CN105551504A - Method and device for triggering function application of intelligent mobile terminal based on crying sound - Google Patents

Abstract

The invention discloses a method and device for triggering the function application of an intelligent mobile terminal based on crying. The method includes: when a sound is detected, extracting the sound feature of the sound and recording it as the first sound feature; if the sound duration is greater than or equal to the first preset value, and the degree of coincidence between the first sound feature and the pre-acquired second sound feature is greater than or equal to the second preset value, triggering the smart mobile terminal to execute the comfort function, wherein, The second sound feature is the crying sound feature of the current user of the smart mobile terminal. Using this method, when the user is crying, the smart mobile terminal can be triggered to actively comfort the user, so as to reduce the user's sadness, achieve the purpose of the smart mobile terminal actively executing functional applications, and reflect the humanized characteristics of the smart mobile terminal. Improved user experience.

Description

A method and device for triggering functional applications of smart mobile terminals based on crying

technical field

The embodiments of the present invention relate to the technical field of computer applications, and in particular to a method and device for triggering functional applications of smart mobile terminals based on crying sounds.

Background technique

With the wide application and development and innovation of computer technology, more and more smart products appear in people's lives. Smart mobile terminals have become one of the popular smart products. In addition to the most basic communication functions, smart mobile terminals also Based on the relevant hardware and various application software installed on it, it provides great help for people's life, study and work.

Existing smart mobile terminals integrate multiple functions into one body, and can be used as a camera to take pictures, navigate as a navigator, watch videos as a player, and entertain as a game console, etc., which fully embodies its versatility. With the widespread use of smart mobile terminals, people have higher and higher requirements for functional applications on smart mobile terminals. It is very hoped that smart mobile terminals can automatically sense user needs and actively provide corresponding smart application services. Many functional applications on the terminal are designed to passively serve users, which cannot well reflect the subjective and humanized characteristics of smart mobile terminals.

Contents of the invention

The purpose of the present invention is to propose a method and device for triggering the function application of an intelligent mobile terminal based on crying, so as to realize the operation that the intelligent mobile terminal actively executes the comfort function when the user is crying.

On the one hand, an embodiment of the present invention provides a method for triggering a functional application of a smart mobile terminal based on crying, including:

When a sound is detected, the sound feature of the sound is extracted and recorded as the first sound feature;

If the duration of the sound is greater than or equal to the first preset value, and the degree of coincidence between the first sound feature and the pre-acquired second sound feature is greater than or equal to the second preset value, trigger the smart mobile terminal to perform comfort function, wherein the second sound feature is the crying sound feature of the current user of the smart mobile terminal.

On the other hand, an embodiment of the present invention provides a device for triggering a functional application of a smart mobile terminal based on a crying sound, including:

The sound monitoring module is used to extract the sound feature of the sound and record it as the first sound feature when a sound is detected;

A function trigger module, configured to when the duration of the sound is greater than or equal to a first preset value, and the degree of coincidence between the first sound feature and the pre-acquired second sound feature is greater than or equal to a second preset value, The smart mobile terminal is triggered to execute the comfort function, wherein the second sound feature is the crying sound feature of the current user of the smart mobile terminal.

The embodiment of the present invention provides a method and device for triggering the function application of an intelligent mobile terminal based on crying sound. Compared with the characteristics of the user's cry, if the preset matching degree is reached and the sound duration is longer than the preset value, it is considered that the current user of the smart mobile terminal is in a sad mood; then the smart mobile terminal is triggered to perform a comfort function. Using this method, when the user is crying, the smart mobile terminal can be triggered to actively comfort the user, so as to reduce the user's sadness, achieve the purpose of the smart mobile terminal actively executing functional applications, and reflect the humanized characteristics of the smart mobile terminal. Improved user experience.

Description of drawings

FIG. 1 is a schematic flowchart of a method for triggering a function application of a smart mobile terminal based on a crying sound according to Embodiment 1 of the present invention;

FIG. 2 is a schematic flowchart of a method for triggering a function application of a smart mobile terminal based on a crying sound according to Embodiment 2 of the present invention;

FIG. 3 is a structural block diagram of an apparatus for triggering a function application of a smart mobile terminal based on a crying sound according to Embodiment 3 of the present invention.

detailed description

The technical solution of the present invention will be further described below in conjunction with the accompanying drawings and through specific implementation methods. It should be understood that the specific embodiments described here are only used to explain the present invention, but not to limit the present invention. In addition, it should be noted that, for the convenience of description, only some structures related to the present invention are shown in the drawings but not all structures.

