Music recommendation method, device, vehicle and storage medium

Abstract

The present invention provides a music recommendation method, device, vehicle and storage medium. The method includes: obtaining real-time operation status information and camera data of a vehicle; determining the operation status label of the vehicle according to the real-time operation status information; determining the initial music recommendation strategy of the vehicle according to the operation status label and the music recommendation label corresponding to the operation status label; determining the driving scene correction coefficient of the initial music recommendation strategy according to the camera data; correcting the initial music recommendation strategy according to the driving scene correction coefficient, determining the target music recommendation strategy of the vehicle, and outputting a music recommendation playlist according to the target music recommendation strategy. The present invention can actively recommend music that matches the current operation status and driving scene of the vehicle to the user when the user is driving the vehicle, thereby meeting the user's need to listen to music while driving the vehicle, reducing vehicle safety risks, and improving the user's driving experience.

Description

Technical Field

[0001] The present invention relates to the field of vehicle-mounted multimedia technology, and in particular to a music recommendation method, device, vehicle and storage medium. Background Art

[0002] In recent years, with the continuous development of in-vehicle multimedia, the function of satisfying users' needs to listen to music while driving has gradually become an indispensable function in vehicles.

[0003] Currently, users usually listen to music while driving by selecting their favorite songs on their mobile phones connected to the car computer or in the car multimedia. However, this implementation method will distract the driver's attention and lead to vehicle safety risks. On the other hand, frequent selection will also bring a bad driving experience to users. Summary of the invention

[0004] The embodiments of the present invention provide a music recommendation method, device, vehicle and storage medium to solve the current problem that users may face vehicle safety risks and poor driving experience when listening to music while driving.

[0005] In a first aspect, an embodiment of the present invention provides a music recommendation method, comprising:

[0006] Obtain real-time operating status information and camera data of the vehicle;

[0007] Determining the running status label of the vehicle according to the real-time running status information;

[0008] Determining an initial music recommendation strategy for the vehicle according to the running status tag and the music recommendation tag corresponding to the running status tag;

[0009] Determining a driving scene correction coefficient of the initial music recommendation strategy according to the camera data;

[0010] The initial music recommendation strategy is corrected according to the driving scenario correction coefficient, and a target music recommendation strategy for the vehicle is determined, so as to output a music recommendation playlist according to the target music recommendation strategy.

[0011] In a possible implementation, the music recommendation method further includes:

[0012] Determining a user emotion correction coefficient of the initial music recommendation strategy based on the camera data;

[0013] The initial music recommendation strategy is modified according to the driving scene correction coefficient to determine a target music recommendation strategy for the vehicle, including:

[0014] The initial music recommendation strategy is modified according to the driving scenario correction coefficient and the user emotion correction coefficient to determine a target music recommendation strategy for the vehicle.

[0015] In a possible implementation, the music recommendation method further includes:

[0016] Get user attribute data;

[0017] Determining a user attribute correction coefficient of the initial music recommendation strategy according to the user attribute data;

[0018] The initial music recommendation strategy is modified according to the driving scene correction coefficient to determine a target music recommendation strategy for the vehicle, including:

[0019] Correcting the initial music recommendation strategy according to the driving scenario correction coefficient and the user attribute correction coefficient to determine a target music recommendation strategy for the vehicle;

[0020] Alternatively, the initial music recommendation strategy is corrected according to the driving scene correction coefficient, the user emotion correction coefficient and the user attribute correction coefficient to determine the target music recommendation strategy for the vehicle.

[0021] In a possible implementation, determining the running status label of the vehicle according to the real-time running status information includes:

[0022] Determining the frequency of change of the operating state of the vehicle according to the real-time operating state information;

[0023] The running state label of the vehicle is determined according to the changing frequency of the running state of the vehicle.

[0024] In a possible implementation, the real-time running status information includes real-time vehicle speed information, real-time gear position information and real-time rotation speed information;

[0025] Determining the running state label of the vehicle according to the change frequency of the running state of the vehicle includes:

[0026] Determine the current speed range of the vehicle and the change in speed according to the real-time vehicle speed information;

[0027] Determine the target speed label of the vehicle according to the speed change frequency, the current speed range of the vehicle, the speed change amount and the preset speed label table;

[0028] Determine the target gear label of the vehicle according to the gear change frequency of the vehicle, the current speed range of the vehicle and the preset gear label table;

[0029] Determining a target speed label of the vehicle according to the real-time speed information and a preset speed label table;

[0030] The running state label of the vehicle is determined according to the target vehicle speed label, the target gear position label and the target rotation speed label.

[0031] In a possible implementation, determining the user emotion correction coefficient of the initial music recommendation strategy according to the camera data includes:

[0032] Acquire the vehicle exterior landscape information and the user emotion information according to the camera data;

[0033] A user emotion correction coefficient of the initial music recommendation strategy is determined according to the vehicle exterior landscape information and the user emotion information.

