Music playing method, device and equipment based on driving scene information

Abstract

The application discloses a music playing method, device and equipment based on driving scene information, comprising: acquiring in-vehicle scene information; when the in-vehicle scene information meets preset quiet environment conditions, determining the volume of to-be-played music as a low volume, and determining the music type of the to-be-played music as a music type matched with the in-vehicle scene information; when the in-vehicle scene does not meet the quiet environment conditions, determining the volume of the to-be-played music as a volume greater than the low volume, acquiring out-of-vehicle scene information, and determining the music type of the to-be-played music as a music type matched with the out-of-vehicle scene information; and controlling a vehicle-mounted entertainment device to play music according to the determined volume and music type. The embodiment of the application can adjust the music playing volume based on driving scene information and recommend music suitable for the current scene to the user, and the user experience is high.

Description

Technical Field

[0001] This invention relates to the field of vehicle control technology, and in particular to a music playback method, apparatus, and device based on driving scenario information. Background Technology

[0002] With the rapid growth of the national economy, various vehicles have been put into use, greatly improving people's transportation conditions. However, at the same time, the large amount of exhaust gas emitted by fuel engines has polluted the environment. Against the backdrop of environmental protection departments advocating green and environmentally friendly practices, electric vehicles for various purposes have emerged.

[0003] Electric vehicles are becoming increasingly intelligent and multifunctional, allowing users to request music to be played from the car's central control system while driving. However, current central control systems can only play the music requested by the user, and cannot adjust the music volume based on the user's situation or recommend suitable music. Summary of the Invention

[0004] This invention provides a music playback method, apparatus, and device based on driving scenario information to solve the problem that existing technologies cannot adjust music playback volume according to the user's scenario and recommend suitable music. This invention can adjust music playback volume based on driving scenario information and recommend music suitable for the current scenario to the user, resulting in a high user experience.

[0005] To achieve the above objectives, embodiments of the present invention provide a music playback method based on driving scenario information, including: Obtain in-vehicle scene information; When the in-vehicle scene information meets the preset quiet environment conditions, the volume of the music to be played is determined to be low, and the music type of the music to be played is determined to be a music type that matches the in-vehicle scene information. When the in-vehicle scene does not meet the quiet environment conditions, the volume of the music to be played is determined to be greater than the low volume, and the external scene information is obtained to determine the music type of the music to be played to be a music type that matches the external scene information. Control the in-vehicle entertainment system to play music at a set volume and music type.

[0006] As an improvement to the above solution, the acquisition of in-vehicle scene information includes: The video footage taken inside the vehicle is obtained through the vehicle's in-vehicle camera; The in-vehicle video is identified to obtain in-vehicle scene information.

[0007] As an improvement to the above solution, the quiet environmental conditions include at least one of the following: The interior light intensity is less than the preset light intensity threshold. The in-car volume is lower than the preset volume threshold; The duration for which passengers' eyes are closed exceeds a preset time threshold; The vehicle contains office equipment, and the office equipment is in operation. There is office equipment inside the vehicle, and the overlapping area between the office equipment and the hands of the passengers inside the vehicle is greater than a preset overlap area threshold.

[0008] As an improvement to the above solution, the acquisition of external scene information includes: Videos taken from outside the vehicle are captured by external cameras; The external video is identified to obtain external scene information.

[0009] As an improvement to the above solution, the step of recognizing the external video to obtain external scene information includes: Extract several image frames and audio information from the external video; All the image frames are input into the first sub-network of the preset scene recognition model for image recognition to obtain the image features of each image frame; The audio information is input into the second sub-network of the scene recognition model for audio analysis to obtain the audio features of the audio information; The image features and audio features are aligned according to time nodes and then input into the main network of the scene recognition model for comprehensive analysis to obtain the vehicle exterior scene information.

[0010] As an improvement to the above solution, the external scene information includes at least: location information, weather information, and holiday information.

