An in-vehicle emotion pacification method and device, electronic equipment and vehicle

Abstract

The application relates to the technical field of in-vehicle interaction, and provides an in-vehicle emotion pacification method and device, electronic equipment and a vehicle. The method comprises the following steps: acquiring in-vehicle sound; analyzing the in-vehicle sound to obtain an analysis result, wherein the analysis result comprises passenger information and passenger emotion of in-vehicle passengers; when the passenger emotion satisfies a pacification condition, determining a target interactive object of the in-vehicle passengers according to the passenger information; generating a replica sound of the target interactive object, playing pacification audio comprising the replica sound to the in-vehicle passengers, and pacifying the in-vehicle passengers by using the pacification audio. Since the pacification audio comprises the replica sound of the target interactive object, the in-vehicle passengers are more intimate and trust the target interactive object, are easy to stabilize the emotion after hearing the targeted pacification audio comprising the replica sound, the pacification effect is more ideal, the child passengers are more likely to stop crying, the driver's concerns are eliminated, the driving risks when there are child passengers are eliminated, and the problem that the pacification effect on the child passengers in the prior art is not ideal is solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of in-vehicle interaction, and in particular to an in-vehicle emotion soothing method and device, an electronic device, and a vehicle. BACKGROUND

[0002] When there is a child passenger in a vehicle, especially when there is only a driver and a child passenger, the child passenger is prone to emotional restlessness and crying, which causes the driver to be distracted, and there is a safety hazard in the driving process, affecting driving safety.

[0003] Currently, a scheme for soothing a child passenger in a vehicle to ensure driving safety generally determines whether there is a child passenger in the vehicle through image recognition of a monitoring device, analyzes the child passenger's mood according to the image, and if the mood is poor, plays an animation or soothing music for the child passenger on a display screen to soothe the child's mood.

[0004] However, this scheme is not targeted, and all child passengers are subjected to the same soothing method. Since different children have different levels of acceptance of images and music, it cannot be guaranteed that the mood of each child passenger will be soothed. SUMMARY

[0005] Therefore, embodiments of the present application provide an in-vehicle emotion soothing method, device, electronic device, and vehicle to solve the problem of unsatisfactory soothing of child passengers in the prior art.

[0006] In a first aspect, an in-vehicle emotion soothing method is provided, including:

[0007] obtaining in-vehicle sound;

[0008] analyzing the in-vehicle sound to obtain an analysis result, the analysis result including passenger information and passenger emotion of an in-vehicle passenger;

[0009] when the passenger emotion meets a soothing condition, determining a target interactive object of the in-vehicle passenger according to the passenger information;

[0010] generating a copied sound of the target interactive object, and playing soothing audio including the copied sound to the in-vehicle passenger to soothe the in-vehicle passenger with the soothing audio.

[0011] In a second aspect, an in-vehicle emotion soothing device is provided, including:

[0012] an obtaining module configured to obtain in-vehicle sound;

[0013] an analysis module configured to analyze the in-vehicle sound to obtain an analysis result, the analysis result including passenger information and passenger emotion of an in-vehicle passenger;

[0014] determining, by the determining module, a target interactive object of the passenger in the vehicle according to the passenger information when the passenger emotion meets the pacification condition;

[0015] playing, by the playing module, a copied sound of the target interactive object, and playing pacification audio including the copied sound to the passenger in the vehicle to pacify the passenger in the vehicle by using the pacification audio.

[0016] In a third aspect, an electronic device is provided, which comprises a sound collector, a sound player, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein:

[0017] The sound collector is configured to collect the sound in the vehicle and send the sound to the processor.

[0018] The processor implements the steps of the method when executing the computer program.

[0019] The sound player is configured to perform the step of playing the pacification audio under the control of the processor.

[0020] In a fourth aspect, a vehicle is provided, which comprises the electronic device.

[0021] Compared with the prior art, the embodiments of the present application have at least the following beneficial effects: the embodiments of the present application analyze the sound in the vehicle to obtain passenger information and a passenger emotion of a passenger in the vehicle, determine a target interactive object of the passenger according to the passenger information when the passenger emotion meets a pacification condition, generate a copied sound of the target interactive object, and play pacification audio including the copied sound, so that the passenger in the vehicle is more intimate and trusting of the target interactive object, is more likely to stabilize the emotion after hearing the pacification audio including the copied sound, and is more likely to stop crying, thereby eliminating the concerns of the driver, eliminating the driving risks when there is a child passenger, and solving the problem of the unsatisfactory pacification effect of the child passenger in the prior art. BRIEF DESCRIPTION OF DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0023] Figure 1 is a flowchart of a vehicle emotion pacification method provided by the embodiments of the present application;

[0024] Figure 2is a flowchart of another in-vehicle emotional pacification method provided by an embodiment of the present application;

[0025] Figure 3 is a flowchart of still another in-vehicle emotional pacification method provided by an embodiment of the present application;

[0026] Figure 4 is a structural diagram of an in-vehicle emotional pacification device provided by an embodiment of the present application;

[0027] Figure 5 is a structural diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0028] In the following description, for the purpose of explanation and not limitation, specific details are set forth, such as particular system configurations, techniques, etc., in order to provide a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application can be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.