[0034] In a possible implementation, the user attribute data includes user characteristic attribute data, user behavior attribute data and user social attribute data;

[0035] Determining a user attribute correction coefficient of the initial music recommendation strategy according to the user attribute data includes:

[0036] Determining the user's music preference according to the user characteristic attribute data, the user behavior attribute data and the user social attribute data;

[0037] According to the user's music preference, a user attribute correction coefficient of the initial music recommendation strategy is determined.

[0038] In a second aspect, an embodiment of the present invention provides a music recommendation device, including:

[0039] An acquisition module is used to obtain the real-time running status information and camera data of the vehicle;

[0040] A first processing module, configured to determine an operation status label of a vehicle according to the real-time operation status information;

[0041] A second processing module, configured to determine an initial music recommendation strategy for the vehicle according to the running state tag and the music recommendation tag corresponding to the running state tag;

[0042] A third processing module, configured to determine a driving scene correction coefficient of the initial music recommendation strategy according to the camera data;

[0043] The music recommendation module is used to correct the initial music recommendation strategy according to the driving scenario correction coefficient, determine the target music recommendation strategy of the vehicle, and output a music recommendation playlist according to the target music recommendation strategy.

[0044] In a third aspect, an embodiment of the present invention provides a vehicle, comprising a control device, wherein the control device comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the method described in the first aspect or any possible implementation of the first aspect are implemented.

[0045] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method described in the first aspect or any possible implementation method of the first aspect are implemented.

[0046] The embodiment of the present invention provides a music recommendation method, device, vehicle and storage medium. By acquiring the real-time running status information and camera data of the vehicle, the running status label of the vehicle can be determined according to the real-time running status information, and the initial music recommendation strategy of the vehicle can be determined according to the running status label and the music recommendation label corresponding to the running status label; then the driving scene correction coefficient of the initial music recommendation strategy can be determined according to the camera data, and the initial music recommendation strategy can be corrected according to the driving scene correction coefficient to determine the target music recommendation strategy of the vehicle, so as to output the music recommendation playlist according to the target music recommendation strategy. Therefore, when the user is driving the vehicle, the user does not need to make a selection, and the music matching the current running status and driving scene of the vehicle is actively recommended to the user, thereby satisfying the user's driving mood and emotional needs in different driving scenes based on the recommended music, reducing the vehicle safety risk and improving the user's driving experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0048] Figure 1 is a flow chart of an implementation of a music recommendation method provided by an embodiment of the present invention;

[0049] Figure 2 is a flowchart of an implementation of a music recommendation method provided by another embodiment of the present invention;

[0050] Figure 3 is a flowchart of an implementation of a music recommendation method provided by another embodiment of the present invention;

[0051] Figure 4 is a structural diagram of a music recommendation device provided by an embodiment of the present invention;

[0052] Figure 5 Schematic diagram of a control device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0053] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present invention.

[0054] In order to make the purpose, technical solutions and advantages of the present invention more clear, specific embodiments will be described below in conjunction with the accompanying drawings.

[0055] See also Figure 1 , which shows a flowchart of the implementation of the music recommendation method provided by an embodiment of the present invention, and is described in detail as follows:

[0056] In step 101, real-time operating status information and camera data of the vehicle are obtained.

[0057] The real-time running status information of the vehicle may include the real-time speed information, real-time gear information, real-time speed information, etc. The running status information of the vehicle may be obtained based on sensors and other devices on the vehicle. The camera data of the vehicle may include data obtained by a driving recorder on the vehicle or other cameras that obtain the environment outside the vehicle.

[0058] In this embodiment, obtaining the real-time operating status information of the vehicle facilitates the subsequent recommendation of different music to the user based on the different operating states of the vehicle. For example, when the vehicle speed and gear position change quickly, more exciting music is recommended to the user, and when the vehicle speed is stable, more soothing music is recommended to the user, and so on. Acquiring camera data facilitates the determination of the driving scene of the vehicle based on the external environment corresponding to the camera data, for example, combining the data about the external environment in the camera data to determine whether the vehicle is currently in a driving scene of intense driving, leisure travel, or daily commuting. On this basis, the driving scene of the vehicle and the operating state of the vehicle can be mutually corrected, so as to actively recommend the music that the user wants to listen to while driving, and improve the success rate of music recommendation.

[0059] In step 102, the operating status label of the vehicle is determined according to the real-time operating status information.

[0060] The vehicle's operating status label can distinguish different operating states of the vehicle. The operating status labels corresponding to different operating status information can be determined by big data, classification models, learning models, or calibration tests.