Embodiment one

Figure 1 is a schematic flowchart of a method for triggering functional applications of an intelligent mobile terminal based on crying sounds provided by Embodiment 1 of the present invention. The method can be executed by a device for triggering functional applications of an intelligent mobile terminal based on crying sounds, wherein the device can be implemented by software and /or implemented by hardware, and generally integrated in an intelligent mobile terminal.

As shown in FIG. 1 , a method for triggering a functional application of a smart mobile terminal based on a crying sound provided by an embodiment of the present invention specifically includes the following operations:

S101. When a sound is detected, extract a sound feature of the sound and record it as a first sound feature.

In this embodiment, based on the method proposed in the present invention, it is possible to always monitor whether there is sound around the smart mobile terminal. Generally, the present invention can monitor all sounds. Preferably, the sound monitored by the present invention is mainly the sound made by people. . Therefore, when a human voice is detected, the detected human voice is extracted. Generally, the main extraction process is to obtain the sound feature of the monitored sound, and the sound feature is generally the frequency spectrum of the sound. For the convenience of expression, in this embodiment, the extracted sound feature is recorded as the first sound feature. In this embodiment, the smart mobile terminal is specifically a smart phone, a tablet computer and other mobile terminals that can provide users with smart application functions.

S102. If the duration of the sound is greater than or equal to the first preset value, and the degree of coincidence between the first sound feature and the pre-acquired second sound feature is greater than or equal to the second preset value, trigger the smart mobile terminal Executing a comforting function, wherein the second sound feature is the crying sound feature of the current user of the smart mobile terminal.

In this embodiment, after the sound feature is extracted from the monitored sound, the duration of the sound should be continuously monitored, and in addition, the extracted first sound feature should be compared and judged. First of all, for the monitoring of the sound duration, it is necessary to judge whether the sound duration is greater than or equal to the first preset value; then for the comparison and judgment of the first sound feature, it is necessary to judge whether the first sound feature and the pre-acquired Whether the matching degree of the second sound feature is greater than or equal to the second preset value; finally, if the above two judgment conditions meet the requirements, then the smart mobile terminal can be triggered to perform the comfort function.

Further, the first preset value is: 20 seconds; the second preset value is 80%.

In this embodiment, the first preset value may specifically refer to the preset value set to determine the duration of the sound. Generally, the preset value is set at 15 seconds to 30 seconds. Preferably, the preset value is set to 20 seconds, but it is not limited to 20 seconds. In addition, the second preset value may specifically refer to a preset value for judging the coincidence degree between the first sound feature and the second sound feature. Generally, the preset value may be set at a value ranging from 70% to 100%. Within the value range, preferably, the preset value is set to 80%, but not limited to 80%.

In this embodiment, the pre-acquired second sound feature is the crying sound feature of the current user of the smart mobile terminal, and the crying sound feature can be obtained through preprocessing. The triggering of the smart mobile terminal to execute the comfort function is specifically manifested in: triggering the smart mobile terminal to play music, video or cute animation, and also triggering the smart mobile terminal to automatically send messages seeking comfort to relatives and friends, so as to alleviate the user's sadness.

Embodiment 1 of the present invention provides a method for triggering the function application of an intelligent mobile terminal based on crying sounds. The method extracts sound features from the monitored user voice, and compares the extracted sound features with pre-acquired crying features. Yes, if the sound duration reaches the preset value and the sound characteristics meet the matching conditions, the smart mobile terminal is triggered to execute the comfort function. By using this method, the purpose of the intelligent mobile terminal actively executing the comfort function when the user is crying is achieved, which embodies the humanized characteristics of the intelligent mobile terminal.

Embodiment two

Fig. 2 is a schematic flowchart of a method for triggering the function application of an intelligent mobile terminal based on crying sound provided by Embodiment 2 of the present invention. This embodiment is optimized on the basis of the above-mentioned embodiment. In this embodiment, in the step When a sound is detected, extract the sound feature of the sound and record it as the first sound feature" before adding the step "collect the sound samples of many people talking and crying, and obtain the correspondence between speaking and crying Collect the speech of the current user of the smart mobile terminal, and extract the sound feature of the speech, which is recorded as the third sound feature; based on the correspondence between the speech and crying and the third sound feature, obtain The feature of the crying sound of the current user is recorded as the second sound feature."

As shown in FIG. 2 , a method for triggering a functional application of a smart mobile terminal based on a crying sound provided by an embodiment of the present invention specifically includes the following steps:

Step S201 , collect voice samples of multiple people speaking and crying, and obtain the correspondence between speaking voices and crying voices.

