CN117573919A - Car end music recommendation method, device, equipment and storage medium - Google Patents
Car end music recommendation method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN117573919A CN117573919A CN202311580199.5A CN202311580199A CN117573919A CN 117573919 A CN117573919 A CN 117573919A CN 202311580199 A CN202311580199 A CN 202311580199A CN 117573919 A CN117573919 A CN 117573919A
- Authority
- CN
- China
- Prior art keywords
- data
- vehicle
- passenger
- keywords
- current
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 62
- 230000008569 process Effects 0.000 claims description 25
- 238000004590 computer program Methods 0.000 claims description 24
- 238000012549 training Methods 0.000 claims description 19
- 230000006870 function Effects 0.000 claims description 18
- 238000004458 analytical method Methods 0.000 claims description 14
- 230000007613 environmental effect Effects 0.000 claims description 14
- 230000001815 facial effect Effects 0.000 claims description 10
- 238000003062 neural network model Methods 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 5
- 230000036651 mood Effects 0.000 description 5
- 238000013527 convolutional neural network Methods 0.000 description 2
- 230000008451 emotion Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 206010013954 Dysphoria Diseases 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000003340 mental effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
- G06F16/63—Querying
- G06F16/635—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/60—Information retrieval; Database structures therefor; File system structures therefor of audio data
- G06F16/63—Querying
- G06F16/632—Query formulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/59—Context or environment of the image inside of a vehicle, e.g. relating to seat occupancy, driver state or inner lighting conditions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/70—Labelling scene content, e.g. deriving syntactic or semantic representations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The invention discloses a vehicle-end music recommendation method, a device, equipment and a storage medium, which are used for responding to a music playing request input by an occupant to acquire environment data, driving state data and occupant data in a vehicle; respectively analyzing the acquired environment data, driving state data and passenger data in the vehicle, and determining corresponding scene keywords, driving keywords and passenger keywords to form a keyword group; and searching the song list according to the generated keyword groups, and determining a target song list according to the number of the matched keywords of the song list. Corresponding music can be accurately matched, and user experience is improved.
Description
Technical Field
The invention relates to the technical field of data recommendation, in particular to a vehicle-end music recommendation method, device, equipment and storage medium.
Background
Currently, in order to meet the living demands of people, more and more people need to drive automobiles for a long time. Such as long distance passenger and cargo drivers, city bus drivers, etc. On one hand, the long-distance driving bus consumes a great deal of physical strength, and on the other hand, the long-distance driving bus consumes the mental power of people, so that people can feel tired and dysphoria easily.
In view of the above, entertainment systems are generally installed in automobiles at present, and some music data can be automatically recommended during leisure, so that a driver can keep pleasant moods. Typical entertainment systems either passively respond to user selection of music data to be played or recommend music data based on historical data. The existing music recommendation method has low accuracy, cannot match corresponding music according to passengers in the vehicle, and is low in user experience.
Disclosure of Invention
In order to solve the problems, the invention provides a vehicle-end music recommendation method, device, equipment and storage medium, which can accurately match corresponding music and improve user experience.
The embodiment of the invention provides a vehicle-end music recommendation method, which comprises the following steps:
responding to a music playing request input by an occupant, and acquiring environment data, driving state data and occupant data in the vehicle;
respectively analyzing the acquired environment data, driving state data and passenger data in the vehicle, and determining corresponding scene keywords, driving keywords and passenger keywords to form a keyword group;
and searching the song list according to the generated keyword groups, and determining a target song list according to the number of the matched keywords of the song list.
Preferably, the environment data specifically includes an external environment image acquired by an external camera;
the scene keyword generation process specifically comprises the following steps:
inputting the acquired external environment image into a pre-trained scene recognition model for feature analysis, outputting a corresponding scene tag, and adding the output scene tag into a scene keyword;
the scene recognition model training process specifically comprises the following steps:
inputting image data which are marked as different scene labels in advance as training data into a neural network model for training to obtain the scene recognition model;
the scene tag includes: cities, beaches, mountain roads and sunset.
