CN115447588A - Vehicle control method and device, vehicle and storage medium - Google Patents
Vehicle control method and device, vehicle and storage medium Download PDFInfo
- Publication number
- CN115447588A CN115447588A CN202211086123.2A CN202211086123A CN115447588A CN 115447588 A CN115447588 A CN 115447588A CN 202211086123 A CN202211086123 A CN 202211086123A CN 115447588 A CN115447588 A CN 115447588A
- Authority
- CN
- China
- Prior art keywords
- relationship
- user
- voiceprint feature
- target user
- voiceprint
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 63
- 230000007613 environmental effect Effects 0.000 claims description 33
- 238000004590 computer program Methods 0.000 claims description 9
- 238000013507 mapping Methods 0.000 description 16
- 230000008569 process Effects 0.000 description 11
- 230000006870 function Effects 0.000 description 8
- 238000000605 extraction Methods 0.000 description 7
- 238000004891 communication Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 230000001755 vocal effect Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 239000012634 fragment Substances 0.000 description 1
- 238000009432 framing Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/08—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to drivers or passengers
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R16/00—Electric or fluid circuits specially adapted for vehicles and not otherwise provided for; Arrangement of elements of electric or fluid circuits specially adapted for vehicles and not otherwise provided for
- B60R16/02—Electric or fluid circuits specially adapted for vehicles and not otherwise provided for; Arrangement of elements of electric or fluid circuits specially adapted for vehicles and not otherwise provided for electric constitutive elements
- B60R16/023—Electric or fluid circuits specially adapted for vehicles and not otherwise provided for; Arrangement of elements of electric or fluid circuits specially adapted for vehicles and not otherwise provided for electric constitutive elements for transmission of signals between vehicle parts or subsystems
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R16/00—Electric or fluid circuits specially adapted for vehicles and not otherwise provided for; Arrangement of elements of electric or fluid circuits specially adapted for vehicles and not otherwise provided for
- B60R16/02—Electric or fluid circuits specially adapted for vehicles and not otherwise provided for; Arrangement of elements of electric or fluid circuits specially adapted for vehicles and not otherwise provided for electric constitutive elements
- B60R16/037—Electric or fluid circuits specially adapted for vehicles and not otherwise provided for; Arrangement of elements of electric or fluid circuits specially adapted for vehicles and not otherwise provided for electric constitutive elements for occupant comfort, e.g. for automatic adjustment of appliances according to personal settings, e.g. seats, mirrors, steering wheel
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W50/08—Interaction between the driver and the control system
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The application discloses a control method and device of a vehicle, the vehicle and a storage medium. The method comprises the following steps: acquiring an audio clip of a target user; determining voiceprint characteristics of the target user based on the audio clip; determining the identity relationship between the target user and the designated person based on a preset relationship network; and controlling the vehicle based on the identity relationship between the target user and the designated person. According to the vehicle, the environment equipment in the vehicle can be correspondingly set according to the identity relation between the target user and the designated person, the situation that the target user is repeatedly set is avoided, the environment equipment is more conveniently and efficiently controlled, and the riding experience of the target user is improved.
Description
Technical Field
The present application relates to the field of intelligent transportation technologies, and in particular, to a method and an apparatus for controlling a vehicle, and a storage medium.
Background
With the development of technology, in order to improve the riding experience of passengers, some vehicles (e.g., cars) are equipped with multimedia video and audio devices (e.g., video players, audio players, etc.) for the passengers to use, and the passengers can select to play their favorite video and audio contents as required.
However, when using the multimedia audio-visual device, the passenger often needs to spend a certain time to search the audio-visual content of the self-mind apparatus, and if the passenger takes the vehicle for many times, the passenger needs to repeat the searching step every time, so that the operation is more complicated, and the efficiency is low.
Disclosure of Invention
The embodiment of the application provides a control method and device of a vehicle, the vehicle and a storage medium.
In a first aspect, some embodiments of the present application provide a control method of a vehicle, the method including: acquiring an audio clip of a target user; determining voiceprint characteristics of the target user based on the audio clip; determining the identity relationship between a target user and an appointed figure based on a relationship network, wherein the relationship network comprises at least one voiceprint feature pair and a prediction relationship corresponding to the voiceprint feature pair, the voiceprint feature pair comprises the voiceprint feature of the appointed figure and the voiceprint feature of the user, and the prediction relationship refers to the identity relationship between the user and the appointed figure obtained through prediction; and controlling the vehicle based on the identity relationship between the target user and the designated person.
In a second aspect, some embodiments of the present application provide a control apparatus for a vehicle, the apparatus including: the device comprises an acquisition module, a first determination module, a second determination module and a control module. The acquisition module is used for acquiring the audio clip of the target user. The first determination module is configured to determine a voiceprint feature of the target user based on the audio clip. The second determining module is used for determining the identity relationship between the target user and the designated person based on a relationship network, wherein the relationship network comprises at least one voiceprint feature pair and a prediction relationship corresponding to the voiceprint feature pair, the voiceprint feature pair comprises the voiceprint feature of the designated person and the voiceprint feature of the user, and the prediction relationship refers to the predicted identity relationship between the user and the designated person. The control module is used for controlling the vehicle based on the identity relationship between the target user and the designated person.
In a third aspect, some embodiments of the present application further provide a vehicle comprising: one or more processors, memory, an audio capture device, and one or more applications. Wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, the one or more programs configured to perform the sleep mode activation method described above.
In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, where computer program instructions are stored in the computer-readable storage medium. Wherein the computer program instructions may be invoked by a processor to perform the above-described control method for a vehicle.
In a fifth aspect, the present application further provides a computer program product, which, when executed, implements the control method for the vehicle described above.
The application provides a control method and device of a vehicle, the vehicle and a storage medium. After the identity relationship between the target user and the designated person is determined through the voiceprint features of the target user and the relationship network, the vehicle is correspondingly controlled based on the determined identity relationship. For example, where the identity relationship indicates an affinity between two persons (e.g., a couple relationship, a parent-child relationship), the environmental device within the vehicle may be set to the specified setting of the target user (e.g., play a historical play video of the target user, push a song based on the historical song list of the target user, etc.). Therefore, the vehicle in the application can carry out corresponding setting on the environment equipment in the vehicle according to the identity relation between the target user and the designated person, the situation that the target user is repeatedly set is avoided, the control of the environment equipment is more convenient and efficient, and the riding experience of the target user is improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the description below are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 shows an application environment schematic diagram of a control method of a vehicle according to an embodiment of the present application.
Fig. 2 shows a flow chart of a control method of a vehicle according to a first embodiment of the present application.
Fig. 3 is a flowchart illustrating a control method for a vehicle according to a second embodiment of the present application.
Fig. 4 shows a flowchart of a method for determining a relationship network according to an embodiment of the present application.
Fig. 5 shows a block diagram of a control device of a vehicle according to an embodiment of the present application.
FIG. 6 shows a block diagram of a vehicle provided by an embodiment of the present application.
FIG. 7 illustrates a block diagram of modules of a computer-readable storage medium provided by embodiments of the present application.
Detailed Description
Reference will now be made in detail to the embodiments of the present application, examples of which are illustrated in the accompanying drawings, wherein like reference numerals refer to the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary only for explaining the present application and are not to be construed as limiting the present application.