[0061] Since different operating states of the vehicle can represent different driving moods and emotional needs of the user driving the vehicle, after obtaining the vehicle's operating state label, various operating state labels can be matched with their corresponding music recommendation labels to obtain the corresponding music recommendation strategy.

[0062] Optionally, determining the vehicle's operating status tag based on the real-time operating status information may include:

[0063] According to the real-time operation status information, the frequency of change of the operation status of the vehicle is determined; according to the frequency of change of the operation status of the vehicle, the operation status label of the vehicle is determined.

[0064] Among them, the frequency of change is the number of times the variable changes in a unit time. The frequency of change of the vehicle's operating state can further distinguish different operating states of the vehicle. For example, the faster the frequency of change of the vehicle's operating state, that is, the more times the vehicle's operating state changes in a unit time, the more intense the vehicle's operating state is, and the user is more likely to be in driving scenes such as intense driving and violent driving. The slower the frequency of change of the vehicle's operating state, that is, the fewer times the vehicle's operating state changes in a unit time, the more stable the vehicle's operating state is, and the user is more likely to be in driving scenes such as stable driving and fatigue driving. Therefore, determining different operating state labels for vehicles based on different change frequencies is conducive to more accurately determining a music recommendation strategy that suits the user's mood in combination with the vehicle's operating state label.

[0065] For example, the process of determining the vehicle operation status label according to the change frequency of the vehicle operation status can also be determined by big data, classification model, learning model or calibration test, etc. Alternatively, different vehicle operation status labels can be determined according to the different change frequencies of vehicle speed, gear position and speed, after the change frequencies of vehicle speed, gear position and speed are determined based on the real-time vehicle speed, real-time gear position and real-time speed, etc., according to a preset operation status label table determined in advance.

[0066] Optionally, the real-time operating status information includes real-time vehicle speed information, real-time gear information and real-time rotation speed information.

[0067] Determining the vehicle's operating status label according to the frequency of change of the vehicle's operating status may include:

[0068] According to the real-time vehicle speed information, the vehicle's current speed range and the speed change are determined. According to the speed change frequency, the vehicle's current speed range, the speed change and the preset speed label table, the vehicle's target speed label is determined.

[0069] The target gear label of the vehicle is determined according to the frequency of gear changes of the vehicle, the current speed range of the vehicle and the preset gear label table.

[0070] The target speed label of the vehicle is determined based on the real-time speed information and the preset speed label table.

[0071] The running state label of the vehicle is determined according to the target vehicle speed label, the target gear position label and the target rotation speed label.

[0072] Among them, in combination with the actual operation of the vehicle, when the real-time vehicle speed information, real-time gear information and real-time speed information are used as the real-time operation information of the vehicle, not only the frequency of change of the vehicle speed and the frequency of change of the gear are different, but also the operation state of the vehicle is different. The current speed range of the vehicle, the amount of change of the vehicle speed each time it changes (i.e. the amount of change of the vehicle speed), the real-time speed information of the vehicle, etc. all have an impact on the operation state of the vehicle. Therefore, based on the impact of various influencing factors on the operation state of the vehicle, a preset vehicle speed label table, a preset gear label table and a preset speed label table can be obtained in advance to determine different target labels based on different label tables.

[0073] Exemplarily, as shown in Tables 1 to 3, when the real-time vehicle speed is 50 km / h, the change ratio (i.e., the amount of change each time the vehicle speed changes) is 5 km / h, and the number of changes in the vehicle speed (i.e., the frequency of changes) is 1, the vehicle speed label is A02. When the real-time vehicle speed is 50 km / h and the number of changes in the gear position (i.e., the frequency of changes) is 3 times, the gear position label is B01. When the difference between the real-time speed and the speed at the last acquisition time is greater than 1200 rpm, the speed label is C01. The vehicle's operating status is characterized by combining the three aspects of vehicle speed, gear position, and speed, and the vehicle's operating status label is A02 / B01 / C01. Among them, the numerical values ​​and label values ​​in Tables 1 to 3 are only examples, and this embodiment does not limit the specific form of the label and the specific values ​​of the classified labels.

[0074] Table 1 Preset vehicle speed label table

[0075]

[0076] Table 2 Preset gear position label table

[0077]

[0078] Table 3 Preset speed label table

[0079] Speed ​​change rate >1200rpm <1200rpm Value / Tag Vn-Vn-1 ● C01 Vn+1-Vn ● C02

[0080] In step 103, an initial music recommendation strategy for the vehicle is determined based on the running status tag and the music recommendation tag corresponding to the running status tag.