In this embodiment, before the comfort function of the smart mobile terminal is triggered based on the user's crying sound, certain preprocessing work is required, for example, the collection of sound samples, the extraction of sound features of the sound samples, etc., therefore, the steps S201 is mainly for collecting and processing sound samples.

Specifically, this step can be described as: collecting and recording the sounds of many people speaking normally, and collecting and recording the sounds of these people when they cry; The voice analysis system analyzes the connection between people's normal speaking voice and crying voice; finally obtains the corresponding relationship between people's speaking voice and crying voice. Generally, the corresponding relationship between the speaking voice and the crying voice is mainly extracted by analyzing the spectrograms of the speaking voice and the crying voice.

Step S202, collect the speech of the current user of the smart mobile terminal, and extract the sound feature of the speech, which is recorded as the third sound feature.

In this embodiment, before the comfort function of the smart mobile terminal is triggered based on the user's crying sound, the preprocessing also includes the operation of sample collection of the current user's voice of the smart mobile terminal, wherein step S202 can be understood It is an operation of collecting and analyzing the voice samples of the current user of the smart mobile terminal.

Specifically, this step can be described as: when the current user of the smart mobile terminal is making a call, collect the voice information of the current user during the call, or deliberately record the voice of the current user of the smart mobile terminal to achieve sound sample collection; Speech analysis is performed on the collected speech of the current user, and sound features of the speech of the current user are extracted. For the convenience of expression, the sound feature of the current user's voice is recorded as the third sound feature.

Step S203 , based on the correspondence between the speaking voice and the crying voice and the third voice feature, acquire the crying voice feature of the current user, and record it as the second voice feature.

In this embodiment, based on the corresponding relationship between the speaking voice and the crying sound acquired in step S201, and the voice feature (third voice feature) of the voice of the current user of the smart mobile terminal acquired in step S202, it is possible to simulate the crying of the current user The sound feature of the time, for the convenience of expression, the simulated crying sound feature of the current user is recorded as the second sound feature.

Step S204, when a sound is detected, extract the sound feature of the sound and record it as the first sound feature.

In this embodiment, after the above steps S201 to S203 are completed, the preprocessing work of triggering the comfort function of the smart mobile terminal based on the crying sound of the user is completed. Then start the sound monitoring based on step S204 to monitor the sound around the smart mobile terminal in real time, and the sound monitored is generally preferably the sound of a person; when a sound is detected, the monitored sound is processed and the sound is extracted feature, the sound feature is the first sound feature.

Further, both the first sound feature and the second sound feature are sound spectrograms.

Specifically, the sound features in the method of the present invention, such as the first sound feature and the second sound feature, all refer to the sound spectrogram. The sound spectrogram can be specifically understood as an image distribution curve obtained by arranging sound frequencies. The sound spectrum can be divided into high frequency range, middle high frequency range, middle low frequency range and low frequency range based on frequency. Generally, the sound spectrum is mainly used for the analysis of timbre and tone, so as to identify different sounds.

Step S205, judging whether the duration of the sound is greater than or equal to the first preset value, if yes, execute step S206; if not, return to step S204.

Exemplarily, step S205 can be understood as: judging whether the duration of the monitored sound is greater than or equal to 20 seconds, if greater than or equal to 20 seconds, then execute step S206; if not 20 seconds, then directly return to step S204. It should be noted that the set sound duration of 20 seconds in this embodiment is a preferred value, and is not limited to this duration.

Step S206, judging whether the degree of coincidence between the first sound feature and the second sound feature is greater than or equal to a second preset value, if yes, execute step S207; if not, return to step S204.

Exemplarily, step S206 can be understood as: judging whether the matching degree of the sound feature of the monitored sound and the second sound feature acquired in advance is greater than or equal to 80%, and if the matching degree is greater than or equal to 80%, perform step S207; otherwise, directly return to step S204.

In this embodiment, the degree of coincidence of the sound features may specifically be understood as the degree of similarity or coincidence of sound spectrograms. It should be noted that the matching degree of 80% set in this embodiment is also a preferred value, and is not limited to this value; in addition, the following step S207 can only be executed when the judgment conditions of step S205 and step S206 are met at the same time .

Step S207, triggering the smart mobile terminal to execute the comfort function.

In this embodiment, the ultimate goal of the method of the present invention is to automatically trigger the comfort function of the smart mobile terminal based on the cry of the user, that is, the smart mobile terminal can respond after recognizing the cry of the user, and actively respond to the smart mobile terminal. The current users of the app are comforted and relieved of sadness.

Further, the triggering the smart mobile terminal to execute the comforting function specifically includes: triggering the smart mobile terminal to play preset music or animation video; and/or triggering the smart mobile terminal to send a preset comfort message to a preset mobile phone number.

In this embodiment, the smart mobile terminal can perform the comfort function in various forms. Specifically, the smart mobile terminal can be triggered to play music or animated videos, wherein the played music is stored in the memory card of the smart mobile terminal in advance. The music content can be set artificially. The set music content can be artificially recorded words for comfort in advance, or it can be the user's favorite song, etc.; similarly, the played video is also stored in the storage device of the smart mobile terminal in advance. In the card, the video content to be played can also be artificially set, and its content can be a pre-recorded real video, or a user's favorite program or animated video.

In addition, the method of the present invention can also trigger the intelligent mobile terminal to automatically send messages seeking comfort to relatives and friends. Before sending the message, it is necessary to manually set the target object and the mobile phone number of the message. Generally, the present invention can simultaneously set Set multiple target objects, and then make the smart mobile terminal send mass text messages to all the preset people; at the same time, the contents of the sent comfort text messages are also pre-edited and stored in corresponding folders.

Embodiment 2 of the present invention provides a method for triggering the function application of an intelligent mobile terminal based on crying. The method first collects samples of speaking and crying of multiple people, extracts and analyzes the corresponding relationship between speaking and crying; and then Collect the voice of the current user of the smart mobile terminal; then, based on the corresponding relationship and the voice of the user, pre-acquire a cry feature sample of a user; finally compare the voice feature acquired during monitoring with the cry feature sample, and perform intelligent mobile The automatic triggering of the comfort function of the terminal enables the smart mobile terminal to automatically play music or video; or the smart mobile terminal automatically sends text messages requiring comfort to preset relatives and friends. Using this method, the intelligent mobile terminal is triggered to automatically execute the comfort function based on the recognition of the characteristics of the crying sound, which embodies the humanized characteristics of the intelligent mobile terminal, and at the same time improves the user experience of the user on the intelligent mobile terminal.

Embodiment three

FIG. 3 is a schematic structural diagram of an apparatus for triggering a function application of a smart mobile terminal based on a crying sound according to Embodiment 3 of the present invention. The device can be implemented by software and/or hardware, and is generally integrated in an intelligent mobile terminal. As shown in FIG. 3 , the specific structure of the device is as follows, including: a sound monitoring module 311 and a function triggering module 312 . in,

The sound monitoring module 311 is used to extract the sound feature of the sound and record it as the first sound feature when a sound is detected;

A function trigger module 312, configured to when the duration of the sound is greater than or equal to a first preset value, and the degree of coincidence between the first sound feature and the pre-acquired second sound feature is greater than or equal to a second preset value , triggering the smart mobile terminal to execute the comfort function, wherein the second sound feature is the crying sound feature of the current user of the smart mobile terminal.

Further, the device further includes: a first collection module 301 , a second collection module 302 and a cry feature acquisition module 303 . in,

The first collection module 301 is used to collect sound samples of many people when speaking and crying, and analyze the correspondence between speaking and crying;

The second collection module 302 is used to collect the speech of the current user of the smart mobile terminal, and extract the sound feature of the speech, which is recorded as the third sound feature;

The crying feature acquisition module 303 is configured to acquire the crying feature of the current user based on the correspondence between the speaking voice and the crying sound and the third voice feature, which is recorded as the second voice feature.

In this embodiment, the device first collects sound samples of many people talking and crying through the first collection module 301 to obtain the correspondence between speaking and crying; The speech of the current user of the terminal; then determine the sound feature of the current user's cry based on the collected speech of the current user and the corresponding relationship between the obtained speech and crying by the cry feature acquisition module 303; then based on sound monitoring Module 311 monitors whether there is a sound at any time, and when a sound is detected, the sound feature of the sound is extracted; finally, the function trigger module 312 is used to determine whether the sound feature extracted is consistent with the sound feature of the user's crying sound. greater than or equal to the preset value, and determine whether the duration of the monitored sound is greater than or equal to the preset value, if the above conditions are met, the smart mobile terminal will be automatically triggered to perform comfort functions, such as playing preset music or animated videos, or sending Relatives and friends send preset text messages for comfort.

On the basis of the above embodiments, the function triggering module 312 is specifically configured to: when the duration of the sound detected by the sound monitoring module is greater than or equal to a first preset value, and the first sound feature is consistent with the pre-acquired When the matching degree of the second sound feature is greater than or equal to the second preset value, the smart mobile terminal is triggered to play preset music or animation video; and/or

When the sound duration monitored by the sound monitoring module is greater than or equal to a first preset value, and the degree of coincidence between the first sound feature and the pre-acquired second sound feature is greater than or equal to a second preset value, The smart mobile terminal is triggered to send a preset text message seeking comfort to a preset mobile phone number.

At the same time, in the device for triggering the function application of the smart mobile terminal based on crying, the first preset value is: 20 seconds; the second preset value is: 80%.

In addition, on the basis of the above embodiments, the first sound feature and the second sound feature are sound spectrograms.

Embodiment 3 of the present invention provides a device for triggering functional applications of smart mobile terminals based on crying sounds. With this device, when a user is crying, the smart mobile terminal can actively play music or video to comfort the user, or the smart mobile terminal can automatically Send comfort messages to relatives and friends of the user, reduce the sadness of the user, and achieve the purpose of the intelligent mobile terminal actively performing the comfort function when the user is crying, reflecting the humanized characteristics of the intelligent mobile terminal.

Note that the above are only preferred embodiments of the present invention and applied technical principles. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the protection scope of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments, and can also include more other equivalent embodiments without departing from the concept of the present invention, and the present invention The scope is determined by the scope of the appended claims.

Claims (10)

1. A method for triggering an intelligent mobile terminal function application based on crying, characterized in that, comprising: When a sound is detected, the sound feature of the sound is extracted and recorded as the first sound feature; If the duration of the sound is greater than or equal to the first preset value, and the degree of coincidence between the first sound feature and the pre-acquired second sound feature is greater than or equal to the second preset value, trigger the smart mobile terminal to perform comfort function, wherein the second sound feature is the crying sound feature of the current user of the smart mobile terminal. 2. The method according to claim 1, characterized in that, before the sound feature of the sound is extracted and recorded as the first sound feature when the sound is detected, it also includes: Collect voice samples of multiple people speaking and crying, and obtain the correspondence between speaking and crying; Collect the voice of the current user of the smart mobile terminal, and extract the voice feature of the voice, which is recorded as the third voice feature; Based on the corresponding relationship between the speaking voice and the crying voice and the third voice feature, the crying voice feature of the current user is obtained, which is recorded as the second voice feature. 3. The method according to claim 1, wherein the triggering the smart mobile terminal to perform a comfort function specifically comprises: Trigger the smart mobile terminal to play preset music or animation video; and/or The smart mobile terminal is triggered to send a preset text message seeking comfort to a preset mobile phone number. 4. The method according to any one of claims 1-3, wherein the first preset value is: 20 seconds; The second preset value is: 80%. 5. The method according to any one of claims 1-3, wherein the first sound feature and the second sound feature are sound spectrograms. 6. A device for triggering functional applications of smart mobile terminals based on crying, characterized in that it comprises: The sound monitoring module is used to extract the sound feature of the sound and record it as the first sound feature when a sound is detected; A function trigger module, configured to when the duration of the sound is greater than or equal to a first preset value, and the degree of coincidence between the first sound feature and the pre-acquired second sound feature is greater than or equal to a second preset value, The smart mobile terminal is triggered to execute the comfort function, wherein the second sound feature is the crying sound feature of the current user of the smart mobile terminal. 7. The device according to claim 6, further comprising: The first collection module is used to collect sound samples of many people speaking and crying, and obtain the corresponding relationship between speaking and crying; The second collection module is used to collect the speech of the current user of the smart mobile terminal, and extract the sound feature of the speech, which is recorded as the third sound feature; The crying feature acquisition module is configured to acquire the crying feature of the current user based on the correspondence between the speaking voice and the crying sound and the third voice feature, which is recorded as the second voice feature. 8. The device according to claim 6, wherein the function trigger module is specifically used for: When the duration of the sound monitored by the sound monitoring module is greater than or equal to a first preset value, and the degree of coincidence between the first sound feature and the pre-acquired second sound feature is greater than or equal to a second preset value, Trigger the smart mobile terminal to play preset music or animation video; and/or When the duration of the sound monitored by the sound monitoring module is greater than or equal to a first preset value, and the degree of coincidence between the first sound feature and the pre-acquired second sound feature is greater than or equal to a second preset value, The smart mobile terminal is triggered to send a preset text message seeking comfort to a preset mobile phone number. 9. The device according to any one of claims 6-8, wherein the first preset value is: 20 seconds; The second preset value is: 80%. 10. The device according to any one of claims 6-8, wherein the first sound feature and the second sound feature are sound spectrograms.