In order to make the technical solutions of the present application better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. It is to be understood that the embodiments described are only a few embodiments of the present application and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The application provides a control method and device of a vehicle, the vehicle and a storage medium. After the identity relationship between the target user and the designated person is determined through the voiceprint features of the target user and the relationship network, the vehicle is correspondingly controlled based on the determined identity relationship. For example, where the identity relationship indicates an affinity between two persons (e.g., a couple relationship, a parent-child relationship), the environmental device within the vehicle may be set to the specified setting of the target user (e.g., play a historical play video of the target user, push a song based on the historical song list of the target user, etc.). Therefore, the vehicle in the application can carry out corresponding setting on the environment equipment in the vehicle according to the identity relation between the target user and the designated person, the situation that the target user is repeatedly set is avoided, the control of the environment equipment is more convenient and efficient, and the riding experience of the target user is improved.
To facilitate the detailed description of the scheme of the present application, the following first introduces a relationship network in the embodiment of the present application with reference to table-1.
The relationship network in the embodiment of the application comprises at least one voiceprint feature pair and a prediction relationship corresponding to the voiceprint feature pair, the voiceprint feature pair comprises the voiceprint feature of the specified person and the voiceprint feature of the user, and the prediction relationship refers to the identity relationship between the user and the specified person obtained through prediction. Specifically, the predicted relationship may be one or more, and the identity relationship between the user and the designated person may be a couple relationship, a father-son relationship, a mother-son relationship, a stranger relationship, an acquaintance relationship, or the like. Referring to table-1, table-1 schematically illustrates a relationship network provided herein in which there is at least one predicted relationship for a voiceprint feature pair.
TABLE-1
Taking the designated person and user as user a and user B, respectively, as an example, the corresponding voiceprint feature pairs include the voiceprint feature of user a and the voiceprint feature of user B, and in table-1, the corresponding predicted relationships of the voiceprint feature pairs are the couple relationship and the father-woman relationship.
In the relationship network shown in table-1, each prediction relationship also corresponds to a determination number, which is a default parameter in the relationship network and represents the historical occurrence number of the voiceprint feature pair corresponding to the prediction relationship. Illustratively, the console identifies the conversation audio of the user a and the user B, and if the predicted relationship between the user a and the user B is determined to be a couple relationship, the determined number of times of the voiceprint feature for the corresponding couple relationship is recorded as one. If the conversation audio of the user A and the user B is obtained for a plurality of times and the relation is determined to be a couple relation, the determined times of the couple relation are updated in an accumulated mode, namely, the determined times of the couple relation are increased by one in an accumulated mode every time the couple relation is determined to be the couple relation. Specifically, the method for determining and updating the relationship network is described in the following embodiments.
For the convenience of describing the scheme of the present application in detail, the following description will first refer to the application environment in the embodiments of the present application with reference to the accompanying drawings. Referring to fig. 1, a control method of a vehicle according to an embodiment of the present application is applied to a vehicle 10, where the vehicle 10 may be a car. Specifically, the vehicle 10 includes a center console 100, an audio acquisition device 200, and at least one environmental apparatus 300.
The console 100 is a control center of the vehicle 10, and is configured to receive and process signals and data generated by the vehicle 10 during driving, and generate corresponding control signals to control devices in the vehicle 10 to operate. In the embodiment of the present application, the console 100 is electrically connected to the audio acquiring device 200, and is configured to receive the audio clip acquired by the audio acquiring device 200. Specifically, the center console 100 has a voiceprint feature extraction function, and is capable of extracting a voiceprint feature of the user from the received audio clip.
In this embodiment, the center console 100 further stores a relationship network for describing an identity relationship between the user and the designated person, and the center console 100 can determine the identity relationship between the user and the designated person through the relationship network under the condition that the voiceprint feature is extracted, so as to control the at least one environmental device 300. In other embodiments, the relationship network may also be stored in a server 20 in communication with the vehicle 10, the console 100 sends the voiceprint feature of the user to the server 20 when the voiceprint feature is obtained, and the server 20 further determines the identity relationship between the user and the designated person and then sends the identity relationship to the console 100. The server 20 may be one server or a server cluster including a plurality of servers.
In some embodiments, the console 100 also has relational network determination and update functionality. Specifically, the center console 100 determines and updates the relationship network by acquiring the voiceprint feature of the specified person, the voiceprint feature of the user, and the identity relationship between the specified person and the user, in a case where the dialogue audio between the specified person and the user is acquired. In other embodiments, the determination and updating process of the relationship network may be performed in the server 20, which is not specifically limited in this application.
The audio capturing device 200 is a device for capturing audio, and is electrically connected to the console 100. Specifically, the audio acquisition device 200 may be a microphone, such as a moving coil microphone, a condenser microphone, or the like.
The environmental device 300 is disposed inside the vehicle 10 and electrically connected to the center console 100. Specifically, the environment device 300 may be an air conditioner, a lighting device, a multimedia audio/video device (e.g., a stereo, a video player), and so on. The console 100 is further configured to control the environment device 300 according to the determined identity relationship. For example, in the case where the identity relationship indicates an affinity (e.g., a couple relationship, a parent-child relationship) between the user and a specified person, the multimedia audio/video device may be set to the specified setting of the user (e.g., playing a history playing video of the user, performing a song push based on a history song list, etc.).
Referring to fig. 2, fig. 2 schematically illustrates a control method of a vehicle according to a first embodiment of the present application. The method is applied to the vehicle in fig. 1. Specifically, the method may include the following steps S210 to S240.
And step S210, acquiring the audio clip of the target user.
In some embodiments, the console acquires the audio clip of the target user through the audio acquiring device every preset time period under the condition that the console is determined to be currently in the working state. The target user in the embodiment of the present application refers to a person other than the designated person, and illustratively, the designated person may be a driver and the target user may be a passenger. The audio duration and the preset duration of the audio clip are default parameters in the console, which is not specifically limited in this application.
In other embodiments, a voice assistant is provided in the center console, wherein the voice assistant refers to an artificial intelligence based voice interaction program. And after the voice assistant receives the awakening words, acquiring the audio clips of the target users through the audio acquisition device. Specifically, the audio piece may be a voice control instruction for controlling an environmental apparatus in the vehicle, for example, the voice control instruction is "turn on the air conditioner", "turn on the back box", or the like. In other possible embodiments, when the voice assistant receives the wakeup word, the console directly takes the audio corresponding to the wakeup word as the audio clip of the target user.
In still other embodiments, the console establishes a communication connection with consoles in other vehicles, receives voice information sent by other consoles, and uses the voice information as an audio clip of a target user. At this time, the target user may be a driver or a passenger in another vehicle. Illustratively, a plurality of vehicles exist in a certain household, and the plurality of vehicles share a relationship network. Specifically, the plurality of vehicles include a first vehicle and a second vehicle, and in the case where a first driver in the first vehicle sends voice information to a second driver in the second vehicle, a center console in the second vehicle determines the voice information as an audio clip of a target user. In addition, the center console in the first vehicle may also receive voice information sent by a second driver in a second vehicle, and use it as an audio clip of the target user.
Step S220, determining the voiceprint characteristics of the target user based on the audio clip.
The voiceprint characteristics include the wavelength, frequency, intensity, tempo, etc. characteristics of the sound. Because the vocal organs of each person have different sizes, shapes and functions, the corresponding vocal print characteristics of each person are different. By identifying and matching the voiceprint features, the identification of the target person can be realized.
