status data, accurately identifies the user's intercom demand pattern based on the user's status data, and then determines the intercom network to be used and the intercom information to be transmitted according to the identified intercom demand pattern, and finally uses the determined intercom network to transmit the intercom information to complete the intercom demand. Since the status data contains audio sampling data and motion sampling data, that is, multimodal data, it can more accurately identify the various types of user's segmented intercom needs in the team sports scene, such as emergency intercom needs, point-to-point intercom needs, etc. In this way, the solution of the present application is conducive to improving the functional scalability and scene applicability of intercoms in team sports scenes, as well as improving the intelligence, comprehensiveness, accuracy and success rate of intercom information processing by intercoms. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings provided in the embodiments of this application are as follows:

[0019] Figure 1 This is a schematic diagram of the system architecture of an intercom information processing system based on a voice control function provided by an embodiment of the present application;

[0020] Figure 2 This is a schematic structural diagram of an intercom device group provided in an embodiment of the present application;

[0021] Figure 3 This is a structural diagram of another intercom device group provided in an embodiment of the present application;

[0022] Figure 4 This is a flow chart of a method for processing intercom information based on a voice control function provided in an embodiment of the present application;

[0023] Figure 5 This is a schematic diagram of an intercom group setting function interface provided by an embodiment of the present application;

[0024] Figure 6 is a schematic diagram of a bicycle sports interface provided by an embodiment of the present application;

[0025] Figure 7 Schematic diagram of a method for determining a target motion scene provided by an embodiment of the present application;

[0026] Figure 8 Schematic diagram of a mel spectrogram provided in an embodiment of the present application;

[0027] Figure 9 1 is a flow chart of data processing steps for human voice semantic features in the second processing of audio sample data provided by an embodiment of the present application;

[0028] Figure 10This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application;

[0029] Figure 11 This is a functional unit block diagram of an intercom information processing system based on voice control function provided in an embodiment of the present application. DETAILED DESCRIPTION

[0030] In order to enable those skilled in the art to better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0031] The terms "first," "second," and the like in the specification and claims of this application and the accompanying drawings are used to distinguish between different objects, not to describe a particular order. Furthermore, the terms "including," "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or elements is not limited to the listed steps or elements but may optionally include steps or elements not listed, or may optionally include other steps or elements inherent to the process, method, product, or apparatus.

[0032] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0033] In the embodiments of this application, "and / or" describes the relationship between associated objects and indicates that three relationships can exist. For example, "A and / or B" can represent the following three situations: A exists alone; A and B exist simultaneously; and B exists alone. A and B can be singular or plural.

[0034] In the embodiments of the present application, the symbol " / " can indicate that the preceding and following objects are in an "or" relationship. In addition, the symbol " / " can also represent a division sign, that is, performing a division operation. For example, A / B can mean A divided by B.

[0035] In the embodiments of the present application, "at least one item" or similar expressions refers to any combination of these items, including any combination of single items or plural items, and refers to one or more, and multiple refers to two or more. For example, at least one item (item) of a, b, or c can represent the following seven situations: a, b, c, a and b, a and c, b and c, a, b, and c. Among them, each of a, b, and c can be an element or a set containing one or more elements.

[0036] In the embodiments of this application, "equal to" can be used in conjunction with "greater than" and is applicable to the technical solution adopted when "greater than" is used, and can also be used in conjunction with "less than" and is applicable to the technical solution adopted when "less than" is used. When "equal to" is used in conjunction with "greater than", it should not be used in conjunction with "less than"; when "equal to" is used in conjunction with "less than", it should not be used in conjunction with "greater than".

[0037] Currently, smart voice walkie-talkies struggle to meet the real-world intercom call needs of team sports scenarios. For example, the loud engine noise of a motorcycle off-road vehicle may completely drown out the user's voice, causing intercom paging to fail in an emergency. Another example is the point-to-point intercom needs of users in team road cycling.

[0038] To address the above-mentioned issues, this application provides a method and system for processing intercom information based on voice control. The device first obtains the first status data of the first user. Then, based on the first status data and the target sports scene, the device identifies the first user's intercom demand pattern, which includes a cross-domain intercom demand pattern, a public domain intercom demand pattern, and a private domain intercom demand pattern. Then, based on the intercom demand pattern, the intercom network to be used and the intercom information to be transmitted are determined. Finally, the intercom information is transmitted via the intercom network. This improves the functional scalability and scenario applicability of intercoms in team sports scenes, as well as the intelligence, comprehensiveness, accuracy, and success rate of intercom information processing.

[0039] See also Figure 1 , Figure 1 A system architecture diagram of an intercom information processing system based on a voice control function provided in an embodiment of the present application, wherein the system is an intercom self-organizing network system including multiple intercom devices, specifically including a first intercom device device group of a first user, a second intercom device device group of a second user that is communicatively connected to the first intercom device device group via an intercom communication channel, and other intercom device groups of other users who have joined the intercom self-organizing network system in addition to the first intercom device device group and the second intercom device device group, wherein the number of other users can be one or more and is not uniquely limited.