[0081] Among them, the music recommendation tag or music tag is a tag that characterizes the fixed attributes of songs such as music genres and singers. It can be imported through third-party music software. Since the operating status tag can correspond to the different driving moods and emotional needs of users driving the vehicle, and the music tag can reflect the emotions expressed by different songs based on music genres, singers, etc. Therefore, based on the connection between the two, the operating status tag and the music recommendation tag can be corresponded, and the initial music recommendation strategy of the vehicle can be determined based on the operating status tag and the music recommendation tag after determining the corresponding relationship. Exemplarily, the maximum song range or the minimum song range or the middle song range corresponding to the operating status tag and the music recommendation tag can be determined as the initial music recommendation strategy of the vehicle.

[0082] In addition to matching the running status tags and music recommendation tags based on their connection, the running status tags and music recommendation tags can also be initialized separately in the data center, and the association between the running status tags and music recommendation tags can be set to form multiple recommendation strategy lines (i.e., initial music recommendation strategies). Alternatively, the music content features can be extracted in multiple dimensions through the explicit tag recognition algorithm, and strategy matching can be performed on both the vehicle's running status tag combination and the music tag combination.

[0083] Among them, a single music track can be associated one-to-many through the music tag, forming an indirect association between the vehicle's operating status tag and the music track.

[0084] For example, according to the running state tag and the music recommendation tag corresponding to the running state tag, the initial music recommendation strategy of the vehicle can be determined as shown in Table 4. Among them, the beats per minute (BPM), timbre / instrumentation, rhythm / tonality, genre, etc. are the tags of fixed attributes of the song or music tags.

[0085] Table 4 Initial music recommendation strategy table

[0086]

[0087] In step 104, a driving scene correction coefficient of the initial music recommendation strategy is determined based on the camera data.

[0088] The camera data may include the vehicle exterior environment information obtained by cameras such as a driving recorder, such as the vehicle exterior landscape information, etc. Different vehicle exterior landscape information may correspond to different driving scenarios. Based on the impact of the driving scenario on each label in the music label, the correction coefficient of different driving scenarios may be determined, that is, the driving scenario correction coefficient of the initial music recommendation strategy.

[0089] For example, the vehicle exterior landscape information may include cities (buildings, sunrise and sunset city skylines, traffic lights and zebra crossings) and outdoors (mountains, grasslands, lakes, forests), etc. Driving scenes may include intense driving, leisure travel, daily commuting, etc. This embodiment does not limit the specific driving scenes.

[0090] In step 105, the initial music recommendation strategy is corrected according to the driving scenario correction coefficient, and the target music recommendation strategy of the vehicle is determined, so as to output a music recommendation playlist according to the target music recommendation strategy.

[0091] Exemplarily, the initial music recommendation strategy is corrected according to the driving scenario correction coefficient, and the target music recommendation strategy of the vehicle is determined as shown in Table 5. After the target music recommendation strategy is obtained, the BPM, timbre / instrumentation, rhythm / tonality, and genre under the strategy can be used to associate and filter the music library, output the music (music recommendation playlist) and play it on the vehicle side.

[0092] Table 5. Revised target music recommendation strategy and output music recommendation playlist

[0093]

[0094]

[0095] Optionally, after correcting the initial music recommendation strategy according to the driving scenario correction coefficient and determining the target music recommendation strategy for the vehicle, and outputting the music recommendation playlist according to the target music recommendation strategy, the vehicle's instrument style can be switched in a linked manner based on the output music recommendation playlist, and the vehicle can be decelerated and braked and the SOS signal can be triggered under extreme conditions of the vehicle and driver, thereby achieving the linkage between people and vehicles and amplifying and optimizing the driving experience.

[0096] The embodiment of the present invention obtains the real-time running status information and camera data of the vehicle, and determines the running status label of the vehicle according to the real-time running status information, and determines the initial music recommendation strategy of the vehicle according to the running status label and the music recommendation label corresponding to the running status label, and can use the real-time running status information of the vehicle such as vehicle speed, rotation speed, gear information as the basis for switching the in-vehicle music recommendation; on this basis, according to the camera data, the driving scene correction coefficient of the initial music recommendation strategy is determined, and the initial music recommendation strategy is corrected according to the driving scene correction coefficient, and the target music recommendation strategy of the vehicle is determined, so as to output the music recommendation playlist according to the target music recommendation strategy. Therefore, when the user is driving the vehicle, the driving scene is judged in combination with the camera data, and songs of different styles are automatically recommended according to the user's driving scene and the running status of the vehicle, without the user making a selection, and the user's driving mood and emotional needs in different driving scenes are actively met, thereby reducing the vehicle safety risk and optimizing and improving the user's driving experience.

[0097] Figure 2 The following is a flowchart of a music recommendation method according to another embodiment of the present invention, which also considers the influence of user emotions on music recommendation results.

[0098] In step 201, real-time operating status information and camera data of the vehicle are obtained.

[0099] In step 202, the operating status label of the vehicle is determined according to the real-time operating status information.