In the embodiment of the application, the voiceprint feature extraction algorithm is stored in the center console, and the voiceprint feature of the target user in the audio clip can be determined by the center console through the voiceprint feature extraction algorithm. Specifically, the voiceprint feature extraction algorithm may be a voiceprint extraction algorithm based on Mel Frequency Cepstral Coefficients (MFCC), a voiceprint extraction algorithm based on Linear Prediction Coefficients (LPC), a voiceprint extraction algorithm based on Linear Prediction Cepstral Coefficients (LPCC), and the like, and the present application is not limited in particular.
In some embodiments, in order to reduce the influence of noise interference in the audio segment on the voiceprint features, a step of preprocessing the audio segment is further included before extracting the voiceprint features. The preprocessing step includes, but is not limited to, a filtering operation, an a/D conversion operation, a pre-emphasis operation, a framing operation, an endpoint detection operation, and the like, which is not limited in this application.
Step S230, determining an identity relationship between the target user and the designated person based on a preset relationship network.
In the embodiment of the application, the center console can determine the identity relationship between the target user and the designated person by searching the relationship network based on the voiceprint characteristics of the target user. The relationship network may be pre-stored in a memory in the console or stored in a server in communication with the vehicle, and specifically, the determination process of the relationship network is described in the following embodiments. Referring to table-2, table-2 schematically illustrates yet another relationship network provided herein.
TABLE-2
Voiceprint feature pair | Predicting relationships |
(voiceprint feature of user A, voiceprint feature of user B) | The relationship between a couple and a sex |
(voiceprint feature for user A, voiceprint feature for user C) | Parent-child relationship |
(voiceprint feature of user A, voiceprint feature of user D) | Relationship between strangers |
(voiceprint feature of user B, voiceprint feature of user C) | Mother-child relationship |
(voiceprint feature of user B, voiceprint feature of user D) | Acquaintance relationships |
… | … |
It should be noted that, in the embodiment of the present application, before determining the identity relationship between the target user and the designated person, the voiceprint feature of the designated person needs to be determined. As an embodiment, the voiceprint feature of the specified person may be a default voiceprint feature, for example, the center console marks the user a as the specified person, that is, the voiceprint feature of the user a is the voiceprint feature of the specified person, and specifically, the voiceprint feature of the specified person in this application may be stored in the center console in advance.
As another implementation, the center console identifies the designated person and determines the voiceprint characteristics of the designated person. Taking an appointed person as an example, when the center console is in a working state, the center console acquires a face image of the driver through a built-in image acquisition device (for example, a built-in camera) of the vehicle, and then determines the driver corresponding to the face image based on a preset face recognition algorithm, and further determines the voiceprint feature of the driver as the voiceprint feature of the appointed person. Illustratively, in the case that the center console recognizes that the driver is the user a through a face recognition algorithm, the voiceprint feature of the user a is determined as the voiceprint feature of the designated person.
Specifically, the center console may store a voiceprint feature mapping table in advance, where the voiceprint feature mapping table represents a one-to-one correspondence relationship between different users and voiceprint features, and the center console may determine the voiceprint feature of the user a based on the voiceprint feature mapping table and determine the voiceprint feature as the voiceprint feature of the designated person when recognizing that the driver is the user a. In addition, the face recognition algorithm may be an artificial neural network-based recognition algorithm, a feature face model (Fisherfaces) -based face recognition algorithm, and the like, which is not limited in the present application. In the embodiment of the application, the center console identifies the designated person, and can adjust the voiceprint characteristics of the designated person under the condition that the designated person (for example, a driver) changes, so that the accuracy of the identity relationship determination between the subsequent target user and the designated person is ensured.
For example, taking the designated person as user a and the target user as user B as an example, the identity relationship between the target user and the designated person can be determined to be a couple relationship through the above table-2. If the designated person is changed to the user C, taking the target user as the user B as an example, the identity relationship between the target user and the designated person can be determined to be a parent-child relationship through the table-2.
In some embodiments, there is no voiceprint feature pair for a given person (e.g., user A) and a target user (e.g., user X) in the relationship network, in which case the console determines the identity relationship between the target user and the given person as a stranger relationship. In the subsequent process, the center console updates the relationship network under the condition that the dialog audio including the user a and the user X is obtained, and specifically, a specific implementation manner of updating the relationship network is described in the following embodiments.
And step S240. And controlling the vehicle based on the identity relationship between the target user and the designated person.
In the embodiment of the present application, the console stores corresponding default parameters for each identity relationship. Specifically, the default parameters in the embodiment of the present application include setting parameters of at least one environmental device in the vehicle, or/and control authority of at least one environmental device in the vehicle. And under the condition that the identity relationship between the target user and the designated person is determined, the console reads the default parameters and controls at least one environmental device in the vehicle. The default parameters may be set by a user through a touch panel of the console, or may be obtained by analyzing the console based on multiple historical usage data of the user, which is not specifically limited in the embodiment of the present application. Specifically, specific embodiments of the console controlling the vehicle based on default parameters are described in the following examples.
The embodiment of the application provides a control method of a vehicle, and particularly the vehicle can be correspondingly controlled according to the identity relation between a target user and an appointed person. For example, where the identity relationship indicates an affinity between two persons (e.g., a couple relationship, a parent-child relationship), the environmental device within the vehicle may be set to the specified setting of the target user (e.g., play a historical play video of the target user, push a song based on the historical song list of the target user, etc.). Therefore, the vehicle in the application can carry out corresponding setting on the environment equipment according to the identity relation between the target user and the designated person, the situation that the target user is repeatedly set is avoided, the control of the environment equipment is more convenient and efficient, and the riding experience of the target user is improved.
Referring to fig. 3, fig. 3 schematically illustrates a control method of a vehicle according to a second embodiment of the present application. The method is applied to the vehicle in fig. 1. In the embodiment of the application, the voiceprint feature pairs in the relationship network have at least one prediction relationship, and each prediction relationship corresponds to a determined number of times. Specifically, the method may include the following steps S310 to S360.
Step S310, the audio clip of the target user is obtained.
Step S320, determining the voiceprint feature of the target user based on the audio clip.
The detailed implementation of steps S310 to S320 may refer to the detailed descriptions in steps S210 and S220, and are not described again.
And step S330, determining a target voiceprint feature pair based on a preset relationship network.
Wherein the target voiceprint feature pair comprises a voiceprint feature of the specified person and a voiceprint feature of the target user. Specifically, the method for determining the voiceprint feature of the designated person may refer to the detailed description in step S230, and is not repeated here.
In the embodiment of the application, the console further stores a voiceprint feature matching algorithm, and the console matches the voiceprint features of the target user with the voiceprint features of the users except for the designated person in the relational network through the voiceprint feature matching algorithm, so that the voiceprint features identical to the voiceprint features of the target user are determined from the voiceprint features of the users, and a voiceprint feature pair comprising the voiceprint features and the voiceprint features of the designated person is determined as a target voiceprint feature pair. Specifically, the voiceprint feature matching algorithm may be a Hidden Markov Model (HMM) based feature matching algorithm, a Dynamic Time Warping (DTW) based feature matching algorithm, and the like, and is not particularly limited in this application.
Step S340, based on the corresponding prediction relation of the target voiceprint characteristics and the determination times of the prediction relation, determining the identity relation between the target user corresponding to the voiceprint characteristics and the designated person.
In some embodiments, there is only one predicted relationship for the target voiceprint feature pair. The console may directly determine the predicted relationship as an identity relationship between the target user and the designated persona. Taking the predicted relationship as a couple relationship as an example, the console directly determines the couple relationship as the identity relationship between the target user and the designated person.
