A sound recognition alarm method and system, electronic device and medium

Abstract

The application discloses a sound recognition alarm method and system, electronic equipment and medium, and relates to the technical field of sound recognition. A plurality of preset time periods are set, corresponding sound collection sensitivities are configured for the plurality of preset time periods and sound types respectively, and are marked in a sound existing model. Sound information in the environment is collected in real time according to the sound existing model, wherein the sound information comprises audio information, the time of collecting the sound and the sound decibel, and the sound information is constructed in the sound existing model. The audio information is analyzed to obtain the sound type, and an alarm mode is implemented on the interference sound corresponding to the sound decibel that does not satisfy the preset condition. The sound type library is obtained by storing the interference sound feature set and the normal sound feature set, has a powerful database for subsequent environmental sound recognition, can help to quickly identify the square dance music in subsequent actual life, and can efficiently react and perform alarm processing.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of sound recognition, in particular to a sound recognition and alarm method and system, an electronic device and a medium. BACKGROUND

[0002] As a popular mass fitness activity among the elderly, square dancing not only enriches the lives of the elderly and promotes their physical and mental health, but also strengthens the exchange and interaction among community members, creating a harmonious community atmosphere.

[0003] However, the popularity of square dancing is accompanied by a series of problems, the most prominent of which is noise pollution. Due to the improper selection of some square dancing venues, such as locations adjacent to residential areas, schools, hospitals and other places that require a quiet environment, high-decibel music and cheers often interfere with the study, work and rest of surrounding residents. It is difficult to identify square dancing in a complex sound environment and thus to perform alarm processing in the current regulation of square dancing. SUMMARY

[0004] The purpose of the present application is to provide a sound recognition and alarm method, system, electronic device and medium to solve the problems in the background art.

[0005] To achieve the above purpose, the present application provides the following technical solution: a sound recognition and alarm method, comprising the following steps:

[0006] A plurality of preset time periods are set, and corresponding sound collection sensitivities are configured for each of the plurality of preset time periods and sound types, and are marked in a sound presence model, wherein the sound types include normal sound and interference sound;

[0007] Sound information in the environment is collected in real time according to the sound presence model, wherein the sound information includes audio information, the time of collecting the sound, and the sound decibel, and the sound information is constructed in the sound presence model;

[0008] The audio information is analyzed to obtain the sound type, and an alarm mode is implemented for the interference sound corresponding to the sound decibel that does not meet the preset condition.

[0009] In a preferred embodiment, the step of setting a plurality of preset time periods, configuring corresponding sound collection sensitivities for each of the plurality of preset time periods and sound types, and marking them in a sound presence model, comprises:

[0010] The jurisdiction range of sound recognition is determined, the geographical environment within the jurisdiction range is obtained, and a sound presence model is obtained by three-dimensional construction based on the geographical environment and the jurisdiction range;

[0011] Mark a plurality of sound collection points in the sound presence model, and set a plurality of wandering position ends in the sound presence model, wherein the wandering position ends and the plurality of sound collection points are both connected by an analog channel for bidirectional communication, and the wandering position end is a port provided with a storage area;

[0012] A plurality of preset time periods are set, and corresponding sound collection sensitivities are configured for the plurality of preset time periods;

[0013] An identification strip is constructed and a sound type library is developed, wherein the sound type library stores a set of interference sound characteristics and a set of normal sound characteristics;

[0014] The set of interference sound characteristics and the set of normal sound characteristics in the sound type library are respectively taken as interference sound and normal sound;

[0015] The interference sound and the normal sound are taken as sound types;

[0016] The preset time periods and the corresponding sound collection sensitivities are marked in the sound presence model.