[0100] In step 203, an initial music recommendation strategy for the vehicle is determined based on the running status tag and the music recommendation tag corresponding to the running status tag.

[0101] In step 204, the driving scene correction coefficient and the user emotion correction coefficient of the initial music recommendation strategy are determined based on the camera data.

[0102] In step 205, the initial music recommendation strategy is corrected according to the driving scenario correction coefficient and the user emotion correction coefficient, and the target music recommendation strategy of the vehicle is determined, so as to output a music recommendation playlist according to the target music recommendation strategy.

[0103] Among them, step 201 to step 203 are similar to the above-mentioned step 101 to step 104, and will not be repeated here.

[0104] In step 204, the driving scene correction coefficient and the user emotion correction coefficient of the initial music recommendation strategy are determined based on the camera data. At this time, the camera data includes not only the data collected by the camera for obtaining the external environment of the vehicle, such as the driving recorder, but also the facial expression information of the driver and the occupant obtained by the driver monitoring system (DMS) or the driver monitoring system (OMS), so as to determine the emotion of the driver / occupant (such as sadness, happiness, anger, etc.) based on the facial expression information of the driver / occupant. And the corresponding user emotion correction coefficient is determined based on the influence of different emotions on each label in the music label.

[0105] Optionally, determining a user emotion correction coefficient of an initial music recommendation strategy based on camera data may include: obtaining exterior landscape information and user emotion information based on camera data; and determining a user emotion correction coefficient of an initial music recommendation strategy based on the exterior landscape information and user emotion information.

[0106] In this embodiment, in addition to directly determining the user emotion correction coefficient based on the emotions obtained by the DMS camera / OMS camera, the user emotion correction coefficient of the initial music recommendation strategy can also be determined by combining the vehicle exterior landscape information obtained by cameras such as a driving recorder that obtain the exterior environment of the vehicle.

[0107] Exemplarily, the initial music recommendation strategy is modified according to the driving scenario correction coefficient and the user emotion correction coefficient, and the target music recommendation strategy for the vehicle is determined as shown in Table 6.

[0108] Table 6 Modified target music recommendation strategy and output music recommendation playlist

[0109]

[0110]

[0111] The embodiment of the present invention uses the vehicle's real-time operating status information such as vehicle speed, rotation speed, gear information as the basis for switching in-vehicle music recommendation, and corrects the initial music recommendation strategy according to the driving scene correction coefficient and user emotion correction coefficient of the initial music recommendation strategy, determines the vehicle's target music recommendation strategy, and outputs a music recommendation playlist according to the target music recommendation strategy. When the user is driving the vehicle, the driving scene and user emotion can be judged in combination with the camera data, and songs of different styles can be automatically recommended according to the user's driving scene, user emotion and vehicle operating status, without the user making a selection, so as to more accurately meet the user's driving mood and emotional needs in different driving scenarios, thereby reducing vehicle safety risks and optimizing and improving the user's driving experience.

[0112] Figure 3 The following is a flowchart of a music recommendation implementation provided by another embodiment of the present invention, wherein the method also considers the influence of user attributes on the music recommendation results. The details are as follows:

[0113] In step 301, the real-time operating status information, camera data and user attribute data of the vehicle are obtained.

[0114] In step 302, the operating status label of the vehicle is determined according to the real-time operating status information.

[0115] In step 303, an initial music recommendation strategy for the vehicle is determined based on the running status tag and the music recommendation tag corresponding to the running status tag.

[0116] In step 304, a driving scene correction coefficient and a user emotion correction coefficient of the initial music recommendation strategy are determined based on the camera data.

[0117] In step 305, the user attribute correction coefficient of the initial music recommendation strategy is determined based on the user attribute data.

[0118] In step 306, the initial music recommendation strategy is corrected according to the driving scene correction coefficient and the user attribute correction coefficient to determine the target music recommendation strategy of the vehicle; or the initial music recommendation strategy is corrected according to the driving scene correction coefficient, the user emotion correction coefficient and the user attribute correction coefficient to determine the target music recommendation strategy of the vehicle, so as to output a music recommendation playlist according to the target music recommendation strategy.

[0119] In step 301, in addition to obtaining the real-time running status information and camera data of the vehicle, user attribute data is also obtained. The user attribute data may include data such as the user's age and gender, and the user attribute data may be obtained through the DMS camera / OMS camera. After obtaining the user attribute data through the DMS camera / OMS camera, the owner's account information may also be read to correct the user attribute data recognized by the DMS camera.

[0120] Steps 302 to 304 correspond to the above-mentioned steps 202 to 204 and will not be described in detail here.

[0121] In step 305, the user attribute correction coefficient of the initial music recommendation strategy is determined based on the user attribute data.

