In-vehicle argument processing method and device, electronic equipment and storage medium

Abstract

The application discloses an in-vehicle quarrel processing method and device, electronic equipment and a storage medium, wherein the processing method comprises: acquiring first audio information of personnel in a vehicle; performing human voice extraction on the first audio information to obtain human voice information; performing decibel size analysis on the human voice information to obtain a first decibel value corresponding to the human voice information; performing emotion recognition on the human voice information to obtain first emotion information corresponding to the human voice information; when the first decibel value is greater than a first threshold value and / or the first emotion information meets a first condition, acquiring second audio information in a preset time period based on a current time; determining the number of conversations and / or the duration of a single conversation in the second audio information; when the number of conversations is greater than a second threshold value and / or the duration of a single conversation is greater than a third threshold value, determining a quarrel level of the personnel in the vehicle according to the second audio information, the quarrel level comprising three levels of weak, medium and strong; and performing a prompt operation corresponding to the quarrel level.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and more specifically to a method, apparatus, electronic device, and storage medium for handling in-vehicle arguments. Background Technology

[0002] Drivers need to concentrate on driving to avoid mistakes. However, during daily rides, arguments between passengers and drivers, or between passengers themselves, are unavoidable due to various circumstances.

[0003] Therefore, there is an urgent need for a method to promptly handle arguments that occur inside vehicles, in order to appease the driver and passengers and reduce traffic accidents. Summary of the Invention

[0004] To address the aforementioned problems in the prior art, this application provides a method, apparatus, electronic device, and storage medium for handling in-vehicle arguments. This method can determine whether a vehicle is in an argument state based on in-vehicle audio information and promptly handle the argument when it occurs, thereby calming the driver and passengers and reducing traffic accidents.

[0005] In a first aspect, embodiments of this application provide a method for handling in-vehicle arguments, including:

[0006] Obtain the initial audio information of the people inside the vehicle;

[0007] Human voice extraction is performed on the first audio information to obtain human voice information;

[0008] Analyze the decibel level of human voice information to obtain the first decibel value corresponding to the human voice information;

[0009] Emotion recognition is performed on human voice information to obtain the first emotion information corresponding to the human voice information;

[0010] When the first decibel value is greater than the first threshold and / or the first emotional information meets the first condition, the second audio information within a preset time period is obtained based on the current time.

[0011] Determine the number of dialogues and / or the duration of each dialogue in the second audio information;

[0012] When the number of conversations exceeds the second threshold and / or the duration of a single conversation exceeds the third threshold, the level of argument among the people in the vehicle is determined based on the second audio information. The argument level includes three levels: weak, medium, and strong.

[0013] Perform the prompt action corresponding to the level of the argument.

[0014] Secondly, embodiments of this application provide an in-vehicle argument handling device, comprising:

[0015] The acquisition module is used to obtain the initial audio information of the people inside the vehicle;

[0016] The analysis module is used to extract human voice from the first audio information to obtain human voice information; to analyze the decibel level of the human voice information to obtain the first decibel value corresponding to the human voice information; and to perform emotion recognition on the human voice information to obtain the first emotion information corresponding to the human voice information.

[0017] The acquisition module is also used to acquire second audio information within a preset time period based on the current time when the first decibel value is greater than the first threshold and / or the first emotional information meets the first condition.

[0018] The analysis module is also used to determine the number of conversations and / or the duration of a single conversation in the second audio information; when the number of conversations is greater than the second threshold, and / or the duration of a single conversation is greater than the third threshold, the level of the argument between the people in the vehicle is determined based on the second audio information, and the argument level includes three levels: weak, medium and strong.

[0019] The processing module is used to execute prompts corresponding to the level of the argument.

[0020] Thirdly, embodiments of this application provide an electronic device, including: a processor connected to a memory for storing a computer program, and the processor for executing the computer program stored in the memory to cause the electronic device to perform the method as described in the first aspect.

[0021] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that causes a computer to perform the method as described in the first aspect.

[0022] Fifthly, embodiments of this application provide a computer program product, the computer program product including a non-transitory computer-readable storage medium storing a computer program, and a computer operable to perform the method as described in the first aspect.

[0023] Implementing the embodiments of this application has the following beneficial effects:

[0024] In this embodiment, real-time first audio information inside the vehicle is detected, and a first decibel value corresponding to the sound level and a first emotional information corresponding to the emotional state of the dialogue are extracted. Then, when the first decibel value is greater than a first threshold, and / or the first emotional information meets a first condition, it is preliminarily determined that an argument may be occurring inside the vehicle. This eliminates the need for detailed analysis of every single dialogue occurring inside the vehicle, reducing the consumption of computing resources. After preliminarily determining that an argument may be occurring inside the vehicle, second audio information within a preset time period is analyzed in detail to determine the number of dialogues and / or the duration of each dialogue. When the number of dialogues is greater than a second threshold, and / or the duration of each dialogue is greater than a third threshold, it is determined that an argument has occurred inside the vehicle, and the argument level of the occupants is determined based on the second audio information. Finally, a prompt operation corresponding to the argument level is executed. This achieves accurate identification of argument events and, by classifying argument levels, diversifies the handling methods to improve the calming effect. Attached Figure Description

[0025] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0026] Figure 1 A flowchart illustrating a method for handling in-vehicle arguments provided for an embodiment of this application;

[0027] Figure 2 A flowchart illustrating a method for determining the level of an argument among occupants in a vehicle based on second audio information, provided for an embodiment of this application;

[0028] Figure 3 A flowchart illustrating a method for determining the level of an argument among occupants in a vehicle based on a second keyword and second emotional information, provided for an embodiment of this application;

[0029] Figure 4 A flowchart illustrating a method for determining a music list based on second audio information and a second decibel value, provided for an embodiment of this application;

[0030] Figure 5 A functional module block diagram of an in-vehicle argument handling device provided for embodiments of this application;

[0031] Figure 6 This is a schematic diagram of the structure of an electronic device provided for an embodiment of this application. Detailed Implementation

[0032] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, not all of them. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0033] The terms "first," "second," "third," and "fourth," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.