[0040] like Figure 2 As shown, Figure 2 This is a schematic diagram of the structure of an intercom device group provided in an embodiment of the present application.Figure 1 The intercom device equipment group may include, for example, an intercom device and a terminal device (such as a mobile phone), wherein the intercom device may be, for example, a smart cycling helmet, which may be provided with a voice recognition function, a voice intercom function, an audio collection function, a motion sensing function, and a Bluetooth or Wi-Fi communication module, etc. The voice recognition function is used to recognize user voice commands, the voice intercom function is used to communicate with other intercom devices on an intercom communication channel, the audio collection function may be implemented by a microphone to collect user voice and ambient sound, the motion sensing function may be implemented by various motion sensors such as a gyroscope, an accelerometer, etc. to collect user motion data, and the Bluetooth or Wi-Fi communication module is used to communicate with terminal devices such as mobile phones to realize functions such as checking the status of the intercom device, creating, adding, and deleting intercom channels and intercom ad hoc network systems.

[0041] Among them, the voice recognition function and voice intercom function can be realized by the walkie-talkie communication chip provided by Hongkete Electronic Technology Co., Ltd., such as the HKT-UV2W series, which supports serial port UART communication interface control, wireless radio frequency RF output power: 2W, frequency range: very high frequency VHF136~174MHZ, ultra high frequency UHF400~470MHZ, voice encryption and scrambling functions, short message SMS sending and receiving functions, built-in continuous tone coded squelch system CTCSS (38 groups), coded digital control squelch system CDCSS (83 groups) encoding and decoding, communication distance: greater than 7 kilometers in open area.

[0042] Among them, the intercom communication channel refers to the communication channel commonly used by walkie-talkies.

[0043] like Figure 3 As shown, Figure 3 This is a structural diagram of another intercom device group provided in an embodiment of the present application. Figure 1 The intercom device group in the example may include an intercom device, a terminal device and a smart headset, wherein the smart headset and the terminal device are connected to each other via a Bluetooth module, and the intercom device and the terminal device are connected to each other via a Bluetooth module or a Wi-Fi module. The intercom device may be a handheld intercom. In this architecture, the smart headset is used to collect the user's voice and ambient sound, and the other functions of the terminal device and the intercom device can be combined with the Figure 1 The same is true in , so I will not repeat it here.

[0044] It should be noted that Figure 2 or Figure 3 This is just an example. Since the walkie-talkie communication chip can be flexibly embedded in products such as mobile phones and smart helmets, the device carrying the walkie-talkie communication chip can be flexibly designed and developed according to the application requirements of the business scenario. This application does not make any sole limitation on the device form that incorporates the walkie-talkie communication chip.

[0045] See also Figure 4 , Figure 4 A flow chart of a method for processing intercom information based on voice control function provided in an embodiment of the present application is applied to Figure 1 The first intercom device group shown includes the following steps:

[0046] Step S401: The first intercom device group obtains first status data of the first user.

[0047] In a specific implementation, the first intercom device group obtains audio sampling data through the first audio acquisition module. The first audio acquisition module can be as follows: Figure 2 The sound collection module of the first intercom device in the device group shown in FIG. 1 may be a Figure 3 The sound collection module of the first smart headset is shown.

[0048] The first state data includes audio sampling data and motion sampling data.

[0049] The first intercom device of the first user is an intercom device in a first public intercom group, and the service scenario to which the first public intercom group belongs is a target motion scenario.

[0050] The target sports scene may be, for example, a motorcycle team mountain road off-road scene, a road bike team road riding scene, a mountain bike team off-road scene, and the like.

[0051] It is understandable that the specific implementation method of the target motion scene determination process can be various, and the embodiments of the present application do not limit it.

[0052] In Example 1, the process of determining the target motion scene may be as follows: Figure 5 As shown, Figure 5 A schematic diagram of an intercom group setting function interface provided in an embodiment of the present application. The intercom group setting function interface of the smart intercom software APP1 installed on the terminal device displays a variety of optional business scenarios on this page, including professional rescue scenarios, sports and entertainment scenarios, etc. After the user selects the interface control of the sports and entertainment scenario, they can jump to the detailed setting interface of the sports and entertainment scenario. The detailed setting interface includes multiple optional scenario entries, such as the motorcycle team mountain road off-road scenario, the road bike team road cycling scenario, and the mountain bike team off-road scenario.

[0053] In Example 2, the process of determining the target motion scene may be as follows: Figure 6 As shown, Figure 6A schematic diagram of a bicycle sports interface provided in an embodiment of the present application. The main interface of the exclusive sports APP2 of a certain bicycle brand installed on the mobile phone of the first user includes an add device control. The user can select the add device control to first connect the intercom device to his or her mobile phone, and then click the "My" function partition icon to jump to the My function partition interface, which includes the "Create Intercom Group" function control. After the user clicks "Create Intercom Group", it jumps to the intercom group creation setting page, which includes setting functions such as adding group members and adding riding areas. After the user completes the creation and setting of the intercom group, the background automatically determines the target sports scene based on the type of bicycle vehicle registered and the set riding area when the user initially registers the account information of the APP2, and adds label information of the target sports scene to the first intercom device.

[0054] In Example 3, the process of determining the target motion scene may be as follows: Figure 7 As shown, Figure 7 A schematic diagram of a target motion scene identification method provided in an embodiment of the present application. A first user's first smart helmet is equipped with a physical "one-touch pairing / teaming" button, which is operated simultaneously with a second intercom device of a second user, and waits for successful pairing. A successful pairing message is displayed on the display screen of the first smart helmet.

[0055] It should be noted that the method for creating the first public intercom group is also involved in the above-mentioned Examples 1 to 3. The method for creating the group can be various, and this application does not make a sole limitation.

[0056] Step S402: The first intercom device group identifies the intercom demand pattern of the first user according to the first status data and the target motion scene.