[0029] An in-vehicle emotional pacification method and device according to an embodiment of the present application will be described in detail below with reference to the accompanying drawings.

[0030] Figure 1 is a flowchart of an in-vehicle emotional pacification method provided by an embodiment of the present application. Figure 1 The in-vehicle emotional pacification method can be executed by a processor inside a vehicle. The processor executes the embodiment method during vehicle driving, to achieve the purpose of monitoring in-vehicle sound and providing pacification service when the in-vehicle sound meets the pacification condition. As shown in Figure 1 The in-vehicle emotional pacification method includes:

[0031] S101: obtaining in-vehicle sound;

[0032] S102: analyzing the in-vehicle sound to obtain an analysis result, the analysis result including passenger information and passenger emotion of in-vehicle passengers;

[0033] S103: when the passenger emotion meets the pacification condition, determining a target interactive object of the in-vehicle passengers according to the passenger information;

[0034] S104: generating a replica sound of the target interactive object, playing pacification audio including the replica sound to the in-vehicle passengers, to pacify the in-vehicle passengers by using the pacification audio.

[0035] The in-vehicle sound can be obtained by collecting the in-vehicle sound through a sound collector. The in-vehicle sound includes environmental sound and passenger sound. In this embodiment, the passenger sound in the in-vehicle sound needs to be analyzed and judged. Therefore, before performing subsequent operations, the in-vehicle sound can be preprocessed to eliminate noise and irrelevant environmental sound in the in-vehicle sound, thereby improving the proportion of the passenger sound in the in-vehicle sound.

[0036] The analysis means of the in-vehicle sound includes obtaining specific sound features from the in-vehicle sound and comparing them. It can be understood that the sound feature types include energy features, time domain features, frequency domain features, music theory features, and perception features. The energy features include the root mean square energy of the in-vehicle sound in a preset time period. The time domain features include attack time, zero crossing rate, and autocorrelation. The attack time is the duration of the note energy of the in-vehicle sound in the rising stage. The zero crossing rate is the number of times that the signal of the in-vehicle sound passes through 0 in a unit of time. The autocorrelation is the similarity between the signal of the in-vehicle sound and the signal segment after time displacement. The frequency domain features include spectral centroid, MFCC (Mel-Frequency Cepstral Coefficients), spectral flatness, and spectral flux. The spectral centroid is the energy concentration point in the signal spectrum, which describes the brightness of the signal timbre. The brighter the signal energy is, the more concentrated it is in the high frequency part. The larger the value corresponding to the spectral centroid is, the more MFCC is the most commonly used feature in speech recognition, which takes into account the degree of human ear perception of different frequencies and can be classified as a perception feature. The spectral flatness is used to quantify the similarity between the signal and the noise. The larger the value is, the more likely the signal is noise. The spectral flux is used to quantify the degree of change between adjacent frames of the signal. The music theory features include fundamental frequency and detuning. The fundamental frequency represents the frequency of the pitch. The detuning represents the degree of deviation between the signal overtone frequency and the integer multiple of the fundamental frequency. The perception features include loudness and sharpness. The loudness represents the signal strength perceived by the human ear subjectively. The sharpness represents the size of the high frequency part energy. The larger the high frequency part energy is, the greater the sharpness perceived by the human ear is.

[0037] In this embodiment, the purpose of analyzing the in-vehicle sound is to obtain passenger information and passenger emotion of the in-vehicle passenger. Therefore, specific sound feature types are selected from the above-mentioned various sound feature types and applied to this embodiment to analyze the in-vehicle sound, obtain the actual sound features of the in-vehicle sound, and compare the actual sound features with the multiple preset sound features in the sound feature library. The sound feature library includes specific sound features or sound feature ranges of different passenger information and different passenger emotions. Through comparison, the corresponding passenger information and passenger emotion can be determined.

[0038] The passenger information of the in-vehicle passenger includes at least the number of in-vehicle passengers and personal information of each in-vehicle passenger, and can be obtained through voiceprint recognition. The personal information of the in-vehicle passenger can be age, gender, and other personal information of the in-vehicle passenger obtained by analyzing the current in-vehicle sound, or pre-stored passenger information obtained by comparing the current voiceprint with a preset voiceprint.