[0034] In this document, the term "implementation" means that a specific feature, result, or characteristic described in connection with an implementation may be included in at least one implementation of this application. The appearance of this phrase in various places in the specification does not necessarily refer to the same implementation, nor is it a separate or alternative implementation mutually exclusive with other implementations. It will be explicitly and implicitly understood by those skilled in the art that the implementations described herein can be combined with other implementations.

[0035] To address this issue, the present application provides a method for handling in-vehicle arguments, which can resolve the aforementioned problems. (See also...) Figure 1 The method for handling arguments inside the car includes the following steps:

[0036] 101: Obtain the first audio information of the people inside the vehicle.

[0037] In this embodiment, the sound acquisition terminal can be installed inside the vehicle to collect audio information from the occupants. For example, the sound acquisition terminal can be a microphone; for instance, it can include multiple microphones, each installed on a door next to each seat inside the vehicle.

[0038] For example, after the microphone picks up in-vehicle sounds such as human voices, it transmits the collected sound signal to the control box via the car audio bus (A2B). The signal is then converted into an analog signal by the A2B chip. This analog signal is then processed by the audio acquisition circuit to extract analog audio information. After being processed by the analog-to-digital converter chip, it forms the first audio information and is transmitted to the microcontroller unit (MCU) for further processing.

[0039] 102: Extract human voice from the first audio information to obtain human voice information.

[0040] 103: Analyze the decibel level of the human voice information to obtain the first decibel value corresponding to the human voice information.

[0041] Generally speaking, 10-20 decibels is considered a very quiet environment; 20-40 decibels is suitable for whispering; 40-60 decibels is for casual conversation; 60-70 decibels is for shouting; 70-90 decibels is very noisy; and 100-120 decibels is extremely noisy. Therefore, by detecting the decibel level of conversations occurring inside a vehicle, it's possible to determine if an argument is possible. For example, if the volume of conversations exceeds 60 decibels, a heated argument may be taking place. In such cases, regardless of whether the driver is involved, it could pose a safety hazard.

[0042] 104: Perform emotion recognition on human voice information to obtain the first emotion information corresponding to the human voice information.

[0043] A person's tone of voice, intonation, and speaking speed remain largely constant throughout life. However, at certain times, changes in inner emotions can alter these characteristics. For example, when angry, adrenaline levels increase compared to normal, leading to a state of heightened arousal. This arousal and excitement excites the brain, causing it to accelerate blood flow, particularly to the brain. This combined with ample blood supply to the brain results in peak mental performance, leading to more agile thinking and fluent speech than usual.

[0044] In summary, it is easy to see that a person's voice, tone, and speaking speed change depending on their emotions. Anger typically manifests as a sharp voice, heavy tone, fast speaking speed, and numerous stresses. Therefore, in this embodiment, feature extraction can be performed on the first audio information to obtain its voice, tone, speaking speed, and stress distribution characteristics. Further analysis of each feature yields the first emotional information corresponding to the voice.

[0045] Furthermore, when people are angry, their voices tend to rise involuntarily, due to a strong desire to persuade the other person, or to dominate or command them. Many people have found that speaking loudly is a good "weapon" for persuading others, at least in terms of overwhelming presence.

[0046] Based on this, in an optional implementation, the first decibel value of the first audio information can also be used to help determine the first emotional information corresponding to the first audio information.

[0047] For example, prior research can be conducted to determine the distribution of decibel levels when people speak under different emotions, and a weight value can be established for different emotions at different decibel levels. For instance, in the 70-80 decibel range, the weight of happiness is 0.3, the weight of sadness is 0.1, the weight of anger is 0.55, and the weight of calmness is 0.05.

[0048] The final result of sentiment analysis is the probability of the analyzed audio information corresponding to each emotion. For example, after sentiment analysis, the probability of happiness is 0.4, the probability of sadness is 0.05, the probability of anger is 0.45, and the probability of calmness is 0.1.

[0049] Therefore, in this embodiment, the product of the probability corresponding to each emotion obtained from emotion analysis and the weight value corresponding to different emotions at that decibel level can be used as the final result of audio emotion recognition. For example, assuming the decibel level of the dialogue is 75, which falls within the 70-80 decibel range, then by combining the weight values ​​corresponding to different emotions at that decibel level, we can obtain the following probabilities: happiness is 0.12, sadness is 0.005, anger is 0.2475, and calmness is 0.005.

[0050] Therefore, the obtained emotion recognition results combine audio characteristics and sound decibel values, making the recognition results more accurate.

[0051] 105: When the first decibel value is greater than the first threshold and / or the first emotional information meets the first condition, the second audio information within a preset time period is obtained based on the current time.