[0011] As an improvement to the above solution, after determining that the music type of the music to be played is a music type that matches the vehicle exterior scene information, the music playback method based on driving scene information further includes: Obtain several keywords of the vehicle exterior scene information and the tags of each piece of music in the music library that matches the vehicle exterior scene information; The keywords are converted into vector form to obtain several first word vectors; the tags are converted into vector form to obtain several second word vectors. For each first word vector, calculate the cosine distance between the first word vector and each second word vector, and select the largest cosine distance from all the cosine distances. For each piece of music, calculate the average of all the largest cosine distances, and use the average value as the degree of matching between the music and the information of the scene outside the vehicle; The music in the music library that matches the external scene information is sorted in descending order of matching degree; Controlling the in-vehicle entertainment system to play music according to a predetermined volume and music genre includes: Control the in-vehicle entertainment system to play music in a predetermined order from high to low volume and matching degree.

[0012] As an improvement to the above solution, after controlling the in-vehicle entertainment device to play music at a determined volume and according to the determined music, the music playback method based on driving scenario information further includes: Acquire facial images of users inside the vehicle; The facial image is recognized to obtain facial expressions; The system analyzes the emotions of the users inside the car based on facial expressions. When the users' emotions are in a preset emotional state, the system controls the in-vehicle entertainment system to switch music.

[0013] To achieve the above objectives, embodiments of the present invention also provide a music playback device based on driving scenario information, comprising: The in-vehicle scene information acquisition module is used to acquire in-vehicle scene information; The first determining module is used to determine that the volume of the music to be played is low when the in-vehicle scene information meets the preset quiet environment conditions, and to determine that the music type of the music to be played is a music type that matches the in-vehicle scene information. The second determining module is used to determine that the volume of the music to be played is greater than the low volume when the in-vehicle scene does not meet the quiet environment conditions, and to obtain the external scene information to determine that the music type of the music to be played is a music type that matches the external scene information. The music playback module is used to control the in-vehicle entertainment system to play music according to a set volume and music type.

[0014] To achieve the above objectives, embodiments of the present invention also provide a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the music playback method based on driving scenario information as described above.

[0015] Compared with the prior art, the music playback method, apparatus, and device based on driving scenario information provided in this invention have the following beneficial effects: (1) When the in-vehicle scene information meets the quiet environment conditions, the volume mode and music type are determined first based on the in-vehicle scene information. When the in-vehicle scene information does not meet the quiet environment conditions, the out-of-vehicle scene information is obtained, the music type that matches the out-of-vehicle scene information is determined, and the music is played in the mid-high frequency mode. The music playback mode can be flexibly adjusted to better suit the driving scenario.

[0016] (2) Matching is performed in vector form, and the second word vector with the largest cosine distance to each first word vector and its corresponding largest cosine distance are selected. The average value of all the largest cosine distances in each piece of music is calculated, and the average value is used as the matching degree between the music and the external scene information to improve the matching accuracy.

[0017] (3) The first sub-network performs image recognition and the second sub-network performs audio analysis. The two networks cooperate to improve the analysis efficiency. At the same time, the image features and corresponding audio features of each image frame obtained by the analysis are aligned according to the time node and then input into the main network for comprehensive analysis to obtain the external scene information. In order to comprehensively analyze the image features and the corresponding time node audio features, the accuracy of external scene information recognition is improved. Attached Figure Description

[0018] Figure 1 This is a flowchart of a music playback method based on driving scenario information provided in an embodiment of the present invention; Figure 2 This is a structural block diagram of a music playback device based on driving scenario information provided in an embodiment of the present invention; Figure 3 This is a structural block diagram of a terminal device provided in an embodiment of the present invention. Detailed Implementation

[0019] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0020] See Figure 1 , Figure 1 This is a flowchart of a music playback method based on driving scenario information provided in an embodiment of the present invention. The music playback method based on driving scenario information includes: S1. Obtain in-vehicle scene information; S2. When the in-vehicle scene information meets the preset quiet environment conditions, determine that the volume of the music to be played is low, and determine that the music type of the music to be played is a music type that matches the in-vehicle scene information. S3. When the in-vehicle scene does not meet the quiet environment conditions, determine that the volume of the music to be played is greater than the low volume, and obtain the external scene information to determine that the music type of the music to be played is a music type that matches the external scene information. S4. Control the in-vehicle entertainment system to play music according to the determined volume and music type.