[0039] The passenger emotion of the in-vehicle passenger can be stable or unstable, or can be crying or not crying. Of course, the passenger emotion can be further divided into more detailed states, such as anxious, crying, noisy, and noisy, which can be adjusted according to actual conditions or the selection of the vehicle owner. Further, a mapping relationship between a plurality of numerical intervals of sound characteristics and passenger emotions can be pre-established and applied to analyze the in-vehicle sound to obtain the passenger emotion in the embodiment. Alternatively, the sound characteristics of the current in-vehicle sound can be directly compared with preset emotional sound characteristics, and the passenger emotion corresponding to the current sound characteristics is determined, that is, the process of analyzing the in-vehicle sound to obtain the analysis result includes: pre-processing the in-vehicle sound to obtain the sound characteristics of the in-vehicle sound; determining whether the sound characteristics match the preset emotional sound characteristics to obtain the passenger emotion corresponding to the sound characteristics. The current passenger emotion can be quickly determined by matching the sound characteristics, and the calculation speed is fast. The method of determining the passenger emotion can be set according to actual needs, which is not limited here.

[0040] On the basis of the known passenger information and passenger emotion of the in-vehicle passenger, once the passenger emotion meets the pacification condition, the pacification operation of steps S103-S104 is performed, the target interactive object is determined through the passenger information, and the corresponding replica sound is generated. The pacification audio including the replica sound is played to the in-vehicle passenger to pacify the passenger emotion.

[0041] The pacification condition includes that the passenger emotion is crying or the passenger emotion is unstable, and the in-vehicle passenger needs to be pacified. Further, a determination condition that the age of the in-vehicle passenger is not greater than a preset age can be added. When the age of the in-vehicle passenger is not greater than the preset age and the passenger emotion meets the pacification condition, the subsequent pacification operation is performed. The preset age can be set to 12 years old or 8 years old. At this time, the object of the pacification operation is clear, which is a child with anxious or crying emotion. When the pacification operation effectively relieves the anxious emotion of the in-vehicle passenger and stops the crying behavior of the in-vehicle passenger, especially when the driver travels alone with a child, the driver can drive the vehicle more attentively, and the safety of driving is improved.

[0042] In the step of determining the target interactive object by passenger information, the voice of the target interactive object can establish a safe and soothing psychological environment for the passengers in the vehicle, thereby effectively relieving the anxious emotions and stopping the crying behavior of the passengers in the vehicle, because the passengers in the vehicle are more intimate and trustworthy to the target interactive object. The target interactive object can be the current driver, a character or role obtained by analyzing the current sound in the vehicle and performing language recognition, a pre-stored interactive object, etc., which can be selected and set according to actual conditions, and is not limited here.

[0043] After determining the target interactive object, a replica sound identical to the sound of the target interactive object is generated by using the replica sound technology, and the replica sound is used to synthesize the soothing audio played to the passengers in the vehicle. The soothing audio includes, but is not limited to, one or more of dialogue sentences, songs, and stories. The priority of different forms of soothing audio can be set as the dialogue sentence being the highest, and the song and the story being the second. When the soothing effect of the dialogue sentence is not ideal, i.e., the passenger's emotions still meet the soothing conditions, the soothing audio of the song or the story is played. The priority of the soothing audio can also be pre-set according to the specific conditions of different passengers in the vehicle, and the automatic voice communication function of artificial intelligence can be used to convert the automatic voice communication content into the soothing audio using the replica sound. The specific content and form of the soothing audio are not limited here, and the replica sound of the target interactive object can be used to effectively soothe the passengers in the vehicle. On this basis, in order to further improve the soothing efficiency, the content of the soothing audio can be further personalized according to the personality and hobbies of the passengers in the vehicle, so as to achieve better soothing effect.

[0044] In step S104, the replica sound of the target interactive object is generated, and when the soothing audio including the replica sound is played to the passengers in the vehicle, a small amount of sound samples of the target interactive object is input into a sound synthesis model. The sound synthesis model processes, encodes, and synthesizes the sound samples to finally generate the soothing audio including the replica sound. The soothing audio emits corresponding soothing content with the replica sound, such as reading the text of dialogue sentences or stories with the replica sound, or singing songs with the replica sound. When the passengers in the vehicle hear the soothing audio, they will have the cognition that the target interactive object is interacting with them, thereby reducing the anxious and uneasy psychology, and gradually stabilizing the emotions, and at the same time, the passengers in the vehicle can also avoid car sickness.