[0052] In this embodiment, the first threshold can be 60 decibels, the first condition can be: the emotion recognition result is anger, grievance, fear, etc., and the preset time period can be 5 minutes. For example, if it is determined that the first decibel value is greater than the first threshold, and / or the time when the first emotion information meets the first condition is 9:00 am, then 9:00 am is taken as the current time, and the dialogue information of the next 5 minutes is obtained as the second audio information for focused analysis.

[0053] 106: Determine the number of dialogues and / or the duration of a single dialogue in the second audio information.

[0054] 107: When the number of conversations exceeds the second threshold and / or the duration of a single conversation exceeds the third threshold, the level of argument among the occupants in the vehicle is determined based on the second audio information.

[0055] In this embodiment, the level of argument can include three levels: weak, medium, and strong.

[0056] Specifically, the intensity of the quarrel can be roughly determined by the frequency of the conversation, the duration of a single conversation, etc. In this embodiment, when the duration of a single conversation is greater than 10 seconds, and / or the number of conversations is greater than 5, it can be determined that the two parties in the conversation are in a quarreling state. At this time, by analyzing the conversations of the two parties, the quarrel theme and the quarrel level can be determined.

[0057] In this embodiment, a method for determining the quarrel level of the people in the vehicle according to the second audio information is given, as Figure 2 shown, this method includes:

[0058] 201: Perform speech recognition on the second audio information to obtain the first text.

[0059] 202: Determine the second keywords in the first text.

[0060] In this embodiment, first, the N-gram segmentation method with an order of 2 and 3 can be used to segment the first text respectively to obtain a number of candidate words. Specifically, the N-gram segmentation method is a method of segmenting a sentence into a sequence of segments each consisting of N characters, and each segment is called an N-gram. When N = 1, the N-gram segmentation method can be called uni-gram (unary gram), when N = 2, the N-gram segmentation method can be called bi-gram (binary gram), and when N = 3, the N-gram segmentation method can be called tri-gram (ternary gram). Exemplarily, if the bi-gram is used to segment the text "I drank coffee yesterday", then the following can be obtained: "I yesterday", "yesterday", "day drank", "drank coffee", "coffee".

[0061] Thus, in this embodiment, after obtaining the segmentation result, the segmentation result can be filtered and cleaned to filter out meaningless segmentation results, such as: "I yesterday", "day drank", and "drank coffee", and retain the segmentation results with certain semantics, such as: "yesterday", "drank coffee", and "coffee" as candidate words.

[0062] Then, the occurrence frequencies of these candidate words in the first text can be counted, and the candidate words with occurrence frequencies higher than the preset value can be selected as the second keywords.

[0063] 203: Perform emotion recognition on the second audio information to obtain the second emotion information corresponding to the second audio information.

[0064] In this embodiment, the emotion recognition method here is similar to the emotion recognition method in step 104, and will not be elaborated here.

[0065] 204: Determine the level of argument among the people inside the vehicle based on the second keyword and the second emotional information.

[0066] This embodiment provides a method for determining the level of argument among occupants in a vehicle based on a second keyword and second emotional information, such as... Figure 3 As shown, the method includes:

[0067] 301: Determine the event level of the argument between people inside the vehicle based on the second keyword.

[0068] Typically, when people argue, they discuss the event being argued about. Therefore, in this embodiment, the event being argued about can be determined by extracting the second keyword. Furthermore, for ease of processing, this embodiment quantifies the events, assigning different event levels to different events. For example, the event levels can be divided into 5 levels: 1, 2, 3, 4, and 5. The higher the level, the more serious the argument.

[0069] 302: Determine the emotional stability value of the occupants based on the second emotional information.

[0070] In this embodiment, the results of emotion recognition can be further subdivided. For example, anger can be further subdivided into: mild anger, moderate anger, rage, hysteria, etc. Similarly, it can be quantified, corresponding to four levels: 1, 2, 3, and 4, as emotional stability values ​​to indicate the emotional stability of the occupants in the vehicle. The higher the level, the worse the emotional stability of the occupants in the vehicle.

[0071] 303: Multiply the event level by the emotional stability value to obtain the first product.

[0072] 304: Perform arctangent processing on the first product to obtain the level of argument among the people inside the vehicle.

[0073] In this embodiment, the level of argument can be represented by formula ①:

[0074]

[0075] Where a represents the event level and b represents the emotional stability value.

[0076] 108: Perform the prompt action corresponding to the level of the argument.

[0077] In this embodiment, the level of argument can include three levels: weak, medium, and strong, each corresponding to different prompts and actions.

[0078] For example, when the argument level is low, it indicates that the argument may be over trivial matters, and the emotions of both parties are relatively stable. Therefore, the second audio information can be analyzed in decibels to obtain a second decibel value corresponding to the second audio information; then, a pre-configured mediation prompt voice can be played at a volume greater than the second decibel value, for example, 5 decibels higher than the second decibel value.

[0079] When the argument level is medium, it indicates that the argument is of high importance and both parties are emotionally charged. In this case, in addition to following the prompts for a low argument level, a music playlist needs to be determined based on the second audio information and the second decibel value. Simultaneously, when the second decibel value is below the fourth threshold, music from the playlist should be played; when the second decibel value is above or equal to the fourth threshold, a mediation prompt should be continuously played, and hazard lights should be activated to warn oncoming vehicles.