[0057] Among them, the intercom demand mode includes a cross-domain intercom demand mode, a public domain intercom demand mode and a private domain intercom demand mode.

[0058] In this possible embodiment, the first intercom device group identifies the intercom demand pattern of the first user based on the first state data and the target motion scene, including: performing a first processing on the motion sampling data to obtain the motion characteristics of the first user; performing a second processing on the audio sampling data to obtain the human voice semantic characteristics and environmental sound characteristics of the first user; and determining the intercom demand pattern of the first user based on the target motion scene, the motion characteristics, the human voice semantic characteristics, and the environmental sound characteristics.

[0059] Among them, action features are used to characterize normal action features / normal motion features, or abnormal action features / abnormal motion features determined by statistical analysis in the target motion scene, such as rolling, falling, moving at a constant speed, accelerating forward, accelerating downhill and other types of features. For example, taking the action features of a car fall as an example, the acceleration and angular velocity of the human body will change dramatically at the moment of the fall. By monitoring and analyzing these physical quantities in the motion sampling data, characteristic data representing the car fall situation is extracted.

[0060] In the specific implementation, the first processing refers to the feature extraction and feature construction method for motion collection data. The specific implementation methods of the feature extraction and feature construction method can be diverse, such as time-frequency statistical methods such as wavelet transform, and feature extraction methods based on kinematic principles and specific action patterns. For example, for road bike riding actions, features such as cadence, speed, and side swing angle are extracted. By combining and screening multi-dimensional features, redundant information is removed, and the most representative action features are retained to form a concise and effective action feature vector for subsequent pattern determination.

[0061] The human voice semantic features are used to represent normal semantic features / normal semantic features and abnormal semantic features / abnormal semantic features determined by statistical analysis in the target motion scene.

[0062] For example, when detecting startled interjections like "ah," the device extracts characteristic data representing the user's emotional state and level of urgency, combining voice pitch, volume, and speaking speed. A rapid tone and high volume indicate a potential emergency and require the immediate attention of teammates. In this case, intercom requirements favor cross-domain or public-domain communication, communicating the emergency to the entire cycling group so they can respond appropriately, such as slowing down or stopping to check the situation.

[0063] For example, when capturing human voice semantic sentences such as "Lao Wang, Lao Wang, come and help me break the wind", the device can construct human voice features according to the structure of {title + demand + tone}. Specifically,

[0064] The repeated "Lao Wang Lao Wang" in the sentence is a clear and specific form of address, indicating that the speaker is communicating with a specific individual, "Lao Wang." This clear directionality suggests that the communication is not directed at the entire group or a wider audience, but rather at a specific individual. This suggests a more private intercom demand model, indicating that the speaker desires private communication and information exchange with a specific person.

[0065] Demand Characteristics: The expression "Come help me break the wind" reflects the professional terminology and needs of the specific sport of team road cycling. "Breaking the wind" in road cycling refers to a teammate riding in front, reducing wind resistance for the rider behind, thereby saving energy and increasing speed.

[0066] Tone: Voice characteristics can be used to extract the speaker's emotions and the urgency of their needs through voice characteristics such as pitch, speed, and volume. If the speaker's voice is high-pitched, fast, and loud, it may indicate that they are currently facing significant wind resistance and urgently need help from their teammates. If the speaker's tone is steady, the pitch is moderate, and the speed is normal, it means that their needs are relatively calm and they are simply requesting a teammate to help break the wind.

[0067] Among them, the environmental sound characteristics are used to characterize the normal environmental background sound patterns and abnormal background sound patterns determined by statistical analysis in the target motion scene, such as the wind noise characteristics generated by different riding speeds and weather conditions during road cycling. The riding wind noise characteristics are identified and extracted through spectral analysis of the environmental sound, sound intensity detection and other means. If other abnormal sounds are detected against the wind noise background, such as sharp braking sounds, collision sounds, etc., it means that an accident or potential risk may have occurred. At this time, the intercom demand mode needs to be judged according to the specific situation. For example, if the abnormal sound comes from the front of the team group position, it is more likely that a public domain or cross-domain intercom demand mode will be used to alert the entire team.

[0068] In a specific implementation, the semantic features of human voice and the features of ambient sound can be determined by using the Mel-frequency cepstral coefficient algorithm. The core of the Mel-frequency cepstral coefficient algorithm is the Mel-frequency spectrogram, such as Figure 8 As shown, Figure 8 This is a schematic diagram of a Mel-frequency spectrogram provided in an embodiment of the present application. It combines the characteristics of time, frequency, and energy domain analysis of audio data. The horizontal axis is time, the vertical axis is frequency, and the color depth represents the energy level. In the Mel-frequency spectrogram, the different shades of color form different patterns called voiceprints. Different people speaking the same words will have different patterns, which also serve as the basis for determining whether the pronunciation is from the same person. The Mel-frequency cepstral coefficient is obtained by performing a cosine transform on the Mel-frequency spectrogram to obtain the low-frequency portion.

[0069] like Figure 9 As shown, Figure 9 This application provides a flow chart of the data processing steps for the second processing of human voice semantic features for audio sampling data. Specifically, 8KHz 16-bit mono can be used as the signal source, and the length of the collected audio data is, for example, no more than 10 seconds.