As a preferable scheme, the environment data specifically comprises the acquired temperature outside the vehicle, the current time, the current date and the current positioning;
the scene keyword generation process specifically comprises the following steps:
automatically matching corresponding current time orders according to the acquired temperature, date and current positioning information, wherein the current time orders comprise spring, summer, autumn and winter;
matching a current region in a region matching table of a preset position and a corresponding current region according to the acquired positioning information, wherein the current region in the region matching table comprises the south and the north;
matching the current time in a time matching table of a preset time period and the corresponding current time according to the acquired current time, wherein the current time in the time matching table comprises early morning, late night, afternoon, evening and late night;
and adding the determined current time, the determined current area and the determined current time to the scene keyword.
Preferably, the running state data includes a current vehicle speed;
the driving keyword generation process specifically comprises the following steps:
matching corresponding vehicle speed grades in a state matching table of the corresponding vehicle speed grades in a preset vehicle speed section according to the current vehicle speed, and outputting the current vehicle speed grades as driving keywords;
the vehicle speed level in the state matching table comprises high speed, low speed and traffic jam.
As a preferable mode, the occupant data includes an in-vehicle occupant image;
the occupant keyword generation process specifically includes:
extracting the facial features of each passenger according to the passenger images in the vehicle, and determining the gender information and the age bracket of each passenger according to the facial features of each passenger;
according to the passenger proportion of different age groups in all passengers and the sex information of all passengers, matching corresponding passenger relations from a preset database, and taking the matched passenger relations as the passenger keywords;
the occupant relationships in the database include: friends, lovers, girls, children and families;
the database comprises corresponding relations among different age groups of ratios, different sexes of ratios and passenger relations.
Preferably, the step of searching the song list according to the generated keyword group, and determining the target song list according to the number of matching keywords of the song list specifically includes:
selecting combination modes containing preset number of key word groups from the key word groups, and taking each combination mode as a search word group;
searching the song list by taking each search phrase as a target, and counting the occurrence frequency of each song list in the song list searched by all the search phrases;
the song with the highest appearance frequency is most matched with the target song with the most keywords.
As a preferred aspect, after responding to a music play request input by an occupant, the method further includes:
acquiring a destination and current time of current car navigation, and judging the destination and the current time;
when the destination is not a place in a preset conventional address library and the current time is not the preset conventional working time, starting a corresponding music recommendation function, acquiring environment data, driving state data and passenger data in the vehicle, and performing keyword recognition according to the acquired data to complete music recommendation;
and when the destination is a place in a preset conventional address library or the current time is a preset conventional working time, acquiring a latest play song list, and playing the acquired latest play song list.
The embodiment of the invention also provides a vehicle-end music recommendation device, which comprises:
the data acquisition module is used for responding to a music playing request input by an occupant and acquiring environment data, driving state data and occupant data in the vehicle;
the keyword analysis module is used for respectively analyzing the acquired environmental data, the running state data and the passenger data in the vehicle, and determining corresponding scene keywords, running keywords and passenger keywords to form a keyword group;
and the song list searching module is used for searching the song list according to the generated keyword groups and determining a target song list according to the number of the matched keywords.
As a preferable scheme, the environment data specifically comprises an external environment image acquired by an external camera;
the scene keyword generation process specifically comprises the following steps:
inputting the acquired external environment image into a pre-trained scene recognition model for feature analysis, outputting a corresponding scene tag, and adding the output scene tag into a scene keyword;
the scene recognition model training process specifically comprises the following steps:
inputting image data which are marked as different scene labels in advance as training data into a neural network model for training to obtain the scene recognition model;
the scene tag includes: cities, beaches, mountain roads and sunset.
Preferably, the environmental data specifically includes an acquired temperature outside the vehicle, a current time, a current date and a current location;
the scene keyword generation process specifically comprises the following steps:
automatically matching corresponding current time orders according to the acquired temperature, date and current positioning information, wherein the current time orders comprise spring, summer, autumn and winter;
matching a current region in a region matching table of a preset position and a corresponding current region according to the acquired positioning information, wherein the current region in the region matching table comprises the south and the north;
matching the current time in a time matching table of a preset time period and the corresponding current time according to the acquired current time, wherein the current time in the time matching table comprises early morning, late night, afternoon, evening and late night;
and adding the determined current time, the determined current area and the determined current time to the scene keyword.
