Method and device for automatically switching voice pronouncing persons based on information of persons in vehicle

Abstract

The invention relates to a method and device for automatically switching a voice speaker based on in-vehicle personnel information, and the method comprises the steps: activating a vehicle-mounted voice broadcast function of a current vehicle, obtaining a face image of a target passenger, and carrying out the face recognition of the face image, so as to obtain the passenger information; based on the passenger information and a weighted scoring mechanism, determining a target voice speaker, obtaining interaction data of the target function, and performing voice broadcast operation through the target voice speaker according to the interaction data; and judging whether other passengers in the current vehicle activate a vehicle-mounted voice broadcast function, if so, acquiring passenger information of the other passengers so as to determine a new target voice speaker according to the passenger information of the other passengers, and performing voice speaker automatic switching operation. According to the method, the voice pronunciation person can be automatically switched according to the gender, age and other characteristics of the person in the vehicle, so that the user experience is improved, and the intelligent level of man-machine interaction is enhanced.

Description

Technical Field

[0001] The present application relates to the technical field of intelligent vehicle-mounted systems, and in particular to a method and device for automatically switching voice speakers based on in-vehicle occupant information. Background Art

[0002] With the development of artificial intelligence technology, intelligent vehicle systems have become an important part of improving driving experience.

[0003] Existing intelligent voice assistants usually use fixed voice speakers and are unable to provide personalized voice services based on the specific circumstances of passengers. For example, passengers of different age groups or genders may have different preferences for voice, and current technology lacks an effective voice adaptation mechanism. Summary of the invention

[0004] The present application provides a method and device for automatically switching voice speakers based on in-vehicle occupant information, so as to solve the problems that the existing intelligent voice technology lacks an effective voice adaptation mechanism and cannot provide personalized voice services according to the specific circumstances of the passengers.

[0005] The first aspect of the present application provides a method for automatically switching voice speakers based on in-vehicle occupant information, comprising the following steps: activating the in-vehicle voice broadcast function of the current vehicle, and obtaining a facial image of a target passenger, and performing face recognition processing on the facial image to obtain the passenger information of the target passenger; determining a target voice speaker based on the passenger information and a preset weighted scoring mechanism, and obtaining interaction data of at least one target function in the current vehicle, and performing a voice broadcast operation according to the interaction data through the target voice speaker; determining whether there are other passengers in the current vehicle who have activated the in-vehicle voice broadcast function, and if there are other passengers who have activated the in-vehicle voice broadcast function, obtaining the passenger information of the other passengers, so as to determine a new target voice speaker based on the passenger information of the other passengers, and performing an automatic voice speaker switching operation through the new target voice speaker.

[0006] Optionally, in one embodiment of the present application, the on-board voice broadcast function of the current vehicle is activated, and the facial image of the target passenger is obtained, and the facial recognition processing is performed on the facial image to obtain the passenger information of the target passenger, including: judging whether the target passenger has pre-set a fixed voice style speaker through the on-board voice broadcast function, if the target passenger has pre-set the fixed voice style speaker, using the fixed voice style speaker to perform the voice broadcast operation; if the target passenger has not pre-set the fixed voice style speaker, obtaining the environmental information of the current vehicle, and determining the working status and voice broadcast parameters of the on-board camera of the current vehicle according to the environmental information, so as to call the on-board camera to capture the facial image of the target passenger based on the working status of the on-board camera and the voice broadcast parameters; inputting the facial image into a pre-trained face recognition model to output the passenger information corresponding to the target passenger, wherein the passenger information includes the passenger gender and the passenger age.

[0007] Optionally, in one embodiment of the present application, if the target passenger pre-sets the fixed voice style speaker, before using the fixed voice style speaker to perform the voice broadcast operation, it also includes: selecting a fixed voice style speaker from a preset fixed style voice library according to a preset multiple speaker options, and storing the fixed voice style speaker in the vehicle-mounted terminal.