[0045] According to the technical scheme provided in the embodiment of the present application, the passenger information and the passenger emotion of the passengers in the vehicle are obtained by analyzing the in-vehicle sound, when the passenger emotion meets the pacification condition, the target interactive object of the passengers is determined according to the passenger information, the replica sound of the target interactive object is generated, and the pacification audio including the replica sound is played. Since the pacification audio includes the replica sound of the target interactive object, the passengers in the vehicle are more intimate and trust the target interactive object, and are easy to stabilize the emotion after hearing the pacification audio including the replica sound, so that the pacification effect is more ideal, the child passengers are more likely to stop crying, the concerns of the driver are eliminated, the driving risks with the child passengers are eliminated, and the problem of the unsatisfactory pacification effect of the child passengers in the prior art is solved.

[0046] It can be understood that the implementation subject of the method of the embodiment includes a processor running a program to execute the method, the processor obtains the in-vehicle sound through a sound collector, and the processor also plays the pacification audio through a sound player. The main data form in the implementation process of the method is audio, and both the hardware device and the computing resource are significantly reduced compared with the prior art, so that the implementation cost of the method of the embodiment is lower, and the method has obvious market advantages.

[0047] The embodiment discloses a specific in-vehicle emotion pacification method, and compared with the previous embodiment, the technical scheme is further described and optimized.

[0048] In some specific embodiments, the process of analyzing the in-vehicle sound to obtain an analysis result includes: identifying the voiceprint of the in-vehicle sound to obtain the passenger information of the passengers in the vehicle. It can be understood that different passengers in the vehicle can be distinguished by voiceprint identification, and the passenger information of each passenger in the vehicle, such as age and gender, can be obtained. Voiceprint identification is an extremely effective technical means in sound analysis. Further, after distinguishing different passengers in the vehicle, it can be determined whether the passengers in the vehicle belong to passengers with pre-stored passenger information according to the voiceprint identification. If the current passengers in the vehicle have pre-stored passenger information, the passenger information can be obtained by analyzing the in-vehicle sound, and the pre-stored passenger information can be directly read. The pre-stored passenger information can also be updated according to the current passenger information obtained from the in-vehicle sound.

[0049] In some specific embodiments, the passenger information includes an age of the in-vehicle passenger; and correspondingly, when the passenger emotion satisfies the pacification condition, the process of determining the target interactive object of the in-vehicle passenger according to the passenger information includes: when the age of the in-vehicle passenger is not greater than a preset age and the passenger emotion satisfies the pacification condition, determining the target interactive object of the in-vehicle passenger according to the passenger information. It can be understood that, compared with other ages of in-vehicle passengers, when the in-vehicle passenger is a child and has no one to take care of, the driver is more likely to care about the child, resulting in inability to focus on driving, which exists a safety hazard. In this embodiment, the age upper limit of the in-vehicle passenger who needs to be pacified is set, and pacification support is provided when the in-vehicle passenger is a child, which more accurately improves the driver's concentration, and at the same time, the possibility of misjudging the passenger emotion to cause misoperation and the amount of operation data involved in this embodiment are greatly reduced due to the reduction in the number of in-vehicle passengers to be judged whether to satisfy the pacification condition.

[0050] In addition to the age judgment of the in-vehicle passenger, a to-be-pacified list can also be preset, the to-be-pacified list including specific in-vehicle passengers and specific passenger emotions, and when the in-vehicle sound analysis identifies that the in-vehicle passenger belongs to the to-be-pacified list, the judgment of whether the passenger emotion satisfies the pacification condition is performed, for example, the user can set the in-vehicle passenger in the to-be-pacified list as a passenger A with a poor mental state, the passenger emotion of the passenger A satisfying the pacification condition is a fretful emotion, and when the in-vehicle sound detection detects that the in-vehicle passenger is the passenger A and the passenger emotion is the fretful emotion, the corresponding pacification audio is played. The setting of the to-be-pacified list provides the user with a more private and personalized choice, further improving the comfort of the user when driving.

[0051] Specifically, referring to Figure 2 In this embodiment, the in-vehicle emotion pacification method includes:

[0052] S201: acquiring in-vehicle sound;

[0053] S202: analyzing the in-vehicle sound to obtain an analysis result;

[0054] S203: when the age of the in-vehicle passenger is not greater than a preset age and the passenger emotion satisfies the pacification condition, determining the target interactive object of the in-vehicle passenger according to the passenger information;

[0055] S204: generating a replica sound of the target interactive object, playing pacification audio including the replica sound to the in-vehicle passenger, and pacifying the in-vehicle passenger by using the pacification audio.