As a preferable mode, the running state data includes a current vehicle speed;
the driving keyword generation process specifically comprises the following steps:
matching corresponding vehicle speed grades in a state matching table of the corresponding vehicle speed grades in a preset vehicle speed section according to the current vehicle speed, and outputting the current vehicle speed grades as driving keywords;
the vehicle speed level in the state matching table comprises high speed, low speed and traffic jam.
Preferably, the occupant data includes an in-vehicle occupant image;
the occupant keyword generation process specifically includes:
extracting the facial features of each passenger according to the passenger images in the vehicle, and determining the gender information and the age bracket of each passenger according to the facial features of each passenger;
according to the passenger proportion of different age groups in all passengers and the sex information of all passengers, matching corresponding passenger relations from a preset database, and taking the matched passenger relations as the passenger keywords;
the occupant relationships in the database include: friends, lovers, girls, children and families;
the database comprises corresponding relations among different age groups of ratios, different sexes of ratios and passenger relations.
Preferably, the song search module is specifically configured to:
selecting combination modes containing preset number of key word groups from the key word groups, and taking each combination mode as a search word group;
searching the song list by taking each search phrase as a target, and counting the occurrence frequency of each song list in the song list searched by all the search phrases;
the song with the highest appearance frequency is most matched with the target song with the most keywords.
Preferably, the apparatus further comprises: the function starting module is used for:
after responding to a music playing request input by an occupant, acquiring a destination and current time of current car navigation, and judging the destination and the current time;
when the destination is not a place in a preset conventional address library and the current time is not the preset conventional working time, starting a corresponding music recommendation function, acquiring environment data, driving state data and passenger data in the vehicle, and performing keyword recognition according to the acquired data to complete music recommendation;
and when the destination is a place in a preset conventional address library or the current time is a preset conventional working time, acquiring a latest play song list, and playing the acquired latest play song list.
The embodiment of the invention also provides a terminal device, which comprises a processor, a memory and a computer program stored in the memory and configured to be executed by the processor, wherein the computer program is executed by the processor to realize the vehicle-end music recommendation method according to any one of the embodiments.
The embodiment of the invention also provides a computer readable storage medium, which comprises a stored computer program, wherein when the computer program runs, equipment where the computer readable storage medium is located is controlled to execute the vehicle-end music recommendation method according to any one of the embodiments.
The invention provides a vehicle-end music recommendation method, a device, equipment and a storage medium, which are used for responding to a music playing request input by an occupant to acquire environment data, driving state data and occupant data in a vehicle; respectively analyzing the acquired environment data, driving state data and passenger data in the vehicle, and determining corresponding scene keywords, driving keywords and passenger keywords to form a keyword group; and searching the song list according to the generated keyword groups, and determining a target song list according to the number of the matched keywords of the song list. Corresponding music can be accurately matched, and user experience is improved.
Drawings
Fig. 1 is a schematic flow chart of a vehicle-end music recommendation method provided by an embodiment of the invention;
fig. 2 is a schematic structural diagram of a vehicle-end music recommendation device according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a terminal device according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, a flow chart of a vehicle-end music recommendation method provided by an embodiment of the invention is shown, and the method includes steps S1 to S3;
s1, acquiring environment data, driving state data and passenger data in a vehicle in response to a music playing request input by a passenger;
s2, respectively analyzing the acquired environmental data, driving state data and passenger data in the vehicle, and determining corresponding scene keywords, driving keywords and passenger keywords to form a keyword group;
and S3, searching the song list according to the generated keyword groups, and determining a target song list according to the number of the matched keywords of the song list.
