Emotion adjustment method and device, intelligent vehicle and computer readable storage medium

Abstract

The invention discloses an emotion adjustment method and device, an intelligent vehicle and a computer readable storage medium. The method comprises the following steps: acquiring sound wave information for detecting a target space; analyzing the sound wave information to determine a target attitude of the target object in the target space; performing emotion marking on the target object according to the target posture to determine a target emotion of the target object; and adjusting the current scene of the target space to the target scene according to the target emotion so as to adjust the target emotion of the target object. Therefore, after the target posture of the target object is determined through the sound wave signal, the target emotion of the target object can be determined according to the target posture of the target object, so that the emotion of the target object is accurately captured, and the accuracy of identifying the emotion of the target object is improved. The effect of adjusting the target emotion of the target object is improved, and then the technical problem of how to adjust the emotion of the person in the vehicle to improve the safety of the driving process is solved.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, and particularly relates to an emotion regulation method, device, intelligent vehicle, and computer-readable storage medium. Background Art

[0002] With the continuous development of intelligent vehicles, intelligent vehicles can provide more user-friendly services for users. And the prerequisite for intelligent vehicles to provide user-friendly services for users is that intelligent vehicles can obtain more accurate user information and provide services that meet the needs of users based on this user information. Therefore, in the technical field of intelligent vehicles, how to obtain more accurate user information to provide more user-friendly services has become a technical hotspot.

[0003] The driving safety of a vehicle is a crucial factor during driving. However, the emotions of the people in the vehicle can affect the driving safety of the vehicle during driving and even cause traffic accidents. Therefore, how to regulate the emotions of the people in the vehicle according to the emotion information collected by the intelligent vehicle to improve the safety during driving has become a technical problem to be solved urgently. Summary of the Invention

[0004] Embodiments of this application provide an emotion regulation method, device, intelligent vehicle, and computer-readable storage medium, which can solve the technical problem of how to regulate the emotions of the people in the vehicle to improve the safety during driving.

[0005] In a first aspect, embodiments of this application disclose an emotion regulation method, including:

[0006] Obtaining acoustic wave information for detecting a target space;

[0007] Analyzing the acoustic wave information to determine a target posture of a target object in the target space;

[0008] Performing an emotion marking on the target object according to the target posture to determine a target emotion of the target object;

[0009] Adjusting a current scene of the target space to a target scene according to the target emotion to regulate the target emotion of the target object.

[0010] In a second aspect, embodiments of this application disclose an emotion regulation device, including:

[0011] An obtaining unit, configured to obtain acoustic wave information for detecting a target space;

[0012] An analyzing unit, configured to analyze the acoustic wave information to determine a target posture of a target object in the target space;

[0013] A marking unit, configured to perform emotion marking on the target object according to the target posture to determine the target emotion of the target object;

[0014] An adjustment unit, configured to adjust the current scene of the target space to a target scene according to the target emotion to adjust the target emotion of the target object.

[0015] In a third aspect, an embodiment of the present application discloses an intelligent vehicle, which includes a processor and a memory. The memory stores a computer program, and the processor calls the computer program to implement the above-mentioned emotion regulation method.

[0016] In a fourth aspect, an embodiment of the present application discloses a computer-readable storage medium, in which program code is stored, and the program code can be called by a processor to implement the above-mentioned emotion regulation method.

[0017] In a fifth aspect, an embodiment of the present application discloses a computer program product or a computer program, which includes computer instructions, and the computer instructions are stored in a computer-readable storage medium.

[0018] In the embodiment of the present application, the acoustic wave information for detecting the target space can be obtained; the acoustic wave information is analyzed to determine the target posture of the target object in the target space; the target object is emotionally marked according to the target posture to determine the target emotion of the target object; according to the target emotion, the current scene of the target space is adjusted to a target scene to adjust the target emotion of the target object. In this way, after determining the target posture of the target object through the acoustic wave signal, the target emotion of the target object can be determined according to the target posture of the target object, so as to accurately capture the emotion of the target object and improve the accuracy of identifying the emotion of the target object. After determining the target emotion of the target object, the corresponding target operation can also be executed according to the target emotion of the target object, so as to improve the effect of emotion regulation on the target emotion of the target object, and further solve the technical problem of how to regulate the emotion of the vehicle occupants to improve the safety of the driving process. Description of the Drawings

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. For those skilled in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0020] Figure 1 It is a schematic structural diagram of an intelligent vehicle provided by an embodiment of the present application;

[0021] Figure 2It is a schematic flowchart of an emotion regulation method disclosed in an embodiment of the present application;

[0022] Figure 2A It is a specific schematic flowchart of an emotion regulation method disclosed in an embodiment of the present application;

[0023] Figure 3 It is another schematic flowchart of an emotion regulation method disclosed in an embodiment of the present application;

[0024] Figure 3A It is a schematic diagram of a scenario of an emotion regulation method disclosed in an embodiment of the present application;

[0025] Figure 3B It is another schematic diagram of a scenario of an emotion regulation method disclosed in an embodiment of the present application;

[0026] Figure 4 It is a schematic structural diagram of an emotion regulation device disclosed in an embodiment of the present application;

[0027] Figure 5 It is a schematic structural diagram of an intelligent vehicle disclosed in an embodiment of the present application;

[0028] Figure 6 It is a schematic structural diagram of a computer-readable storage medium disclosed in an embodiment of the present application. Detailed implementation manners

[0029] The following details the implementation manners of the present application. Examples of the implementation manners are shown in the accompanying drawings, where the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The implementation manners described below by referring to the accompanying drawings are exemplary only for explaining the present application and should not be construed as a limitation of the present application.