[0021] Understandably, during music playback or in response to a music playback command, the system acquires in-vehicle scene information. When the in-vehicle scene information meets the conditions for a quiet environment, it determines that the user in the vehicle needs a quiet environment. Therefore, it sets the volume of the music to be played to a low volume and determines that the music type of the music to be played is a music type that matches the in-vehicle scene information. This music type needs to be suitable for the current quiet environment and can be a music type that the user has pre-set to match the in-vehicle scene information, such as light music or sleep aids. No specific restrictions are made here.

[0022] When the in-vehicle scene information does not meet the quiet environment conditions, it is determined that the user does not require a quiet environment. External scene information is then acquired, a music type matching the external scene information is determined, and the music is played in a mid-to-high frequency mode. This embodiment of the invention, by combining in-vehicle and external scene information—i.e., driving scene information—flexibly adjusts the music playback mode to better suit driving scenarios.

[0023] In an optional embodiment, obtaining the in-vehicle scene information includes: The video footage taken inside the vehicle is obtained through the vehicle's in-vehicle camera; The in-vehicle video is identified to obtain in-vehicle scene information.

[0024] It is understood that, in this embodiment of the invention, the in-vehicle video is identified by a preset scene recognition model to obtain in-vehicle scene information.

[0025] In an alternative embodiment, the quiet environmental conditions include at least one of the following: The interior light intensity is less than the preset light intensity threshold. The in-car volume is lower than the preset volume threshold; The duration for which passengers' eyes are closed exceeds a preset time threshold; The vehicle contains office equipment, and the office equipment is in operation. There is office equipment inside the vehicle, and the overlapping area between the office equipment and the hands of the passengers inside the vehicle is greater than a preset overlap area threshold.

[0026] It is understandable that when the in-vehicle scene information indicates that someone is sleeping or working, and the in-vehicle scene information meets the preset quiet environment conditions, the music playback volume is determined to be in bass mode, and the music type is determined to be a music type that matches the in-vehicle scene information.

[0027] In an optional embodiment, acquiring the external scene information includes: Videos taken from outside the vehicle are captured by external cameras; The external video is identified to obtain external scene information.

[0028] In one optional embodiment, the step of recognizing the external video to obtain external scene information includes: Extract several image frames and audio information from the external video; All the image frames are input into the first sub-network of the preset scene recognition model for image recognition to obtain the image features of each image frame; The audio information is input into the second sub-network of the scene recognition model for audio analysis to obtain the audio features of the audio information; The image features and audio features are aligned according to time nodes and then input into the main network of the scene recognition model for comprehensive analysis to obtain the vehicle exterior scene information.

[0029] It is understood that the external video is identified through a preset scene recognition model to obtain external scene information. The scene recognition model consists of a main network and a first sub-network and a second sub-network. Specifically, multiple image frames of the external video stream are first extracted, and the multiple image frames are input into the first sub-network for image recognition to obtain the image features of each image frame. Then, the audio information of the external video stream is extracted, and the audio information is input into the second sub-network for audio analysis to obtain the audio features corresponding to the audio information. The image features and corresponding audio features of each image frame obtained from the analysis are aligned according to the time node and then input into the main network for comprehensive analysis to obtain the external scene information. This embodiment of the invention can improve the accuracy of external scene information recognition.

[0030] In one optional embodiment, the external scene information includes at least: location information, weather information, and holiday information.

[0031] It is understandable that the external scene information includes location information, weather information, holiday information, etc. The music content to be played is determined based on the external scene information. For example, if the external scene information indicates that the holiday is the Spring Festival, then music related to celebrating the Spring Festival will be played; if the external scene information indicates that the location is Chengdu, then the song "Chengdu" will be played.