[0080] Specifically, the fourth threshold can be 80 decibels. When the second decibel value, i.e., the decibel value when the two parties are arguing, exceeds 80 decibels, it indicates that the argument is intense. At this point, forcibly playing music might be ineffective, firstly because it could be masked by the noise of the argument; secondly, the high decibel level suggests that the arguing parties are likely highly emotional, and playing music might have the opposite effect. Therefore, when the second decibel value exceeds 80 decibels, the recommended action is to continuously play a peace-discussing voice prompt and activate the vehicle's hazard lights to warn oncoming traffic.

[0081] When the argument level is "Strong," it indicates that the argument is extremely important, and both parties are in very poor emotional stability, with the argument potentially escalating into a physical conflict at any moment. In this case, in addition to following the prompts for a "Medium" argument level, it is also necessary to control the vehicle's speed, ensuring it falls below the fifth threshold.

[0082] Specifically, a deceleration command can be sent to the vehicle's telematics BOX (T-BOX) to gradually reduce the driving speed to 30 kilometers per hour and limit the maximum driving speed to 30 kilometers per hour.

[0083] Meanwhile, in this embodiment, the level of argument can also be dynamically changed. For example, if the argument level is low and the two parties are still arguing within a predetermined time period after the prompting operation, such as 5 minutes, the argument level can be gradually increased to medium or strong.

[0084] In addition, this embodiment also provides a method for determining a music list based on second audio information and a second decibel value, such as... Figure 4 As shown, the method includes:

[0085] 401: Determine the sound restoration model corresponding to the second decibel value based on the second decibel value.

[0086] In this embodiment, the sound restoration model is used to restore high-decibel sounds to a preset decibel level. Specifically, human voices undergo a series of changes at high decibel levels, such as becoming sharper, resulting in a difference between the characteristics of high-decibel sounds and those of normal speech.

[0087] Specifically, in this embodiment, the high-decibel region can be divided into intervals of 10 decibels. For example, the high-decibel region can be [60, 120]. After dividing it into intervals of 10 decibels, the intervals [60, 70), [70, 80), [80, 90), [90, 100), [100, 110), and [110, 120] can be obtained. For each interval, a sound restoration model is constructed. Therefore, after determining the second decibel value, the corresponding sound restoration model can be obtained based on the interval in which the second decibel value is located.

[0088] Meanwhile, this embodiment provides a training method for a sound restoration model, taking the interval [70, 80) as an example, as follows:

[0089] First, construct the training set. Obtain several audio recordings of the same person speaking normally, as the original audio; and several audio recordings of the person speaking at [70, 80) decibels, as reference audio. Associate the original audio with the reference audio to form a set of training samples. Obtain multiple sets of training samples in the same way to construct the training set.

[0090] Next, the model is constructed. For each training sample in the multiple training samples, a first functional relationship between the original audio and the reference audio is constructed, resulting in multiple first functional relationships corresponding one-to-one with the multiple training samples. Curve fitting is performed on the multiple first functional relationships to obtain second functional relationships, and an initial model is built based on the second functional relationships.

[0091] Finally, model training. The original audio from each training sample is input into the initial model to obtain the processing result. Based on the processing result and the reference audio corresponding to the input original audio, the parameters of the initial model are adjusted to obtain the sound restoration model.

[0092] Thus, a sound restoration model can be obtained to restore high-decibel audio to the level of normal speech. Furthermore, in an optional implementation, sample sets can be established separately for male and female voices, and corresponding male and female voice restoration models can then be built, improving the accuracy of the sound restoration model.

[0093] 402: Input the second audio information into the sound restoration model to obtain the third audio information.

[0094] In this embodiment, the third audio information is the audio at the decibel level of normal speech after restoration.

[0095] In an optional implementation, a sound restoration method is also provided, as follows:

[0096] First, a compression factor corresponding to the second decibel value is determined. Then, the amplitude of the spectrum of the second audio information is compressed according to this compression factor to obtain the compressed spectrum. Finally, the third audio information is constructed based on the compressed spectrum. This allows for rapid audio restoration.

[0097] 403: Determine the vocal characteristics of the arguing parties based on the third audio information.

[0098] 404: Identify the individuals arguing based on their voice characteristics.

[0099] In this embodiment, after obtaining the voice characteristics of the arguing individuals, the similarity between the voice characteristics and the voice characteristics stored in the database can be calculated by feature comparison, thereby determining the identity information of the arguing individuals.

[0100] Specifically, for drivers, audio information can be collected during their daily passenger transport, linked to their identity, and stored in a pre-set database. For passengers, audio information can be collected during their ride, linked to their identity information in the app they used when boarding, and stored in a pre-set database.

[0101] 405: Based on the identity information, retrieve the first music list collected or liked by the person arguing.

[0102] Specifically, the system can retrieve music saved or liked by the individuals involved in the argument through their personal information and generate a primary music playlist.

[0103] 406: Based on the second audio information, determine the first keyword corresponding to the second audio information.

[0104] In this embodiment, the emotion recognition method is similar to the keyword determination method in step 202, and will not be described again here.

[0105] 407: Based on the first keyword and the second decibel value, filter the first music list to determine the music list.

[0106] Specifically, the first keyword can be used to determine the music's style and rhythmic characteristics, while the second decibel value can determine its dynamics and tempo. This allows for filtering of the initial music list, resulting in a final music playlist. By combining the event of the argument, the environment, and the preferences of the individuals involved, the generated music playlist will be better suited to the current situation and have a more effective calming effect.