[0030] To enable those skilled in the art to better understand the solution of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of them. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present application.

[0031] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments. However, it can be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments and can be combined with each other without conflict. In the following description, the term "a plurality" refers to at least two.

[0032] In the following description, the terms "first" and "second" only distinguish similar objects and do not represent a specific order for the objects. Understandably, "first" and "second" can be interchanged in a specific order or sequence when permitted, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.

[0033] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0034] To enable those skilled in the technical field to better understand the solution of this application, the application environment of the solution of this application will be described first. The emotion regulation method provided by this application can be applied to, for example, Figure 1 the system architecture shown.

[0035] Please refer to Figure 1 , Figure 1 which is an exemplary structural schematic diagram of the intelligent vehicle 100 provided by the embodiment of this application. As Figure 1 shown, the intelligent vehicle 100 includes a microphone array 1, a body control unit 2, an actuator 3, an in-vehicle host 4, a display screen 5, an external power amplifier 6, a speaker 7, and a cloud database 8 that communicates with the in-vehicle host.

[0036] Among them, the microphone array 1 may include multiple microphones, and the multiple microphones may be installed at various positions such as the vehicle roof, headrest, and control main board of the intelligent vehicle 100. The microphone array 1 may be installed corresponding to multiple installation positions of the speaker 7 in the intelligent vehicle 100. The microphone array 1 may be used to receive the sound wave signals returned by detecting the target space by the sound wave signals emitted by the speaker 7. The microphone array 1 may achieve data transmission with the in-vehicle host 4. For example, the microphone array 1 may transmit the collected sound wave signals to the in-vehicle host 4.

[0037] The body control unit 2 may communicate with the actuator 3 and the in-vehicle host 4. The body control unit 2 may be used to receive the control instructions of the in-vehicle host. After receiving the control instructions from the in-vehicle host, it may send the control instructions to the actuator 3 to perform corresponding operations. For example, the body control unit 2 may receive a music playback instruction from the in-vehicle host 4, and after receiving the music playback instruction, it may send the music playback instruction to the corresponding actuator (external power amplifier 6) to play the music corresponding to the music playback instruction.

[0038] The execution structure 3 may include execution modules such as an ambient light module and an air conditioner control module. The execution structure 3 may be used to perform corresponding operations.

[0039] The in-vehicle host 4 can execute the emotion regulation method of the present application. Specifically, after receiving the sound wave signal from the microphone array 1, it can obtain the sound wave information for detecting the target space of the sound wave signal. After obtaining the sound wave information, it analyzes the sound wave information to determine the target posture of the target object. After determining the target posture of the target object, it determines the target emotion of the target object, and controls the actuator 3 to execute the corresponding operation to regulate the target emotion of the target object.

[0040] The display screen 5 can be used to respond to the execution operation of the user, and can also display the content to be displayed to the user to realize the interaction between the user and the intelligent vehicle. The display screen 5 can transmit data with the in-vehicle host. For example, the display screen 5 can determine the execution instruction in response to the execution operation of the user, and the in-vehicle host 4 can receive the execution instruction.

[0041] The external power amplifier 6 can be used to play audio information. The external power amplifier 6 can be used as an execution module of the actuator 3. The external power amplifier 6 can directly communicate with the in-vehicle host 4.

[0042] The speaker 7 can include multiple speakers, and the speaker 7 can be used to emit sound wave signals to the driving space and the passenger space of the intelligent vehicle.

[0043] The cloud database 8 can be used to store the data in the solution of the present application. For example, the cloud database 8 can store the correspondence between the target posture and the target emotion of the target object, and the correspondence between the target emotion and the corresponding target operation. The cloud database can transmit data with the in-vehicle host.

[0044] The communication relationship and data transmission relationship between the intelligent vehicle 100 and the cloud database, and between the various units in the intelligent vehicle 100 can be based on network connection and / or wired connection. Among them, the network can include local area network and / or wide area network. The local area network can include ZIGBEE or Bluetooth, etc., and the wide area network can include 2G / 3G / 4G / 5G / WIFI, etc.

[0045] As a specific embodiment, the emotion regulation method can be applied to the in-vehicle host 4. Specifically, a plurality of speakers 7 installed at different positions in the vehicle can emit acoustic wave signals into the interior space of the intelligent vehicle 100. After the acoustic wave signals touch an object in the interior space, the acoustic waves rebound, and the microphone array 1 correspondingly installed with the plurality of speakers 7 can receive the corresponding rebound acoustic wave signals. After the microphone array 7 receives the rebound acoustic wave signals, the in-vehicle host 4 can obtain the acoustic wave information for acoustic wave detection of the target space. After obtaining the acoustic wave information, the in-vehicle host 4 can analyze the acoustic wave information to determine the target posture of the target object, and determine the target emotion of the target object according to the target posture of the target object. After determining the target emotion of the target object, the current scene of the target space can also be switched to the target scene according to the target emotion of the target object to regulate the target emotion of the target object.