[0032] For example, the external scene information has a priority. For instance, festival information has the highest priority, location information has the next highest priority, and weather information has the lowest priority. Specifically, festival information is analyzed first. If it is determined that the day is a festival, music for that festival is played. If not, the location information is analyzed to find music whose lyrics contain the location information and play it. If not, the weather information is analyzed and music that matches the weather information is played.

[0033] In an optional embodiment, after determining that the music type of the music to be played is a music type that matches the vehicle exterior scene information, the music playback method based on driving scene information further includes: Obtain several keywords of the vehicle exterior scene information and the tags of each piece of music in the music library that matches the vehicle exterior scene information; The keywords are converted into vector form to obtain several first word vectors; the tags are converted into vector form to obtain several second word vectors. For each first word vector, calculate the cosine distance between the first word vector and each second word vector, and select the largest cosine distance from all the cosine distances. For each piece of music, calculate the average of all the largest cosine distances, and use the average value as the degree of matching between the music and the information of the scene outside the vehicle; The music in the music library that matches the external scene information is sorted in descending order of matching degree; Controlling the in-vehicle entertainment system to play music according to a predetermined volume and music genre includes: Control the in-vehicle entertainment system to play music in a predetermined order from high to low volume and matching degree.

[0034] Understandably, once the music type matching the vehicle exterior scene information is determined, the music tracks included in that music type can be played sequentially based on their matching degree. Specifically, one or more keywords describing the vehicle exterior scene are extracted from the vehicle exterior scene information, and the tags of each song in that music type in the music library are obtained. These tags include the theme, lyrics, or song title of the music, etc. Each keyword is converted into a vector form to obtain multiple first word vectors, and each tag is also converted into a vector form to obtain multiple second word vectors. The cosine distance between each first word vector and each second word vector is calculated. The second word vector with the largest cosine distance to each first word vector and its corresponding maximum cosine distance are selected, and the average of all maximum cosine distances is calculated. This average value is used to reflect the matching degree between the vehicle exterior scene information and the music. These songs are sorted in descending order of matching degree, and the in-vehicle entertainment device is controlled to play music in descending order of volume and matching degree. For example, if the first word vector is a, b, c, and the second word vector of the music is A, B, C, D, assuming the cosine distances between a and each of A, B, C, and D are 30%, 40%, 50%, and 60%, respectively, then the second word vector with the largest cosine distance to a is D, with a maximum cosine distance of 60%. Similarly, assuming the second word vector with the largest cosine distance to b is A, with a maximum cosine distance of 60%; the second word vector with the largest cosine distance to c is D, with a maximum cosine distance of 80%; and the second word vector with the largest cosine distance to d is B, with a maximum cosine distance of 80%, then the average of all the maximum cosine distances for the music is... The average value is then used as the degree of matching between the music and the information of the scene outside the car.

[0035] In an optional embodiment, after controlling the in-vehicle entertainment device to play music at a determined volume and setting, the music playback method based on driving scenario information further includes: Acquire facial images of users inside the vehicle; The facial image is recognized to obtain facial expressions; The system analyzes the emotions of the users inside the car based on facial expressions. When the users' emotions are in a preset emotional state, the system controls the in-vehicle entertainment system to switch music.

[0036] It is understood that embodiments of the present invention can also collect facial images of users in the vehicle while playing music, call a preset expression recognition model to recognize the facial images, obtain facial expressions, analyze the emotions of users in the vehicle based on facial expressions, and when the emotions of users in the vehicle are expressed as disliking the target music, switch the music, for example, switch to music with a matching degree only lower than the currently playing music, and play it.