[0107] In addition, in an optional implementation, when it is determined that an argument is taking place inside the vehicle, information such as the vehicle's location, the people inside the vehicle, the content of the argument, the average decibel level, and the maximum decibel level can be sent to the monitoring platform cloud, so that the monitoring center can monitor and handle the vehicle in accordance with the operation and supervision procedures.

[0108] In summary, the in-vehicle argument handling method provided by this invention detects real-time first audio information within the vehicle, extracting a first decibel value corresponding to the sound level and a first emotional information corresponding to the emotional state of the dialogue. Then, when the first decibel value exceeds a first threshold and / or the first emotional information meets a first condition, it is preliminarily determined that an argument may have occurred within the vehicle. This eliminates the need for detailed analysis of every single dialogue occurring within the vehicle, reducing computational resource consumption. After preliminarily determining that an argument may have occurred, the second audio information within a preset time period is analyzed in detail to determine the number of dialogues and / or the duration of each dialogue. When the number of dialogues exceeds a second threshold and / or the duration of each dialogue exceeds a third threshold, an argument is confirmed to have occurred within the vehicle, and the argument level of the occupants is determined based on the second audio information. Finally, a prompt operation corresponding to the argument level is executed. This achieves accurate identification of argument events and allows for a more diversified approach to handling arguments, thereby improving the calming effect.

[0109] See Figure 5 , Figure 5 This is a functional module block diagram of an in-vehicle argument handling device provided for an embodiment of this application. For example... Figure 5 As shown, the in-vehicle argument handling device 500 includes:

[0110] Acquisition module 501 is used to acquire the first audio information of the people inside the vehicle;

[0111] The analysis module 502 is used to extract human voice from the first audio information to obtain human voice information; to analyze the decibel level of the human voice information to obtain the first decibel value corresponding to the human voice information; and to perform emotion recognition on the human voice information to obtain the first emotion information corresponding to the human voice information.

[0112] The acquisition module 501 is also used to acquire second audio information within a preset time period based on the current time when the first decibel value is greater than the first threshold and / or the first emotional information meets the first condition.

[0113] The analysis module 502 is also used to determine the number of conversations and / or the duration of a single conversation in the second audio information; when the number of conversations is greater than the second threshold and / or the duration of a single conversation is greater than the third threshold, the level of the argument between the people in the vehicle is determined based on the second audio information, and the level of the argument includes three levels: weak, medium and strong.

[0114] Processing module 503 is used to perform prompting operations corresponding to the level of the argument.

[0115] In an embodiment of the present invention, when the argument level is weak, the processing module 503 is specifically configured to: perform a prompt operation corresponding to the argument level.

[0116] Analyze the second audio information in decibels to obtain the second decibel value corresponding to the second audio information;

[0117] Play a pre-configured peace-discipline prompt voice, wherein the decibel level of the peace-discipline prompt voice is greater than the second decibel value.

[0118] In an embodiment of the present invention, when the argument level is medium, the processing module 503 is specifically configured to perform a prompting operation corresponding to the argument level, wherein the processing module 503 is used to:

[0119] Analyze the second audio information in decibels to obtain the second decibel value corresponding to the second audio information;

[0120] Play a pre-configured peace-discipline prompt voice, wherein the decibel level of the peace-discipline prompt voice is greater than the second decibel value;

[0121] The music list is determined based on the second audio information and the second decibel value;

[0122] When the second decibel value is lower than the fourth threshold, play music from the music list;

[0123] When the second decibel value is higher than or equal to the fourth threshold, a dissuasion prompt voice will be continuously played, and the hazard lights will be activated to warn other vehicles.

[0124] In an embodiment of the present invention, when the argument level is high, the processing module 503 is specifically used for executing a prompt operation corresponding to the argument level, in order to:

[0125] Analyze the second audio information in decibels to obtain the second decibel value corresponding to the second audio information;

[0126] Play a pre-configured peace-discipline prompt voice, wherein the decibel level of the peace-discipline prompt voice is greater than the second decibel value;

[0127] The music list is determined based on the second audio information and the second decibel value;

[0128] When the second decibel value is lower than the fourth threshold, play music from the music list;

[0129] When the second decibel value is higher than or equal to the fourth threshold, the alarm prompt will continue to play and the hazard lights will be activated to warn other vehicles.

[0130] Control the vehicle's speed to be below the fifth threshold.

[0131] In an embodiment of the present invention, in determining the music list based on the second audio information and the second decibel value, the processing module 503 is specifically configured to:

[0132] A sound restoration model corresponding to the second decibel value is determined based on the second decibel value. The sound restoration model is used to restore the sound at a high decibel level to the sound at a preset decibel level.

[0133] The second audio information is input into the sound restoration model to obtain the third audio information;

[0134] Determine the vocal characteristics of the arguing individuals based on third-party audio information;

[0135] Identify the individuals arguing based on their voice characteristics;

[0136] Based on the identity information, retrieve the first music list that the person arguing has saved or liked;

[0137] Based on the second audio information, determine the first keyword corresponding to the second audio information;

[0138] Based on the first keyword and the second decibel value, the first music list is filtered to determine the music list.

[0139] In an embodiment of the present invention, in determining the level of argument among occupants of a vehicle based on second audio information, the analysis module 502 is specifically configured to:

[0140] Speech recognition is performed on the second audio information to obtain the first text;

[0141] Identify the second keyword in the first text;

[0142] Emotion recognition is performed on the second audio information to obtain the second emotional information corresponding to the second audio information;

[0143] The level of argument among the people inside the vehicle is determined based on the second keyword and the second emotional information.