[0046] Please refer to Figure 2 , Figure 2 which is a schematic flowchart of an emotion regulation method disclosed in an embodiment of the present application. Among them, the emotion regulation method can be applied to an intelligent vehicle. As Figure 2 shown, the emotion regulation method can include the following steps.

[0047] Step 201, obtain the acoustic wave information for detecting the target space.

[0048] Among them, the target space can be the space in the intelligent vehicle, and the space can include the driving space and the riding space. The acoustic wave information can be the acoustic wave information determined by a plurality of speakers installed at different positions in the intelligent vehicle and a microphone array correspondingly installed with the plurality of speakers. The acoustic wave information can include time information, frequency information, etc. between the emitted acoustic wave signal and the rebound acoustic wave signal.

[0049] After the speaker emits an acoustic wave signal into the target space, the acoustic wave information for detecting the target space can be obtained. In some specific implementation manners, a first acoustic wave signal can be emitted into the target space through a sound generating device. The second acoustic wave signal reflected by the target space from the first acoustic wave signal is detected to determine the acoustic wave information. Among them, the sound generating device can be a speaker. The first acoustic wave signal can be the acoustic wave signal emitted by the sound generating device, and the second acoustic wave signal can be the acoustic wave signal received by the microphone array after the acoustic wave signal emitted by the speaker touches an object and rebounds. After determining the first acoustic wave signal and the second acoustic wave signal, the acoustic wave information for acoustic wave detection of the target space can be determined according to the emitted acoustic wave signal and the rebound acoustic wave signal.

[0050] Step 202, analyze the acoustic wave information to determine the target posture of the target object in the target space.

[0051] Among them, the target object can be the object to be detected in the target space. The target object can include the driver and multiple passengers in the target space. The target posture can be the body posture shown by the target object in the target space during the acoustic wave detection process. The target posture can include multiple body parts of the target object. For example, arms, necks, main trunks, etc.

[0052] After obtaining the acoustic wave information for detecting the target space, the acoustic wave information can be analyzed, and after analyzing the acoustic wave information, the target posture of the target object in the target space can be determined. In a specific implementation manner, the echo intensity of the acoustic wave information can be calculated. When it is determined that there is a target object in the target space according to the echo intensity of the acoustic wave information, the acoustic wave information corresponding to the target object is determined according to the echo intensity. After determining the acoustic wave information corresponding to the target object, the echo duration of the acoustic wave information corresponding to the target object can be calculated to obtain the spectral information of the acoustic wave information corresponding to the target object. After determining the spectral information corresponding to the target object, feature extraction can be performed on the spectral information to obtain the spectral features of the acoustic wave information corresponding to the target object. After determining the spectral features corresponding to the target object, the spectral features can be analyzed to determine the target posture of the target object.

[0053] After obtaining the acoustic wave information, the echo intensity can be calculated according to the acoustic wave information. Among them, the echo intensity can be the intensity of the acoustic wave frequency absorbed by the contacted object between the emitted acoustic wave signal and the rebounded acoustic wave signal corresponding to the acoustic wave information. It should be noted that there is a loss (weakening) of the acoustic wave frequency during the propagation process between the emitted acoustic wave signal and the rebounded acoustic wave signal. Especially when the emitted acoustic wave signal contacts an object, the object will absorb the acoustic wave signal and rebound the acoustic wave signal until the rebounded acoustic wave signal is determined. Since the target space of the intelligent vehicle is a relatively small space, the loss of the acoustic wave signal by other media during the process is small. Therefore, the difference between the emitted acoustic wave signal and the rebounded acoustic wave signal can be used as the loss caused by the absorption of the acoustic wave signal by the object.

[0054] After determining the echo intensity of the acoustic wave information, it is possible to determine whether the object contacted by the acoustic wave signal corresponding to the acoustic wave information is the target object according to the echo intensity of the acoustic wave information. Among them, the object can be any object included in the intelligent vehicle. For example, seats, windows, drivers, etc. in the intelligent vehicle. The echo intensities corresponding to the acoustic wave information generated when the acoustic wave signal contacts different objects are different. Among them, the corresponding relationship between the acoustic wave signals of different objects and the echo intensity can be preset in the cloud database. Therefore, it is possible to determine whether the object contacted by the acoustic wave information is the target object according to the echo intensity corresponding to the acoustic wave information generated when the acoustic wave signal contacts different objects. And after detecting the target space in the intelligent vehicle, it is determined whether there is a target object in the target space.

[0055] In another implementation, the frequency absorption coefficient of the acoustic wave signal can be calculated according to the echo intensity of the acoustic wave information. Among them, the frequency absorption coefficient is the frequency difference coefficient between the two moments when the acoustic wave signal is emitted and received again. When the frequency absorption coefficient is within the preset range, it is determined that there is a target object in the target space.

[0056] After determining that there is a target object in the target space, the echo duration of the acoustic wave information corresponding to the target object can be calculated. Among them, the echo duration can be the time difference between the emitted acoustic wave signal and the rebounded acoustic wave signal. The echo duration of the acoustic wave information corresponding to the target object can be the time difference between when the acoustic wave signal contacting the target object is emitted and when it is received again. The echo duration can be used to represent the distance to the target object. After determining the echo duration of the acoustic wave information corresponding to the target object, the spectral information of the acoustic wave signal corresponding to the target object can be determined according to the echo duration (transmission time) and the echo intensity (frequency loss).