When the embodiment is implemented, the vehicle controller acquires environment data, driving state data and occupant data in the vehicle when receiving a music playing request input by the occupant;
the process of inputting the music playing request by the passenger can specifically input a control signal through a control panel arranged on the vehicle, and also can input a corresponding voice command, such as a voice command for playing music, through a voice interaction function configured on the vehicle, and the vehicle responds after detecting the control signal or recognizing the voice command to acquire current environment data, driving state data and passenger data in the vehicle;
the environment data are used for evaluating the scene outside the current vehicle, and scene keywords outside the vehicle can be determined by analyzing the acquired environment data;
the driving state data are used for evaluating the driving state of the current driver on the vehicle, and the driving keywords of the vehicle can be determined by analyzing the acquired driving state data;
the passenger data in the vehicle is used for evaluating the identity relation of passengers in the vehicle, and the acquired passenger data are analyzed to determine passenger keywords of the passengers;
under different external scenes, different running states and different passenger relations in the vehicle, different music is matched for passengers in the vehicle, and the preferences of the passengers in the vehicle and the internal scene can be met; in combination with the environment outside the vehicle, under the condition of different relation of passengers in the vehicle, different types of music are recommended, and the music recommendation type is more accurate.
In still another embodiment of the present invention, the environmental data specifically includes an external environment image acquired by an external camera;
the scene keyword generation process specifically comprises the following steps:
inputting the acquired external environment image into a pre-trained scene recognition model for feature analysis, outputting a corresponding scene tag, and adding the output scene tag into a scene keyword.
When the embodiment is implemented specifically, during external scene recognition, the acquired environmental data are specifically environmental images outside the vehicle, a picture of the current driver at a 180-degree view angle is shot, and the environmental images are obtained through the shot picture;
the scene tag outside the vehicle can be determined by analyzing according to the environment image, and the specific process comprises the following steps: inputting the acquired external environment image into a pre-trained scene recognition model for feature analysis; the scene recognition model is input into image data, output into corresponding scene labels, and the output scene labels are added into scene keywords.
In this embodiment, a pre-trained scene recognition model is used as a recognition method of a scene keyword, in other embodiments, scene recognition may be implemented by other methods in the prior art, and a scene keyword is output, for example, the scene recognition is performed by using the existing computer vision scene recognition method, and a scene in a corresponding scene database is output as a scene keyword.
In another embodiment provided by the present invention, the scene recognition model training process specifically includes:
inputting image data which are marked as different scene labels in advance as training data into a neural network model for training to obtain the scene recognition model;
the scene tag includes: cities, beaches, mountain roads and sunset.
When the embodiment is implemented, the scene recognition model training process specifically includes:
acquiring image data of different scene labels as training data, and labeling the different image data;
and taking the label mark as the output of the model, taking the image data as the model input, inputting the training data into the convolutional neural network model for training, and taking the trained convolutional neural network model as the scene recognition model.
In the model training process, in order to improve the accuracy of model identification, the training image can be processed, and the image can be rotated, scaled, cut, normalized and the like, so that the calculated graph is more robust.
The scene labels comprise different scenes such as cities, beaches, mountain roads, sunset and the like.
The scene labels can also improve the number of the pattern recognition scenes by adding new scene label data in the model training, so that more common scenes can be added in a self-adaptive mode, and the model recognition accuracy is improved.
In yet another embodiment provided by the present invention, the environmental data specifically includes an obtained temperature outside the vehicle, a current time, a current date, and a current location;
the scene keyword generation process specifically comprises the following steps:
automatically matching corresponding current time orders according to the acquired temperature, date and current positioning information, wherein the current time orders comprise spring, summer, autumn and winter;
matching a current region in a region matching table of a preset position and a corresponding current region according to the acquired positioning information, wherein the current region in the region matching table comprises the south and the north;
matching the current time in a time matching table of a preset time period and the corresponding current time according to the acquired current time, wherein the current time in the time matching table comprises early morning, late night, afternoon, evening and late night;
and adding the determined current time, the determined current area and the determined current time to the scene keyword.