[0008] Optionally, in one embodiment of the present application, the target voice speaker is determined based on the passenger information and a preset weighted scoring mechanism, and the interaction data of at least one target function in the current vehicle is obtained, and the voice broadcast operation is performed by the target voice speaker according to the interaction data, including: obtaining the number of users and the total number of users of each voice speaker in a preset voice speaker database, and calculating the popularity corresponding to each voice speaker according to the number of users and the total number of users; determining the gender weight, age weight and popularity weight of the target passenger according to the weighted scoring mechanism; calculating the pronunciation score of each voice speaker based on the gender weight, the age weight and the popularity weight, so as to sort each voice speaker in descending order according to the pronunciation score to obtain a sorted list; and sending the sorted list to the on-board terminal of the current vehicle, so that the target passenger auditions the voice speakers in the sorted list to determine the target voice speaker.

[0009] The second aspect of the present application provides a device for automatically switching voice speakers based on in-vehicle occupant information, including: a recognition module, used to activate the in-vehicle voice broadcast function of the current vehicle, and obtain the facial image of the target passenger, and perform face recognition processing on the facial image to obtain the passenger information of the target passenger; an acquisition module, used to determine the target voice speaker based on the passenger information and a preset weighted scoring mechanism, and obtain the interaction data of at least one target function in the current vehicle, and perform a voice broadcast operation according to the interaction data through the target voice speaker; a switching module, used to determine whether there are other passengers in the current vehicle who activate the in-vehicle voice broadcast function, if there are other passengers who activate the in-vehicle voice broadcast function, then obtain the passenger information of the other passengers, so as to determine a new target voice speaker according to the passenger information of the other passengers, and perform an automatic voice speaker switching operation through the new target voice speaker.

[0010] Optionally, in one embodiment of the present application, the recognition module includes: a judgment unit, used to judge whether the target passenger has pre-set a fixed voice style speaker through the in-vehicle voice broadcast function, and if the target passenger has pre-set the fixed voice style speaker, the fixed voice style speaker is used to perform the voice broadcast operation; a collection unit, used to obtain environmental information of the current vehicle if the target passenger has not pre-set the fixed voice style speaker, and determine the working status and voice broadcast parameters of the in-vehicle camera of the current vehicle based on the environmental information, so as to call the in-vehicle camera to collect the facial image of the target passenger based on the working status of the in-vehicle camera and the voice broadcast parameters; an input unit, used to input the facial image into a pre-trained face recognition model to output the passenger information corresponding to the target passenger, wherein the passenger information includes the passenger gender and the passenger age.

[0011] Optionally, in one embodiment of the present application, it also includes: a selection module, which is used to select a fixed voice style speaker from a preset fixed style voice library according to a preset multiple speaker options before using the fixed voice style speaker to perform a voice broadcast operation if the target passenger pre-sets the fixed voice style speaker, and store the fixed voice style speaker in the vehicle-mounted terminal.

[0012] Optionally, in one embodiment of the present application, the acquisition module includes: a calculation unit, used to obtain the number of users and the total number of users of each voice speaker in a preset voice speaker database, and calculate the popularity corresponding to each voice speaker through the number of users and the total number of users; a determination unit, used to determine the gender weight, age weight and popularity weight of the target passenger according to the weighted scoring mechanism; a sorting unit, used to calculate the pronunciation score of each voice speaker based on the gender weight, the age weight and the popularity weight, so as to sort each voice speaker in descending order according to the pronunciation score to obtain a sorted list; and an audition unit, used to send the sorted list to the on-board terminal of the current vehicle, so that the target passenger auditions the voice speakers in the sorted list to determine the target voice speaker.

[0013] A third aspect of the present application provides a vehicle, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method of automatically switching a voice speaker based on in-vehicle occupant information as described in the above embodiment.

[0014] The fourth aspect of the present application provides a computer-readable storage medium, which stores a computer program. When the program is executed by a processor, it implements the above method of automatically switching the voice speaker based on the information of the people in the vehicle.

[0015] The fifth aspect of the present application provides a computer program product, including a computer program, which is executed to implement the above-mentioned method of automatically switching the voice speaker based on the information of the people in the car.