[0122] Among them, due to different user attributes (such as age, gender), different favorite music styles, and different corresponding music labels. Therefore, the music styles preferred by different user attributes can be determined through big data, classification models, learning models or calibration experiments, and then the user attribute correction coefficient of the initial music recommendation strategy can be determined based on the music styles preferred by different user attributes.

[0123] Optionally, determining a user attribute correction coefficient for an initial music recommendation strategy based on user attribute data may include: determining a user's music preference based on user characteristic attribute data, user behavior attribute data, and user social attribute data; and determining a user attribute correction coefficient for an initial music recommendation strategy based on the user's music preference.

[0124] Among them, user characteristic attribute data can be obtained by introducing external user attributes to confirm the user portrait, which defines the user characteristics and is then used by the user model to infer the recommended music interest preferences.

[0125] In addition, user behavior attribute data and user social attribute data can be obtained by linking the user data of the car enterprise APP background, and reading the behavior, social attribute and other data related to the user to determine their potential music interests. For example, QQ Music provides the content tag information related to the user's music, including a large amount of recommendation basis information that has been provided, and this recommendation basis information can be used as one of the historical data sources for music recommendations.

[0126] In this embodiment, since the user's music preference is determined from several aspects, including user characteristic attribute data, user behavior attribute data, and user social attribute data, based on the music preference, the proportion / playback weight of a certain style of music in the initial music recommendation strategy can be increased, and the proportion / playback weight of another style of music in the initial music recommendation strategy can be reduced. That is, the user attribute correction coefficient of the initial music recommendation strategy is determined according to the user's music preference.

[0127] In this embodiment, before the vehicle leaves the factory, the initial music recommendation strategy can be corrected only according to the driving scene correction coefficient. When the vehicle leaves the factory and a portion of user-related data is accumulated, such as user characteristic attribute data, user behavior attribute data, and user social attribute data, the initial music recommendation strategy can be corrected or updated based on the feedback information of the user's use of the vehicle's music recommendation system, so as to improve the success rate of music recommendation based on the corrected or updated target music recommendation strategy and further enhance the user experience.

[0128] In the process of revising or updating the target music recommendation strategy, it is also possible to obtain unstructured tags such as song keywords co-created by users, and use crawlers and NLP technology to extract "keywords" such as common adjectives, sentences, nouns, etc. that are often used when each song is mentioned from user comments, and set different weights for these keywords, so as to quantify which songs are similar songs in the eyes of car owners.

[0129] In this embodiment, the priority of the user emotion correction coefficient and the user attribute correction coefficient can also be set, so that after the initial music recommendation strategy of the vehicle is determined according to the operating status label and the music recommendation label corresponding to the operating status label, the initial music recommendation strategy can be corrected by the user emotion correction coefficient and the user attribute correction coefficient in order of priority.

[0130] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0131] The following is an embodiment of the device of the present invention. For details not described in detail therein, reference may be made to the corresponding method embodiment described above.

[0132] Figure 4 The structure diagram of the music recommendation device provided by the embodiment of the present invention is shown. For the convenience of description, only the part related to the embodiment of the present invention is shown, which is described in detail as follows:

[0133] like Figure 4 As shown, the music recommendation device includes: an acquisition module 41, a first processing module 42, a second processing module 43, a third processing module 44 and a music recommendation module 45.

[0134] The acquisition module 41 is used to acquire the real-time running status information and camera data of the vehicle.

[0135] The first processing module 42 is used to determine the running status label of the vehicle according to the real-time running status information.

[0136] The second processing module 43 is used to determine an initial music recommendation strategy for the vehicle according to the running status tag and the music recommendation tag corresponding to the running status tag.

[0137] The third processing module 44 is used to determine the driving scene correction coefficient of the initial music recommendation strategy according to the camera data.

[0138] The music recommendation module 45 is used to correct the initial music recommendation strategy according to the driving scenario correction coefficient, determine the target music recommendation strategy of the vehicle, and output the music recommendation playlist according to the target music recommendation strategy.

[0139] By acquiring the real-time running status information and camera data of the vehicle, the embodiment of the present invention can determine the running status label of the vehicle according to the real-time running status information, and determine the initial music recommendation strategy of the vehicle according to the running status label and the music recommendation label corresponding to the running status label; then, the driving scene correction coefficient of the initial music recommendation strategy can be determined according to the camera data, and the initial music recommendation strategy can be corrected according to the driving scene correction coefficient to determine the target music recommendation strategy of the vehicle, so as to output the music recommendation playlist according to the target music recommendation strategy. Therefore, when the user is driving the vehicle, the user does not need to make a selection, and the music matching the current running status and driving scene of the vehicle is actively recommended to the user, thereby reducing the vehicle safety risk and improving the user's driving experience.