[0056] According to the technical scheme provided in the embodiment of the present application, the passenger information and the passenger emotion of the passengers in the vehicle are obtained by analyzing the sound in the vehicle, when the age of the passengers in the vehicle is not greater than the preset age and the passenger emotion satisfies the pacifying condition, the target interactive object of the passengers is determined according to the passenger information, the replica sound of the target interactive object is generated, and the pacifying audio including the replica sound is played. Since the pacifying audio includes the replica sound of the target interactive object, the passengers in the vehicle are more intimate and trust the target interactive object, and are easy to stabilize the emotion after hearing the pacifying audio including the replica sound, so that the pacifying effect is more ideal, the child passengers are more likely to stop crying, the concerns of the driver are eliminated, the driving risks with the child passengers are eliminated, and the problem that the pacifying effect on the child passengers in the prior art is not ideal is solved.

[0057] The embodiment discloses a specific emotion pacifying method in the vehicle, and relative to the previous embodiment, the technical scheme is further described and optimized.

[0058] In some specific embodiments, the passenger information includes personal information of the passengers in the vehicle and a relationship network corresponding to the personal information, and the relationship network includes interactive objects of the passengers in the vehicle and interaction frequencies of the interactive objects and the passengers in the vehicle. It can be understood that the relationship network provides a necessary and reliable selection range for determining the target interactive object of the passengers in the vehicle, and according to the relationship network, the target interactive object that is more effective for pacifying the emotion can be determined.

[0059] In some specific embodiments, the process of analyzing the sound in the vehicle to obtain an analysis result includes:

[0060] analyzing the sound in the vehicle to obtain personal information and a real-time relationship network of the passengers in the vehicle;

[0061] According to the personal information, a historical relationship network corresponding to the personal information in the historical database is searched;

[0062] combining the real-time relationship network and the historical relationship network to obtain the relationship network;

[0063] The historical database is updated by using the real-time relationship network.

[0064] It can be understood that the in-vehicle sound is analyzed to obtain the personal information of the in-vehicle passenger such as age and gender, and further through voiceprint recognition, it can be determined whether the in-vehicle passenger is pre-stored in the historical database. If yes, the pre-stored passenger information in the historical database is obtained, and the pre-stored passenger information includes pre-stored personal information and a historical relationship network; if no, the historical relationship network is determined to be empty. While analyzing the in-vehicle sound to obtain the personal information of the in-vehicle passenger, the voice content of the in-vehicle sound can also be analyzed to obtain the real-time relationship network of the in-vehicle passenger, for example, the interaction frequency between each in-vehicle passenger and the interaction frequency between the in-vehicle passenger and the driver are analyzed, the number of mentions of characters or roles and the language color in the voice content are analyzed, for example, the number of mentions of a certain animation character by the in-vehicle passenger and the degree of love, and then a real-time relationship network of the in-vehicle passenger including one or more interaction objects is constructed. It can be understood that in this embodiment, the relationship network is analyzed in real time, combined with the historical relationship network, and the historical database is updated, and the relationship network is continuously updated to ensure that the passenger information determined in this embodiment for the target interaction object is comprehensive and reliable and has pertinence.

[0065] In some specific embodiments, when the passenger emotion satisfies the pacification condition, the process of determining the target interaction object of the in-vehicle passenger according to the passenger information includes: when the passenger emotion satisfies the pacification condition, the target interaction object of the in-vehicle passenger is determined from all interaction objects according to the interaction frequency between each interaction object and the in-vehicle passenger. It can be understood that the higher the interaction frequency, the higher the intimacy of the in-vehicle passenger to the interaction object, and therefore the pacification effect is better. Further, the number of target interaction objects can also be set according to the interaction frequency between the in-vehicle passenger and the interaction object and the correlation degree between the interaction objects, the interaction frequency being determined by the number of conversations or the conversation time in each session, and the correlation degree being determined by the time duration and the time interval of each interaction object participating in each session, for example, according to the historical relationship network, the correlation degree between interaction objects A and B is high, and the number of times that interaction objects A and B appear and interact with the in-vehicle passenger at the same time is high. At this time, interaction objects A and B can be simultaneously determined as target interaction objects, and a replica sound of each target interaction object is generated accordingly, and a pacification audio including the two replica sounds is played, thereby simulating an interaction scenario in which interaction objects A and B appear together for the in-vehicle passenger, and further improving the safety of the in-vehicle passenger.

[0066] All the above optional technical solutions can be replaced and optimized according to actual needs, including providing options for users to provide multiple types of pre-stored information, options for artificial intelligence assisted interaction, historical data analysis and personalized adjustment, etc.