[0144] In an embodiment of the present invention, in determining the level of argument among occupants of a vehicle based on a second keyword and second emotional information, the analysis module 502 is specifically used for:

[0145] Based on the second keyword, determine the incident level of the argument between the people inside the vehicle;

[0146] Based on the second emotional information, the emotional stability value of the occupants in the vehicle is determined, whereby the emotional stability value is used to indicate the emotional stability of the occupants in the vehicle.

[0147] The first product is obtained by multiplying the event level by the emotional stability value;

[0148] The arctangent of the first product is applied to obtain the level of argument among the people inside the vehicle.

[0149] See Figure 6 , Figure 6 This is a schematic diagram of the structure of an electronic device provided for an embodiment of this application. For example... Figure 6 As shown, the electronic device 600 includes a transceiver 601, a processor 602, and a memory 603. These are connected via a bus 604. The memory 603 stores computer programs and data, and can transfer data stored in the memory 603 to the processor 602.

[0150] Processor 602 is used to read the computer program in memory 603 and perform the following operations:

[0151] Obtain the initial audio information of the people inside the vehicle;

[0152] Human voice extraction is performed on the first audio information to obtain human voice information;

[0153] Analyze the decibel level of human voice information to obtain the first decibel value corresponding to the human voice information;

[0154] Emotion recognition is performed on human voice information to obtain the first emotion information corresponding to the human voice information;

[0155] When the first decibel value is greater than the first threshold and / or the first emotional information meets the first condition, the second audio information within a preset time period is obtained based on the current time.

[0156] Determine the number of dialogues and / or the duration of each dialogue in the second audio information;

[0157] When the number of conversations exceeds the second threshold and / or the duration of a single conversation exceeds the third threshold, the level of argument among the people in the vehicle is determined based on the second audio information. The argument level includes three levels: weak, medium, and strong.

[0158] Perform the prompt action corresponding to the level of the argument.

[0159] In an embodiment of the present invention, when the argument level is weak, the processor 602 is specifically configured to perform the following operations in order to execute a prompt operation corresponding to the argument level:

[0160] Analyze the second audio information in decibels to obtain the second decibel value corresponding to the second audio information;

[0161] Play a pre-configured peace-discipline prompt voice, wherein the decibel level of the peace-discipline prompt voice is greater than the second decibel value.

[0162] In an embodiment of the present invention, when the argument level is medium, the processor 602 is specifically configured to perform the following operations in order to execute a prompt operation corresponding to the argument level:

[0163] Analyze the second audio information in decibels to obtain the second decibel value corresponding to the second audio information;

[0164] Play a pre-configured peace-discipline prompt voice, wherein the decibel level of the peace-discipline prompt voice is greater than the second decibel value;

[0165] The music list is determined based on the second audio information and the second decibel value;

[0166] When the second decibel value is lower than the fourth threshold, play music from the music list;

[0167] When the second decibel value is higher than or equal to the fourth threshold, a dissuasion prompt voice will be continuously played, and the hazard lights will be activated to warn other vehicles.

[0168] In an embodiment of the present invention, when the argument level is high, the processor 602 is specifically configured to perform the following operations in order to execute a prompt operation corresponding to the argument level:

[0169] Analyze the second audio information in decibels to obtain the second decibel value corresponding to the second audio information;

[0170] Play a pre-configured peace-discipline prompt voice, wherein the decibel level of the peace-discipline prompt voice is greater than the second decibel value;

[0171] The music list is determined based on the second audio information and the second decibel value;

[0172] When the second decibel value is lower than the fourth threshold, play music from the music list;

[0173] When the second decibel value is higher than or equal to the fourth threshold, the alarm prompt will continue to play and the hazard lights will be activated to warn other vehicles.

[0174] Control the vehicle's speed to be below the fifth threshold.

[0175] In an embodiment of the present invention, in determining the music list based on the second audio information and the second decibel value, the processor 602 is specifically configured to perform the following operations:

[0176] A sound restoration model corresponding to the second decibel value is determined based on the second decibel value. The sound restoration model is used to restore the sound at a high decibel level to the sound at a preset decibel level.

[0177] The second audio information is input into the sound restoration model to obtain the third audio information;

[0178] Determine the vocal characteristics of the arguing individuals based on third-party audio information;

[0179] Identify the individuals arguing based on their voice characteristics;

[0180] Based on the identity information, retrieve the first music list that the person arguing has saved or liked;

[0181] Based on the second audio information, determine the first keyword corresponding to the second audio information;

[0182] Based on the first keyword and the second decibel value, the first music list is filtered to determine the music list.

[0183] In an embodiment of the present invention, in determining the level of argument among occupants of a vehicle based on second audio information, processor 602 is specifically configured to perform the following operations:

[0184] Speech recognition is performed on the second audio information to obtain the first text;

[0185] Identify the second keyword in the first text;

[0186] Emotion recognition is performed on the second audio information to obtain the second emotional information corresponding to the second audio information;

[0187] The level of argument among the people inside the vehicle is determined based on the second keyword and the second emotional information.

[0188] In an embodiment of the present invention, in determining the level of argument among occupants of a vehicle based on a second keyword and second emotional information, the processor 602 is specifically configured to perform the following operations:

[0189] Based on the second keyword, determine the incident level of the argument between the people inside the vehicle;

[0190] Based on the second emotional information, the emotional stability value of the occupants in the vehicle is determined, whereby the emotional stability value is used to indicate the emotional stability of the occupants in the vehicle.