[0057] After determining the spectral information of the acoustic wave signal corresponding to the target object, feature extraction can be performed on the spectral information of the acoustic wave signal corresponding to the target object. The spectral features of the acoustic wave information corresponding to the target object are obtained. Among them, the spectral features can be the key point information of the target object determined according to the echo duration.

[0058] In another implementation, preprocessing is performed on the spectral information corresponding to the target object to obtain the processed spectral information. After obtaining the processed spectral information, feature extraction can be performed on the processed spectral information to obtain the spectral features corresponding to the target object.

[0059] After determining the spectral characteristics of the acoustic wave information corresponding to the target object, the spectral characteristics can be analyzed to determine the target posture of the target object. Specifically, the spectral characteristics can be input into a preset posture determination model to determine the corresponding target posture. Among them, the posture determination model can include the corresponding relationship between different acoustic waves and postures, and the posture determination model can be a model determined by pre-training based on known posture data and acoustic wave data.

[0060] Step 203: Perform an emotion label on the target object according to the target posture to determine the target emotion of the target object.

[0061] Among them, the target emotion can be the emotion determined after identifying the target object. The target emotion can include emotions such as anger, fear, disgust, happiness, sadness, surprise, and neutral.

[0062] After determining the target posture of the target object, the matching values between each part of the target object in the target posture and various emotions can be determined. And according to the matching values between each part of the target object and various emotions, an overall emotion label is performed on the target object to obtain the similarity between the target emotion and various different emotions. After determining the similarity between the target emotion and each emotion, the target emotion of the target object can be determined.

[0063] In some specific implementation manners, after determining the target posture of the target object, the target object can be labeled according to the target posture of the target object, and the target emotion of the target object can be determined after labeling the target object. Specifically, after determining the target posture of the target object, the skeleton diagram corresponding to the target object can be determined according to the target posture. The skeleton diagram is compared with a preset standard skeleton diagram to determine multiple emotion factors corresponding to the target object and various emotions. Among them, the multiple emotion factors correspond one by one to various emotions. Select the target emotion factor that meets the preset conditions from the multiple emotion factors. Determine the target emotion of the target object according to the target emotion factor.

[0064] Step 204: Adjust the current scene bar of the target space to the target scene according to the target emotion to adjust the target emotion of the target object.

[0065] After determining the target emotion of the target object, the target scene that can relieve the emotion of the target object can be determined according to the target emotion of the target object, and the current scene in the target space can be switched to the target scene to regulate the emotion of the target object in the target space. Among them, the corresponding relationship between emotion and scene can be preset and stored in the cloud database, and the corresponding relationship between emotion and scene can be determined according to the known target emotion and target scene. After determining the target scene corresponding to relieving the target emotion of the target object, the adjustment device that needs to perform operations in the target scene can be determined. Among them, the adjustment device can be an actuator including an atmosphere light module, an air conditioner control module, etc. After determining the adjustment device that needs to perform operations in the target scene, it can be determined whether the adjustment device is turned on or whether the target operation is performed. If it is not turned on, the adjustment device is automatically turned on; if the target operation is not performed, the adjustment device is adjusted to perform the target operation to regulate the target emotion of the target object.

[0066] In some specific embodiments, after determining the target emotion of the target object and the target scene that needs to be adjusted corresponding to the target emotion, the corresponding target operation can be determined according to the target scene, and the target operation can be executed to regulate the target emotion of the target object. Specifically, after determining the target scene that needs to be adjusted, according to the corresponding relationship between emotion, adjustment device and adjustment operation, the target adjustment device corresponding to the target emotion and the target adjustment operation corresponding to the target adjustment device can be determined. Control the target adjustment device to execute the corresponding target adjustment operation to regulate the target emotion of the target object in the target space.

[0067] Please refer to Figure 2A , Figure 2A which is a schematic diagram of a specific process disclosed in this application. Specifically, after obtaining the acoustic wave information of the target object, the acoustic wave information can be feature-extracted to determine the target posture of the target object. After determining the target posture of the target object, the target object can be emotionally marked. After emotionally marking the target object, it can be determined that the intelligent vehicle performs target operations such as video / image adjustment, sound adjustment, or light adjustment to relieve the target emotion of the target object.

[0068] In Figure 2In the described method embodiments, acoustic wave information for detecting a target space can be obtained; the acoustic wave information can be analyzed to determine the target posture of a target object in the target space; the target object can be emotionally tagged according to the target posture to determine the target emotion of the target object; and according to the target emotion, the current scene of the target space can be adjusted to a target scene to adjust the target emotion of the target object. In this way, after determining the target posture of the target object through the acoustic wave signal, the target emotion of the target object can be determined according to the target posture of the target object, so as to accurately capture the emotion of the target object and improve the accuracy of identifying the emotion of the target object. After determining the target emotion of the target object, corresponding target operations can also be performed according to the target emotion of the target object, thereby improving the effect of emotion regulation on the target emotion of the target object, and further solving the technical problem of how to regulate the emotion of vehicle occupants to improve the safety of the driving process.

[0069] Please refer to Figure 3 , Figure 3 which is a schematic flowchart of another emotion regulation method disclosed in the embodiments of the present application. This emotion regulation method can be applied to intelligent vehicles. As Figure 3 shown, this emotion regulation method can include the following steps.

[0070] Step 301: Transmit a first acoustic wave signal to the target space through a sound emitting device.