[0140] In one possible implementation, the third processing module 44 can also be used to determine the user emotion correction coefficient of the initial music recommendation strategy based on the camera data; the music recommendation module 45 can be used to correct the initial music recommendation strategy based on the driving scene correction coefficient and the user emotion correction coefficient to determine the target music recommendation strategy for the vehicle.

[0141] In a possible implementation, the acquisition module 41 can also be used to acquire user attribute data; the fourth processing module 46 is used to determine the user attribute correction coefficient of the initial music recommendation strategy based on the user attribute data; the music recommendation module 45 can be used to correct the initial music recommendation strategy according to the driving scene correction coefficient and the user attribute correction coefficient to determine the target music recommendation strategy for the vehicle; or, the initial music recommendation strategy can be corrected according to the driving scene correction coefficient, the user emotion correction coefficient and the user attribute correction coefficient to determine the target music recommendation strategy for the vehicle.

[0142] In a possible implementation, the first processing module 42 may be used to determine the frequency of changes in the operating state of the vehicle according to the real-time operating state information; and determine the operating state label of the vehicle according to the frequency of changes in the operating state of the vehicle.

[0143] In one possible implementation, the real-time operating status information includes real-time vehicle speed information, real-time gear information and real-time speed information; the first processing module 42 can be used to determine the current speed range of the vehicle and the change in speed based on the real-time vehicle speed information; determine the target speed label of the vehicle based on the frequency of speed changes, the current speed range of the vehicle, the change in speed and a preset speed label table; determine the target gear label of the vehicle based on the frequency of gear changes, the current speed range of the vehicle and a preset gear label table; determine the target speed label of the vehicle based on the real-time speed information and the preset speed label table; determine the operating status label of the vehicle based on the target speed label, target gear label and target speed label.

[0144] In a possible implementation, the third processing module 44 may be used to obtain the vehicle exterior landscape information and the user emotion information based on the camera data; and determine the user emotion correction coefficient of the initial music recommendation strategy based on the vehicle exterior landscape information and the user emotion information.

[0145] In one possible implementation, the user attribute data includes user characteristic attribute data, user behavior attribute data and user social attribute data; the fourth processing module 46 can be used to determine the user's music preference based on the user characteristic attribute data, user behavior attribute data and user social attribute data; and determine the user attribute correction coefficient of the initial music recommendation strategy based on the user's music preference.

[0146] Figure 5 Schematic diagram of a control device provided by an embodiment of the present invention. Figure 5 As shown, the control device 5 of this embodiment includes: a processor 50, a memory 51, and a computer program 52 stored in the memory 51 and executable on the processor 50. When the processor 50 executes the computer program 52, the steps in the above-mentioned various music recommendation method embodiments are implemented, for example Figure 1 Steps 101 to 105 shown, or Figure 2 Steps 201 to 205 shown, or Figure 3 Alternatively, when the processor 50 executes the computer program 52, the functions of each module / unit in the above-mentioned device embodiments are implemented, for example Figure 4 Functionality of the modules / units 41 to 45 shown.

[0147] Exemplarily, the computer program 52 may be divided into one or more modules / units, one or more modules / units are stored in the memory 51 and executed by the processor 50 to implement the present invention. One or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, and the instruction segments are used to describe the execution process of the computer program 52 in the control device 5. For example, the computer program 52 may be divided into Figure 4 Modules / units 41 to 45 are shown.

[0148] The control device 5 may be an in-vehicle multimedia device, a central control module on a vehicle, etc. The control device 5 may include, but is not limited to, a processor 50 and a memory 51. Those skilled in the art will appreciate that Figure 5 It is only an example of the control device 5 and does not constitute a limitation of the control device 5. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the control device may also include input and output devices, network access devices, buses, etc.

[0149] The processor 50 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0150] The memory 51 may be an internal storage unit of the control device 5, such as a hard disk or memory of the control device 5. The memory 51 may also be an external storage device of the control device 5, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the control device 5. Further, the memory 51 may also include both an internal storage unit of the control device 5 and an external storage device. The memory 51 is used to store computer programs and other programs and data required by the control device. The memory 51 may also be used to temporarily store data that has been output or is to be output.

[0151] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0152] As another embodiment of the present invention, the present invention may also include a vehicle, including the control device of any of the above embodiments, and having the same beneficial effects as the above control device, which will not be repeated here.

[0153] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0154] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0155] In the embodiments provided by the present invention, it should be understood that the disclosed devices / control devices and methods can be implemented in other ways. For example, the device / control device embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0156] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0157] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0158] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned music recommendation method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electric carrier signals and telecommunication signals.

[0159] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.