In another embodiment, when the number of times of determining the predicted relationship is greater than a preset threshold, the center console determines the predicted relationship as the identity relationship between the target user and the designated person. The preset threshold is a default parameter in the center console, and can be dynamically adjusted based on the actual use condition of the relational network. Specifically, the preset threshold may be a natural number greater than 2, and taking the preset threshold as 3 and the number of times of determining the couple relationship as 5 as an example, at this time, the console determines the identity relationship between the target user and the designated person as the couple relationship. Otherwise, when the number of times of determining the predicted relationship is less than or equal to the preset threshold, the console cannot determine the identity relationship between the target user and the designated person, and at this time, the console does not perform the subsequent steps. In the embodiment of the application, the preset threshold is set in the console, so that the situation that the judgment of the predicted relationship is wrong when the determination times of the predicted relationship is too small (for example, the determination times is 1) is avoided. For example, when the couple relation is determined only once, in order to avoid the couple relation being determined incorrectly, the console does not perform the subsequent steps, that is, the console does not control the vehicle.
In other embodiments, where there are multiple predicted relationships for the target voiceprint feature pair, step S340 includes step S3410.
In step S3410, if the maximum value among the determination times of the plurality of predicted relationships is greater than the predetermined threshold value, the predicted relationship corresponding to the maximum value is determined as the identity relationship between the target user and the designated person.
The specified threshold is a default parameter in the center console, and can also be dynamically adjusted based on the actual use condition of the relational network. Specifically, the specified threshold may be a natural number greater than 2, taking the preset threshold as 6, and taking as an example that the target voiceprint feature pair includes the voiceprint feature of the user a and the voiceprint feature of the user B, please refer to table-1 above, where the corresponding predicted relationship of the target voiceprint feature pair includes a couple relationship and a parent-female relationship, where the number of determinations of the couple relationship is 12, and the number of determinations of the parent-female relationship is 1, and at this time, the console determines the identity relationship between the target user and the specified person as the couple relationship (i.e., the predicted relationship corresponding to the maximum number of determinations of 12). Specifically, the maximum value among the determination times of the plurality of predicted relationships may be determined by a ranking algorithm (e.g., a selection ranking method, a bubble ranking method, etc.), and the present application is not particularly limited.
Otherwise, if the maximum value of the determination times of the plurality of predicted relationships is less than or equal to the specified threshold, the console cannot determine the identity relationship between the target user and the specified person, and at this time, the console does not perform the subsequent steps. Taking the preset threshold value of 6 and the target voiceprint feature pair including the voiceprint feature of the user a and the voiceprint feature of the user C as an example, as can be seen from the table-1, the maximum value of the determination times is 2, and the central console cannot determine the identity relationship between the target user and the designated person. In the embodiment of the application, the center console sets the designated threshold value, so that the situation that the judgment of the predicted relationship is wrong under the condition that the determination times of the predicted relationship is too small is avoided. For example, when the number of times of determining the parent-child relationship is only two, in order to avoid the occurrence of a case where the parent-child relationship is determined incorrectly, the center console does not perform the subsequent steps, that is, the center console does not control the vehicle.
And step S350, acquiring default parameters corresponding to the target user based on the identity relationship between the target user and the designated person.
The default parameters comprise setting parameters of at least one environmental device in the vehicle or/and control authority of at least one environmental device in the vehicle.
In some embodiments, the default parameters include set parameters for at least one environmental device in the vehicle. The setting parameter may be an operating parameter of the environment device, or may be a usage record of the environment device.
As an implementation manner, a working parameter mapping table may be stored in the console, where the working parameter mapping table represents a one-to-one correspondence relationship between different identity relationships and working parameters. Exemplarily, taking an environmental device as an air conditioner, the operating parameter may be an operating temperature of the air conditioner, an air outlet speed, and the like; taking the environment device as the lighting device as an example, the operating parameter may be the lighting brightness of the lighting device, and the like. And under the condition that the identity relationship is determined, the center console determines the working parameters of the environmental equipment corresponding to the target user based on the working parameter mapping table.
As an embodiment, a usage record mapping table may be stored in the center console, where the usage record mapping table represents a one-to-one correspondence between different identity relationships and usage records. Illustratively, taking the environment device as a multimedia audiovisual device as an example, the usage record may be a history play record of the user, such as a history played video, a song, and so on. And under the condition that the identity relationship is determined, the center console determines the use record of the environment equipment corresponding to the target user based on the use record mapping table.
In other embodiments, the default parameter includes a control authority of at least one environmental device in the vehicle. As an implementation manner, a control authority mapping table may be stored in the center console, where the control authority mapping table represents a one-to-one correspondence relationship between different identity relationships and control authorities. For example, the identity relationship of the relationship between the relatives, such as the relationship between the couples and parents, and the like, is high; otherwise, the corresponding control authority is low for the identity relationship of non-relatives such as friend relationship, acquaintance relationship, stranger relationship, etc. For example, please refer to table-3, wherein table-3 schematically shows the control authority mapping table provided in the present application.
TABLE-3
Identity relationships | Controlling authority |
Relationships between couples and husband | High (a) |
Parent-child relationship | Height of |
Relationship between strangers | Is low in |
Friendship | Is low in |
Acquaintance relationships | Is low in |
… | … |
And under the condition that the identity relationship is determined by the center console, determining the control authority of the environmental equipment corresponding to the target user based on the control authority mapping table. Illustratively, if the identity relationship is a couple relationship, based on the table-3, the console determines that the control authority of the environmental device corresponding to the target user is high.
And step S360, controlling the vehicle based on the default parameters.
In some embodiments, the default parameters include operating parameters of the environmental devices, and the console controls the environmental devices in the vehicle to operate based on the operating parameters of the environmental devices corresponding to the target user. For example, the operating temperature of the air conditioner is set to a temperature preset by a target user.
In other embodiments, the default parameters include usage records of the environmental devices, and the center console controls the environmental devices in the vehicle to work based on the usage records of the environmental devices corresponding to the target users. For example, the console controls the multimedia video equipment to continue playing the same video or song according to the historical playing record of the target user; or determining the favorite type of the target user according to the historical playing record of the target user, and pushing the video or the song matched with the favorite type, so that the environmental equipment can be more intelligent and humanized when in work.
In still other embodiments, the default parameters include control authority of the environmental device, and the center console controls the environmental device in the vehicle to work based on the control authority of the environmental device corresponding to the target user.
In one embodiment, the center console responds to the voice control command of the target user when determining that the control authority of the target user is high, that is, controls the environment device to work based on the voice control command of the target user. The voice control instruction is obtained by an audio acquisition device in the vehicle after the voice assistant receives the awakening word. And taking the voice control instruction as 'opening the trunk', and opening the trunk of the vehicle by the center console under the condition that the control authority of the target user is determined to be high. Otherwise, under the condition that the control authority of the target user is low, the center console does not respond to the voice control instruction of the target user. Through the arrangement, strangers (such as passengers of a networked car) can be prevented from controlling the vehicle, and the privacy and the safety of the vehicle in use are guaranteed.