[0071] The first acoustic wave signal can be an acoustic wave signal emitted by the sound emitting device. The intelligent vehicle can emit an audio signal through an in-vehicle host, and the emitted audio can be amplified by an external power amplifier and drive a speaker to emit an audio signal according to the amplified audio signal. The audio signal emitted by the speaker can be an acoustic wave signal of 20 Hz - 30 KHz.

[0072] Step 302: Detect a second acoustic wave signal that rebounds from the target space to the first acoustic wave signal to determine the acoustic wave information.

[0073] The second acoustic wave signal can be an acoustic wave signal that rebounds after the acoustic wave signal emitted by the speaker touches an object and is received by a microphone array. The audio signal emitted by the speaker can form a sound field through direct transmission and reflection of the acoustic wave signal during the transmission process in the target space corresponding to the intelligent vehicle, and the microphone arrays installed at different positions of the vehicle can receive the sound field information. The in-vehicle host can obtain the acoustic wave signal from the microphone array.

[0074] Step 303: Analyze the acoustic wave information to determine the target posture of the target object.

[0075] Among them, the specific content of step 303 can refer to the specific description of the echo intensity in step 202 and will not be elaborated here.

[0076] Step 304: Determine the skeleton diagram corresponding to the target object according to the target pose.

[0077] After determining the target pose of the target object, the key points in the target can be identified to determine the different joint points of each body part in the target pose of the target object. After determining the different joint points of each body part in the target pose of the target object, the target pose (human pose) can be converted into a human skeleton diagram, and the skeleton model can be extracted to obtain the corresponding skeleton diagram.

[0078] Please refer to Figure 3A , Figure 3A which is a schematic diagram of a scenario disclosed in the present application. Specifically, after determining the corresponding skeleton diagram according to the target pose of the target object, the skeleton diagram may include the head, neck, left shoulder, right shoulder, left elbow, right elbow, waist, left hand, right hand, left hip, right hip, left knee, right knee, left foot, and right foot of the target object.

[0079] Step 305: Compare the skeleton diagram with a preset standard skeleton diagram to determine multiple emotion factors corresponding to the target object and multiple emotions.

[0080] Among them, the multiple emotion factors correspond one by one to the multiple emotions.

[0081] After determining the skeleton diagram corresponding to the target object, the skeleton diagram can be uploaded to the cloud. Based on the cloud server, the skeleton diagram corresponding to the target object is compared with multiple standard skeleton diagrams to determine the similarity between the skeleton diagram corresponding to the target object and the multiple standard skeleton diagrams, and the emotion factors between the standard skeleton diagrams corresponding to each emotion are obtained.

[0082] In another implementation, the corresponding relationship between multiple emotions and multiple standard skeleton diagrams pre-stored in the cloud database can also be called by the in-vehicle host of the vehicle. The in-vehicle host calculates the similarity between the skeleton diagram of the target object and the standard skeleton diagram corresponding to each emotion to obtain the emotion factors between the standard skeleton diagrams corresponding to each emotion.

[0083] Specifically, each node in the skeleton diagram corresponding to the target object can be compared with the nodes in the standard skeleton diagram corresponding to each emotion. When making a comparison for each node, the corresponding eigenvalue of each node can be substituted into the following formula to obtain the corresponding emotion factor.

[0084] K0 = ∑λ·K / K n ,

[0085] where λ is a correction coefficient, K is the eigenvalue of the node in the skeleton diagram of the target object, and K n is the standard eigenvalue of the node in the standard skeleton diagram corresponding to an emotion.

[0086] After calculating the comparison between each node in the skeleton diagram corresponding to the target object and the standard skeleton diagrams corresponding to each emotion respectively, the emotion factors between the skeleton diagram corresponding to the target object and the standard skeleton diagrams corresponding to each emotion can be determined, and multiple emotion factors are obtained.

[0087] Please refer to Figure 3B , Figure 3B , which is a schematic diagram of another scenario disclosed in this application. Specifically, there can be standard skeleton diagrams corresponding to multiple emotions, also known as typical skeleton diagrams. Specifically, it can include the typical skeleton diagram of anger, the typical skeleton diagram of fear, the typical skeleton diagram of disgust, the typical skeleton diagram of happiness, the typical skeleton diagram of sadness, the typical skeleton diagram of surprise, and the typical skeleton diagram of neutrality.

[0088] Step 306: Select a target emotion factor that meets the preset conditions from multiple emotion factors.

[0089] After obtaining multiple emotion factors by calculating the comparison between each node in the skeleton diagram corresponding to the target object and the standard skeleton diagrams corresponding to each emotion respectively, the largest emotion factor among the multiple emotion factors can be selected, and this largest emotion factor can be used as the target emotion factor of the target object. Among them, this target emotion factor can be used to represent the highest similarity between the skeleton diagram of the target object and the standard skeleton diagram corresponding to an emotion.

[0090] Exemplarily, the K0 value between the skeleton diagram of the driver and the standard skeleton diagrams corresponding to each emotion can be obtained, and the largest K0 value is taken, which is the emotion factor representing the current emotional state of the driver.

[0091] Step 307: Determine the target emotion of the target object according to the target emotion factor.

[0092] After determining the target emotion factor of the target object, the target emotion of the target object can be determined according to this target emotion factor. Specifically, after determining the target emotion factor of the target object, the target emotion factor of the target object can be uploaded to the cloud. Based on the comparison between the target emotion factor of the target object and the K0 values corresponding to multiple emotions by the cloud server, the target emotion corresponding to the target object is determined.