[0067] Specifically, referring to FIG. 1, Figure 3 The in-vehicle emotion pacification method in this embodiment includes:

[0068] S301: Obtain in-vehicle sound;

[0069] S302: analyzing the in-vehicle sound to obtain personal information and a real-time relationship network of the in-vehicle passenger;

[0070] S303: searching for a historical relationship network corresponding to the personal information in the historical database according to the personal information;

[0071] S304: merging the real-time relationship network and the historical relationship network to obtain a relationship network, and updating the historical database by using the real-time relationship network;

[0072] S305: when the passenger emotion satisfies the pacification condition, determining a target interactive object of the in-vehicle passenger from all interactive objects according to the interaction frequency of each interactive object with the in-vehicle passenger;

[0073] S306: generating a replica sound of the target interactive object, and playing pacification audio including the replica sound to the in-vehicle passenger to pacify the in-vehicle passenger by using the pacification audio.

[0074] When the target interactive object of the passenger is determined in step S305, an inquiry operation for the driver can be added, and the inquiry operation includes whether to perform the pacification operation and whether to select the target interactive object, that is, when the passenger emotion satisfies the pacification condition, a first inquiry request of whether to perform the pacification operation is sent; after receiving a first confirmation reply to the first inquiry request, when the first confirmation reply is yes, a second inquiry request of whether to select the driver as the target interactive object is sent; after receiving a second confirmation reply to the second inquiry request, when the second confirmation reply is yes, the target interactive object is determined as the driver, and when the second confirmation reply is no, the target interactive object of the in-vehicle passenger is determined from all interactive objects according to the interaction frequency of each interactive object with the in-vehicle passenger; when the first reply is no, a corresponding operation can be performed according to a preset selection, and the preset selection includes continuously performing the step of obtaining the in-vehicle sound and stopping the in-vehicle emotion pacification method of the embodiment. It can be understood that the inquiry operation for the driver in the above in-vehicle emotion pacification method is only an example, and the specific inquiry operation can be set, adjusted or cancelled at any stage of the embodiment according to actual needs and user needs, so that the flexibility of the embodiment method is improved.

[0075] According to the technical scheme provided in the embodiment of the present application, the passenger information and the passenger emotion of the passengers in the vehicle are obtained by analyzing the sound in the vehicle, when the age of the passengers in the vehicle is not greater than the preset age and the passenger emotion satisfies the pacification condition, the target interactive object of the passengers is determined according to the passenger information, the replica sound of the target interactive object is generated, and the pacification audio including the replica sound is played. Since the pacification audio includes the replica sound of the target interactive object, the passengers in the vehicle are more intimate and trust the target interactive object, and are easy to stabilize the emotion after hearing the pacification audio including the replica sound, so that the pacification effect is more ideal, the child passengers are more likely to stop crying, the concerns of the driver are eliminated, the driving risks with the child passengers are eliminated, and the problem that the pacification effect on the child passengers in the prior art is not ideal is solved.

[0076] All the optional technical solutions described above can be combined to form optional embodiments of the present application, which will not be described one by one here. It should be understood that the size of the serial number of each step in the above embodiments does not mean the order of execution, and the execution order of each process should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0077] The following is an apparatus embodiment of the present application, which can be used to execute the method embodiments of the present application. For details not disclosed in the apparatus embodiments of the present application, please refer to the method embodiments of the present application.

[0078] Figure 4 is a schematic diagram of an in-vehicle emotion pacification device provided by an embodiment of the present application. As shown in Figure 4 , the in-vehicle emotion pacification device includes:

[0079] The acquisition module 401 is configured to acquire the sound in the vehicle.

[0080] The analysis module 402 is configured to analyze the sound in the vehicle to obtain an analysis result, the analysis result including passenger information and a passenger emotion of the passengers in the vehicle.

[0081] The determination module 403 is configured to, when the passenger emotion satisfies a pacification condition, determine a target interactive object of the passengers in the vehicle according to the passenger information.

[0082] The playing module 404 is configured to generate a replica sound of the target interactive object, and play pacification audio including the replica sound to the passengers in the vehicle, so as to pacify the passengers in the vehicle by using the pacification audio.

[0083] According to the technical scheme provided in the embodiments of the present application, the passenger information and the passenger emotion of the passenger in the vehicle are obtained by analyzing the sound in the vehicle, when the passenger emotion meets the pacification condition, the target interactive object of the passenger is determined according to the passenger information, the replica sound of the target interactive object is generated, and the pacification audio including the replica sound is played. Since the pacification audio includes the replica sound of the target interactive object, the passenger in the vehicle is more intimate and trusting to the target interactive object, and is easy to stabilize the emotion after hearing the pacification audio including the replica sound, so that the pacification effect is more ideal, the child passenger is more likely to stop crying, the concern of the driver is eliminated, the driving risk with the child passenger is eliminated, and the problem that the pacification effect on the child passenger in the prior art is not ideal is solved.