When the embodiment is implemented, the temperature outside the vehicle, the current time, the current date and the current positioning can be obtained as environment data when scene keyword recognition is carried out;
through the acquired environmental data, multidimensional scene analysis is carried out, and more scene keywords are determined, specifically:
automatically matching corresponding current time orders according to the acquired temperature, date and current positioning information, wherein the current time orders comprise spring, summer, autumn and winter;
the specific identification is that the current position of the vehicle can be determined according to the current positioning information, and the specific positions of areas comprise a southern hemisphere, a northern hemisphere, an eastern hemisphere, a western hemisphere and the like; further, according to the current date, matching the time command of the corresponding area position, and further calibrating the time command according to the current temperature;
when the temperature and the time order of passing the date matching deviate, the time order of the temperature matching can be preferentially selected to overcome the influence of abnormal weather.
The current time includes spring, summer, autumn and winter;
it should be noted that, the current time slots may be further divided into more detailed time slots, and more detailed time slots are determined as keywords.
Matching a current region in a region matching table of a preset position and a corresponding current region according to the acquired positioning information, and matching the current region corresponding to the positioning information according to a specific position of the positioning information and a region matching table of a pre-divided southern region and a northern region, wherein the current region in the region matching table comprises the southern region and the northern region;
it should be noted that the region matching table may further include more detailed location region information.
According to the obtained current time, matching the current time in a time matching table, wherein the time matching table divided in advance comprises the corresponding relation between different time intervals and the current time, and the current time in the time matching table comprises early morning, late night, afternoon, evening and late night;
it should be noted that the time matching table may further include a more detailed current time.
And adding the determined current time, the determined current area and the determined current time to the scene keyword.
It should be noted that, in this embodiment, the current time, the current area and the current time as the scene keywords may be used in combination with the scene keywords in other embodiments, so as to increase the dimension of the scene keywords and improve the music recommendation accuracy.
By acquiring the current time, the current area and the current moment as scene keywords, the scene recognition degree can be improved, different music recommendations can be provided for different scenes at different moments, the mood of the current passengers can be more met, for example, the passengers in the early morning and late night can have completely different feelings under urban roads, and music conforming to the mood of the passengers needs to be recommended.
In yet another embodiment provided by the present invention, the driving state data includes a current vehicle speed;
the driving keyword generation process specifically comprises the following steps:
matching corresponding vehicle speed grades in a state matching table of the corresponding vehicle speed grades in a preset vehicle speed section according to the current vehicle speed, and outputting the current vehicle speed grades as driving keywords;
the vehicle speed level in the state matching table comprises high speed, low speed and traffic jam.
In the specific implementation of the embodiment, the driving state data obtained in the process of performing the driving keyword analysis specifically includes the current vehicle speed;
and matching the corresponding vehicle speed grade according to the current vehicle speed, namely matching the corresponding vehicle speed grade in a preset state matching table according to the current vehicle speed, wherein the state matching table comprises the corresponding relation between the preset vehicle speed interval and the vehicle speed grade. The vehicle speed level in the state matching table comprises high speed, low speed and traffic jam.
The high speed and slow speed states can be determined by the magnitude of the vehicle speed at which the vehicle is maintained stable, and in the high speed running state and the slow speed running state, the reaction passengers have different moods.
When the vehicle speed is always switched between 0 and low speed, the vehicle is in a traffic jam state, and in the traffic jam state, the passengers are unavoidably accompanied with the fidgeted emotion, and the corresponding English is matched at the moment, so that the emotion of the passengers can be relieved.
Outputting the current vehicle speed level as a driving keyword;
it should be noted that, the driving keyword analysis may further determine a driving keyword by acquiring other vehicle parameters, specifically, by acquiring a destination of the current vehicle navigation information, determining a destination attribute according to the destination, and determining the destination attribute as the driving keyword, where the destination is a preset facility with different attributes such as a restaurant, a hotel or a cinema, or where the destination is a place such as an address or a company, the moods of the passengers are different, and the driving information may be analyzed by using the driving attributes. Namely, different destinations are matched with different attributes through the real-time acquired destinations by dividing attribute matching tables of the corresponding relations between the different destinations and the different attributes.
Through analysis of the driving keywords, the current vehicle state can be attached, and corresponding music can be matched.