[0017] In one preferred embodiment, the step of constructing an identification strip and developing a sound type library comprises:

[0018] An audio storage strip is set, a plurality of identification nodes are provided on the audio storage strip, and the plurality of identification nodes on the audio storage strip are all connected to one cloud server;

[0019] The audio storage strip is structurally copied to obtain a plurality of type library audio storage strips, and the plurality of identification nodes on the plurality of type library audio storage strips are all connected to the corresponding cloud server of the audio storage strip;

[0020] The type library audio storage strips are respectively one-to-one bound with the audio of the interference sound and the audio of the normal sound, and the audio of the interference sound and the audio of the normal sound are respectively placed in the corresponding bound type library audio storage strips to obtain a set of interference sound characteristics and a set of normal sound characteristics;

[0021] The set of interference sound characteristics and the set of normal sound characteristics are stored to obtain a sound type library.

[0022] In one preferred embodiment, the step of placing the audio of the interference sound and the audio of the normal sound in the corresponding bound type library audio storage strips to obtain a set of interference sound characteristics and a set of normal sound characteristics comprises:

[0023] The audio of the interference sound and the audio of the normal sound are respectively placed in the corresponding bound type library audio storage strips;

[0024] Collecting feature information of the audio of the interference sound or the audio of the normal sound through the identification nodes in the type library audio storage bar, wherein the feature information comprises sound frequency change information between adjacent identification nodes and gap information between sound tone peaks between adjacent identification nodes;

[0025] Storing the feature information through the adjacent identification nodes into the corresponding cloud server to obtain an interference sound feature set and a normal sound feature set in each type library audio storage bar.

[0026] In a preferred embodiment, the step of constructing the sound information in the sound presence model comprises:

[0027] Collecting audio information in the environment, time of collecting the sound, audio time and sound decibel as the sound information in the jurisdiction range corresponding to the sound presence model;

[0028] Extracting the audio information in terms of tone, and dividing the audio information according to the tone and the audio time to obtain a plurality of independent audio information;

[0029] When the plurality of independent audio information is obtained, a corresponding number of wandering position terminals are enabled to wander in the sound presence model, the wandering position terminals and the plurality of sound collection points are always in a connected state, the plurality of sound collection points reversely transmit the sound information corresponding to the collected independent audio information to the wandering position terminals through the simulation channel, and the plurality of sound collection points and the wandering position terminals can jointly determine the position where the sound information is generated as the generation position of the independent audio information, and the plurality of independent audio information is marked in the sound presence model according to the generation position.

[0030] In a preferred embodiment, the step of analyzing the audio information to obtain the sound type and implementing the alarm mode for the interference sound corresponding to the sound decibel not satisfying the preset condition comprises:

[0031] Processing the independent audio information according to the audio storage bar to obtain the sound type;

[0032] Implementing the alarm mode when the sound type is the interference sound and the sound decibel does not satisfy the preset condition, wherein the alarm mode comprises emitting a sound wave opposite in phase to the interference sound for noise reduction, actively reducing the normal sound and alarming.

[0033] In a preferred embodiment, the step of processing the independent audio information according to the audio storage bar to obtain the sound type comprises:

[0034] Copying the audio storage bar according to the number of independent audio information to obtain a plurality of identification audio storage bars;

[0035] The independent audio information is placed one-to-one in the identification audio storage strip, and the identification feature information of the independent audio information is extracted by the identification nodes on the identification audio storage strip, wherein the identification feature information includes sound frequency change information between adjacent identification nodes and gap information between pitch peaks between adjacent identification nodes.

[0036] The identification feature information is stored through adjacent identification nodes to a corresponding cloud server to match the interference sound feature set and the normal sound feature set in the sound type library to obtain the sound types corresponding to the plurality of independent audio information.

[0037] The application also provides a sound identification alarm system, comprising:

[0038] The setting module is configured to set a plurality of preset time periods, configure corresponding sound collection sensitivities for the plurality of preset time periods and sound types respectively, and mark in a sound presence model, wherein the sound types include normal sound and interference sound.