[0016] Therefore, the embodiments of the present application have the following beneficial effects:

[0017] The embodiment of the present application can activate the vehicle-mounted voice broadcast function of the current vehicle, and obtain the facial image of the target passenger, and perform face recognition processing on the facial image to obtain the passenger information of the target passenger; based on the passenger information and the preset weighted scoring mechanism, determine the target voice speaker, and obtain the interactive data of at least one target function in the current vehicle, and perform voice broadcast operation according to the interactive data through the target voice speaker; judge whether there are other passengers in the current vehicle to activate the vehicle-mounted voice broadcast function, if there are other passengers activating the vehicle-mounted voice broadcast function, then obtain the passenger information of other passengers, so as to determine a new target voice speaker according to the passenger information of other passengers, and perform automatic voice speaker switching operation through the new target voice speaker. The present application can automatically switch the voice speaker according to the characteristics of the gender, age, etc. of the people in the car, thereby improving the user experience and enhancing the intelligent level of human-computer interaction. Thus, the existing intelligent voice technology lacks an effective voice adaptation mechanism and cannot provide personalized voice services according to the specific circumstances of the passengers.

[0018] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0020] Figure 1 A flowchart of a method for automatically switching a voice speaker based on in-vehicle personnel information provided according to an embodiment of the present application;

[0021] Figure 2 A schematic diagram of the execution logic of a method for automatically switching a voice speaker based on in-vehicle personnel information provided by an embodiment of the present application;

[0022] Figure 3 A schematic diagram of a process for a user to select a voice speaker provided in an embodiment of the present application;

[0023] Figure 4 A schematic diagram of a flow chart of selecting a voice speaker for different passengers provided in one embodiment of the present application;

[0024] Figure 5 This is an example diagram of a device for automatically switching a voice speaker based on in-vehicle personnel information according to an embodiment of the present application;

[0025] Figure 6 A schematic diagram of the structure of a vehicle provided in an embodiment of the present application.

[0026] Among them, 10-a device for automatically switching the voice speaker based on the information of the people in the car, 100-a recognition module, 200-an acquisition module, 300-a switching module, 601-a memory, 602-a processor, and 603-a communication interface. DETAILED DESCRIPTION

[0027] Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0028] The following is a method and device for automatically switching voice speakers based on in-vehicle personnel information of the present application embodiment with reference to the accompanying drawings. In view of the problems mentioned in the above background technology, the present application provides a method for automatically switching voice speakers based on in-vehicle personnel information, in which the vehicle-mounted voice broadcast function of the current vehicle is activated, and the facial image of the target passenger is obtained, and the facial image is processed by face recognition to obtain the passenger information of the target passenger; based on the passenger information and the preset weighted scoring mechanism, the target voice speaker is determined, and the interaction data of at least one target function in the current vehicle is obtained, and the voice broadcast operation is performed according to the interaction data by the target voice speaker; it is determined whether there are other passengers in the current vehicle to activate the vehicle-mounted voice broadcast function, if there are other passengers activating the vehicle-mounted voice broadcast function, the passenger information of the other passengers is obtained, so as to determine a new target voice speaker according to the passenger information of the other passengers, and the voice speaker is automatically switched by the new target voice speaker. The present application can automatically switch the voice speaker according to the characteristics of the gender, age, etc. of the in-vehicle personnel, thereby improving the user experience and enhancing the intelligent level of human-computer interaction. This solves the problem that existing intelligent voice technology lacks an effective voice adaptation mechanism and is unable to provide personalized voice services based on the specific circumstances of passengers.

[0029] Specifically, Figure 1 A flowchart of a method for automatically switching voice speakers based on in-vehicle occupant information provided in an embodiment of the present application.

[0030] like Figure 1 As shown, the method for automatically switching the voice speaker based on the in-vehicle personnel information includes the following steps:

[0031] In step S101, the vehicle-mounted voice broadcast function of the current vehicle is activated, and the facial image of the target passenger is obtained, and face recognition processing is performed on the facial image to obtain the passenger information of the target passenger.

[0032] In the embodiment of the present application, after the passenger activates the in-vehicle voice broadcast function, the in-vehicle camera can be used to collect the passenger's facial image, and the facial image can be processed by a preset deep learning algorithm for face recognition, such as Figure 2 As shown, the passenger information of the passenger can be obtained, thereby providing reliable data guidance and basis for the automatic switching of the subsequent voice speaker.

[0033] Optionally, in one embodiment of the present application, the on-board voice broadcast function of the current vehicle is activated, and the facial image of the target passenger is obtained, and the facial image is subjected to face recognition processing to obtain the passenger information of the target passenger, including: judging through the on-board voice broadcast function whether the target passenger has pre-set a fixed voice style speaker, if the target passenger has pre-set a fixed voice style speaker, using the fixed voice style speaker to perform the voice broadcast operation; if the target passenger has not pre-set a fixed voice style speaker, obtaining the environmental information of the current vehicle, and determining the working status and voice broadcast parameters of the on-board camera of the current vehicle based on the environmental information, so as to call the on-board camera to capture the facial image of the target passenger based on the working status and voice broadcast parameters of the on-board camera; and inputting the facial image into a pre-trained face recognition model to output the passenger information corresponding to the target passenger, wherein the passenger information includes the passenger's gender and the passenger's age.

[0034] Specifically, the embodiments of the present application can activate the in-vehicle voice broadcast function of the current vehicle through button activation or voice wake-up, so as to determine whether the passenger has pre-set a fixed voice style speaker through the in-vehicle voice broadcast function. If the passenger has pre-set a fixed voice style speaker, the embodiments of the present application can use the fixed voice style speaker set by the passenger to perform the voice broadcast operation.

[0035] Optionally, in one embodiment of the present application, if the target passenger pre-sets a fixed voice style speaker, before using the fixed voice style speaker to perform the voice broadcast operation, it also includes: selecting a fixed voice style speaker from a preset fixed style voice library according to a preset multiple speaker options, and storing the fixed voice style speaker in the vehicle-mounted terminal.

[0036] As a feasible method, the embodiment of the present application can preset some fixed voice styles, such as a voice library of speaker options such as child-like cute type, mature and stable type, and energetic and youthful type. After the user makes a selection, he can directly use the preset speaker style. The embodiment of the present application can give priority to using the fixed voice style speaker selected by the user for voice broadcast, and store the fixed voice style speaker selected by the user in the vehicle-mounted terminal to improve the user's subsequent efficiency and usage experience of using the voice style speaker.

[0037] In addition, if the passenger has not pre-set a fixed voice style speaker, the embodiment of the present application can obtain the current vehicle's environmental information and adjust the camera's working status and voice playback parameters according to the vehicle's internal and external environment (such as light and noise) through the environmental perception function unit to ensure the best experience under various conditions.

[0038] Afterwards, the embodiments of the present application can call the vehicle-mounted camera to capture facial images of passengers in the car based on the working status of the vehicle-mounted camera and the voice broadcast parameters, and input the facial images into a pre-trained face recognition model to quickly and accurately identify the passenger's corresponding passenger information such as passenger gender and passenger age.

[0039] Therefore, the embodiments of the present application can effectively ensure the reliability and efficiency of automatically switching the voice speaker according to the gender, age and other characteristics of the occupants of the vehicle through technical means such as camera face recognition, thereby improving the user experience and the level of vehicle intelligence.

[0040] In step S102, based on the passenger information and a preset weighted scoring mechanism, a target voice speaker is determined, and interaction data of at least one target function in the current vehicle is obtained, and the target voice speaker performs a voice broadcast operation according to the interaction data.

[0041] In step S103, it is determined whether there are other passengers in the current vehicle who have activated the in-vehicle voice broadcast function. If there are other passengers who have activated the in-vehicle voice broadcast function, the passenger information of the other passengers is obtained to determine a new target voice speaker based on the passenger information of the other passengers, and the voice speaker is automatically switched through the new target voice speaker.

[0042] Furthermore, the embodiments of the present application can determine the voice speaker according to the above passenger information and the preset weighted scoring mechanism, and perform voice broadcasting operation on the interactive data through the voice speaker, such as Figure 3 As shown; thereafter, the embodiments of the present application can convert navigation, entertainment information or other interactive content into the voice of the corresponding speaker, and play it through the vehicle's audio system, such as turning on the car's air conditioner, turning on the wipers, etc.

[0043] In addition, when there are two or more passengers in the car, each passenger can select their favorite speaker on the screen in front of the seat (if the car has this configuration, the driver selects it on the central control screen); Figure 4 As shown, when different passengers in the car wake up the in-car assistant, the embodiment of the present application can imperceptibly switch the corresponding voice speaker based on the identified current passenger information.

[0044] Therefore, the embodiments of the present application can automatically switch the voice speaker according to the gender, age and other characteristics of the occupants of the vehicle through technical means such as camera face recognition, thereby improving the user experience and enhancing the level of intelligence of human-computer interaction.

[0045] Optionally, in one embodiment of the present application, based on passenger information and a preset weighted scoring mechanism, a target voice speaker is determined, and interaction data of at least one target function in the current vehicle is obtained, and a voice broadcast operation is performed by the target voice speaker according to the interaction data, including: obtaining the number of users and the total number of users of each voice speaker in a preset voice speaker database, and calculating the popularity corresponding to each voice speaker based on the number of users and the total number of users; determining the gender weight, age weight and popularity weight of the target passenger according to the weighted scoring mechanism; calculating the pronunciation score of each voice speaker based on the gender weight, age weight and popularity weight, so as to sort each voice speaker in descending order according to the pronunciation score to obtain a sorted list; and sending the sorted list to the on-board terminal of the current vehicle, so that the target passenger can audition the voice speakers in the sorted list to determine the target voice speaker.

[0046] It should be noted that the embodiment of the present application maintains a database containing speaker characteristics of different genders, ages, etc., and each speaker is accompanied by his or her voice sample and metadata (gender, age range, etc.); the embodiment of the present application can be based on the gender and age range of the passenger information of each passenger obtained as above, and combined with a weighted scoring mechanism. When the genders are the same, the item is 100 points, and if they are different, it is 0 points; when the ages are the same, the item is 100 points, and if there is a difference of 1 year, 1 point is subtracted; the popularity is calculated based on the number of users and the total number of users of the speaker. The higher the proportion of users to the total number of users, the higher the popularity; among them, the weights of gender and age matching and the popularity of the speaker are 0.3, 0.3, and 0.4, respectively.

[0047] According to the above rules, the embodiment of the present application can calculate the scores of all speakers in the database and display them in a descending order list for users to select and audition and set their preferred speakers, as shown in Table 1:

[0048] Table 1

[0049] Pronounced by gender age Popularity A male 30 22 B female 6 10 C male 10 3 D female 18 15 E male 20 20 F female 30 30

[0050] As shown in Table 1, assuming that the embodiment of the present application has 6 built-in speakers, if the vehicle camera recognizes a male person around 25 years old, the score of speaker A is 100*0.3+(100-(30-25))*0.3+22*0.4=67.3, and the scores of all speakers are shown in Table 2:

[0051] Table 2

[0052] Pronounced by Gender score Age score Popularity score Overall rating A male 30 22 67.3 B female 6 10 28.3 C male 10 3 56.7 D female 18 15 33.9 E male 20 20 66.5 F female 30 30 40.5

[0053] The sorted list is obtained according to the score sorting, as shown in Table 3:

[0054] Table 3

[0055]

[0056]

[0057] Afterwards, the embodiment of the present application can display the speakers in order on the central control screen, and provide an audition function for the user to choose. When the user makes a selection, the user information is saved and bound to the speaker. If the user is not satisfied with the default displayed speakers, the embodiment of the present application can replace a batch of speakers for selection until a satisfactory speaker is selected. If the user wants to change the currently used speaker, he or she can also make a new selection.

[0058] Therefore, the embodiments of the present application automatically adjust the voice assistant's voice according to the specific characteristics of the passenger and combine it with advanced AI technology, so that it can autonomously learn passenger preferences, continuously optimize services, improve the level of intelligence, and provide more personalized voice services to increase user satisfaction.

[0059] According to the method for automatically switching the voice speaker based on the in-car personnel information proposed in the embodiment of the present application, the in-car voice broadcast function of the current vehicle is activated, and the facial image of the target passenger is obtained, and the facial image is processed for face recognition to obtain the passenger information of the target passenger; based on the passenger information and the preset weighted scoring mechanism, the target voice speaker is determined, and the interaction data of at least one target function in the current vehicle is obtained, and the voice broadcast operation is performed according to the interaction data by the target voice speaker; it is determined whether there are other passengers in the current vehicle to activate the in-car voice broadcast function, if there are other passengers activating the in-car voice broadcast function, the passenger information of other passengers is obtained, so as to determine a new target voice speaker according to the passenger information of other passengers, and the voice speaker is automatically switched by the new target voice speaker. The present application can automatically switch the voice speaker according to the characteristics of the gender, age, etc. of the in-car personnel, thereby improving the user experience and enhancing the intelligent level of human-computer interaction.

[0060] Secondly, a device for automatically switching a voice speaker based on in-vehicle occupant information according to an embodiment of the present application is described with reference to the accompanying drawings.

[0061] Figure 5 It is a block diagram of a device for automatically switching a voice speaker based on in-vehicle occupant information according to an embodiment of the present application.

[0062] like Figure 5As shown, the device 10 for automatically switching a voice speaker based on in-vehicle personnel information includes: a recognition module 100 , an acquisition module 200 and a switching module 300 .

[0063] The recognition module 100 is used to activate the vehicle-mounted voice broadcast function of the current vehicle, obtain the facial image of the target passenger, and perform face recognition processing on the facial image to obtain the passenger information of the target passenger.

[0064] The acquisition module 200 is used to determine the target voice speaker based on the passenger information and the preset weighted scoring mechanism, and obtain the interaction data of at least one target function in the current vehicle, and perform voice broadcast operations according to the interaction data through the target voice speaker.

[0065] The switching module 300 is used to determine whether there are other passengers in the current vehicle who have activated the in-vehicle voice broadcast function. If there are other passengers who have activated the in-vehicle voice broadcast function, the passenger information of the other passengers is obtained to determine a new target voice speaker based on the passenger information of the other passengers, and automatically switch the voice speaker through the new target voice speaker.

[0066] Optionally, in one embodiment of the present application, the identification module 100 includes: a judgment unit, a collection unit and an input unit.

[0067] Among them, the judgment unit is used to judge whether the target passenger has pre-set a fixed voice style speaker through the vehicle-mounted voice broadcast function. If the target passenger has pre-set a fixed voice style speaker, the fixed voice style speaker is used to perform the voice broadcast operation.

[0068] The acquisition unit is used to obtain the environmental information of the current vehicle if the target passenger has not pre-set a fixed voice style speaker, and determine the working status and voice broadcast parameters of the on-board camera of the current vehicle according to the environmental information, so as to call the on-board camera to acquire the facial image of the target passenger based on the working status and voice broadcast parameters of the on-board camera.

[0069] The input unit is used to input the facial image into a pre-trained face recognition model to output passenger information corresponding to the target passenger, wherein the passenger information includes the passenger's gender and the passenger's age.

[0070] Optionally, in one embodiment of the present application, the device 10 for automatically switching voice speakers based on in-vehicle occupant information of the embodiment of the present application also includes: a selection module, which is used to select a fixed voice style speaker from a preset fixed style voice library according to a preset multiple speaker options before using the fixed voice style speaker to perform a voice broadcast operation if the target passenger has pre-set a fixed voice style speaker, and store the fixed voice style speaker in the vehicle-mounted terminal.

[0071] Optionally, in one embodiment of the present application, the acquisition module 200 includes: a calculation unit, a determination unit, a sorting unit and an audition unit.

[0072] The calculation unit is used to obtain the number of users and the total number of users of each voice speaker in the preset voice speaker database, and calculate the popularity corresponding to each voice speaker based on the number of users and the total number of users.

[0073] A determination unit is used to determine the gender weight, age weight and popularity weight of the target passenger according to a weighted scoring mechanism.

[0074] The sorting unit is used to calculate the pronunciation score of each voice speaker based on the gender weight, age weight and popularity weight, so as to sort each voice speaker in descending order according to the pronunciation score to obtain a sorted list.

[0075] The audition unit is used to send the sorted list to the vehicle-mounted terminal of the current vehicle, so that the target passenger auditions the voice speakers in the sorted list to determine the target voice speaker.

[0076] It should be noted that the aforementioned explanation of the method embodiment for automatically switching the voice speaker based on the information of the people in the car is also applicable to the device for automatically switching the voice speaker based on the information of the people in the car in this embodiment, and will not be repeated here.

[0077] According to the device for automatically switching the voice speaker based on the information of the people in the car proposed in the embodiment of the present application, it includes a recognition module for activating the vehicle-mounted voice broadcast function of the current vehicle, and obtaining the facial image of the target passenger, and performing face recognition processing on the facial image to obtain the passenger information of the target passenger; an acquisition module for determining the target voice speaker based on the passenger information and a preset weighted scoring mechanism, and obtaining the interactive data of at least one target function in the current vehicle, and performing a voice broadcast operation according to the interactive data by the target voice speaker; a switching module for judging whether there are other passengers in the current vehicle to activate the vehicle-mounted voice broadcast function, if there are other passengers activating the vehicle-mounted voice broadcast function, then obtaining the passenger information of other passengers, so as to determine a new target voice speaker according to the passenger information of other passengers, and automatically switching the voice speaker by the new target voice speaker. The present application can automatically switch the voice speaker according to the characteristics of the gender, age, etc. of the people in the car, thereby improving the user experience and enhancing the intelligent level of human-computer interaction.

[0078] Figure 6 A schematic diagram of the structure of a vehicle provided in an embodiment of the present application. The vehicle may include:

[0079] A memory 601 , a processor 602 , and a computer program stored in the memory 601 and executable on the processor 602 .

[0080] When the processor 602 executes the program, the method for automatically switching the voice speaker based on the in-vehicle occupant information provided in the above embodiment is implemented.

[0081] Furthermore, the vehicle also includes:

[0082] The communication interface 603 is used for communication between the memory 601 and the processor 602 .

[0083] The memory 601 is used to store computer programs that can be executed on the processor 602 .

[0084] The memory 601 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0085] If the memory 601, the processor 602 and the communication interface 603 are implemented independently, the communication interface 603, the memory 601 and the processor 602 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 6 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0086] Optionally, in a specific implementation, if the memory 601, the processor 602 and the communication interface 603 are integrated on a chip, the memory 601, the processor 602 and the communication interface 603 can communicate with each other through an internal interface.

[0087] The processor 602 may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0088] An embodiment of the present application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above method of automatically switching the voice speaker based on the information of the people in the vehicle.

[0089] An embodiment of the present application also provides a computer program product, including a computer program, which, when executed, is used to implement the above-mentioned method of automatically switching the voice speaker based on the information of the people in the car.

[0090] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0091] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0092] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or N executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0093] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or N wirings (electronic devices), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways as necessary and then storing it in a computer memory.

[0094] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above embodiment, the N steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. If implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0095] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0096] In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0097] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present application. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A method for automatically switching voice speakers based on in-vehicle personnel information, characterized in that: The following steps are involved: Activate the in-vehicle voice broadcast function of the current vehicle, obtain a facial image of a target passenger, and perform face recognition processing on the facial image to obtain passenger information of the target passenger; Based on the passenger information and a preset weighted scoring mechanism, a target voice speaker is determined, and interaction data of at least one target function in the current vehicle is obtained, and a voice broadcast operation is performed by the target voice speaker according to the interaction data; Determine whether there are other passengers in the current vehicle who have activated the in-vehicle voice broadcast function. If there are other passengers who have activated the in-vehicle voice broadcast function, obtain the passenger information of the other passengers, determine a new target voice speaker based on the passenger information of the other passengers, and perform an automatic voice speaker switching operation through the new target voice speaker.

2. The method according to claim 1, characterized in that The activating the vehicle-mounted voice broadcast function of the current vehicle, acquiring the facial image of the target passenger, and performing face recognition processing on the facial image to acquire the passenger information of the target passenger includes: Determining whether the target passenger has set a fixed voice style speaker in advance through the vehicle-mounted voice broadcast function, and if the target passenger has set the fixed voice style speaker in advance, performing the voice broadcast operation using the fixed voice style speaker; If the target passenger has not set the fixed voice style speaker in advance, then obtain the environmental information of the current vehicle, and determine the working state of the vehicle-mounted camera and the voice broadcast parameters of the current vehicle according to the environmental information, so as to call the vehicle-mounted camera to collect the facial image of the target passenger based on the working state of the vehicle-mounted camera and the voice broadcast parameters; The facial image is input into a pre-trained face recognition model to output passenger information corresponding to the target passenger, wherein the passenger information includes passenger gender and passenger age.

3. The method according to claim 2, characterized in that If the target passenger pre-sets the fixed voice style speaker, before using the fixed voice style speaker to perform the voice broadcast operation, the method further includes: A fixed voice style speaker is selected from a preset fixed style voice library according to the preset multiple speaker options, and the fixed voice style speaker is stored in the vehicle terminal.

4. The method according to claim 2, characterized in that: The method of determining a target voice speaker based on the passenger information and a preset weighted scoring mechanism, acquiring interaction data of at least one target function in the current vehicle, and performing a voice broadcast operation according to the interaction data by the target voice speaker includes: Obtain the number of users and the total number of users of each voice speaker in a preset voice speaker database, and calculate the popularity corresponding to each voice speaker according to the number of users and the total number of users; Determining the gender weight, age weight and popularity weight of the target passenger according to the weighted scoring mechanism; Calculating the pronunciation score of each voice speaker based on the gender weight, the age weight and the popularity weight, and sorting each voice speaker in descending order according to the pronunciation score to obtain a sorted list; The sorted list is sent to the vehicle-mounted terminal of the current vehicle, so that the target passenger auditions the voice speakers in the sorted list to determine the target voice speaker.

5. A device for automatically switching voice speakers based on in-vehicle personnel information, characterized in that: include: The recognition module is used to activate the vehicle-mounted voice broadcast function of the current vehicle, obtain the facial image of the target passenger, and perform face recognition processing on the facial image to obtain the passenger information of the target passenger; An acquisition module, used to determine a target voice speaker based on the passenger information and a preset weighted scoring mechanism, and to acquire interaction data of at least one target function in the current vehicle, and to perform a voice broadcast operation through the target voice speaker according to the interaction data; The switching module is used to determine whether there are other passengers in the current vehicle who activate the in-vehicle voice broadcast function. If there are other passengers who activate the in-vehicle voice broadcast function, the passenger information of the other passengers is obtained to determine a new target voice speaker based on the passenger information of the other passengers, and the voice speaker is automatically switched through the new target voice speaker.

6. The device according to claim 5, characterized in that The identification module comprises: a judgment unit, used for judging whether the target passenger has preset a fixed voice style speaker through the vehicle-mounted voice broadcast function, and if the target passenger has preset the fixed voice style speaker, performing the voice broadcast operation using the fixed voice style speaker; A collection unit, for obtaining environmental information of the current vehicle if the target passenger has not preset the fixed voice style speaker, and determining the working state of the vehicle-mounted camera and the voice broadcast parameters of the current vehicle according to the environmental information, so as to call the vehicle-mounted camera to collect the facial image of the target passenger based on the working state of the vehicle-mounted camera and the voice broadcast parameters; An input unit is used to input the facial image into a pre-trained face recognition model to output passenger information corresponding to the target passenger, wherein the passenger information includes the passenger's gender and passenger age.

7. The device according to claim 5, characterized in that Also includes: A selection module is used to select a fixed voice style speaker from a preset fixed style voice library according to a preset multiple speaker options before using the fixed voice style speaker to perform a voice broadcast operation if the target passenger pre-sets the fixed voice style speaker, and store the fixed voice style speaker in the vehicle-mounted terminal.

8. A vehicle, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method for automatically switching a voice speaker based on in-vehicle occupant information as described in any one of claims 1 to 4.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement the method for automatically switching the voice speaker based on the in-vehicle occupant information as described in any one of claims 1 to 4.

10. A computer program product, comprising a computer program, characterized in that The computer program is executed to implement the method for automatically switching the voice speaker based on the in-vehicle occupant information as described in any one of claims 1 to 4.

Images