[0191] The first product is obtained by multiplying the event level by the emotional stability value;

[0192] The arctangent of the first product is applied to obtain the level of argument among the people inside the vehicle.

[0193] It should be understood that the in-vehicle argument handling device in this application may include smartphones (such as Android phones, iOS phones, Windows Phones, etc.), tablets, PDAs, laptops, mobile internet devices (MIDs), robots, or wearable devices. The above-mentioned in-vehicle argument handling devices are merely examples, not an exhaustive list, and include, but are not limited to, the aforementioned in-vehicle argument handling devices. In practical applications, the aforementioned in-vehicle argument handling device may also include: intelligent in-vehicle terminals, computer equipment, etc.

[0194] Through the above description of the embodiments, those skilled in the art can clearly understand that the present invention can be implemented by means of software combined with a hardware platform. Based on this understanding, all or part of the technical solution of the present invention that contributes to the background art can be embodied in the form of a software product. This computer software product can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in various embodiments or some parts of the embodiments of the present invention.

[0195] Therefore, embodiments of this application also provide a computer-readable storage medium storing a computer program that is executed by a processor to implement some or all of the steps of any of the in-vehicle argument handling methods described in the above method embodiments. For example, the storage medium may include a hard disk, floppy disk, optical disk, magnetic tape, magnetic disk, USB flash drive, flash memory, etc.

[0196] This application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps of any of the in-vehicle argument handling methods described in the above method embodiments.

[0197] It should be noted that, for the sake of simplicity, the aforementioned methods are described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are optional, and the actions and modules involved are not necessarily essential to this application.

[0198] In the above embodiments, the descriptions of each embodiment have their own emphasis. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0199] In the several embodiments provided in this application, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical or other forms.

[0200] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0201] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software program module.

[0202] If the integrated unit is implemented as a software program module and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, 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. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0203] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage device, which may include: flash drive, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0204] The embodiments of this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The above description of the embodiments is only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for handling arguments inside a car, characterized in that, The processing method includes: Obtain the initial audio information of the people inside the vehicle; Human voice extraction is performed on the first audio information to obtain human voice information; The human voice information is analyzed in decibels to obtain a first decibel value corresponding to the human voice information; Emotion recognition is performed on the human voice information to obtain first emotion information corresponding to the human voice information; When the first decibel value is greater than the first threshold, and / or when the first emotional information meets the first condition, the second audio information within a preset time period is obtained based on the current time, wherein the first condition is that the emotional recognition result is at least one of anger, grievance, and fear; Determine the number of dialogues and / or the duration of a single dialogue in the second audio information; When the number of conversations exceeds the second threshold and / or the duration of a single conversation exceeds the third threshold, the level of argument among the people in the vehicle is determined based on the second audio information. The level of argument includes three levels: weak, medium, and strong. Perform the prompt action corresponding to the level of argument; The step of determining the level of argument among the occupants of the vehicle based on the second audio information includes: The second audio information is subjected to speech recognition to obtain the first text; Identify the second keyword in the first text; Perform emotion recognition on the second audio information to obtain second emotion information corresponding to the second audio information; Based on the second keyword and the second emotional information, the level of argument among the people inside the vehicle is determined.

2. The processing method according to claim 1, characterized in that, When the argument level is weak, the step of performing the prompt operation corresponding to the argument level includes: The second audio information is analyzed in decibels to obtain the second decibel value corresponding to the second audio information. Play a pre-configured peace-discipline prompt voice, wherein the decibel level of the peace-discipline prompt voice is greater than the second decibel value.

3. The processing method according to claim 1, characterized in that, When the argument level is medium, the step of performing the prompt operation corresponding to the argument level includes: The second audio information is analyzed in decibels to obtain the second decibel value corresponding to the second audio information. Play a pre-configured peace-discipline prompt voice, wherein the decibel level of the peace-discipline prompt voice is greater than the second decibel value; The music list is determined based on the second audio information and the second decibel value; When the second decibel value is lower than the fourth threshold, play music from the music list; When the second decibel value is higher than or equal to the fourth threshold, the admonition voice prompt will be played continuously, and the hazard lights will be activated to warn other vehicles.

4. The processing method according to claim 1, characterized in that, When the argument level is high, the step of executing the prompt operation corresponding to the argument level further includes: The second audio information is analyzed in decibels to obtain the second decibel value corresponding to the second audio information. Play a pre-configured peace-discipline prompt voice, wherein the decibel level of the peace-discipline prompt voice is greater than the second decibel value; The music list is determined based on the second audio information and the second decibel value; When the second decibel value is lower than the fourth threshold, play music from the music list; When the second decibel value is higher than or equal to the fourth threshold, the dissuasion prompt voice will be played continuously, and the hazard lights will be activated to warn other vehicles. Control the vehicle's speed to be less than the fifth threshold.

5. The processing method according to claim 3 or 4, characterized in that, The step of determining the music list based on the second audio information and the second decibel value includes: A sound restoration model corresponding to the second decibel value is determined based on the second decibel value, wherein the sound restoration model is used to restore the sound at a high decibel level to the sound at a preset decibel level; The second audio information is input into the sound restoration model to obtain the third audio information; The vocal characteristics of the arguing individuals are determined based on the third audio information. Based on the voice characteristics, the identity information of the arguing parties is determined; Based on the identity information, obtain the first music list collected or liked by the person arguing; Based on the second audio information, determine the first keyword corresponding to the second audio information; Based on the first keyword and the second decibel value, the first music list is filtered to determine the music list.