[0070] In step S901, since the mid- and high-frequency components of the audio sample data are weak and the low-frequency components are strong, the first intercom device group pre-emphasizes the low-frequency components of the audio sample data, i.e., amplifies the low-frequency parts to obtain first audio data. The amplification factor can be set based on empirical values.

[0071] Step S902: Next, the first intercom device group performs a frame operation on the first audio data to obtain a plurality of first audio data blocks.

[0072] In a specific implementation, the system uses 256 sampling points as a frame, and performs framing and windowing processing with 128 overlapping sound frames between adjacent audio data blocks.

[0073] Step S903: Perform Fourier transform on each audio data block to obtain a plurality of audio spectrum data.

[0074] Step S904 : Process the plurality of audio spectrum data using a Mel filter to obtain Mel spectrum data of the audio sampling data.

[0075] Step S905 , performing a logarithmic operation on the mel-spectrogram data to obtain logarithmic mel-spectrogram data.

[0076] Step S906 , performing discrete cosine transform on the logarithmic Mel-frequency spectrum data to obtain a first MFCC Mel-frequency cepstrum coefficient.

[0077] Step S907: Perform voice feature analysis on the MFCC coefficients to obtain voice semantic features.

[0078] Among them, the distribution relationship feature value of frequency and time in the MFCC feature value is used to divide human voice and environmental sound.

[0079] In addition, the characteristic value of the distribution relationship between energy and time in the MFCC coefficient can also be used to distinguish the voiceprint characteristics of different users, thereby realizing functions such as identity recognition and control of walkie-talkie usage permissions.

[0080] Similarly, the first intercom device group can use the Mel-frequency cepstral coefficient algorithm to process the audio sampling data to obtain the second MFCC coefficient, and perform ambient sound feature analysis on the second MFCC coefficient to obtain the ambient sound feature.

[0081] It can be seen that in this example, the first intercom device equipment group can process the motion sampling data to obtain the motion characteristics of the first user, process the audio sampling data to obtain the human voice semantic characteristics and environmental sound characteristics of the first user, and determine the intercom demand pattern of the first user according to the target motion scene, motion characteristics, human voice semantic characteristics and environmental sound characteristics. Since the motion characteristics, human voice semantic characteristics and environmental sound characteristics under the target motion scene can comprehensively and accurately reflect the user's need to intercom with other people due to certain needs in the current motion scene, it is beneficial to improve the refinement and accuracy of the first intercom device equipment group in identifying the user's intercom demand pattern.

[0082] In this embodiment, the first intercom device group determines the intercom demand pattern of the first user based on the target motion scene, the action characteristics, the human voice semantic characteristics and the ambient sound characteristics, including: querying the intercom demand pattern mapping relationship set according to the target motion scene, and obtaining the target intercom demand pattern mapping relationship subset corresponding to the target motion scene; merging the action characteristics, the human voice semantic characteristics and the ambient sound characteristics to obtain a comprehensive state characteristic; querying the target intercom demand pattern mapping relationship subset according to the comprehensive state characteristic, and obtaining the intercom demand pattern of the first user that is adapted to the comprehensive state characteristic.

[0083] Among them, the intercom demand pattern mapping relationship set includes the correspondence between preset sports scenes and intercom demand pattern mapping relationship subsets. The sports scenes include, for example, motorcycle team mountain road off-road scenes, road bike team riding scenes, etc.

[0084] The intercom demand mode mapping relationship subset includes a mapping relationship between a preset comprehensive state feature and an intercom demand mode. For example, the mapping relationship may be:

[0085] The comprehensive state features are {["crash" action features]["ah" modal particle]["handlebar hitting the ground sound"]}, and the corresponding intercom demand mode is the cross-domain intercom demand mode;

[0086] The comprehensive state features are {["slowing down riding" action features]["Lao Wang" appellation, "breaking wind" demand]["riding wind noise features]}, and the corresponding intercom demand mode is the private domain intercom demand mode;

[0087] The comprehensive state features are {[“constant speed riding” action features][“be careful of the stone in the center of the curve ahead” semantic features][“wind noise during riding”]}, and the corresponding intercom demand mode is the public domain intercom demand mode.

[0088] It can be seen that in this example, the first intercom device group first queries the intercom demand pattern mapping relationship set based on the target motion scene to obtain the target intercom demand pattern mapping relationship subset corresponding to the target motion scene; then combines the action features, human voice semantic features and ambient sound features to obtain the comprehensive state features; finally, based on the comprehensive state features, queries the target intercom demand pattern mapping relationship subset to obtain the intercom demand pattern of the first user that is adapted to the comprehensive state features. Since the intercom demand pattern mapping relationship set pre-sets various types of motion scenes and intercom demand pattern mapping relationship subsets, that is, first performing exclusive classification and adaptation based on the motion scene, further accurately and efficiently queries the intercom demand pattern of the first user that is adapted to the comprehensive state features in the exclusive intercom demand pattern mapping relationship subset of the current motion scene, thereby improving the refinement and efficiency of the intercom demand pattern.

[0089] Step S403: The first intercom device group determines the intercom network to be used and the intercom information to be transmitted according to the intercom demand mode.

[0090] Step S404: The first intercom device group transmits the intercom information via the intercom network.

[0091] In this possible example, the intercom demand mode is the cross-domain intercom demand mode; the first intercom device equipment group determines the intercom network to be used and the intercom information to be transmitted according to the intercom demand mode, including: obtaining a pre-stored public intercom channel set corresponding to the cross-domain intercom demand mode, the public intercom channel set including the first public intercom channel of the first public intercom group and the second public intercom channel of the second public intercom group; determining that the intercom information to be transmitted is a preset distress message and / or the voice information of the first user, the preset distress message including the location information and risk broadcast information of the first user; determining that the intercom network to be used is a public intercom channel in the public intercom channel set that has been responded to after polling.