[0084] In some specific embodiments, the process of analyzing the sound in the vehicle to obtain an analysis result includes:

[0085] The voiceprint of the sound in the vehicle is recognized to obtain the passenger information of the passenger in the vehicle.

[0086] In some specific embodiments, the passenger information includes the age of the passenger in the vehicle. Correspondingly, when the passenger emotion meets the pacification condition, the process of determining the target interactive object of the passenger in the vehicle according to the passenger information includes: when the age of the passenger in the vehicle is not greater than a preset age and the passenger emotion meets the pacification condition, the target interactive object of the passenger in the vehicle is determined according to the passenger information.

[0087] In some specific embodiments, the passenger information includes the personal information of the passenger in the vehicle and a relationship network corresponding to the personal information; the relationship network includes the interactive object of the passenger in the vehicle and the interaction frequency of each interactive object with the passenger in the vehicle.

[0088] In some specific embodiments, the process of analyzing the sound in the vehicle to obtain an analysis result includes:

[0089] The sound in the vehicle is analyzed to obtain the personal information and the real-time relationship network of the passenger in the vehicle;

[0090] According to the personal information, the historical relationship network corresponding to the personal information in the historical database is searched;

[0091] The real-time relationship network and the historical relationship network are merged to obtain the relationship network;

[0092] The historical database is updated by using the real-time relationship network.

[0093] In some specific embodiments, when the passenger emotion meets the pacification condition, the process of determining the target interactive object of the passenger in the vehicle according to the passenger information includes:

[0094] When the passenger emotion meets the pacification condition, the target interactive object of the passenger in the vehicle is determined from all the interactive objects according to the interaction frequency of each interactive object with the passenger in the vehicle.

[0095] In some specific embodiments, the process of analyzing the in-vehicle sound to obtain an analysis result comprises:

[0096] preprocessing the in-vehicle sound to obtain a sound feature of the in-vehicle sound;

[0097] determining whether the sound feature matches a preset emotional sound feature to obtain a passenger emotion corresponding to the sound feature.

[0098] Figure 5 is a schematic diagram of an electronic device 5 provided by an embodiment of the present application. As shown in Figure 5 the electronic device 5 of this embodiment includes a sound collector 501, a sound player 502, a memory 503, a processor 504, and a computer program 505 stored in the memory 503 and executable on the processor 504, wherein:

[0099] The sound collector 501 is configured to collect the in-vehicle sound and send it to the processor 504;

[0100] The processor 504 implements the steps in the above method embodiments when executing the computer program 505; or the processor 504 implements the functions of the modules / units in the above device embodiments when executing the computer program 505;

[0101] The sound player 502 is configured to execute the step of playing the soothing audio under the control of the processor 504.

[0102] Specifically, the electronic device 5 can be a desktop computer, a notebook computer, a palm computer, a cloud server, or the like. The electronic device 5 can include but is not limited to the processor 504 and the memory 503. Those skilled in the art can understand that Figure 5 is merely an example of the electronic device 5 and does not constitute a limitation on the electronic device 5, which can include more or fewer components or different components than those shown.

[0103] The processor 504 can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs) or other programmable logic devices, discrete gates or transistor logic components, discrete hardware components, etc.

[0104] The memory 503 can be an internal storage unit of the electronic device 5, for example, a hard disk or a memory of the electronic device 5. The memory 503 can also be an external storage device of the electronic device 5, for example, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 5. The memory 503 can also include both the internal storage unit and the external storage device of the electronic device 5. The memory 503 is used to store computer programs and other programs and data required by the electronic device.

[0105] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above-mentioned division of each functional unit and module is exemplified, and in actual application, the above-mentioned functions can be completed by different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0106] The integrated module / unit, if realized in the form of a software functional unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on this understanding, all or part of the processes in the above-mentioned embodiment methods can also be completed by a computer program instructing related hardware, and the computer program can be stored in a computer readable storage medium. The computer program can be executed by a processor to implement the steps of each method embodiment described above. The computer program can include computer program code, which can be in the form of source code, object code, executable files or some intermediate forms, etc.

[0107] The embodiment of the present application also provides a vehicle comprising the electronic device as in the above-mentioned embodiments.

[0108] For specific content of the electronic device, refer to the detailed description of the electronic device in the above embodiments, which will not be repeated here.

[0109] The electronic device and the vehicle in the embodiment both have the same technical effects as the in-cabin emotional pacification method in the above-mentioned embodiments, which will not be repeated here.