[0037] See Figure 2, Figure 2 This is a structural block diagram of a music playback device 10 based on driving scenario information provided in an embodiment of the present invention. The music playback device 10 based on driving scenario information includes: The in-vehicle scene information acquisition module 11 is used to acquire in-vehicle scene information; The first determining module 12 is used to determine that the volume of the music to be played is low when the in-vehicle scene information meets the preset quiet environment conditions, and to determine that the music type of the music to be played is a music type that matches the in-vehicle scene information. The second determining module 13 is used to determine that the volume of the music to be played is greater than the low volume when the in-vehicle scene does not meet the quiet environment conditions, and to obtain the external scene information and determine that the music type of the music to be played is a music type that matches the external scene information. The music playback module 14 is used to control the in-vehicle entertainment system to play music according to a determined volume and music type.

[0038] Optionally, obtaining the in-vehicle scene information includes: The video footage taken inside the vehicle is obtained through the vehicle's in-vehicle camera; The in-vehicle video is identified to obtain in-vehicle scene information.

[0039] Optionally, the quiet environmental conditions include at least one of the following: The interior light intensity is less than the preset light intensity threshold. The in-car volume is lower than the preset volume threshold; The duration for which passengers' eyes are closed exceeds a preset time threshold; The vehicle contains office equipment, and the office equipment is in operation. There is office equipment inside the vehicle, and the overlapping area between the office equipment and the hands of the passengers inside the vehicle is greater than a preset overlap area threshold.

[0040] Optionally, acquiring the external scene information includes: Videos taken from outside the vehicle are captured by external cameras; The external video is identified to obtain external scene information.

[0041] Optionally, the step of recognizing the external video to obtain external scene information includes: Extract several image frames and audio information from the external video; All the image frames are input into the first sub-network of the preset scene recognition model for image recognition to obtain the image features of each image frame; The audio information is input into the second sub-network of the scene recognition model for audio analysis to obtain the audio features of the audio information; The image features and audio features are aligned according to time nodes and then input into the main network of the scene recognition model for comprehensive analysis to obtain the vehicle exterior scene information.

[0042] Optionally, the external scene information includes at least: location information, weather information, and holiday information.

[0043] Optionally, the music playback device based on driving scenario information further includes: The keyword and tag acquisition module is used to acquire several keywords of the vehicle exterior scene information and the tags of each piece of music in the music library that matches the vehicle exterior scene information; The conversion module is used to convert the keywords into vector form to obtain several first word vectors; and to convert the tags into vector form to obtain several second word vectors. The cosine distance calculation module is used to calculate the cosine distance between each first word vector and each second word vector, and select the largest cosine distance from all the cosine distances. The matching degree calculation module is used to calculate the average of all the largest cosine distances for each piece of music, and use the average value as the matching degree between the music and the external scene information. The sorting module is used to sort the music in the music library that matches the music type of the vehicle exterior scene information in descending order of matching degree; Therefore, the music playback module is further used for: Control the in-vehicle entertainment system to play music in a predetermined order from high to low volume and matching degree.

[0044] Optionally, the music playback device based on driving scenario information further includes: The face image acquisition module is used to acquire face images of users inside the vehicle; A facial expression recognition module is used to recognize the facial image and obtain facial expressions; The music switching module is used to analyze the emotions of the users in the car based on facial expressions. When the users in the car are in a preset emotional state, the module controls the in-vehicle entertainment system to switch music.

[0045] It is worth noting that the working process of each module in the music playback device 10 based on driving scenario information described in the embodiments of the present invention can refer to the working process of the music playback method based on driving scenario information described in the above embodiments, and will not be repeated here.

[0046] This invention also provides a computer-readable storage medium, which includes a stored computer program; wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to perform the music playback method based on driving scenario information as described in the above embodiments.

[0047] See Figure 3 , Figure 3 This is a structural block diagram of a terminal device 20 provided in an embodiment of the present invention. The terminal device 20 includes: a processor 21, a memory 22, and a computer program stored in the memory 22 and executable on the processor 21. When the processor 21 executes the computer program, it implements the steps in the above-described embodiment of the music playback method based on driving scenario information. Alternatively, when the processor 21 executes the computer program, it implements the functions of each module / unit in the above-described device embodiments.