As still another embodiment, the center console responds to the voice information of the target user issued by the driver or the passenger in the other vehicle in the case where the control authority of the target user is determined to be high, that is, controls the vehicle to operate based on the voice of the target user. Specifically, the center console responds to the voice information sent by the target user in the other vehicle when determining that the second driver in the own vehicle (i.e., the second vehicle) and the first driver in the other vehicle (i.e., the first vehicle) are in a relationship (e.g., a couple relationship). For example, the voice information may include address information, and the center console navigates using the address information as a destination when recognizing specific content of the address information through a voice recognition technology. On the contrary, in the case that the control authority of the target user is low, the center console does not respond to the voice information of the target user (i.e., the driver in the other vehicle).
The embodiment of the application provides a vehicle control method, in the method, a voiceprint feature pair in a relation network corresponds to at least one prediction relation, and each prediction relation corresponds to a determined number of times. The center console can accurately determine the identity relationship between the target user and the designated person based on the determination times corresponding to the prediction relationship, so that the subsequent control of the center console on the vehicle is more reliable.
The following describes the determination process of the relationship network.
Referring to fig. 4, fig. 4 schematically illustrates a method for determining a relationship network according to a first embodiment of the present application. Specifically, the method may include the following steps S410 to S440.
In step S410, a dialog audio is acquired.
In one embodiment, the console acquires dialogue audio through the audio acquiring device every set time period under the condition that the vehicle is determined to be in the driving state. The audio duration and the set duration of the dialogue audio are default parameters in the console, which is not specifically limited in this application.
In step S420, based on the dialogue audio, the voiceprint feature of the specified person and the voiceprint feature of the user are determined.
The voiceprint characteristics of the designated person and the voiceprint characteristics of the user are different. The method for extracting the voiceprint features may refer to the detailed description in step S220. Here, when the console extracts the voiceprint features based on the dialogue audio, if only the voiceprint features of one user are extracted, the console does not execute the subsequent steps, and returns to step S410 to start executing. If the voiceprint characteristics of a plurality of users are extracted, the center console judges whether the voiceprint characteristics of the appointed figure exist in the dialogue audio, and if the voiceprint characteristics of the appointed figure exist, the voiceprint characteristics except the voiceprint characteristics of the appointed figure are determined as the voiceprint characteristics of the users; if the voiceprint feature of the designated person does not exist, the subsequent steps are not executed, and the step S410 is returned to start the execution.
The method for determining the voiceprint feature of the designated person may refer to the description in step S230, and is not described herein again. Specifically, the center console matches the extracted voiceprint features of the multiple users with the voiceprint features of the designated person through a voiceprint feature matching algorithm, and then judges whether the voiceprint features of the designated person exist in the dialogue audio. Specifically, the voiceprint feature matching algorithm may be a Hidden Markov Model (HMM) based feature matching algorithm, a Dynamic Time Warping (DTW) based feature matching algorithm, and the like, and is not particularly limited in this application.
In step S430, the predicted relationship between the designated person and the user is determined based on the dialogue audio.
In the embodiment of the application, the center console determines the predicted relationship between the designated person and the user by judging whether the relation words exist in the conversation audio. The relation words refer to words which directly or indirectly represent the identity relation between the designated person and the user. Illustratively, if the relationship words are "dad" and "daughter," then the identity relationship between the designated person and the user is a father-daughter relationship. Specifically, step S430 may include step S4310 to step S4330.
Step S4310, based on the dialogue audio, determines whether the relation word exists in the dialogue audio.
As an embodiment, target audios corresponding to a plurality of relation words and an audio comparison algorithm are stored in the console, for example, the target audios corresponding to the plurality of relation words may be an audio corresponding to "dad", "wife", and so on. The center console compares the conversation audio frequency with the target audio frequency through an audio frequency comparison algorithm, and if sub-audio frequency fragments identical to the target audio frequency exist in the comparison audio frequency, the relation words exist in the conversation audio frequency; otherwise, if the sub-audio segment which is the same as the target audio does not exist in the comparison audio, determining that the relation word does not exist in the dialogue audio. Specifically, the audio comparison algorithm may be an audio comparison algorithm based on Mel-frequency Cepstral Coefficients (MFCCs), which is not specifically limited in this embodiment.
As another implementation, the console determines the text content of the dialogue audio by recognizing the dialogue audio, and then determines whether the relation word exists based on the text content. Specifically, an audio recognition algorithm and a text matching algorithm are stored in the console, and the console converts the conversation audio into text content based on the audio recognition algorithm. The audio recognition algorithm may be an audio recognition algorithm based on Dynamic Time Warping (Dynamic Time Warping), or the like. In the embodiment of the application, a plurality of relation words, such as "dad", "mom", "old man", and the like, are stored in the console in advance, and whether the relation words exist in the text content is determined through a text matching algorithm. Among them, the text matching algorithm may be a text matching algorithm based on a Jaccard (Jaccard) similarity coefficient, or the like.
Step S4320, if the relation word exists in the dialogue audio, determining a specific relationship corresponding to the relation word as a predicted relationship between the designated person and the user.
In some embodiments, there are multiple related words in the conversational audio. The center console of this embodiment is preset with a specific relational mapping table. The specific relationship mapping table represents a one-to-one correspondence between the relationship words and the specific relationships, for example, if the relationship words are "dad" and "daughter", the specific relationship is a father-woman relationship, and if the relationship words are "husband" and "wife", the specific relationship is a couple relationship. And when a plurality of keywords are determined, the center console determines a specific relation corresponding to the related words based on the specific relation mapping table, and determines the specific relation as a predicted relation between the designated person and the user.
In some embodiments, there is one relational word in the conversational audio. In this embodiment, a gender recognition algorithm is further provided in the console, and the console determines a specific relationship corresponding to a relation word based on the gender information of the designated person and the user determined by the gender recognition algorithm when only one relation word is obtained. Illustratively, taking the relation word as "dad" as an example, the corresponding specific relationship may be a parent-child relationship or a parent-child relationship. And the console further determines that the specific relationship between the designated person and the user is a parent-female relationship under the condition that the gender information of the designated person and the gender information of the user are respectively male and female based on the gender identification algorithm. Specifically, the gender identification algorithm may be a voiceprint feature-based identification algorithm, or a face feature-based identification algorithm, which is not specifically limited in this embodiment. It should be noted that, in some cases, a specific relationship may also be directly determined by a relation word, for example, in the case that the relation word is "husband" or "wife", the corresponding specific relationship is a couple relationship. In the embodiment of the application, the center console further acquires the gender information of the user under the condition that a plurality of specific relationships are determined based on one relationship word, so that the accuracy of determining the specific relationships can be improved.
Step S4330, if the relation words do not exist in the dialogue audio, determining that the predicted relation between the designated person and the user is stranger relation or acquaintance relation.
In the embodiment of the application, when the relation words do not exist in the dialogue audio, the console further determines that the predicted relation between the designated person and the user is stranger relation or acquaintance relation based on the relation network. Specifically, if the relationship network comprises a relationship between the voiceprint features of the designated person and the voiceprint features of the user and strangers, the central console determines that the predicted relationship is a stranger relationship; if the relationship network includes the voiceprint feature pair of the specified person and the voiceprint feature pair of the user to have an acquaintance relationship, the center console determines that the predicted relationship is the acquaintance relationship. In some possible cases, there is no voiceprint feature pair in the relationship network that includes the voiceprint feature of the specified person and the voiceprint feature of the user, and the console then determines that the predicted relationship is a stranger relationship. In other possible cases, the relationship network may include a voiceprint feature pair comprising the voiceprint feature of the designated person and the voiceprint feature of the user corresponding to other specific relationships (e.g., a couple relationship), and the console may not perform any further steps.