6. The processing method according to claim 1, characterized in that, The step of determining the level of argument among the occupants of the vehicle based on the second keyword and the second emotional information includes: Based on the second keyword, the event level of the argument between the people inside the vehicle is determined; Based on the second emotional information, the emotional stability value of the occupants in the vehicle is determined, wherein the emotional stability value is used to identify the emotional stability of the occupants in the vehicle. The first product is obtained by multiplying the event level by the emotional stability value; The argument level of the occupants in the vehicle is obtained by performing arctangent processing on the first product.

7. A device for handling in-vehicle arguments, characterized in that, The processing device includes: The acquisition module is used to obtain the initial audio information of the people inside the vehicle; The analysis module is used to extract human voice from the first audio information to obtain human voice information; to analyze the decibel level of the human voice information to obtain a first decibel value corresponding to the human voice information; and to perform emotion recognition on the human voice information to obtain first emotion information corresponding to the human voice information. The acquisition module is further configured to acquire second audio information within a preset time period based on the current time when the first decibel value is greater than the first threshold and / or the first emotional information meets the first condition, wherein the first condition is that the emotional recognition result is at least one of anger, grievance, and fear; The analysis module is also used to determine the number of conversations and / or the duration of a single conversation in the second audio information; when the number of conversations is greater than a second threshold, and / or the duration of a single conversation is greater than a third threshold, the argument level of the people in the vehicle is determined according to the second audio information, and the argument level includes three levels: weak, medium and strong. The processing module is used to execute a prompt operation corresponding to the level of argument. In determining the level of argument among the occupants of the vehicle based on the second audio information, the analysis module is used to: The second audio information is subjected to speech recognition to obtain the first text; Identify the second keyword in the first text; Perform emotion recognition on the second audio information to obtain second emotion information corresponding to the second audio information; Based on the second keyword and the second emotional information, the level of argument among the people inside the vehicle is determined.

8. The processing apparatus according to claim 7, characterized in that, When the argument level is weak, the processing module is configured to: Regarding the execution of the prompting operation corresponding to the argument level, the processing module is configured to: The second audio information is analyzed in decibels to obtain the second decibel value corresponding to the second audio information. Play a pre-configured peace-discipline prompt voice, wherein the decibel level of the peace-discipline prompt voice is greater than the second decibel value.

9. The processing apparatus according to claim 7, characterized in that, When the argument level is medium, the processing module is configured to: Regarding the execution of the prompt operation corresponding to the argument level, the processing module is used to: The second audio information is analyzed in decibels to obtain the second decibel value corresponding to the second audio information. Play a pre-configured peace-discipline prompt voice, wherein the decibel level of the peace-discipline prompt voice is greater than the second decibel value; The music list is determined based on the second audio information and the second decibel value; When the second decibel value is lower than the fourth threshold, play music from the music list; When the second decibel value is higher than or equal to the fourth threshold, the admonition voice prompt will be played continuously, and the hazard lights will be activated to warn other vehicles.

10. The processing apparatus according to claim 7, characterized in that, When the argument level is high, the processing module is used to: Regarding the execution of the prompt operation corresponding to the argument level, the processing module is configured to: The second audio information is analyzed in decibels to obtain the second decibel value corresponding to the second audio information. Play a pre-configured peace-discipline prompt voice, wherein the decibel level of the peace-discipline prompt voice is greater than the second decibel value; The music list is determined based on the second audio information and the second decibel value; When the second decibel value is lower than the fourth threshold, play music from the music list; When the second decibel value is higher than or equal to the fourth threshold, the dissuasion prompt voice will be played continuously, and the hazard lights will be activated to warn other vehicles. Control the vehicle's speed to be less than the fifth threshold.

11. The processing apparatus according to claim 9 or 10, characterized in that, In determining the music list based on the second audio information and the second decibel value, the processing module is configured to: A sound restoration model corresponding to the second decibel value is determined based on the second decibel value, wherein the sound restoration model is used to restore the sound at a high decibel level to the sound at a preset decibel level; The second audio information is input into the sound restoration model to obtain the third audio information; The vocal characteristics of the arguing individuals are determined based on the third audio information. Based on the voice characteristics, the identity information of the arguing parties is determined; Based on the identity information, obtain the first music list collected or liked by the person arguing; Based on the second audio information, determine the first keyword corresponding to the second audio information; Based on the first keyword and the second decibel value, the first music list is filtered to determine the music list.

12. The processing apparatus according to claim 7, characterized in that, In determining the level of argument among the occupants of the vehicle based on the second keyword and the second emotional information, the analysis module is used to: Based on the second keyword, the event level of the argument between the people inside the vehicle is determined; Based on the second emotional information, the emotional stability value of the occupants in the vehicle is determined, wherein the emotional stability value is used to identify the emotional stability of the occupants in the vehicle. The first product is obtained by multiplying the event level by the emotional stability value; The argument level of the occupants in the vehicle is obtained by performing arctangent processing on the first product.

13. An electronic device, characterized in that, The method includes a processor, a memory, a communication interface, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and the one or more programs include instructions for performing the steps of the method of any one of claims 1-6.

14. A readable computer storage medium, characterized in that, The readable computer storage medium stores a computer program that is executed by a processor to implement the method as described in any one of claims 1-6.

Images