[0048] For example, the computer program may be divided into one or more modules / units, which are stored in the memory 22 and executed by the processor 21 to complete the present invention. The one or more modules / units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in the terminal device 20.

[0049] The terminal device 20 can be a desktop computer, laptop, handheld computer, cloud server, or other computing device. The terminal device 20 may include, but is not limited to, a processor 21 and a memory 22. Those skilled in the art will understand that the schematic diagram is merely an example of the terminal device 20 and does not constitute a limitation on the terminal device 20. It may include more or fewer components than shown, or combine certain components, or use different components. For example, the terminal device 20 may also include input / output devices, network access devices, buses, etc.

[0050] The processor 21 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor. The processor 21 is the control center of the terminal device 20, connecting all parts of the terminal device 20 via various interfaces and lines.

[0051] The memory 22 can be used to store the computer programs and / or modules. The processor 21 implements various functions of the terminal device 20 by running or executing the computer programs and / or modules stored in the memory 22 and calling the data stored in the memory 22. The memory 22 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the mobile phone (such as audio data, phonebook, etc.). In addition, the memory 22 may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0052] Wherein, if the modules / units integrated in the terminal device 20 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by the processor 21, it can implement the steps of the various method embodiments described above. Wherein, the computer program includes computer program code, which can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, portable hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc.

[0053] It should be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Furthermore, in the accompanying drawings of the device embodiments provided by this invention, the connection relationships between modules indicate that they have communication connections, which can be specifically implemented as one or more communication buses or signal lines. Those skilled in the art can understand and implement this without any creative effort.

[0054] Compared with the prior art, the music playback method, apparatus, and device based on driving scenario information provided in this invention have the following beneficial effects: (1) When the in-vehicle scene information meets the quiet environment conditions, the volume mode and music type are determined first based on the in-vehicle scene information. When the in-vehicle scene information does not meet the quiet environment conditions, the out-of-vehicle scene information is obtained, the music type that matches the out-of-vehicle scene information is determined, and the music is played in the mid-high frequency mode. The music playback mode can be flexibly adjusted to better suit the driving scenario.

[0055] (2) Matching is performed in vector form, and the second word vector with the largest cosine distance to each first word vector and its corresponding largest cosine distance are selected. The average value of all the largest cosine distances in each piece of music is calculated, and the average value is used as the matching degree between the music and the external scene information to improve the matching accuracy.

[0056] (3) The first sub-network performs image recognition and the second sub-network performs audio analysis. The two networks cooperate to improve the analysis efficiency. At the same time, the image features and corresponding audio features of each image frame obtained by the analysis are aligned according to the time node and then input into the main network for comprehensive analysis to obtain the external scene information. In order to comprehensively analyze the image features and the corresponding time node audio features, the accuracy of external scene information recognition is improved.

[0057] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A music playback method based on driving scenario information, characterized in that, include: Obtain in-vehicle scene information; When the in-vehicle scene information meets the preset quiet environment conditions, the volume of the music to be played is determined to be low, and the music type of the music to be played is determined to be a music type that matches the in-vehicle scene information. When the in-vehicle scene does not meet the quiet environment conditions, the volume of the music to be played is determined to be greater than the low volume, and the external scene information is obtained to determine the music type of the music to be played to be a music type that matches the external scene information. Control the in-vehicle entertainment system to play music according to the determined volume and music type; After determining that the music type of the music to be played is a music type that matches the vehicle exterior scene information, the music playback method based on driving scene information further includes: Obtain several keywords of the vehicle exterior scene information and the tags of each piece of music in the music library that matches the vehicle exterior scene information; The keywords are converted into vector form to obtain several first word vectors; the tags are converted into vector form to obtain several second word vectors. For each first word vector, calculate the cosine distance between the first word vector and each second word vector, and select the largest cosine distance from all the cosine distances. For each piece of music, calculate the average of all the largest cosine distances, and use the average value as the degree of matching between the music and the information of the scene outside the vehicle; The music in the music library that matches the external scene information is sorted in descending order of matching degree; Controlling the in-vehicle entertainment system to play music according to a predetermined volume and music genre includes: Control the in-vehicle entertainment system to play music in a predetermined order from high to low volume and matching degree.