It should be noted that the determination frequency of the relationships between acquaintances is greater than the determination frequency of the relationships between strangers, specifically, in the case that the determination frequency of the relationships between strangers is greater than the first threshold, the center console will change the relationships between strangers to relationships between acquaintances, so that the relationships between strangers and acquaintances do not exist simultaneously in the corresponding predicted relationship of the same voiceprint feature pair, specifically, the implementation process of changing the relationships between strangers to relationships between acquaintances is introduced in step S440.
Step S440, based on the voiceprint characteristics of the designated person, the voiceprint characteristics of the user and the predicted relationship, a relationship network is determined.
In some embodiments, if the voiceprint feature of the user does not exist in the relationship network, that is, the console acquires the voiceprint feature of the user from the dialog audio for the first time, the console stores the voiceprint feature of the user, adds a voiceprint feature pair including the voiceprint feature of the user and the voiceprint feature of the specified person in the relationship network, records a prediction relationship corresponding to the voiceprint feature pair, and sets the number of times of determining the prediction relationship to be one.
In some embodiments, if the voiceprint feature of the user exists in the relationship network but the predicted relationship does not exist, the console determines a voiceprint feature pair including the voiceprint feature of the user and the voiceprint feature of the specified person, records the predicted relationship in the corresponding voiceprint feature pair, and sets the number of times of determination of the predicted relationship to one.
In some embodiments, if the voiceprint feature of the user and the predicted relationship exist in the relationship network, the console determines a voiceprint feature pair including the voiceprint feature of the user and the voiceprint feature of the specified person, and adds one to the number of determinations of the predicted relationship.
It should be noted that, in the case that the predicted relationship is a stranger relationship, the console further includes a step of determining whether the updated determination number is greater than a first threshold after adding one to the determination number of the stranger relationship, and if the updated determination number is greater than the first threshold, the stranger relationship is changed to be an acquaintance relationship. Otherwise, if the updated determination times are less than or equal to the first threshold, the determination times are kept unchanged. The first threshold is a default parameter in the console, and the console can also adjust the relationship network based on the actual use condition of the relationship network. In this embodiment, when the number of times of determining the stranger relationship is greater than the first threshold, it is described that a plurality of conversations have been performed between the designated person and the user, and at this time, the identity relationship between the two is adjusted from the stranger relationship to the acquaintance relationship, so that the identity relationship between the target user and the designated person determined by the subsequent center console based on the relationship network can be more accurate and reliable.
In some embodiments, specifically, in the case where the predicted relationship between the human and the user is specified as a specific relationship, step S440 includes steps S4410 to S4420.
In step S4410, if the predicted relationship between the designated person and the user is a stranger relationship in the relationship network, the stranger relationship is changed to the designated relationship, and the number of times of determination of the designated relationship is set to one.
For example, taking a specific relationship as a couple relationship as an example, if the predicted relationship between the designated person and the user in the relationship network is a stranger relationship, the console changes the stranger relationship into the couple relationship, and sets the number of determinations of the couple relationship to one. That is, in the relationship network, the stranger relationship and the determination frequency of the stranger relationship are deleted, the specified relationship is recorded, and the determination frequency of the specified relationship is set to be one.
In step S4420, if the specified relationship between the designated person and the user is an acquaintance relationship in the relationship network, the acquaintance relationship is changed to the designated relationship, and the number of determinations of the designated relationship is set as the number of determinations of the acquaintance relationship.
Illustratively, taking the specific relationship as a couple relationship as an example, if the predicted relationship between the designated person and the user in the relationship network is an acquaintance relationship and the number of determinations of the acquaintance relationship is three, the console changes the acquaintance relationship into the couple relationship and sets the number of determinations of the couple relationship to three.
The embodiment of the application provides a method for determining a relationship network, wherein a center console can determine and update the relationship network based on the determination method, so that the identity relationship between a target user and an appointed person determined by the center console based on the relationship network can be more accurate and reliable.
In some embodiments, the console also has the ability to check and correct errors in the relationship network. Specifically, the central console may check the relationship network every preset check duration under the condition that the central console is in a working state; the relationship network may also be checked after each determination and update of the relationship network. Specifically, the process of checking the relationship network includes step a100 to step a200.
Step A100, judging whether at least two specified voiceprint feature pairs in the relationship network have a specific prediction relationship.
Wherein the specified voiceprint feature pair refers to a voiceprint feature pair comprising voiceprint features of a specified person, and the specific predicted relationship refers to an identity relationship existing between only one user and the specified person, such as a couple relationship. If the vocal print characteristics of the designated person and the vocal print characteristics of at least two users have a couple relationship, the relationship network is indicated to be wrong, and in such a case, the relationship network needs to be adjusted.
In the embodiment of the application, a console determines a plurality of specified voiceprint feature pairs including voiceprint features of specified persons, further sequentially judges whether the prediction relation corresponding to each specified voiceprint feature pair contains the specific prediction relation, determines the number of the specified voiceprint feature pairs containing the specific prediction relation, and determines that at least two voiceprint feature pairs in a relation network have the specific prediction relation if the number is more than one; otherwise, if the number is equal to one, it is determined that only one specified voiceprint feature pair has a particular predictive relationship.
Step A200, under the condition that at least two specified voiceprint feature pairs have specific prediction relations, correcting the relation network based on the determined times of the specific prediction relations.
Illustratively, taking the designated person as user a as an example, in this case, the voiceprint features of user a and the voiceprint features of user B and user C have a specific predictive relationship, for example, a couple relationship. In this case, the console obtains a first determination time and a second determination time corresponding to the two specific prediction relationships, respectively (where the first determination time corresponds to the specific prediction relationship between the user a and the user B, and the second determination time corresponds to the specific prediction relationship between the user a and the user C), and then determines a difference between the first determination time and the second determination time, and if the difference is greater than a preset difference, determines a smaller value between the first determination time and the second determination time, and changes the specific prediction relationship corresponding to the smaller value into an acquaintance relationship. And if the difference is less than or equal to the preset difference, changing the two specific prediction relations into acquaintance relations.
The preset difference is a default parameter in the center console, and can be dynamically adjusted based on the actual use condition of the relational network. Specifically, the preset difference may be a natural number greater than 2, for example, if the preset difference is 5, the first determination time is 9, and the second determination time is 2, at this time, if the difference between the first determination time and the second determination time is greater than the preset difference, the specific prediction relationship corresponding to the smaller value (that is, the second determination time) is changed to an acquaintance relationship, for example, the couple relationship between the voiceprint feature of the user a and the voiceprint feature of the user C is changed to an acquaintance relationship. If the first determination frequency is 4, at this time, the difference between the first determination frequency and the second determination frequency is less than or equal to a preset difference, the couple relationship between the voiceprint feature of the user a and the voiceprint feature of the user C is changed into an acquaintance relationship, and the couple relationship between the voiceprint feature of the user a and the voiceprint feature of the user B is changed into an acquaintance relationship. The center console in the embodiment of the application can check and correct the relation network, so that the identity relation between the target user and the designated person determined by the subsequent center console based on the relation network can be more accurate and reliable.