[0092] Among them, in the cross-domain intercom demand mode scenario, the voice information of the first user can be a recording of the user's real-time voice, or it can be dynamically processed according to the first user's voice situation in the actual scenario. If it is detected that the first user has not made any sound for more than a preset time, he may have been unconscious or unable to speak actively. At this time, the device side can extract the pre-stored preset distress information and transmit it on the current public intercom channel.

[0093] It can be seen that in this example, when the intercom demand mode is a cross-domain intercom demand mode, the first intercom device equipment group determines the intercom network to be used and the intercom information to be transmitted according to the business demand situation of the current mode. Since the preset distress information and / or the voice information of the first user can accurately reflect the user's physical condition and degree of urgency, and the public intercom channel in the public intercom channel set that is responded to after polling can maximize the probability that the emergency status information will be received by other users and then respond and rescue in the first time, the timeliness and success rate of intercom information transmission in the cross-domain intercom demand mode are improved.

[0094] In this possible example, the public intercom channel set is created by the following steps: obtaining the location information of at least one group member among multiple group members in the first public intercom group to obtain at least one location information; determining the reference activity area of ​​the first public intercom group based on the at least one location information and a pre-stored map library; querying the public intercom group creation database to obtain the second public intercom channel of the second public intercom group whose activity area matches the reference activity area; creating the public intercom channel set based on the first public intercom channel of the first public intercom group and the second public intercom channel of the second public intercom group.

[0095] Among them, the activity area of ​​the second public intercom group can be set in advance by the group users in the intercom APP function interface, or any device with positioning function in the intercom device group can report the location information. The server or gateway device can determine the activity area by summarizing the multiple location information reported by the devices of multiple intercom group members.

[0096] In a specific implementation, a public intercom channel set can be created on the server side. The server can be directly or indirectly connected to multiple intercom devices, or be connected to an intercom group setting device. Through the communication connection, the server can obtain setting information of the geographical areas and motion scenes of different intercom groups.

[0097] It can be seen that in this example, since the multiple intercom group members belonging to the multiple public intercom channels in the public intercom channel set are all in the same activity area, when an emergency occurs to the first user, any other users in the current activity area have the opportunity to be quickly reached by intercom, thereby improving the timeliness and success rate of conveying emergency intercom information in the same activity area.

[0098] In this possible example, transmitting the intercom information through the intercom network includes: transmitting the preset distress message and / or the voice message through the first public intercom channel; and monitoring the first public intercom channel for a first intercom response message within a first time window;

[0099] If the first intercom response message is detected within the first time window, maintaining the use state of the first public intercom channel;

[0100] If the first intercom response message is not detected within the first time window, transmitting the preset distress message and / or the voice message through the second public intercom channel, and monitoring the second intercom response message on the second public intercom channel within a second time window;

[0101] If the second intercom response message is detected within the second time window, maintaining the use state of the second public intercom channel;

[0102] If the second intercom response message is not detected within the second time window, repeat the steps of transmitting the preset distress message and / or the voice message through the first public intercom channel and subsequent steps until the first intercom response message or the second intercom response message is detected.

[0103] In a specific implementation, the first public intercom channel can be sorted higher in the time window sequence, that is, priority is given to trying to contact other group members in the first intercom group to which the first user belongs. Since users in the same intercom group are more familiar with each other, and other group members in the first user group may have prepared medicines or emergency treatment equipment for the special physical condition of the first user, it is beneficial to improve subsequent response and work efficiency, such as reaching the first user's location in time and removing emergency treatment equipment according to the first user's call for help.

[0104] It can be seen that in this example, multiple public intercom channels in the public intercom channel set are polled through the time window mechanism until the public intercom channel that is responded to for the first time is detected, which improves the timeliness and success rate of the first user's intercom information being reached to other users in the current active area, and improves the intelligence and success rate of the first intercom device group in processing intercom information.

[0105] In some embodiments, the intercom demand mode is the public domain intercom demand mode; determining the intercom network to be used and the intercom information to be transmitted based on the intercom demand mode includes: determining that the intercom network to be used is the first public intercom channel of the first public intercom group; performing a first analysis on the audio sampling data to determine the intercom paging information of the first user; and determining that the intercom information to be transmitted is the intercom paging information.

[0106] In the specific implementation example 1, the first analysis may be: analyzing whether the human voice of the audio sample data is clear; if it is clear, directly using the audio sample data as the intercom paging information; if it is not clear, performing human voice enhancement processing on the audio sample data, and using the processed audio sample data as the intercom paging information;

[0107] In specific implementation example 2, the first analysis can be: first extract human voice features from the audio sampling data to obtain human voice features, and determine the intercom paging information of the first user based on the human voice features, where the human voice features include, for example, semantic features, volume features, speech speed features, etc.; then create the intercom paging information based on the human voice features.

[0108] It should be noted that according to the usage logic of general walkie-talkies, after the user turns on the intercom function, the intercom voice data is transmitted in real time, and after the first user finishes speaking, he will wait for the intercom response information of other users. This waiting intercom response period can be set according to the actual data processing situation in the background. In the waiting intercom response period, if the first user continues to voice instruct the first intercom device to perform other operations, and the other operations conflict with the frequency band scanning and receiving operations of the intercom information in the waiting intercom response period, the first user can be prompted by voice to wait for a response to avoid the first user confusing the usage logic and misunderstanding the abnormal device status.

[0109] It can be seen that in this example, in the public domain intercom demand mode, the first intercom device group determines the first public intercom channel of the first public intercom group as the intercom network to be used, and uses this channel to transmit the intercom paging information of the determined first user, thereby realizing the function of quickly and accurately transmitting the intercom paging information of the first user in the public domain intercom demand mode.

[0110] In some embodiments, the intercom demand mode is the private domain intercom demand mode; determining the intercom network to be used and the intercom information to be transmitted according to the intercom demand mode includes: performing a second analysis on the audio sampling data to determine the intercom call intention of the first user to the second user, and creating a private domain intercom channel; determining that the intercom network to be used is the private domain intercom channel; performing a third analysis on the audio sampling data to determine the intercom paging information of the first user; and determining that the intercom information to be transmitted is the intercom paging information.

[0111] Among them, the intercom paging information can be the semantic content information of the first user in the third analysis result, such as "Lao Wang, come and help me break the wind."

[0112] The private intercom channel is a temporarily created intercom channel. In a specific implementation, transmitting the intercom information through the intercom network includes: sending channel configuration information of the private intercom channel to the second intercom device of the second user through the first public intercom channel of the first public intercom group; and sending the intercom paging information to the second intercom device through the private intercom channel.

[0113] There are various ways to implement the second analysis of the audio sampling data according to the private domain intercom demand pattern to determine the intercom call intention of the first user to the second user.

[0114] In the specific implementation example 1, performing a second analysis on the audio sample data according to the private domain intercom demand pattern to determine the intercom call intention of the first user to the second user includes:

[0115] Performing semantic analysis on the audio sampling data to obtain a semantic analysis result;

[0116] Obtaining a private domain voice command set for the first public intercom group;

[0117] Performing a query operation on the private domain voice instruction set using the vocabulary to obtain a first query result;

[0118] If the first query result indicates that the vocabulary corresponds to an instruction vocabulary referring to the second user in the private domain voice instruction set, an intercom intention of the first user to call the second user is determined.

[0119] The private domain voice command set can include private chat command words for group members, such as "private chat Lao Wang" corresponding to a group member nicknamed Lao Wang, which is used to create a temporary intercom group for the first user and Lao Wang to talk to each other, and "Lao Wang Lao Wang" with repeated words can also correspond to a group member nicknamed Lao Wang, which is used to create a temporary intercom group for the first user and Lao Wang to talk to each other. Specifically, the user can flexibly define and set it in the function interface of the intercom software APP, or the system can default to a rule and inform the user through an interface notification message to facilitate correct use.

[0120] In addition, the private domain voice command set may also include command words for dedicated purpose channels, such as "tower, tower" corresponding to the tower's dedicated intercom channel for communicating with the intercom device of the control center.

[0121] In specific implementation example 2, performing a second analysis on the audio sample data according to the private domain intercom demand pattern to determine the intercom call intention of the first user to the second user includes:

[0122] Performing semantic analysis on the audio sampling data to obtain a semantic analysis result;

[0123] Get the preset nickname set of group members;

[0124] Extracting words with the first word order from the semantic analysis result;

[0125] The word is found to be the group member nickname of the second user in the group member nickname set, and an intercom intention of the first user to call the second user is determined.

[0126] Among them, since the device (such as the first intercom device of the first user or the first mobile terminal communicating with the first intercom device) has previously identified the intercom demand mode of the first user as a private domain intercom demand mode based on the first status data and the target motion scene, and the first feature word in the human voice semantic feature has been determined to be a title in the process of determining the intercom demand mode, the device can directly extract the words of the first word order for query in the current link.

[0127] For example, a certain brand of cycling application APP1 is installed in the first user's mobile phone, and the first intercom device is the first smart intercom helmet worn by the first user. The first smart intercom helmet is equipped with an intercom communication module responsible for intercom communication with other intercom devices, and can also be equipped with a Bluetooth communication module to communicate with mobile phones, smart wearable devices, etc.

[0128] In the "Riding" interface of APP1, there are "Add Device" control and "Create Intercom Group" control. The first user clicks the "Add Device" control to add the first smart intercom helmet. The "Create Intercom Group" control can realize the creation and configuration of the intercom group, such as generating an intercom group QR code and supporting WeChat sharing with other group members. Other group members can scan the code in the mobile phone APP software with one click to obtain the configuration information of the intercom group, and send the configuration information to their own smart intercom helmets to join the intercom group's intercom network.

[0129] In addition, other functional modules in the APP can be used to realize functions such as group member nickname notes, temporary intercom private group creation, chat and location sharing within the group space (offline maps can be downloaded in advance), etc.

[0130] It can be seen that in this example, in the private domain intercom demand mode, the first intercom device group can create a temporary private domain intercom channel based on the first user's intention to have a private chat with the second user, and perform a third analysis on the audio sampling data to determine the intercom paging information of the first user, and then transmit the intercom paging information through the private domain intercom channel, thereby realizing the private chat needs between some group members without the need for manual operation by the user, thereby improving the intelligence, convenience and applicability of processing intercom information.

[0131] It can be seen that in the embodiment of the present application, compared with the existing solution based on voice control of the intercom function of the intercom, the device of the present application first obtains the user's status data, accurately identifies the user's intercom demand pattern based on the user's status data, and then determines the intercom network to be used and the intercom information to be transmitted according to the identified intercom demand pattern, and finally uses the determined intercom network to transmit the intercom information to complete the intercom demand. Since the status data contains audio sampling data and motion sampling data, that is, multimodal data, it can more accurately identify the various types of user's segmented intercom needs in the team sports scene, such as emergency intercom needs, point-to-point intercom needs, etc. In this way, the solution of the present application is conducive to improving the functional scalability and scene applicability of intercoms in team sports scenes, as well as improving the intelligence, comprehensiveness, accuracy and success rate of intercom information processing by intercoms.

[0132] For the same method as above, please refer to Figure 10 , Figure 10 This is a structural diagram of an electronic device 1000 provided in an embodiment of the present application. As shown in the figure, the electronic device 1000 includes a processor 1010, a memory 1020, an intercom communication module 1030 and one or more programs 1021, wherein the one or more programs 1021 are stored in the above-mentioned memory 1020 and are configured to be executed by the above-mentioned processor 1010, and the one or more programs 1021 include instructions for executing any step in the above-mentioned method embodiment.

[0133] The above mainly introduces the solution of the embodiment of the present application from the perspective of the execution process of the method side. It is understandable that, in order to realize the above functions, the electronic device includes a hardware structure and / or software module corresponding to the execution of each function. Those skilled in the art should easily realize that, in combination with the units and algorithm steps of each example described in the embodiment provided herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in a hardware or computer software driven hardware manner depends on the specific application and design constraints of the technical solution. Professional and technical personnel can 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.

[0134] The embodiment of the present application can divide the functional units of the electronic device according to the above method example. For example, each functional unit can be divided according to each function, or two or more functions can be integrated into one processing unit. The above integrated unit can be implemented in the form of hardware or in the form of software functional units. It should be noted that the division of units in the embodiment of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation.

[0135] like Figure 11 As shown, the embodiment of the present application also provides a functional unit block diagram of an intercom information processing system based on a voice control function, including:

[0136] An acquiring unit 110 is configured to acquire first status data of a first user, the first status data including audio sampling data and motion sampling data, the first intercom device of the first user being an intercom device in a first public intercom group, and the service scenario to which the first public intercom group belongs being a target motion scenario;

[0137] An identification unit 111 is configured to identify an intercom demand pattern of the first user based on the first status data and the target motion scene, where the intercom demand pattern includes a cross-domain intercom demand pattern, a public domain intercom demand pattern, and a private domain intercom demand pattern;

[0138] The determining unit 112 is used to determine the intercom network to be used and the intercom information to be transmitted according to the intercom demand mode; the transmitting unit 113 is used to transmit the intercom information through the intercom network.

[0139] It can be seen that in the embodiment of the present application, compared with the existing solution based on voice control of the intercom function of the intercom, the device of the present application first obtains the user's status data, accurately identifies the user's intercom demand pattern based on the user's status data, and then determines the intercom network to be used and the intercom information to be transmitted according to the identified intercom demand pattern, and finally uses the determined intercom network to transmit the intercom information to complete the intercom demand. Since the status data contains audio sampling data and motion sampling data, that is, multimodal data, it can more accurately identify the various types of user's segmented intercom needs in the team sports scene, such as emergency intercom needs, point-to-point intercom needs, etc. In this way, the solution of the present application is conducive to improving the functional scalability and scene applicability of intercoms in team sports scenes, as well as improving the intelligence, comprehensiveness, accuracy and success rate of intercom information processing by intercoms.

[0140] In one possible example, in terms of identifying the intercom demand pattern of the first user based on the first state data and the target motion scene, the identification unit 111 is specifically used to: perform a first processing on the motion sampling data to obtain the motion characteristics of the first user; and perform a second processing on the audio sampling data to obtain the human voice semantic characteristics and environmental sound characteristics of the first user; and determine the intercom demand pattern of the first user based on the target motion scene, the action characteristics, the human voice semantic characteristics and the environmental sound characteristics.

[0141] The embodiment of the present application further provides a computer storage medium, wherein the computer storage medium stores a computer program for electronic data exchange, and the computer program causes a computer to execute part or all steps of any method described in the above method embodiments, and the computer includes an electronic device.

[0142] It should be noted that, for the above-mentioned method embodiments, in order to simply describe, they are all expressed as a series of action combinations, but those skilled in the art should know that the present application is not limited to the action sequence described, because according to the present application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should know that the embodiments described in the specification all belong to preferred embodiments, and the actions and modules involved are not necessarily necessary for the present application.

[0143] In the above embodiments, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0144] In several embodiments provided by the present application, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely schematic. The division of the above units is only a logical function division. There can be another division manner in actual implementation. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interfaces, devices or units, and can be electrical or other forms.

[0145] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on a plurality of network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0146] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically independently, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0147] If the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a memory and includes a number of instructions for enabling a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the above-mentioned methods in each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk, and other media that can store program code.

[0148] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, which may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0149] The above is a detailed introduction to the embodiments of the present application. Specific examples are used herein to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, for those skilled in the art, according to the idea of ​​the present application, there may be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A method for processing intercom information based on voice control function, characterized in that: include: Acquiring first status data of a first user, where the first status data includes audio sampling data and motion sampling data, where the first intercom device of the first user is an intercom device in a first public intercom group, and where the service scenario to which the first public intercom group belongs is a target motion scenario; identifying an intercom demand pattern of the first user according to the first status data and the target motion scene, the intercom demand pattern including a cross-domain intercom demand pattern, a public domain intercom demand pattern, and a private domain intercom demand pattern; Determining the intercom network to be used and the intercom information to be transmitted according to the intercom demand mode; The intercom information is transmitted through the intercom network.