[0039] The analysis module is connected with the setting module and is configured to collect sound information in the environment in real time according to the sound presence model, wherein the sound information includes audio information, sound collection time, and sound decibel, and the sound information is constructed in the sound presence model.

[0040] The alarm module is connected with the analysis module and is configured to analyze the audio information to obtain the sound type, and implement an alarm mode for the interference sound corresponding to the sound decibel that does not meet the preset condition.

[0041] In the above technical solution, the application provides technical effects and advantages:

[0042] The application can extract square dance music from environmental sound, store the feature information through adjacent identification nodes to a corresponding cloud server to obtain the interference sound feature set and the normal sound feature set in each type library audio storage strip, realize the collection and storage of features of various audios under big data, store the interference sound feature set and the normal sound feature set to obtain a sound type library, have a powerful database for subsequent environmental sound identification, help to quickly identify square dance music in subsequent actual life, and efficiently react to alarm processing. BRIEF DESCRIPTION OF DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed in the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments described in the present application, and other drawings can also be obtained by those skilled in the art based on these drawings.

[0044] Figure 1A flow chart of the method of the present application.

[0045] Figure 2 A system block diagram of the present application. DETAILED DESCRIPTION

[0046] For the purpose, technical solutions and advantages of the embodiments of the present application to be clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the scope of protection of the present application.

[0047] Embodiment 1, please refer to Figure 1 The sound recognition alarm method described in the embodiment includes the following steps:

[0048] S1, a plurality of preset time periods are set, and the plurality of preset time periods and sound types are respectively configured with corresponding sound collection sensitivities and marked in a sound presence model, wherein the sound types include normal sound and interference sound;

[0049] S2, sound information in the environment is collected in real time according to the sound presence model, wherein the sound information includes audio information, the time of collecting the sound, and the sound decibel, and the sound information is constructed in the sound presence model (representing that the sound information is marked in the sound presence model, for example, the set parameters of the sound information are A, and A is marked in the sound presence model at the position where the sound information is generated in the sound presence model);

[0050] S3, the audio information is analyzed to obtain the sound type, and an alarm mode is implemented for the interference sound corresponding to the sound decibel that does not meet the preset condition;

[0051] As described in steps S1-S3 above, the popularity of square dance is also accompanied by a series of problems, the most prominent of which is noise pollution. Due to the improper selection of some square dance venues, such as the vicinity of residential areas, schools, hospitals and other places that require quiet environment, high-decibel music and cheers often interfere with the study, work and rest of the surrounding residents. It is difficult to identify square dancing in complex sound environment in the current regulation of square dancing, and then it is difficult to perform alarm processing. In the present application, the square dance music can be extracted from the environmental sound, and the feature information is stored in the corresponding cloud server through the adjacent identification node to obtain the interference sound feature set and the normal sound feature set in each type library audio storage bar. The feature collection and storage of various audios under big data can be realized, the interference sound feature set and the normal sound feature set are stored to obtain the sound type library, which has a powerful database for subsequent environmental sound identification, which can help the subsequent rapid identification of square dance music to determine, and can efficiently react to alarm processing.

[0052] In one embodiment, the step S1 of setting a plurality of preset time periods, corresponding to a plurality of preset time periods and sound types, respectively configuring corresponding sound collection sensitivity, and marking in the sound existence model, comprises:

[0053] S11, determining the jurisdiction range of sound identification, obtaining the geographical environment in the jurisdiction range, and constructing a three-dimensional sound existence model based on the geographical environment and the jurisdiction range;

[0054] S12, marking a plurality of sound collection points in the sound existence model, and setting a plurality of wandering position ends in the sound existence model, wherein the wandering position ends and the plurality of sound collection points are both connected by an analog channel for bidirectional communication, and the wandering position end is a port provided with a storage area;

[0055] S13, setting a plurality of preset time periods, respectively corresponding to a plurality of preset time periods configuring corresponding sound collection sensitivity;