Referring to fig. 5, a block diagram of a control device 500 of a vehicle according to an embodiment of the present application is shown. Wherein the apparatus 500 comprises: an acquisition module 510, a first determination module 520, a second determination module 530, and a control module 540. The obtaining module 510 is configured to obtain an audio clip of a target user. The first determination module 520 is configured to determine voiceprint characteristics of the target user based on the audio segment. The second determining module 530 is configured to determine an identity relationship between the target user and the designated person based on a preset relationship network, where the relationship network includes at least one voiceprint feature pair and a predicted relationship corresponding to the voiceprint feature pair, the voiceprint feature pair includes a voiceprint feature of the designated person and a voiceprint feature of the user, and the predicted relationship is the predicted identity relationship between the user and the designated person. The control module 540 is configured to control the vehicle based on the identity relationship between the target user and the designated person.
In some embodiments, the relationship network further comprises a number of determinations of predicted relationships, and the second determining module 530 is further configured to determine a target voiceprint feature pair based on a preset relationship network, wherein the target voiceprint feature pair comprises a voiceprint feature of a specified person and a voiceprint feature of a target user; and determining the identity relationship between the target user corresponding to the voiceprint features and the designated person based on the corresponding prediction relationship of the target voiceprint features and the determination times of the prediction relationship.
In some embodiments, the target voiceprint feature pair has a plurality of predicted relationships, and the second determining module 530 is further configured to determine, if a maximum value of the determined times of the plurality of predicted relationships is greater than a specified threshold, a predicted relationship corresponding to the maximum value as an identity relationship between the target user and the specified person.
In some embodiments, the control module 540 is further configured to obtain a default parameter corresponding to the target user based on the identity relationship between the target user and the designated person, where the default parameter includes a setting parameter of at least one environmental device in the vehicle, or/and a control authority of at least one environmental device in the vehicle; the vehicle is controlled based on default parameters.
In some embodiments, the apparatus 500 further comprises a relationship network determination module (not shown in the figures). The relation network determining module is used for acquiring conversation audio; determining the voiceprint characteristics of the designated person and the voiceprint characteristics of the user based on the conversation audio, wherein the voiceprint characteristics of the designated person are different from the voiceprint characteristics of the user; determining a predicted relationship of the designated person and the user based on the conversational audio; and determining a relationship network based on the voiceprint characteristics of the specified person, the voiceprint characteristics of the user and the predicted relationship.
In some embodiments, the relationship network determining module is further configured to determine whether a relationship word exists in the conversation audio based on the conversation audio, where the relationship word is a word that directly or indirectly represents an identity relationship between a specified person and the user; if the relation words exist in the dialogue audio, determining the specific relation corresponding to the relation words as the prediction relation between the designated character and the user; if the relation words do not exist in the dialogue audio, determining that the predicted relation between the specified person and the user is stranger relation or acquaintance relation based on the occurrence frequency of the voiceprint feature pairs, wherein the voiceprint feature pairs comprise voiceprint features of the specified person and voiceprint features of the user.
In some embodiments, the relationship network determining module is further configured to determine that the predicted relationship between the designated person and the user is a stranger relationship if the relationship word does not exist in the dialogue audio and the occurrence frequency is less than a second threshold; and if the relation words do not exist in the conversation audio and the occurrence frequency is greater than or equal to a second threshold value, determining that the predicted relation between the designated person and the user is an acquaintance relation.
In some embodiments, the relationship network determining module is further configured to, in a case where the predicted relationship between the designated person and the user is a specific relationship, change the predicted relationship between the designated person and the user to a stranger relationship if the predicted relationship between the designated person and the user is the stranger relationship in the relationship network, and set the number of times of determination of the designated relationship to one; if the specific relationship between the designated person and the user is an acquaintance relationship in the relationship network, the acquaintance relationship is changed into the designated relationship, and the number of times of determination of the designated relationship is set as the number of times of determination of the acquaintance relationship.
It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described apparatuses and modules may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided in the present application, the coupling between the modules may be electrical, mechanical or other type of coupling.
In addition, functional modules in the embodiments of the present application may be integrated into one processing module, or each module may exist alone physically, or two or more modules are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode.
The embodiment of the application provides a control device of a vehicle, and particularly, the vehicle can be correspondingly controlled according to the identity relation between a target user and a designated person. For example, where the identity relationship indicates an affinity between two persons (e.g., a couple relationship, a parent-child relationship), the environmental device in the vehicle may be set to a specified setting of the target user (e.g., play a history play video of the target user, perform a song push based on a history song list of the target user, etc.). Therefore, the vehicle in the application can carry out corresponding setting on the environment equipment according to the identity relation between the target user and the designated person, the situation that the target user is repeatedly set is avoided, the control of the environment equipment is more convenient and efficient, and the riding experience of the target user is improved.
Referring to fig. 6, it shows that the embodiment of the present application further provides a vehicle 600, where the vehicle 600 includes: one or more processors 610, memory 620, audio acquisition device 630, and one or more applications. Wherein one or more application programs are stored in the memory 620 and configured to be executed by the one or more processors 610, the one or more application programs configured to perform the methods described in the above embodiments.
The processor 610 may include one or more processing cores. The processor 610, using various interfaces and lines to connect various parts throughout the battery management system, performs various functions of the battery management system and processes data by executing or executing instructions, programs, code sets, or instruction sets stored in the memory 620 and invoking data stored in the memory 620. Alternatively, the processor 610 may be implemented in hardware using at least one of Digital Signal Processing (DSP), field-Programmable Gate Array (FPGA), and Programmable Logic Array (PLA). The processor 610 may integrate one or more of a Central Processing Unit (CPU) 610, a Graphics Processing Unit (GPU) 610, a modem, and the like. The CPU mainly processes an operating system, a user interface, an application program and the like; the GPU is used for rendering and drawing display content; the modem is used to handle wireless communications. It is understood that the modem may not be integrated into the processor 610, but may be implemented by a communication chip.
The Memory 620 may include a Random Access Memory (RAM) 620, and may also include a Read-Only Memory (Read-Only Memory) 620. The memory 620 may be used to store instructions, programs, code, sets of codes, or sets of instructions. The memory 620 may include a stored program area and a stored data area, wherein the stored program area may store instructions for implementing an operating system, instructions for implementing at least one function (such as a touch function, a sound playing function, an image playing function, etc.), instructions for implementing various method embodiments described below, and the like. The storage data area can also store data (such as a phone book, audio and video data, chatting record data) created by the electronic device map in use and the like.
Referring to fig. 7, a computer-readable storage medium 700 is provided according to an embodiment of the present application, in which computer program instructions 710 are stored, and the computer program instructions 710 can be called by a processor to execute the method described in the above embodiment.
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. Alternatively, the computer-readable storage medium comprises a non-volatile computer-readable storage medium. The computer readable storage medium 700 has storage space for computer program instructions 710 to perform any of the method steps of the method described above. The computer program instructions 710 may be read from or written to one or more computer program products.
Although the present application has been described with reference to the preferred embodiments, it is to be understood that the present application is not limited to the disclosed embodiments, but rather, the present application is intended to cover various modifications, equivalents and alternatives falling within the spirit and scope of the present application.
Claims (10)
1. A control method of a vehicle, characterized by comprising:
acquiring an audio clip of a target user;
determining voiceprint features of the target user based on the audio clip;
determining an identity relationship between the target user and an appointed person based on a preset relationship network, wherein the relationship network comprises at least one voiceprint feature pair and a prediction relationship corresponding to the voiceprint feature pair, the voiceprint feature pair comprises a voiceprint feature of the appointed person and a voiceprint feature of the user, and the prediction relationship refers to the predicted identity relationship between the user and the appointed person;
and controlling the vehicle based on the identity relationship between the target user and the designated person.