[0093] In another embodiment, the correspondence between multiple emotions and multiple target emotion factors pre-stored in the cloud database can also be called by the in-vehicle host of the vehicle. The in-vehicle host matches the target emotion corresponding to the target emotion factor of the target object according to the correspondence between multiple emotions and multiple target emotion factors, and obtains the target emotion of the target object.

[0094] Emotional factor Angry Afraid Disgusted Happy Level 1 <![CDATA[0≤K0<1]]> <![CDATA[0≤K0<1]]> <![CDATA[0 ≤ K0 < 1]]> <![CDATA[0≤K0<1]]> Level 2 <![CDATA[1≤K0<2]]> <![CDATA[1≤K0<2]]> <![CDATA[1≤K0<2]]> <![CDATA[1≤K0<2]]> Level 3 <![CDATA[2≤K0]]> <![CDATA[2≤K0]]> <![CDATA[2≤K0]]> <![CDATA[2≤K0]]>

[0095] Table 1.1 Corresponding relationships between multiple emotions and multiple target emotion factors

[0096] Emotional factor Sad Surprised Neutral Level 1 <![CDATA[0≤K0<1]]> <![CDATA[0≤K0<1]]> <![CDATA[0≤K0<1]]> Level 2 <![CDATA[1≤K0<2]]> <![CDATA[1≤K0<2]]> <![CDATA[1≤K0<2]]> Level 3 <![CDATA[2≤K0]]> <![CDATA[2≤K0]]> <![CDATA[2≤K0]]>

[0097] Table 1.2 Corresponding relationships between multiple emotions and multiple target emotion factors

[0098] Step 308: Determine a target scene corresponding to the target emotion according to the target emotion, where the target scene is used to adjust the current emotion of the target object.

[0099] Among them, the target scene may be different from the current scene in the target space, and the target scene may be used to adjust the emotion of the target object by adjusting the scene atmosphere in the target space.

[0100] After determining the target emotion, a target scene for adjusting the target emotion of the target object can be matched. For example, when determining that the target emotion of the target object in the target space is anger, it can be determined that the scene that can be matched with "anger" is humorous and witty to relieve the anger emotion of the target object; when determining that the target emotion of the target object in the target space is sadness, it can be determined that the scene that can be matched with "sadness" is inspiring and encouraging to relieve the sadness emotion of the target object.

[0101] Step 309: Determine a target adjustment device corresponding to the target emotion and a target adjustment operation corresponding to the target adjustment device according to the corresponding relationship between the target scene, the adjustment device, and the adjustment operation.

[0102] After determining the target scene required to adjust the target emotion of the target object, according to the corresponding relationship between different scenes, the adjustment device, and the adjustment operation, a target adjustment device corresponding to the target scene and a target adjustment operation corresponding to the target adjustment device can be determined. Specifically, after determining the target scene, the target scene required by the target object can be uploaded to the cloud. Based on the cloud server, match the adjustment device and the adjustment operation corresponding to the target scene to determine the target adjustment operation corresponding to the target emotion.

[0103] In another implementation manner, the corresponding relationship between emotions, the adjustment device, and the adjustment operation pre-stored in the cloud database can also be called through the in-vehicle host of the vehicle. The in-vehicle host matches the target adjustment operation corresponding to the target emotion of the target object according to the corresponding relationship between emotions, the adjustment device, and the adjustment operation.

[0104]

[0105] Table 2 Corresponding relationships between emotions, the adjustment device, and the adjustment operation

[0106] Step 310: By controlling the target adjustment device to perform the corresponding target adjustment operation, adjust the current scenario of the vehicle to the target scenario to adjust the target emotion of the target object.

[0107] After determining the target adjustment operation, the intelligent vehicle can control each actuator on the intelligent vehicle through the in-vehicle host to perform the corresponding target adjustment operation, and adjust the target emotion of the target object after performing the target adjustment operation.

[0108] In Figure 3 In the described method embodiments, the acoustic wave information for detecting the target space can be obtained; the acoustic wave information can be analyzed to determine the target posture of the target object in the target space; the target object can be emotionally marked according to the target posture to determine the target emotion of the target object; according to the target emotion, the current scenario of the target space can be adjusted to the target scenario to adjust the target emotion of the target object. In this way, after determining the target posture of the target object through the acoustic wave signal, the target emotion of the target object can be determined according to the target posture of the target object, so as to more accurately capture the emotion of the target object and improve the accuracy of identifying the emotion of the target object. After determining the target emotion of the target object, the corresponding target operation can also be performed according to the target emotion of the target object, so as to improve the effect of emotion regulation on the target emotion of the target object, and further solve the technical problem of how to regulate the emotion of the vehicle occupants to improve the safety of the driving process.

[0109] It should be understood that the same or corresponding information in the above different embodiments can be referred to each other.

[0110] It should be understood that although Figure 2 , 3 the steps in the flowchart are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise clearly stated in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, Figure 2 , 3 at least a part of the steps in

[0111] can include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same moment, but can be executed at different moments. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or sub-steps or stages of other steps. Figure 4 , Figure 4 Please refer to

[0112] An acquisition unit 401, configured to acquire acoustic wave information for detecting a target space;

[0113] An analysis unit 402, configured to analyze the acoustic wave information to determine a target posture of a target object in the target space;

[0114] A marking unit 403, configured to perform emotion marking on the target object according to the target posture to determine a target emotion of the target object;

[0115] An adjustment unit 404, configured to adjust a current scene of the target space to a target scene according to the target emotion to adjust the target emotion of the target object.

[0116] In some embodiments, the acquisition unit 401 may be specifically configured to:

[0117] Transmit a first acoustic wave signal to the target space through a sound emitting device;

[0118] Detect a second acoustic wave signal reflected by the target space from the first acoustic wave signal to determine the acoustic wave information.

[0119] In some embodiments, the analysis unit 402 may be specifically configured to:

[0120] Calculate an echo intensity of the acoustic wave information;

[0121] When it is determined that there is a target object in the target space according to the echo intensity of the acoustic wave information, determine the acoustic wave information corresponding to the target object according to the echo intensity;

[0122] Calculate an echo duration of the acoustic wave information corresponding to the target object to obtain spectral information of the acoustic wave information corresponding to the target object;

[0123] Extract features from the spectral information to obtain spectral features of the acoustic wave information corresponding to the target object;

[0124] Analyze the spectral features to determine the target posture of the target object.

[0125] In some embodiments, the emotion adjustment device 400 further includes:

[0126] A calculation unit 405, configured to calculate a frequency absorption coefficient of an acoustic wave signal according to the echo intensity of the acoustic wave information; wherein, the frequency absorption coefficient is a frequency difference coefficient between two moments when the acoustic wave signal is emitted and received again;

[0127] The calculation unit 405 is configured to determine that there is a target object in the target space when the frequency absorption coefficient is within a preset range.

[0128] In some embodiments, the emotion regulation device 400 further includes:

[0129] A preprocessing unit 406, configured to preprocess the spectrum information corresponding to the target object to obtain processed spectrum information.

[0130] In some embodiments, the analysis unit 402 may specifically be configured to:

[0131] Extract features from the processed spectrum information to obtain spectrum features corresponding to the target object.

[0132] In some embodiments, the marking unit 403 may specifically be configured to:

[0133] Determine a skeleton diagram corresponding to the target object according to the target posture;

[0134] Compare the skeleton diagram with a preset standard skeleton diagram to determine multiple emotion factors corresponding to the target object and multiple emotions; wherein, the multiple emotion factors correspond to the multiple emotions one by one;

[0135] Select a target emotion factor that meets a preset condition from the multiple emotion factors;

[0136] Determine the target emotion of the target object according to the target emotion factor.

[0137] In some embodiments, the regulation unit 404 may specifically be configured to:

[0138] Determine a target scene corresponding to the target emotion according to the target emotion, where the target scene is used to regulate the current emotion of the target object;

[0139] Determine a target regulation device and a target adjustment operation corresponding to the target regulation device according to the corresponding relationship between the target scene, the regulation device, and the regulation operation;

[0140] Adjust the current scene of the vehicle to the target scene by controlling the target regulation device to execute the corresponding target adjustment operation, so as to regulate the target emotion of the target object.

[0141] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described devices and units can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.

[0142] In several embodiments disclosed in the present application, the coupling between units may be electrical, mechanical, or other forms of coupling.

[0143] In addition, in each embodiment of the present application, each functional unit can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

[0144] As Figure 5 shown, an embodiment of the present application also discloses a schematic structural diagram of an intelligent vehicle. The intelligent vehicle includes a processor 501 and a memory 502. The memory 502 stores computer program instructions. When the computer program instructions are called by the processor 501, the various method steps disclosed in the above embodiments can be executed. Those skilled in the art can understand that the structure of the intelligent vehicle shown in the figure does not constitute a limitation on the intelligent vehicle, and it may include more or fewer components than shown in the figure, or combine some components, or have different component arrangements. Among them:

[0145] The processor 501 may include one or more processing cores. The processor 501 uses various interfaces and lines to connect various parts within the entire battery management system. By running or executing instructions, programs, code sets, or instruction sets stored in the memory 502, calling the data stored in the memory 502, performing various functions of the battery management system and processing data, and performing various functions of the intelligent vehicle and processing data, the intelligent vehicle can be monitored as a whole. Optionally, the processor 501 can be implemented in at least one hardware form of digital signal processing (DSP), field-programmable gate array (FPGA), or programmable logic array (PLA). The processor 501 can integrate a combination of one or more of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. Among them, the CPU mainly processes the operating system, user interface, and application programs, etc.; the GPU is responsible for rendering and drawing the displayed content; the modem is used to process wireless communication. It can be understood that the above modem may not be integrated into the processor 501 and can be implemented separately through a communication chip.

[0146] The memory 502 may include a Random Access Memory (RAM), or may also include a Read-Only Memory. The memory 502 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 502 may include a program storage area and a data storage area. Among them, the program storage area may store instructions for implementing an operating system, instructions for implementing at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing various method embodiments described below, etc. The data storage area may also store data created during the use of the intelligent vehicle (such as a phone book, audio / video data, chat record data, etc.). Correspondingly, the memory 502 may further include a memory controller to facilitate access of the processor 501 to the memory 502.

[0147] Although not shown, the intelligent vehicle may further include a display unit, etc., which will not be elaborated here. Specifically, in this embodiment, the processor 501 in the intelligent vehicle will load the executable files corresponding to the processes of one or more application programs into the memory 502 according to the following instructions, and the processor 501 will run the application programs stored in the memory 502 to implement the various method steps disclosed in the foregoing embodiments.