[0110] The above examples are only used to illustrate the technical solutions of the present application, but not limit the same; although the present application has been described in detail with reference to the foregoing examples, those skilled in the art should understand that the technical solutions recorded in the foregoing examples can be modified, or some technical features can be replaced by equivalent ones; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A method for calming emotions inside a car, characterized in that, include: By analyzing the sounds inside the vehicle, passenger information and passenger emotions can be obtained. The passenger information includes the personal information of the passengers and the relationship network corresponding to the personal information. Based on the personal information, the historical relationship network corresponding to the personal information is searched in the historical database. If the historical relationship network of the passenger in the vehicle is empty, the number of times the person or role is mentioned and the language color in the voice content of the in-vehicle sound are analyzed to construct the real-time relationship network of the passenger in the vehicle. The real-time relationship network includes one or more interactive objects, and the relationship network of the personal information is the real-time relationship network. If a historical relationship network corresponding to the passengers in the vehicle exists in the historical database, then the historical relationship network is obtained; By analyzing the sounds inside the vehicle, a real-time relationship network of the passengers inside the vehicle can be obtained; The real-time relationship network and the historical relationship network are merged to obtain the relationship network; The historical database is updated using the real-time relationship network; When the passenger's emotions meet the conditions for calming down, the target interaction object of the passenger in the vehicle is determined according to the relationship network; A replica of the target interactive object's voice is generated, and a soothing audio containing the replica voice is played to the passengers in the vehicle to soothe them.

2. The method according to claim 1, characterized in that, Analyzing the sounds inside the vehicle yields passenger information, including: By identifying the voiceprint of the sounds inside the vehicle, passenger information of the passengers inside the vehicle can be obtained.

3. The method according to claim 1, characterized in that, The passenger information also includes the age of the passengers in the vehicle; Accordingly, when the passenger's emotions meet the conditions for calming them down, the process of determining the target interaction object for the passenger based on the passenger's age includes: If the age of the passenger in the vehicle is not greater than a preset age and the passenger's emotions meet the conditions for calming down, the target interaction object of the passenger in the vehicle is determined based on the passenger information.

4. The method according to claim 1, characterized in that, The relationship network includes the interaction objects of the passengers in the vehicle and the interaction frequency between each interaction object and the passengers in the vehicle.

5. The method according to claim 4, characterized in that, When the passenger's emotions meet the conditions for calming them down, the process of determining the target interaction object for the passenger in the vehicle based on the relationship network includes: When the passenger's emotions meet the conditions for calming down, the target interaction object for the passenger in the vehicle is determined from all the interaction objects based on the interaction frequency between each interaction object and the passenger in the vehicle.

6. The method according to any one of claims 1 to 5, characterized in that, Analyzing the in-vehicle sounds yields passenger information and passenger emotions, including: The in-vehicle sound is preprocessed to obtain the sound characteristics of the in-vehicle sound; Determine whether the voice feature matches a preset emotional voice feature to obtain the passenger's emotion corresponding to the voice feature.

7. An in-vehicle emotional calming device, characterized in that, include: The analysis module is used to analyze the sounds inside the vehicle to obtain passenger information and passenger emotions. The passenger information includes the personal information of the passengers inside the vehicle and the relationship network corresponding to the personal information. The construction module is used to search the historical relationship network corresponding to the personal information in the historical database based on the personal information. If the historical relationship network of the passenger in the vehicle is empty, the module analyzes the number of times the person or role is mentioned and the language color in the voice content of the in-vehicle sound to construct the real-time relationship network of the passenger in the vehicle. The real-time relationship network includes one or more interactive objects, and the relationship network of the personal information is the real-time relationship network. If a historical relationship network corresponding to the passengers in the vehicle exists in the historical database, then the historical relationship network is obtained; By analyzing the sounds inside the vehicle, a real-time relationship network of the passengers inside the vehicle can be obtained; The real-time relationship network and the historical relationship network are merged to obtain the relationship network; The historical database is updated using the real-time relationship network; The determination module is used to determine the target interaction object of the passenger in the vehicle based on the relationship network when the passenger's emotions meet the calming conditions. The playback module is used to generate a replica of the target interactive object's sound and play a soothing audio message including the replica sound to the passengers in the vehicle, so as to soothe the passengers in the vehicle using the soothing audio message.

8. An electronic device, characterized in that, It includes a sound collector, a sound player, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: The sound collector is used to collect the sound inside the vehicle and send it to the processor; When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1 to 6; The sound player is used to perform the step of playing soothing audio under the control of the processor.

9. A vehicle, characterized in that, Including the electronic device as described in claim 8.

Images