Claims

1. A music recommendation method, characterized in that: include: Acquire real-time operating status information and camera data of the vehicle; wherein the camera data includes external environment information; Determining the running status label of the vehicle according to the real-time running status information; Determining an initial music recommendation strategy for the vehicle according to the running status tag and the music recommendation tag corresponding to the running status tag; Determining a driving scene correction coefficient of the initial music recommendation strategy according to the camera data; The initial music recommendation strategy is modified according to the driving scenario correction coefficient to determine a target music recommendation strategy for the vehicle, so as to output a music recommendation playlist according to the target music recommendation strategy; Wherein, determining the driving scene correction coefficient of the initial music recommendation strategy according to the camera data includes: Determining a corresponding driving scene according to the vehicle exterior environment information in the camera data; According to the influence of the driving scene on each label in the music label, a driving scene correction coefficient of the initial music recommendation strategy is determined.

2. The music recommendation method according to claim 1, characterized in that: Also includes: Determining a user emotion correction coefficient of the initial music recommendation strategy based on the camera data; The initial music recommendation strategy is modified according to the driving scene correction coefficient to determine a target music recommendation strategy for the vehicle, including: The initial music recommendation strategy is modified according to the driving scenario correction coefficient and the user emotion correction coefficient to determine a target music recommendation strategy for the vehicle.

3. The music recommendation method according to claim 2, characterized in that: Also includes: Get user attribute data; Determining a user attribute correction coefficient of the initial music recommendation strategy according to the user attribute data; The initial music recommendation strategy is modified according to the driving scene correction coefficient to determine a target music recommendation strategy for the vehicle, including: Correcting the initial music recommendation strategy according to the driving scenario correction coefficient and the user attribute correction coefficient to determine a target music recommendation strategy for the vehicle; Alternatively, the initial music recommendation strategy is corrected according to the driving scene correction coefficient, the user emotion correction coefficient and the user attribute correction coefficient to determine the target music recommendation strategy for the vehicle.

4. The music recommendation method according to any one of claims 1 to 3, characterized in that: Determining the running status label of the vehicle according to the real-time running status information includes: Determining the frequency of change of the operating state of the vehicle according to the real-time operating state information; The running state label of the vehicle is determined according to the changing frequency of the running state of the vehicle.

5. The music recommendation method according to claim 4, characterized in that: The real-time running status information includes real-time vehicle speed information, real-time gear position information and real-time speed information; Determining the running state label of the vehicle according to the change frequency of the running state of the vehicle includes: Determine the current speed range of the vehicle and the change in speed according to the real-time vehicle speed information; Determine the target speed label of the vehicle according to the speed change frequency, the current speed range of the vehicle, the speed change amount and the preset speed label table; Determine the target gear label of the vehicle according to the gear change frequency of the vehicle, the current speed range of the vehicle and the preset gear label table; Determining a target speed label of the vehicle according to the real-time speed information and a preset speed label table; The running state label of the vehicle is determined according to the target vehicle speed label, the target gear position label and the target rotation speed label.

6. The music recommendation method according to claim 2 or 3, characterized in that: Determining a user emotion correction coefficient of the initial music recommendation strategy according to the camera data includes: Acquire the vehicle exterior landscape information and the user emotion information according to the camera data; A user emotion correction coefficient of the initial music recommendation strategy is determined according to the vehicle exterior landscape information and the user emotion information.

7. The music recommendation method according to claim 3, characterized in that: The user attribute data includes user characteristic attribute data, user behavior attribute data and user social attribute data; Determining a user attribute correction coefficient of the initial music recommendation strategy according to the user attribute data includes: Determining the user's music preference according to the user characteristic attribute data, the user behavior attribute data and the user social attribute data; According to the user's music preference, a user attribute correction coefficient of the initial music recommendation strategy is determined.

8. A music recommendation device, characterized in that: include: An acquisition module, used to acquire real-time running status information and camera data of the vehicle; wherein the camera data includes external environment information of the vehicle; A first processing module, configured to determine an operation status label of a vehicle according to the real-time operation status information; A second processing module, configured to determine an initial music recommendation strategy for the vehicle according to the running state tag and the music recommendation tag corresponding to the running state tag; A third processing module, configured to determine a driving scene correction coefficient of the initial music recommendation strategy according to the camera data; A music recommendation module, used to modify the initial music recommendation strategy according to the driving scenario correction coefficient, determine a target music recommendation strategy for the vehicle, and output a music recommendation playlist according to the target music recommendation strategy; The third processing module is specifically used for: Determining a corresponding driving scene according to the vehicle exterior environment information in the camera data; According to the influence of the driving scene on each label in the music label, a driving scene correction coefficient of the initial music recommendation strategy is determined.

9. A vehicle, characterized in that: The invention comprises a control device, wherein the control device comprises a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to call and run the computer program stored in the memory to execute the method as claimed in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method as claimed in any one of claims 1 to 7 are implemented.

Images