2. The music playback method based on driving scenario information as described in claim 1, characterized in that, The acquisition of in-vehicle scene information includes: The video footage taken inside the vehicle is obtained through the vehicle's in-vehicle camera; The in-vehicle video is identified to obtain in-vehicle scene information.

3. The music playback method based on driving scenario information as described in claim 1, characterized in that, The quiet environmental conditions include at least one of the following: The interior light intensity is less than the preset light intensity threshold. The in-car volume is lower than the preset volume threshold; The duration for which passengers' eyes are closed exceeds a preset time threshold; The vehicle contains office equipment, and the office equipment is in operation. There is office equipment inside the vehicle, and the overlapping area between the office equipment and the hands of the passengers inside the vehicle is greater than a preset overlap area threshold.

4. The music playback method based on driving scenario information as described in claim 1, characterized in that, The acquisition of external scene information includes: Videos taken from outside the vehicle are captured by external cameras; The external video is identified to obtain external scene information.

5. The music playback method based on driving scenario information as described in claim 4, characterized in that, The step of recognizing the external video to obtain external scene information includes: Extract several image frames and audio information from the external video; All the image frames are input into the first sub-network of the preset scene recognition model for image recognition to obtain the image features of each image frame; The audio information is input into the second sub-network of the scene recognition model for audio analysis to obtain the audio features of the audio information; The image features and audio features are aligned according to time nodes and then input into the main network of the scene recognition model for comprehensive analysis to obtain the vehicle exterior scene information.

6. The music playback method based on driving scenario information as described in claim 1, characterized in that, The external scene information includes at least: location information, weather information, and holiday information.

7. The music playback method based on driving scenario information as described in claim 1, characterized in that, After controlling the in-vehicle entertainment system to play music at a determined volume and setting, the music playback method based on driving scenario information further includes: Acquire facial images of users inside the vehicle; The facial image is recognized to obtain facial expressions; The system analyzes the emotions of the users inside the car based on facial expressions. When the users' emotions are in a preset emotional state, the system controls the in-vehicle entertainment system to switch music.

8. A music playback device based on driving scenario information, characterized in that, include: The in-vehicle scene information acquisition module is used to acquire in-vehicle scene information; The first determining module is used to determine that the volume of the music to be played is low when the in-vehicle scene information meets the preset quiet environment conditions, and to determine that the music type of the music to be played is a music type that matches the in-vehicle scene information. The second determining module is used to determine that the volume of the music to be played is greater than the low volume when the in-vehicle scene does not meet the quiet environment conditions, and to obtain the external scene information to determine that the music type of the music to be played is a music type that matches the external scene information. The music playback module is used to control the in-vehicle entertainment system to play music according to a set volume and music type; The music playback device based on driving scenario information also includes: The keyword and tag acquisition module is used to acquire several keywords of the vehicle exterior scene information and the tags of each piece of music in the music library that matches the vehicle exterior scene information; The conversion module is used to convert the keywords into vector form to obtain several first word vectors; and to convert the tags into vector form to obtain several second word vectors. The cosine distance calculation module is used to calculate the cosine distance between each first word vector and each second word vector, and select the largest cosine distance from all the cosine distances. The matching degree calculation module is used to calculate the average of all the largest cosine distances for each piece of music, and use the average value as the matching degree between the music and the external scene information. The sorting module is used to sort the music in the music library that matches the music type of the vehicle exterior scene information in descending order of matching degree; Therefore, the music playback module is further used for: Control the in-vehicle entertainment system to play music in a predetermined order from high to low volume and matching degree.

9. A terminal device, characterized in that, The device includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor, when executing the computer program, implements the music playback method based on driving scenario information as described in any one of claims 1 to 7.

Images