2. The method according to claim 1, characterized in that The identifying the intercom demand pattern of the first user according to the first status data and the target motion scene includes: performing a first processing on the motion sampling data to obtain motion features of the first user; performing a second processing on the audio sampling data to obtain a human voice semantic feature and an ambient sound feature of the first user; The intercom demand pattern of the first user is determined according to the target motion scene, the action characteristics, the human voice semantic characteristics and the ambient sound characteristics.

3. The method according to claim 2, characterized in that The determining the intercom demand mode of the first user according to the target motion scene, the action feature, the human voice semantic feature, and the ambient sound feature includes: Querying an intercom demand pattern mapping relationship set according to the target sports scene to obtain a target intercom demand pattern mapping relationship subset corresponding to the target sports scene; Combining the action feature, the human voice semantic feature and the environmental sound feature to obtain a comprehensive state feature; The target intercom demand pattern mapping relationship subset is queried according to the comprehensive status feature to obtain the intercom demand pattern of the first user that is adapted to the comprehensive status feature.

4. The method according to any one of claims 1 to 3, characterized in that The intercom demand mode is the cross-domain intercom demand mode; and determining the intercom network to be used and the intercom information to be transmitted according to the intercom demand mode includes: Obtaining a pre-stored public intercom channel set corresponding to the cross-domain intercom demand mode, the public intercom channel set including a first public intercom channel of the first public intercom group and a second public intercom channel of the second public intercom group; Determining that the intercom information to be transmitted is a preset distress message and / or a voice message of the first user, wherein the preset distress message includes location information and risk broadcast information of the first user; The intercom network to be used is determined to be a public intercom channel in the public intercom channel set that is responded to after polling.

5. The method according to claim 4, characterized in that The public intercom channel set is created by the following steps: Acquire location information of at least one group member among a plurality of group members in the first public intercom group to obtain at least one piece of location information; determining a reference activity area of ​​the first public intercom group according to the at least one location information and a pre-stored map library; Querying a public intercom group creation database to obtain the second public intercom channel of the second public intercom group whose activity area matches the reference activity area; The public intercom channel set is created according to the first public intercom channel of the first public intercom group and the second public intercom channel of the second public intercom group.

6. The method according to claim 4, characterized in that The transmitting the intercom information through the intercom network includes: Transmitting the preset distress message and / or the voice message through the first public intercom channel; Monitoring the first public intercom channel for a first intercom response message within a first time window; If the first intercom response message is detected within the first time window, maintaining the use state of the first public intercom channel; If the first intercom response message is not detected within the first time window, transmitting the preset distress message and / or the voice message through the second public intercom channel, and monitoring the second intercom response message on the second public intercom channel within a second time window; If the second intercom response message is detected within the second time window, maintaining the use state of the second public intercom channel; If the second intercom response message is not detected within the second time window, repeat the steps of transmitting the preset distress message and / or the voice message through the first public intercom channel and subsequent steps until the first intercom response message or the second intercom response message is detected.

7. The method according to any one of claims 1 to 3, characterized in that The intercom demand mode is the public domain intercom demand mode; and determining the intercom network to be used and the intercom information to be transmitted according to the intercom demand mode includes: Determining that the intercom network to be used is the first public intercom channel of the first public intercom group; performing a first analysis on the audio sampling data to determine intercom paging information of the first user; Determine that the intercom information to be transmitted is the intercom paging information.

8. The method according to any one of claims 1 to 3, characterized in that The intercom demand mode is the private domain intercom demand mode; and determining the intercom network to be used and the intercom information to be transmitted according to the intercom demand mode includes: Performing a second analysis on the audio sampling data to determine the first user's intercom call intention with respect to the second user, and creating a private intercom channel; Determining that the intercom network to be used is the private domain intercom channel; performing a third analysis on the audio sampling data to determine intercom paging information of the first user; Determine that the intercom information to be transmitted is the intercom paging information.

9. An intercom information processing system based on voice control function, characterized in that: include: an acquiring unit, configured to acquire first status data of a first user, the first status data including audio sampling data and motion sampling data, the first intercom device of the first user being an intercom device in a first public intercom group, and the service scenario to which the first public intercom group belongs being a target motion scenario; an identification unit, configured to identify an intercom demand pattern of the first user according to the first status data and the target motion scene, the intercom demand pattern including a cross-domain intercom demand pattern, a public domain intercom demand pattern, and a private domain intercom demand pattern; A determination unit, configured to determine an intercom network to be used and intercom information to be transmitted according to the intercom demand mode; A transmission unit is used to transmit the intercom information through the intercom network.

10. The system according to claim 9, characterized in that In terms of identifying the intercom demand pattern of the first user based on the first state data and the target motion scene, the identification unit is specifically used to: perform a first processing on the motion sampling data to obtain the motion characteristics of the first user; and perform a second processing on the audio sampling data to obtain the human voice semantic characteristics and environmental sound characteristics of the first user; and determine the intercom demand pattern of the first user based on the target motion scene, the action characteristics, the human voice semantic characteristics and the environmental sound characteristics.

Images