[0148] As Figure 6 shown, an embodiment of the present application also discloses a computer-readable storage medium storing computer program instructions that can be called by a processor to execute the methods described in the above embodiments.

[0149] The computer-readable storage medium may be an electronic memory such as a flash memory, an EEPROM (Electrically Erasable Programmable Read-Only Memory), an EPROM, a hard disk or a ROM. Optionally, the computer-readable storage medium includes a non-transitory computer-readable storage medium. The computer-readable storage medium has a storage space for program codes for executing any method steps in the above methods. These program codes can be read from or written into one or more computer program products. The program codes may be compressed in an appropriate form, for example.

[0150] According to one aspect of the present application, a computer program product or a computer program is disclosed. The computer program product or the computer program includes computer instructions stored in a computer-readable storage medium. The processor of the intelligent vehicle reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, causing the intelligent vehicle to execute the methods disclosed in the various alternative implementations disclosed in the above embodiments.

[0151] The above are only the preferred embodiments of the present application, and do not impose any form of limitation on the present application. Although the present application has been disclosed above with the preferred embodiments, it is not intended to limit the present application. Any person skilled in the art can make some changes or modifications to equivalent embodiments with equivalent changes by using the technical content disclosed above within the scope of the technical solution of the present application. However, as long as it does not depart from the content of the technical solution of the present application, any brief modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present application still fall within the scope of the technical solution of the present application.

Claims

1. A method for emotion regulation, characterized in that, The method includes: Obtaining acoustic wave information for detecting a target space; Analyzing the acoustic wave information to determine the target posture of a target object in the target space; Performing an emotion label on the target object according to the target posture to determine the target emotion of the target object; Adjusting the current scene of the target space to a target scene according to the target emotion to adjust the target emotion of the target object.

2. The method according to claim 1, wherein The obtaining of the acoustic wave information for detecting the target space includes: Transmitting a first acoustic wave signal to the target space through a sound - emitting device; Detecting a second acoustic wave signal that rebounds from the target space to the first acoustic wave signal to determine the acoustic wave information.

3. The method according to claim 1, characterized in that The analyzing of the acoustic wave information to determine the target posture of the target object includes: Calculating the echo intensity of the acoustic wave information; When it is determined that there is a target object in the target space according to the echo intensity of the acoustic wave information, determining the acoustic wave information corresponding to the target object according to the echo intensity; Calculating the echo duration of the acoustic wave information corresponding to the target object to obtain the spectrum information of the acoustic wave information corresponding to the target object; Performing feature extraction on the spectrum information to obtain the spectrum features of the acoustic wave information corresponding to the target object; Analyzing the spectrum features to determine the target posture of the target object.

4. The method according to claim 3, wherein The method further includes: Calculating a frequency absorption coefficient of the acoustic wave signal according to the echo intensity of the acoustic wave information; wherein, the frequency absorption coefficient is a frequency difference coefficient between two moments when the acoustic wave signal is emitted and received again; When the frequency absorption coefficient is within a preset range, determining that there is a target object in the target space.

5. The method according to claim 3, wherein The method further includes: Performing pre - processing on the spectrum information corresponding to the target object to obtain processed spectrum information; The performing of the feature extraction on the spectrum information to obtain the spectrum features of the acoustic wave information corresponding to the target object includes: Performing feature extraction on the processed spectrum information to obtain the spectrum features corresponding to the target object.

6. The method according to claim 1, wherein The performing of the emotion label on the target object according to the target posture to determine the target emotion of the target object includes: Determining a skeleton diagram corresponding to the target object according to the target posture; Comparing the skeleton diagram with a preset standard skeleton diagram to determine a plurality of emotion factors corresponding to the target object and a plurality of emotions; wherein, the plurality of emotion factors correspond to the plurality of emotions one by one; Selecting a target emotion factor that meets a preset condition from the plurality of emotion factors; Determining the target emotion of the target object according to the target emotion factor.

7. The method according to claim 1, characterized in that, The adjusting of the current scene of the target space to a target scene according to the target emotion to adjust the target emotion of the target object includes: Determining a target scene corresponding to the target emotion according to the target emotion, and the target scene is used to adjust the current emotion of the target object; Determining a target adjustment device and a target adjustment operation corresponding to the target adjustment device according to the corresponding relationship between the target scene, the adjustment device, and the adjustment operation; By controlling the target adjustment device to perform the corresponding target adjustment operation, the current scene of the vehicle is adjusted to the target scene to adjust the target emotion of the target object.

8. An emotion regulation device, characterized in that, The emotion adjustment device includes: An acquisition unit, configured to acquire acoustic wave information for detecting a target space; An analysis unit, configured to analyze the acoustic wave information to determine the target posture of the target object in the target space; A marking unit, configured to perform emotion marking on the target object according to the target posture to determine the target emotion of the target object; An adjustment unit, configured to adjust the current scene of the target space to a target scene according to the target emotion to adjust the target emotion of the target object.

9. An intelligent vehicle, characterized in that, It includes a memory and a processor, the memory stores a computer program, and the processor calls the computer program to implement the method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program or computer instructions, and when the computer program or the computer instructions are run by a processor, the method according to any one of claims 1-7 is implemented.

Images