2. The method of claim 1, wherein the relationship network further comprises a number of determinations of the predicted relationship, and wherein determining the identity relationship between the target user corresponding to the voiceprint feature and the designated person based on a preset relationship network comprises:
determining a target voiceprint feature pair based on the preset relationship network, wherein the target voiceprint feature pair comprises the voiceprint feature of the specified person and the voiceprint feature of the target user;
and determining the identity relationship between the target user corresponding to the voiceprint features and the designated person based on the corresponding prediction relationship of the target voiceprint features and the determination times of the prediction relationship.
3. The method of claim 2, wherein the target voiceprint feature pair has a plurality of the predicted relationships, and wherein determining the identity relationship between the target user and the designated person corresponding to the voiceprint feature pair based on the predicted relationship corresponding to the target voiceprint feature pair and the determined number of times of the predicted relationship comprises:
and if the maximum value of the determined times of the plurality of predicted relationships is larger than a specified threshold value, determining the predicted relationship corresponding to the maximum value as the identity relationship between the target user and the specified person.
4. The method of any of claims 1 to 3, wherein the controlling the vehicle based on the identity relationship between the target user and the designated person comprises:
acquiring default parameters corresponding to the target user based on the identity relationship between the target user and the designated person, wherein the default parameters comprise setting parameters of at least one environmental device in the vehicle or/and control authority of at least one environmental device in the vehicle;
controlling the vehicle based on the default parameters.
5. The method according to any one of claims 1 to 3, wherein the determining of the relationship network comprises:
acquiring conversation audio;
determining the voiceprint characteristics of the designated person and the voiceprint characteristics of the user based on the conversation audio, wherein the voiceprint characteristics of the designated person are different from the voiceprint characteristics of the user;
determining a predicted relationship of the designated person and the user based on the conversational audio;
and determining the relationship network based on the voiceprint characteristics of the specified person, the voiceprint characteristics of the user and the predicted relationship.
6. The method of claim 5, wherein determining the predicted relationship between the designated person and the user based on the conversational audio comprises:
judging whether relation words exist in the conversation audio based on the conversation audio, wherein the relation words refer to vocabularies which directly or indirectly represent the identity relation between the designated person and the user;
if the relation words exist in the dialogue audio, determining the specific relation corresponding to the relation words as the prediction relation between the designated figure and the user;
and if the relation words do not exist in the conversation audio, determining that the predicted relation between the designated person and the user is a stranger relation or an acquaintance relation, wherein the determination frequency of the acquaintance relation is greater than that of the stranger relation.
7. The method of claim 6, wherein determining the relationship network based on the voiceprint characteristics of the designated person, the voiceprint characteristics of the user, and the predicted relationship comprises:
under the condition that the predicted relationship between the designated person and the user is the specific relationship, if the predicted relationship between the designated person and the user is a stranger relationship in the relationship network, changing the stranger relationship into the designated relationship, and setting the determination frequency of the designated relationship as one;
if the specific relationship between the designated person and the user is an acquaintance relationship in the relationship network, changing the acquaintance relationship into the designated relationship, and setting the determined times of the designated relationship as the determined times of the acquaintance relationship.
8. A control apparatus of a vehicle, characterized by comprising:
the acquisition module is used for acquiring an audio clip of a target user;
a first determining module, configured to determine a voiceprint feature of the target user based on the audio clip;
a second determining module, configured to determine an identity relationship between the target user and an appointed person based on a preset relationship network, where the relationship network includes at least one voiceprint feature pair and a prediction relationship corresponding to the voiceprint feature pair, the voiceprint feature pair includes a voiceprint feature of the appointed person and a voiceprint feature of the user, and the prediction relationship is an identity relationship between the user and the appointed person obtained through prediction;
and the control module is used for controlling the vehicle based on the identity relationship between the target user and the designated person.
9. A vehicle, characterized by comprising:
one or more processors;
a memory;
an audio acquisition device;
one or more applications, wherein one or more of the applications are stored in the memory and configured to be executed by one or more of the processors, the one or more applications configured to perform the method of any of claims 1-7.
10. A computer-readable storage medium having computer program instructions stored therein that are callable by a processor to perform the method of any one of claims 1-7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211086123.2A CN115447588A (en) | 2022-09-06 | 2022-09-06 | Vehicle control method and device, vehicle and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211086123.2A CN115447588A (en) | 2022-09-06 | 2022-09-06 | Vehicle control method and device, vehicle and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115447588A true CN115447588A (en) | 2022-12-09 |
Family
ID=84302930
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211086123.2A Pending CN115447588A (en) | 2022-09-06 | 2022-09-06 | Vehicle control method and device, vehicle and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115447588A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115848303A (en) * | 2022-12-16 | 2023-03-28 | 润芯微科技(江苏)有限公司 | Automobile self-adaptive intelligent auxiliary sleep adjustment method and system |
-
2022
- 2022-09-06 CN CN202211086123.2A patent/CN115447588A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115848303A (en) * | 2022-12-16 | 2023-03-28 | 润芯微科技(江苏)有限公司 | Automobile self-adaptive intelligent auxiliary sleep adjustment method and system |
CN115848303B (en) * | 2022-12-16 | 2023-08-18 | 润芯微科技(江苏)有限公司 | Self-adaptive intelligent auxiliary sleep adjusting method and system for automobile |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11989219B2 (en) | Profile disambiguation | |
US7769588B2 (en) | Spoken man-machine interface with speaker identification | |
US10504513B1 (en) | Natural language understanding with affiliated devices | |
US11455989B2 (en) | Electronic apparatus for processing user utterance and controlling method thereof | |
CN108630231B (en) | Information processing apparatus, emotion recognition method, and storage medium | |
CN108447471A (en) | Audio recognition method and speech recognition equipment | |
EP4022602A1 (en) | Customizable keyword spotting system with keyword adaptation | |
CN113035231B (en) | Keyword detection method and device | |
CN107483445A (en) | A kind of silent Application on Voiceprint Recognition register method, device, server and storage medium | |
CN110544468B (en) | Application awakening method and device, storage medium and electronic equipment | |
CN112634897B (en) | Equipment awakening method and device, storage medium and electronic device | |
WO2021169365A1 (en) | Voiceprint recognition method and device | |
CN110826637A (en) | Emotion recognition method, system and computer-readable storage medium | |
CN117636872A (en) | Audio processing method, device, electronic equipment and readable storage medium | |
US10866948B2 (en) | Address book management apparatus using speech recognition, vehicle, system and method thereof | |
CN115447588A (en) | Vehicle control method and device, vehicle and storage medium | |
CN110473542B (en) | Awakening method and device for voice instruction execution function and electronic equipment | |
KR20210001082A (en) | Electornic device for processing user utterance and method for operating thereof | |
CN111506183A (en) | Intelligent terminal and user interaction method | |
CN116391225A (en) | Method and system for assigning unique voices to electronic devices | |
CN111477226A (en) | Control method, intelligent device and storage medium | |
CN111145748A (en) | Audio recognition confidence determining method, device, equipment and storage medium | |
US10990614B1 (en) | Endpoint device relationships in processing user inputs | |
CN112037772A (en) | Multi-mode-based response obligation detection method, system and device | |
JP2005534065A (en) | Man-machine interface unit operation and / or control method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |