CN115953996A - A method and device for generating natural language based on in-vehicle user information - Google Patents

Abstract

The present application discloses a method and device for generating natural language based on in-vehicle user information. The method for generating natural language based on in-vehicle user information includes: acquiring the voice information of the occupants in the vehicle; acquiring the basic information of the occupants in the vehicle; The voice information of the people in the vehicle obtains the template information to be played; the natural language information to be played is generated according to the template information to be played and the slot information to be played. The method for generating natural language based on in-vehicle user information provided by this application obtains the slot information to be played according to the basic information of the in-vehicle personnel, thereby generating different natural voice information to be played according to different basic information of the in-vehicle personnel, so that Voice interaction is more user-friendly.

Description

A method and device for generating natural language based on in-vehicle user information

technical field

The present application relates to the technical field of vehicle human-computer interaction, and in particular to a method for generating natural language based on in-vehicle user information and a device for generating natural language based on in-vehicle user information.

Background technique

At present, the general use of natural language generation only considers the voice interaction initiator for natural language generation. However, in the vehicle usage scenario, there are situations where multiple users use the same cockpit at the same time. The existing technology cannot realize the problem of considering the specific conditions of multiple users in the process of voice interaction, and performing natural language generation according to the specific conditions of different users.

Therefore, it is desirable to have a technical solution to solve or at least alleviate the above-mentioned deficiencies of the prior art.

Contents of the invention

The purpose of the present invention is to provide a method for generating natural language based on in-vehicle user information to at least solve one of the above technical problems.

The present invention provides following scheme:

According to one aspect of the present invention, a method for generating natural language based on in-vehicle user information is provided, and the method for generating natural language based on in-vehicle user information includes:

Obtain the voice information of the people in the car;

Get the basic information of the people in the car;

Obtain the slot information to be played according to the voice information of the personnel in the vehicle;

Obtain template information to be played according to the basic information of the personnel in the vehicle and the voice information of the personnel in the vehicle;

Generate natural language information to be played according to the to-be-played template information and the to-be-played slot information.

Optionally, said obtaining the slot information to be played according to the voice information of the personnel in the vehicle includes:

Analyzing the voice information of the people in the vehicle to obtain semantic information;

Judging whether to generate natural language information to be played according to the semantic analysis information, if so, then

Obtain slot information to be played based on semantic information.

Optionally, the obtaining basic information of people in the vehicle includes:

Obtain the pressure information transmitted by the pressure sensor on each seat in the car;

Obtain the number of people in the car according to the pressure information.

Optionally, the obtaining basic information of people in the vehicle includes:

Obtain the in-vehicle image information captured by the in-vehicle camera device;

Identify the image information to obtain the basic information of the occupants in the vehicle.

Optionally, the basic information about people in the vehicle includes number information, face image information and age information of people.

Optionally, the acquiring the template information to be played according to the basic information of the personnel in the vehicle and the voice information of the personnel in the vehicle includes:

Acquiring a preset template database, the preset template database including at least two preset templates and preset personnel conditions, one preset template corresponding to one preset personnel condition;

Judging whether the obtained personnel number information, personnel facial image information and personnel age information conform to a preset personnel condition in the preset template database, if so, then

Obtain the preset template corresponding to the preset personnel condition that meets the preset conditions as the template information to be played.

Optionally, the method for generating natural language based on in-vehicle user information further includes:

Acquiring a preset face database, the preset face database including at least one preset face information;

Perform the following operations for each person's face image information:

Carry out similarity calculation between the obtained person's face image information and each preset face information, so as to obtain the similarity value;

Determine whether there is a similarity value greater than the preset threshold, if so, then

Judging whether there is more than one face and face feature information whose similarity value is greater than a preset threshold in each face feature information, if not, then

Obtaining a preset special voice bank, the preset special voice bank includes at least one preset special voice type and preset face information, one preset special voice type corresponds to one preset face information;

Obtaining a preset special voice type corresponding to preset face information whose similarity value is greater than a preset threshold;

The to-be-played natural language information is announced through the preset special voice type.

Optionally, the method for generating natural language based on in-vehicle user information further includes:

Judging whether there is more than one face and face feature information with a similarity value greater than a preset threshold in each face feature information, if so, then

Obtaining a personnel relationship graph, the personnel relationship graph includes at least two personnel name information and preset face information, wherein one personnel name information has a priority relationship with at least one other personnel name information except itself, and one The person name information corresponds to a preset face information;

Acquiring the preset face information corresponding to the face feature information whose similarity value is greater than the preset threshold in each face feature information;

Respectively obtain the person name information corresponding to each preset face information;

Judging whether there is a priority relationship between the obtained personnel name information, if so, then

Obtain the preset special voice type corresponding to the preset face information corresponding to the name information of the person with a high priority relationship;

The to-be-played natural language information is announced through the preset special voice type.

Optionally, before broadcasting the natural language information to be played through the preset special voice type, the method for generating natural language based on in-vehicle user information further includes:

Get sleep recognition classifier;

Obtaining facial image information of each of the persons;

Extract the feature information in the facial image information of each person;

Inputting each of the characteristic information into the sleep recognition classifier respectively, so as to obtain classification labels, the classification labels including sleep labels;

When there is a classification label as a sleep label, get the volume information of the current system broadcast voice;

Determine whether the volume information exceeds the preset volume threshold, and if so, then

Decreasing the volume information below the preset volume threshold and broadcasting the to-be-played natural language information.

The present application also provides a device for generating natural language based on in-vehicle user information, the device for generating natural language based on in-vehicle user information includes:

The voice information acquisition module of the personnel in the vehicle, the voice information acquisition module of the personnel in the vehicle is used to obtain the voice information of the personnel in the vehicle;

The basic information acquisition module of the personnel in the vehicle, the basic information acquisition module of the personnel in the vehicle is used to obtain the basic information of the personnel in the vehicle;

The slot information acquisition module to be played, the slot information acquisition module to be played is used to acquire the slot information to be played according to the voice information of the personnel in the vehicle;

A template information acquisition module to be played, the template information acquisition module to be played is used to obtain the template information to be played according to the basic information of the personnel in the vehicle and the voice information of the personnel in the vehicle;

A to-be-played natural language information generating module, the to-be-played natural language information generating module is used to generate to-be-played natural language information according to the to-be-played template information and the to-be-played slot information.

The method for generating natural language based on in-vehicle user information provided by this application obtains the slot information to be played according to the basic information of the in-vehicle personnel, thereby generating different natural voice information to be played according to different basic information of the in-vehicle personnel, so that Voice interaction is more user-friendly.

Description of drawings

Fig. 1 is a flowchart of a method for generating natural language based on in-vehicle user information provided by one or more embodiments of the present invention.

Fig. 2 is a structural block diagram of an electronic device of a method for generating natural language based on in-vehicle user information provided by one or more embodiments of the present invention.

FIG. 3 is a schematic diagram of template information to be played in the method for generating natural language based on in-vehicle user information shown in FIG. 1 .

Detailed ways

The technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Apparently, the described embodiments are some of the embodiments of the present invention, but not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

Fig. 1 is a flowchart of a method for generating natural language based on in-vehicle user information provided by one or more embodiments of the present invention.

The method for generating natural language based on in-vehicle user information as shown in Figure 1 includes:

Step 1: Get the voice information of the people in the car;

Step 2: Get the basic information of the people in the car;

Step 3: Obtain the slot information to be played according to the voice information of the personnel in the vehicle;

Step 4: Obtain the template information to be played according to the basic information of the personnel in the vehicle and the voice information of the personnel in the vehicle;

Step 5: Generate natural language information to be played according to the template information to be played and the slot information to be played.

The method for generating natural language based on in-vehicle user information provided by this application obtains the slot information to be played according to the basic information of the in-vehicle personnel, thereby generating different natural voice information to be played according to different basic information of the in-vehicle personnel, so that Voice interaction is more user-friendly.

In this embodiment, obtaining the slot information to be played according to the voice information of the personnel in the vehicle includes:

Analyze the voice information of people in the car to obtain semantic information;

Judging whether to generate natural language information to be played according to the semantic analysis information, if so, then

Obtain slot information to be played based on semantic information.

In one embodiment, obtaining the basic information of people in the vehicle includes:

Obtain the pressure information transmitted by the pressure sensor on each seat in the car;

Obtain the number of people in the car according to the pressure information.

It can be known by the pressure sensor which seats are occupied by people. In this embodiment, an in-vehicle camera can also be set. There can be multiple in-vehicle cameras. One in-vehicle camera is used to capture the image of a person in front of a seat. In this way, after obtaining which seats are occupied, the image information of the persons on the seats can be obtained by turning on the corresponding camera device.

In this embodiment, obtaining the basic information of people in the vehicle includes:

Obtain the in-vehicle image information captured by the in-vehicle camera device;

Identify the image information to obtain the basic information of the occupants in the vehicle.

In this embodiment, the pressure sensor is not used to detect the condition of the seat, but each camera device is directly turned on to capture image information inside the vehicle, and the basic information of the occupants in the vehicle is obtained through image recognition.

In this embodiment, the basic information about people in the vehicle includes information about the number of people, information about facial images of people, and information about the age of people.

In this embodiment, the information on the number of people can be identified and acquired through each image captured by the camera device. For example, a face image classifier can be used to determine whether each image has a human face. Quantity can know the number of personnel information.

After the facial image information of each person is obtained, the features of the facial image information of each person can be extracted, and then input into a preset trained age classifier, so as to obtain the age information of each person.

In this embodiment, obtaining the template information to be played according to the basic information of the personnel in the vehicle and the voice information of the personnel in the vehicle includes:

Acquiring a preset template database, the preset template database including at least two preset templates and preset personnel conditions, one preset template corresponding to one preset personnel condition;

Judging whether the obtained personnel number information, personnel facial image information and personnel age information conform to a preset personnel condition in the preset template database, if so, then

Obtain the preset template corresponding to the preset personnel condition that meets the preset conditions as the template information to be played.

In this embodiment, the method for generating natural language based on in-vehicle user information further includes:

Acquiring a preset face database, the preset face database including at least one preset face information;

Perform the following operations for each person's face image information:

Carry out similarity calculation between the obtained person's face image information and each preset face information, so as to obtain the similarity value;

Determine whether there is a similarity value greater than the preset threshold, if so, then

Judging whether there is more than one face and face feature information whose similarity value is greater than a preset threshold in each face feature information, if not, then

Obtaining a preset special voice bank, the preset special voice bank includes at least one preset special voice type and preset face information, one preset special voice type corresponds to one preset face information;

Obtaining a preset special voice type corresponding to preset face information whose similarity value is greater than a preset threshold;

The to-be-played natural language information is announced through the preset special voice type.

In this way, on the one hand, the basic information of each person in the car is considered, and on the other hand, the situation of some special characters is also considered. For example, there are some children who often ride in the car, and the children like a certain special voice. Type, for example like the dubbing of Doraemon, at this time, when performing the natural language information to be played, it is necessary to reflect the natural language information to be played by preset special voice type (such as the voice of Doraemon's dubbing).

In this embodiment, the method for generating natural language based on in-vehicle user information further includes:

Judging whether there is more than one face and face feature information with a similarity value greater than a preset threshold in each face feature information, if so, then

Obtaining a personnel relationship graph, the personnel relationship graph includes at least two personnel name information and preset face information, wherein one personnel name information has a priority relationship with at least one other personnel name information except itself, and one The person name information corresponds to a preset face information;

Acquiring the preset face information corresponding to the face feature information whose similarity value is greater than the preset threshold in each face feature information;

Respectively obtain the person name information corresponding to each preset face information;

Judging whether there is a priority relationship between the obtained personnel name information, if so, then

Obtain the preset special voice type corresponding to the preset face information corresponding to the name information of the person with a high priority relationship;

The to-be-played natural language information is announced through the preset special voice type.

In some cases, there may be multiple special persons. At this time, it is determined which preset special voice type to use according to the relationship between each special person. , the priority of the child is relatively high. It is understandable that the priority relationship can be set according to the situation.

In this embodiment, before broadcasting the natural language information to be played through the preset special voice type, the method for generating natural language based on in-vehicle user information further includes:

Get sleep recognition classifier;

Obtaining facial image information of each of the persons;

Extract the feature information in the facial image information of each person;

Inputting each of the characteristic information into the sleep recognition classifier respectively, so as to obtain classification labels, the classification labels including sleep labels;

When there is a classification label as a sleep label, get the volume information of the current system broadcast voice;

Determine whether the volume information exceeds the preset volume threshold, and if so, then

Decreasing the volume information below the preset volume threshold and broadcasting the to-be-played natural language information.

In some cases, the sound that may be played may wake up the sleeping child. At this time, by this method, the sound can be played with a softer sound as much as possible.

The present application will be further described in detail below by way of examples, and it should be understood that the examples do not constitute any limitation to the present application.

In this example, the scenario where music needs to be played is used as an example. It can be understood that this application can also be applied to other interactive scenarios, such as navigation, etc., which will not be repeated here.

In the scene where music needs to be played, methods for generating natural language based on user information in the car include:

Step 1: Obtain the voice information of the people in the car; in this embodiment, the voice information of the people in the car is: play the song Singing the Motherland.

Step 2: Get the basic information of the people in the car. In this embodiment, the basic information of the people in the car is: there are 3 people in the car. The basic information of the people in the car is obtained through image recognition: the driver is a male, and his age is an adult People (18 to 30 years old), the co-pilot position is female (18 to 30 years old), the age is adults, the rear seat is male, and the age is children (6 to 10 years old). It can be understood that the above-mentioned age can be obtained through an age classifier, and details will not be described here.

Step 3: Obtain the slot information to be played according to the voice information of the people in the car, specifically, analyze the voice information of the people in the car to obtain semantic information;

Judging whether to generate natural language information to be played according to the semantic analysis information, if so, then

The slot information to be played is obtained according to the semantic information. In this embodiment, the semantic information is to play and sing about the motherland, and the slot information to be played is to sing about the motherland.

Step 4 obtains the template information to be played according to the basic information of the personnel in the vehicle and the voice information of the personnel in the vehicle. In this embodiment, obtaining the template information to be played according to the basic information of the personnel in the vehicle and the voice information of the personnel in the vehicle includes:

Acquiring a preset template database, the preset template database including at least two preset templates and preset personnel conditions, one preset template corresponding to one preset personnel condition;

Judging whether the obtained personnel number information, personnel facial image information and personnel age information conform to a preset personnel condition in the preset template database, if so, then

Obtain the preset template corresponding to the preset personnel condition that meets the preset conditions as the template information to be played.

Referring to FIG. 3 , in this embodiment, assuming that the preset personnel condition is: a user whose age characteristic is a child, the generated template information to be played is: children, let's listen.

It is understandable that the preset personnel conditions can be set in many ways, as shown in Figure 3, if there are multiple people, it can be the template 4 in Figure 3, if it is other conditions, it can also be other corresponding templates, it is understandable Yes, when multiple preset personnel conditions are met, you can also select by priority. For example, the template with children is the highest priority template, and the multi-person template is the second priority template. In this way, set the Priority, so that when obtaining templates, obtain the template with the highest priority.

Step 5: Generate natural language information to be played according to the template information to be played and the slot information to be played, and the generated slot information to be played is: children, let us listen and the slot information to be played sings the combination of the motherland, thereby Generate natural language information to be played: children, let's listen to singing about the motherland.

In this embodiment, the to-be-played natural language information includes to-be-played template information (TTSID (PlayMusic)) and slot information (SongName, Singer). The content included in the natural language information to be played belongs to the prior art, and will not be repeated here.

After the natural language information to be played is generated, it is also necessary to consider what type of voice is used for broadcasting. At this time, judge according to the faces of the people in the vehicle, specifically, obtain a preset face database, and the preset It is assumed that the face database includes at least one preset face information;

Perform the following operations for each person's face image information:

Carry out similarity calculation between the obtained person's face image information and each preset face information, so as to obtain the similarity value;

Determine whether there is a similarity value greater than the preset threshold, if so, then

Judging whether there is more than one face and face feature information whose similarity value is greater than a preset threshold in each face feature information, if not, then

Obtaining a preset special voice bank, the preset special voice bank includes at least one preset special voice type and preset face information, one preset special voice type corresponds to one preset face information;

Obtaining a preset special voice type corresponding to preset face information whose similarity value is greater than a preset threshold;

The to-be-played natural language information is announced through the preset special voice type.

For example, taking the above-mentioned three people as an example, if the child's face image information is the same as the preset face information in the preset face database, it means that the child has been registered in the preset face database. At this time, It has a preset special voice type, for example, the voice type of Doraemon. At this time, the to-be-played natural language information is broadcast through the preset special voice type.

In this embodiment, when broadcasting, it is also considered whether other passengers are sleeping, for example, the female among the three people is sleeping, at this time, the sound should be lowered.

The present application also provides a device for generating natural language based on in-vehicle user information. The device for generating natural language based on in-vehicle user information includes a voice information acquisition module for in-vehicle personnel, an acquisition module for basic information about in-vehicle personnel, and a slot to be played. Bit information acquisition module, template information acquisition module to be played and natural language information generation module to be played, wherein,

The voice information acquisition module of the personnel in the vehicle is used to obtain the voice information of the personnel in the vehicle; the basic information acquisition module of the personnel in the vehicle is used to obtain the basic information of the personnel in the vehicle; the slot information acquisition module to be played is used to obtain the voice information of the personnel in the vehicle to be played Slot information; the template information acquisition module to be played is used to obtain the template information to be played according to the basic information of the personnel in the car and the voice information of the personnel in the vehicle; the natural language information generation module to be played is used to obtain the template information to be played according to the template information to be played and the Describe the slot information to be played to generate natural language information to be played.

Fig. 2 is a structural block diagram of an electronic device provided by one or more embodiments of the present invention.

As shown in Figure 2, the present application also discloses an electronic device, including: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory complete communication with each other through the communication bus; There is a computer program which, when executed by the processor, causes the processor to perform the steps of the method of generating natural language based on in-vehicle user information.

The present application also provides a computer-readable storage medium, which stores a computer program executable by an electronic device, and when the computer program runs on the electronic device, the electronic device executes the steps of the method for generating natural language based on in-vehicle user information .

The communication bus mentioned in the above-mentioned electronic device may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (Extended Industry Standard Architecture, EISA) bus or the like. The communication bus can be divided into an address bus, a data bus, a control bus, and the like. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

An electronic device includes a hardware layer, an operating system layer running on the hardware layer, and an application layer running on the operating system. The hardware layer includes hardware such as a central processing unit (CPU, Central Processing Unit), a memory management unit (MMU, Memory Management Unit) and memory. The operating system can be any one or more computer operating systems that realize electronic device control through processes, for example, Linux operating system, Unix operating system, Android operating system, iOS operating system, or windows operating system. And in the embodiment of the present invention, the electronic device may be a handheld device such as a smart phone or a tablet computer, or may be an electronic device such as a desktop computer or a portable computer, which is not particularly limited in the embodiment of the present invention.

The execution subject of electronic device control in the embodiment of the present invention may be an electronic device, or a functional module in the electronic device that can call a program and execute the program. The electronic device can obtain the firmware corresponding to the storage medium. The firmware corresponding to the storage medium is provided by the supplier. The firmware corresponding to different storage media may be the same or different, which is not limited here. After the electronic device obtains the firmware corresponding to the storage medium, it may write the firmware corresponding to the storage medium into the storage medium, specifically burn the firmware corresponding to the storage medium into the storage medium. The process of burning the firmware into the storage medium can be realized by using the existing technology, and will not be repeated in the embodiment of the present invention.

The electronic device can also obtain a reset command corresponding to the storage medium. The reset command corresponding to the storage medium is provided by the supplier. The reset commands corresponding to different storage media can be the same or different, which is not limited here.

At this time, the storage medium of the electronic device is the storage medium in which the corresponding firmware is written, and the electronic device can respond to the reset command corresponding to the storage medium in the storage medium in which the corresponding firmware is written, so that the electronic device can The reset command resets the storage medium in which the corresponding firmware is written. The process of resetting the storage medium according to the reset command can be implemented in the prior art, and will not be described in detail in this embodiment of the present invention.

For the convenience of description, when describing the above devices, the functions are divided into various units and modules and described separately. Of course, when implementing the present application, the functions of each unit and module can be implemented in one or more software and/or hardware.

Those skilled in the art can understand that, unless otherwise defined, all terms (including technical terms and scientific terms) used herein have the same meaning as commonly understood by those of ordinary skill in the art to which this invention belongs. It should also be understood that terms, such as those defined in commonly used dictionaries, should be understood to have meanings consistent with the meanings in the context of the prior art, and will not be used in an idealized or overly formal sense unless specifically defined to explain.

For the method embodiment, for the sake of simple description, it is expressed as a series of action combinations, but those skilled in the art should know that the embodiment of the present invention is not limited by the described action order, because according to the embodiment of the present invention , certain steps may be performed in other order or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification belong to preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.

It can be known from the above description of the implementation manners that those skilled in the art can clearly understand that the present application can be implemented by means of software plus a necessary general-purpose hardware platform. Based on this understanding, the essence of the technical solution of this application or the part that contributes to the prior art can be embodied in the form of software products, and the computer software products can be stored in storage media, such as ROM/RAM, disk , optical disc, etc., including several instructions to make a computer device (which may be a personal computer, server or network device, etc.) execute the methods described in various embodiments or some parts of the embodiments of this application.

Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present invention, rather than limiting them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: It is still possible to modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the technical solutions of the various embodiments of the present invention. scope.

Claims (10)

1. A method for generating natural language based on in-vehicle user information, characterized in that, the method for generating natural language based on in-vehicle user information comprises: Obtain the voice information of the people in the car; Get the basic information of the people in the car; Obtain the slot information to be played according to the voice information of the personnel in the vehicle; Obtain template information to be played according to the basic information of the personnel in the vehicle and the voice information of the personnel in the vehicle; Generate natural language information to be played according to the to-be-played template information and the to-be-played slot information. 2. the method for generating natural language based on user information in the car as claimed in claim 1, is characterized in that, described according to the personnel voice information in the car to obtain the slot information to be played comprises: Analyzing the voice information of the people in the vehicle to obtain semantic information; Judging whether to generate natural language information to be played according to the semantic analysis information, if so, then Obtain slot information to be played based on semantic information. 3. the method for generating natural language based on user information in the car according to claim 2, is characterized in that, described acquisition basic information of personnel in the car comprises: Obtain the pressure information transmitted by the pressure sensor on each seat in the car; Obtain the number of people in the vehicle according to the pressure information. 4. the method for generating natural language based on user information in the car according to claim 2, is characterized in that, described acquisition basic information of personnel in the car comprises: Obtain the in-vehicle image information captured by the in-vehicle camera device; Identify the image information to obtain the basic information of the occupants in the vehicle. 5. The method for generating natural language based on in-vehicle user information as claimed in claim 4, wherein the basic information about the occupants in the vehicle includes information on the number of persons, information on facial images of persons, and information on the age of persons. 6. the method for generating natural language based on user information in the car as claimed in claim 5, is characterized in that, described according to the basic information of the people in the car and the voice information of the people in the car to obtain the template information to be played comprises: Acquiring a preset template database, the preset template database including at least two preset templates and preset personnel conditions, one preset template corresponding to one preset personnel condition; Judging whether the obtained personnel number information, personnel facial image information and personnel age information conform to a preset personnel condition in the preset template database, if so, then Obtain the preset template corresponding to the preset personnel condition that meets the preset conditions as the template information to be played. 7. The method for generating natural language based on in-vehicle user information as claimed in claim 6, wherein the method for generating natural language based on in-vehicle user information further comprises: Acquiring a preset face database, the preset face database including at least one preset face information; Perform the following operations for each person's face image information: Carry out similarity calculation between the obtained person's face image information and each preset face information, so as to obtain the similarity value; Determine whether there is a similarity value greater than the preset threshold, if so, then Judging whether there is more than one face and face feature information whose similarity value is greater than a preset threshold in each face feature information, if not, then Obtaining a preset special voice bank, the preset special voice bank includes at least one preset special voice type and preset face information, one preset special voice type corresponds to one preset face information; Obtaining a preset special voice type corresponding to preset face information whose similarity value is greater than a preset threshold; The to-be-played natural language information is announced through the preset special voice type. 8. The method for generating natural language based on in-vehicle user information as claimed in claim 7, wherein the method for generating natural language based on in-vehicle user information further comprises: Judging whether there is more than one face and face feature information with a similarity value greater than a preset threshold in each face feature information, if so, then Obtaining a personnel relationship graph, the personnel relationship graph includes at least two personnel name information and preset face information, wherein one personnel name information has a priority relationship with at least one other personnel name information except itself, and one The person name information corresponds to a preset face information; Acquiring the preset face information corresponding to the face feature information whose similarity value is greater than the preset threshold in each face feature information; Respectively obtain the person name information corresponding to each preset face information; Judging whether there is a priority relationship between the obtained personnel name information, if so, then Obtain the preset special voice type corresponding to the preset face information corresponding to the name information of the person with a high priority relationship; The to-be-played natural language information is announced through the preset special voice type. 9. The method for generating natural language based on in-vehicle user information as claimed in claim 8, wherein, before the broadcast of the natural language information to be played through the preset special voice type, the The method for generating natural language from user information in the vehicle further includes: Get a sleep recognition classifier; Acquiring facial image information of each of the persons; Extract the feature information in the facial image information of each person; Inputting each of the characteristic information into the sleep recognition classifier respectively, so as to obtain classification labels, the classification labels including sleep labels; When there is a classification label as a sleep label, get the volume information of the current system broadcast voice; Determine whether the volume information exceeds the preset volume threshold, and if so, then Decreasing the volume information below the preset volume threshold and broadcasting the to-be-played natural language information. 10. A device for generating natural language based on in-vehicle user information, characterized in that the device for generating natural language based on in-vehicle user information comprises: The voice information acquisition module of the personnel in the vehicle, the voice information acquisition module of the personnel in the vehicle is used to obtain the voice information of the personnel in the vehicle; The basic information acquisition module of the personnel in the vehicle, the basic information acquisition module of the personnel in the vehicle is used to obtain the basic information of the personnel in the vehicle; The slot information acquisition module to be played, the slot information acquisition module to be played is used to acquire the slot information to be played according to the voice information of the personnel in the vehicle; A template information acquisition module to be played, the template information acquisition module to be played is used to obtain the template information to be played according to the basic information of the personnel in the vehicle and the voice information of the personnel in the vehicle; A to-be-played natural language information generating module, the to-be-played natural language information generating module is used to generate to-be-played natural language information according to the to-be-played template information and the to-be-played slot information.

Images