[0056] S14, constructing an identification bar and formulating a sound type library, wherein the sound type library stores an interference sound feature set and a normal sound feature set;

[0057] S15, the interference sound feature set and the normal sound feature set in the sound type library are respectively taken as interference sound and normal sound;

[0058] S16, taking the interference sound and the normal sound as the sound type;

[0059] S17, marking the preset time period and the corresponding sound collection sensitivity in the sound existence model;

[0060] As described in steps S11-S17, a set of voice recognition system has a certain management range, and the voice is recognized in the management range. First, the jurisdiction range of voice recognition is determined, the geographical environment in the jurisdiction range is obtained, and the three-dimensional construction is carried out based on the geographical environment and the jurisdiction range to obtain the sound existence model. The sound existence model is a three-dimensional scene model constructed in the space of the jurisdiction range. Here, as the sound existence model, for example, in the leisure garden in the community in the city, the leisure garden is the jurisdiction range, so the buildings and geographical environment in the leisure garden are three-dimensionally constructed to obtain a three-dimensional scene model showing the leisure garden. Here, as the sound existence model, in the actual sound collection process, a plurality of sound collection points need to be marked in the sound existence model. The sound collection point is a device used for subsequent sound information collection. The device is installed on the site to collect sound information in the jurisdiction range. A plurality of wandering position ends are set in the sound existence model. The wandering position end and the plurality of sound collection points are connected by an analog channel for bidirectional communication. The wandering position end is a port provided with a storage area. When there is no sound, the plurality of wandering position ends do not need to simulate the position where the sound is generated. When the position where the sound is generated needs to be simulated and determined, the corresponding wandering position end is enabled according to the number of simulated sounds. In actual use, for example, when there is sound information in a certain area in the jurisdiction range, the wandering position end is enabled to wander in the sound existence model. The wandering position end and the plurality of sound collection points are always in communication. Therefore, the corresponding sound information of the independent audio information collected by the plurality of sound collection points is transmitted to the wandering position end through the analog channel. The analog channel simulates the attenuation characteristics and direction characteristics of the actual sound transmission in the environment. The plurality of sound collection points and the wandering position end can jointly determine the position where the sound information is generated. The storage area of the wandering position end is used to store the position of the wandering position end in the sound existence model, which conforms to the attenuation characteristics and direction characteristics of the sound transmission in the environment. The position is the position where the sound information is generated. The position of the independent audio information can be determined. Therefore, the rules of voice recognition alarm need to be made in advance for the management range. The first purpose is to recognize square dance music in the environment and alarm if it does not meet the subsequent preset conditions. Therefore, the alarm rules need to be set according to the conditions of square dance music in actual life. First, the square dance usually starts in the afternoon or in the morning and at night. For example, from 4 pm to 2 am and from 6 am to 10 am are the time periods when square dance is likely to occur.The square dance basically does not exist from 2 a.m. to 6 a.m. and from 10 a.m. to 4 p.m. According to the actual living environment, multiple time periods are preset, and the corresponding sound collection sensitivity is configured corresponding to the multiple preset time periods. The adjustment of the sound collection sensitivity is to adjust the sensitivity of the sound decibel detection by changing the working quantity of the sensitivity microphone receiving module. The working quantity of the sensitivity microphone receiving module can be reasonably used according to the sensitivity required by the actual collection. In addition, the present application is to identify the alarm of the square dance music that affects the environmental noise, but in actual life, there will be other normal life sounds, such as car horn sound, calling sound and other environmental sound, so it is necessary to distinguish the environmental sound as a sound type. The sound of the square dance here is regarded as an interference sound, and other life sounds are regarded as normal sounds. In order to better identify the interference sound, a recognition strip is constructed for subsequent type identification of the collected sound. In addition, an interference sound feature set and a normal sound feature set need to be prepared in advance for storage to obtain a sound type library. The interference sound feature set here is a feature set corresponding to a big data music library. The interference sound feature set and the normal sound feature set in the sound type library are respectively regarded as interference sound and normal sound. The interference sound and the normal sound are regarded as sound types. The preset time period and the corresponding sound collection sensitivity are marked in the sound existence model. The sound recognition alarm management can be displayed through the sound existence model, which has faster recognition efficiency and can improve the recognition accuracy.

[0061] In one embodiment, the step S13 of constructing the recognition strip and preparing the sound type library comprises:

[0062] S131, set an audio storage strip, and set multiple recognition nodes on the audio storage strip. The multiple recognition nodes on the audio storage strip are all connected to one cloud server.

[0063] S132, structure copy the audio storage strip to obtain multiple type library audio storage strips. The multiple recognition nodes on the multiple type library audio storage strips are all connected to the cloud server corresponding to the audio storage strip.

[0064] S133, bind the type library audio storage strip with the audio of the interference sound and the audio of the normal sound one by one, respectively. The audio of the interference sound and the audio of the normal sound are respectively placed in the corresponding bound type library audio storage strip to obtain the interference sound feature set and the normal sound feature set.

[0065] S134, store the interference sound feature set and the normal sound feature set to obtain a sound type library.

[0066] As described in steps S131-S134, first, the audio storage bar is set, which can store a large amount of interference sound audio and normal sound audio, and a plurality of identification nodes are arranged on the audio storage bar. The plurality of identification nodes on the audio storage bar are each connected to a cloud server, the type library audio storage bar is bound one-to-one with the interference sound audio and the normal sound audio, the interference sound audio and the normal sound audio are placed in the corresponding bound type library audio storage bar to obtain the interference sound feature set and the normal sound feature set, the identification node is used to identify the feature information in the audio, and then the feature information is stored in the cloud server. The feature information is the sound frequency change information between adjacent identification nodes and the difference information between adjacent identification nodes. The application is mainly used for identifying square dance music. The square dance music is basically regular audio, so after collection, it can be used for subsequent rapid identification and determination of square dance music in actual situations. The square dance music can be extracted from the environment sound, the feature information is stored in the corresponding cloud server through adjacent identification nodes to obtain the interference sound feature set and the normal sound feature set in each type library audio storage bar, and the collection and storage of the features of various audios in big data can be realized. The interference sound feature set and the normal sound feature set are stored to obtain the sound type library, which has a powerful database for subsequent environmental sound identification, can help subsequent rapid identification and determination of square dance music in actual life, and can efficiently react and alarm.

[0067] In one embodiment, the step S133 of placing the interference sound audio and the normal sound audio in the corresponding bound type library audio storage bar to obtain the interference sound feature set and the normal sound feature set, comprises:

[0068] S1331, placing the interference sound audio and the normal sound audio in the corresponding bound type library audio storage bar;

[0069] S1332, collecting feature information of the interference sound audio or the normal sound audio through the identification nodes in the type library audio storage bar, wherein the feature information includes sound frequency change information between adjacent identification nodes and difference information between adjacent identification nodes.

[0070] S1333, storing the feature information in the corresponding cloud server through adjacent identification nodes to obtain the interference sound feature set and the normal sound feature set in each type library audio storage bar.

[0071] In one embodiment, the step S2 of constructing the sound information in the sound presence model, comprises:

[0072] S21, collect audio information in the jurisdiction corresponding to the sound presence model, time of collecting sound, audio time and sound decibel as sound information;

[0073] S22, extract timbre from the audio information, divide the audio information according to the timbre and the audio time to obtain multiple independent audio information;

[0074] S23, when the multiple independent audio information is obtained, enable the corresponding number of wandering position terminals to wander in the sound presence model, the wandering position terminal and the multiple sound collection points are always in communication state, the multiple sound collection points reversely transmit the sound information corresponding to the collected independent audio information to the wandering position terminal through the simulation channel, the multiple sound collection points and the wandering position terminal can jointly determine the position where the sound information is generated, as the generation position of the independent audio information, and mark the multiple independent audio information in the sound presence model according to the generation position;

[0075] As described above in steps S21-S23, in actual collection, the audio information in the jurisdiction corresponding to the sound presence model, the time of collecting sound, the audio time and the sound decibel are collected as sound information. Since there are various sounds in the environment, the collected audio is a mixture of various sounds, therefore, it is necessary to extract the timbre from the audio information, divide the audio information according to the timbre and the audio time to obtain multiple independent audio information. The audio time: the time of a song is generally 3-6 minutes, and at most 7-8 minutes, but there are very few music less than 90s, and there is basically no music less than 20s, therefore, the range of the preset time period is set to 20s-90s, which basically covers all the music content, therefore, it can accurately identify whether the sound is square dance music. In addition, it can also be set to 30s, 45s, etc., therefore, according to the audio time, a part of the sound can be screened out to obtain multiple independent audio information, and then the multiple independent audio information is obtained to obtain the corresponding generation position, and the multiple independent audio information is marked in the sound presence model according to the generation position, which can better help personnel understand whether the sound is interference information, and can assist the police to maintain the living noise environment in subsequent alarm.

[0076] In one embodiment, the step S3 of analyzing the audio information to obtain the sound type, and implementing the alarm mode for the interference sound corresponding to the sound decibel not meeting the preset condition, comprises:

[0077] S31, processing the independent audio information according to the audio storage bar to obtain the sound type;

[0078] S32, when the sound type is an interference sound and the sound decibel does not satisfy the preset condition, implementing an alarm mode, wherein the alarm mode comprises emitting a sound wave opposite to the interference sound in phase to reduce noise, actively reducing normal sound, and alarming.

[0079] In one embodiment, the independent audio information is processed according to the audio storage bar to obtain a sound type S31, comprising:

[0080] S311, copying the audio storage bar according to the number of independent audio information to obtain a plurality of identification audio storage bars;

[0081] S312, placing the independent audio information one by one in the identification audio storage bar, and extracting identification feature information of the independent audio information by the identification node on the identification audio storage bar, wherein the identification feature information comprises sound frequency change information between adjacent identification nodes and gap information between adjacent identification node pitch peaks;

[0082] S313, storing the identification feature information through adjacent identification nodes into a corresponding cloud server to match an interference sound feature set and a normal sound feature set in a sound type library to obtain a sound type corresponding to the plurality of independent audio information.

[0083] As described in steps S311-S313, after collecting a plurality of independent audio information, the number of corresponding independent audio information is copied to obtain a plurality of identification audio storage strips, and the identification audio storage strip is used to extract the features of the independent audio information to obtain identification feature information, wherein the identification feature information includes the sound frequency change information between adjacent identification nodes, and the gap information between adjacent identification nodes. The identification feature information is stored through adjacent identification nodes to the corresponding cloud server, and is matched with the interference sound feature set and the normal sound feature set in the sound type library to obtain the sound type corresponding to the plurality of independent audio information. Then, it can be distinguished whether the plurality of independent audio information is normal sound or interference sound, and can be quickly analyzed and identified, greatly improving the subsequent alarm response capability. In addition, when the sound type is interference sound and the sound decibel does not meet the preset condition, an alarm mode is implemented, wherein the alarm mode includes emitting sound waves opposite in phase to the interference sound for noise reduction, actively reducing the normal sound, and alarming, emitting warning sound and / or sending prompt information to relevant personnel; actively reducing the normal sound: emitting sound waves opposite in phase to the interference sound; actively reducing the sound includes: emitting sound waves opposite in phase to the interference sound. By emitting warning sound and light, the crowd dancing in the square can be prompted to avoid causing adverse interference to the surrounding people. In addition, active noise reduction uses sound waves opposite in phase, including identifying the sound wave of the current sound, generating an opposite sound wave, and additionally, the position of the sound wave of the current sound can be detected, and the opposite sound wave is sent in the direction of the position of the sound wave of the current sound.

[0084] Embodiment 2, please refer to Figure 2 The sound recognition alarm system described in the embodiment comprises:

[0085] The setting module is configured to set a plurality of preset time periods, and configure corresponding sound collection sensitivities for the plurality of preset time periods and sound types respectively, and mark them in the sound presence model, wherein the sound types include normal sound and interference sound.

[0086] The analysis module is connected with the setting module, and is configured to collect sound information in the environment in real time according to the sound presence model, wherein the sound information includes audio information, the time of collecting the sound, and the sound decibel, and the sound information is constructed in the sound presence model.

[0087] The alarm module is connected with the analysis module, and is configured to analyze the audio information to obtain the sound type, and implement an alarm mode for the interference sound corresponding to the sound decibel that does not meet the preset condition.

[0088] It should be noted that the interference sound feature set and the normal sound feature set in the sound type library are respectively taken as interference sound and normal sound, the interference sound and the normal sound are taken as sound types, and the preset time period and the corresponding sound collection sensitivity are marked in the sound presence model, so that the recognition alarm management of the displayed sound can be performed through the sound presence model, the recognition efficiency is high, and the recognition accuracy can be improved; the alarm mode includes emitting sound waves opposite in phase to the interference sound for noise reduction, actively reducing the normal sound, and alarming, emitting warning sound and / or sending prompt information to relevant personnel; actively reducing the normal sound includes emitting sound waves opposite in phase to the interference sound. By emitting warning sound and light, the crowd dancing in the square can be prompted to avoid adversely interfering with people around. In addition, active noise reduction uses sound waves opposite in phase, including identifying the sound waves of the current sound, generating opposite sound waves, and additionally detecting the position of the sound waves of the current sound and sending the opposite sound waves in the direction of the position of the sound waves of the current sound.

[0089] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto, and any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A sound recognition alarm method, characterized in that, Includes the following steps: Multiple preset time periods are set, and corresponding sound acquisition sensitivities are configured for each preset time period and sound type, and marked in the sound presence model. The sound types include normal sound and interference sound. Sound information in the environment is collected in real time according to the sound presence model. The sound information includes audio information, the time of sound collection, and the sound decibel. The sound information is then constructed in the sound presence model. The audio information is analyzed to determine the sound type, and an alarm is triggered for the interfering sound corresponding to the decibel level of the sound that does not meet the preset conditions. The steps of setting multiple preset time periods, configuring corresponding sound acquisition sensitivities for each preset time period and sound type, and marking them in the sound presence model include: Determine the jurisdiction of sound recognition, obtain the geographical environment within the jurisdiction, and construct a three-dimensional model of the sound presence based on the geographical environment and the jurisdiction. Multiple sound acquisition points are marked in the sound existence model, and multiple wandering position terminals are set in the sound existence model. A simulated channel is constructed between each wandering position terminal and multiple sound acquisition points for bidirectional connection. The wandering position terminal is a port with a storage area. Set multiple preset time periods, and configure the corresponding sound acquisition sensitivity for each preset time period; Construct recognition bars and establish a sound type library, which stores a set of interference sound features and a set of normal sound features; The set of interference sound features and the set of normal sound features in the sound type library are respectively regarded as interference sound and normal sound; Disruptive sounds and normal sounds are classified as sound types; Mark the preset time period and the corresponding sound acquisition sensitivity in the sound existence model; The steps of constructing recognition bars and developing a sound type library include: Configure an audio storage bar, set up multiple recognition nodes on the audio storage bar, and configure each of the multiple recognition nodes on the audio storage bar to connect to a cloud server; Multiple type library audio storage bars are obtained by structurally copying the audio storage bar. Multiple recognition nodes on the multiple type library audio storage bars are connected to the cloud server corresponding to the audio storage bar. The type library audio storage bar is bound one-to-one with the audio of the interference sound and the audio of the normal sound, and the audio of the interference sound and the audio of the normal sound are placed in the corresponding bound type library audio storage bar to obtain the interference sound feature set and the normal sound feature set. A sound type library is obtained by storing the sets of interference sound features and the sets of normal sound features; The step of placing the audio of the interfering sound and the audio of the normal sound into the corresponding bound type library audio storage slots to obtain the interfering sound feature set and the normal sound feature set includes: Place the audio of the interfering sound and the audio of the normal sound into the corresponding bound type library audio storage slots respectively; The feature information of the audio of interference sound or normal sound is collected by the recognition node in the audio storage bar of the type library. The feature information includes the sound frequency change information between adjacent recognition nodes and the difference information between the tone peaks between adjacent recognition nodes. The feature information is stored in the corresponding cloud server through adjacent recognition nodes to obtain the set of interference sound features and the set of normal sound features in each type of audio storage bar; The step of constructing sound information in a sound existence model includes: Within the jurisdiction corresponding to the sound existence model, audio information in the environment, the time of sound acquisition, the audio duration, and the sound decibels are collected as sound information. The audio information is extracted by timbre, and the audio information is divided into multiple independent audio information based on timbre and audio time; When multiple independent audio information is obtained, a corresponding number of wandering position terminals are activated to wander in the sound existence model. The wandering position terminals and multiple sound acquisition points are always connected. The multiple sound acquisition points transmit the sound information corresponding to the acquired independent audio information back to the wandering position terminals through the analog channel. The multiple sound acquisition points and the wandering position terminals can jointly determine the location where the sound information is generated, which is used as the generation location corresponding to the independent audio information. The multiple independent audio information is marked in the sound existence model according to the generation location. The steps of analyzing audio information to obtain the sound type and issuing an alarm for interference sounds that do not meet preset conditions (in decibel levels) include: The sound type is obtained by processing the independent audio information based on the audio storage bar; When the sound type is interference sound and the sound decibel does not meet the preset conditions, an alarm mode is implemented. The alarm mode includes emitting a sound wave with the opposite phase to the interference sound for noise reduction, actively reducing noise for normal sound, and alarm. The process of processing independent audio information based on the audio storage bar to obtain the sound type includes: Multiple audio storage bars are obtained by copying the audio storage bars according to the number of independent audio information; Individual audio information is placed one-to-one in the recognition audio storage bar. The recognition nodes on the recognition audio storage bar extract the recognition feature information of the individual audio information. The recognition feature information includes the sound frequency change information between adjacent recognition nodes and the difference information between the tone peaks of adjacent recognition nodes. The identification feature information is stored in the corresponding cloud server through adjacent identification nodes and matched with the interference sound feature set and normal sound feature set in the sound type library to obtain the sound type corresponding to multiple independent audio information.

2. A sound recognition alarm system, used to implement the sound recognition alarm method according to claim 1, characterized in that, include: The settings module is used to set multiple preset time periods. For each preset time period and sound type, the corresponding sound acquisition sensitivity is configured and marked in the sound presence model. The sound type includes normal sound and interference sound. The analysis module, connected to the settings module, is used to collect sound information in the environment in real time according to the sound presence model. The sound information includes audio information, the time of sound collection, and the sound decibel level. The sound information is then constructed in the sound presence model. The alarm module, connected to the analysis module, is used to analyze audio information to obtain the sound type and to issue an alarm for interference sounds that do not meet preset conditions in decibel level.

3. An electronic device, characterized in that, Electronic devices include: The processor and the memory are communicatively connected. The memory is used to store at least one executable instruction executed by the processor, the processor being used to execute the executable instruction to implement a sound recognition alarm method as described in claim 1.

4. A computer-readable storage medium having a computer program stored thereon, characterized in that... Therefore, when the computer program is executed by the processor, it implements the sound recognition alarm method according to claim 1.

Images