In yet another embodiment provided by the present invention, the occupant data includes an in-vehicle occupant image;
the occupant keyword generation process specifically includes:
extracting the facial features of each passenger according to the passenger images in the vehicle, and determining the gender information and the age bracket of each passenger according to the facial features of each passenger;
according to the passenger proportion of different age groups in all passengers and the sex information of all passengers, matching corresponding passenger relations from a preset database, and taking the matched passenger relations as the passenger keywords;
the occupant relationships in the database include: friends, lovers, girls, children and families;
the database comprises corresponding relations among different age groups of ratios, different sexes of ratios and passenger relations.
When the embodiment is implemented, the passenger data acquired when the key words of the passengers in the vehicle are analyzed comprise images of the passengers in the vehicle;
acquiring, as an occupant image, an image of an occupant on each seat in the vehicle by a camera apparatus disposed in the vehicle;
the method comprises the steps of extracting facial features of each passenger by carrying out image recognition on passengers in the vehicle, extracting the images of the passengers in the vehicle, and carrying out passenger analysis according to the extracted facial features, wherein the analysis result is the age and the sex of the passengers.
In this embodiment, the conventional image recognition algorithm may be used to recognize the sex and year of the occupant.
In performing the occupant sex information and the age identification, the age of the occupant is output in the age group in which the age of the occupant is in the different age groups divided in advance.
Counting the number of passengers and the proportion of the passengers corresponding to different age groups, wherein the proportion of men and women of the passengers of different age groups;
and determining the passenger relationship of the passengers in the vehicle according to the pre-constructed corresponding mapping relationship between the passenger ratios of different ages and the passenger relationship. The occupant relationships in the database include: friends, lovers, girls, children and families;
when the number of occupants in the age group of the occupants in the vehicle is 2, the ratio is 50%, and the sex ratio of male occupants in the age group of 20-35 is 50%, and the number of occupants in the age group of the occupants in the vehicle is 2, the current occupant relationship is recognized as a family under this condition.
When the number of passengers in the age group of the passenger in the vehicle is 3, the ratio is 100%, and the sex ratio of the male passengers in the age group of 20-35 is 0%, the current passenger relationship is recognized as a girlform under this condition.
When the number of occupants in the age group of the occupants in the vehicle is 5, the ratio is 100%, and the sex ratio of male occupants in the age group of 20-35 is 3%, the current occupant relationship will be identified as friends under this condition.
When the number of occupants in the age group of the occupants in the vehicle is 4 in the age group of 3 to 12 years old, the current occupant relationship will be recognized as child under this condition when the ratio is 75%.
In the above embodiment, several common passenger relationship recognition examples are given, and all the passenger relationships in the database can be recognized by the corresponding relationships of the different age group ratios, the different gender ratios and the passenger relationships.
By identifying the occupant relationships, different music can be matched when the occupant relationships in the vehicle are different, for example, when the occupant relationships in the vehicle are identified as children, the music output at the moment is focused as the child song or the cartoon music, and when the relationships are friends, the corresponding music is matched. And directly searching the song list by taking the matched passenger relationship as a keyword, so as to realize accurate recommendation of the song list.
In another embodiment of the present invention, the searching for the song list according to the generated keyword group, and determining the target song list according to the number of matching keywords of the song list, specifically includes:
selecting combination modes containing preset number of key word groups from the key word groups, and taking each combination mode as a search word group;
searching the song list by taking each search phrase as a target, and counting the occurrence frequency of each song list in the song list searched by all the search phrases;
the song with the highest appearance frequency is most matched with the target song with the most keywords.
When the embodiment is implemented, when the song searching is performed according to the matched keyword groups, all keywords in the keyword groups are arranged and combined, and all the keywords are output to the searching group containing the preset number of keywords;
for example, if the number of keywords in the keyword group is 8 and the number of keywords in the search group is 3, the corresponding output is C 3 8 =56 search phrases;
it should be noted that the number of keywords in the search phrase may be specifically determined according to the actual situation.
And searching the songs by taking each search phrase as a target, outputting the songs obtained by each search, counting the occurrence frequency of all the searched songs, and playing the songs by using the target songs with the highest occurrence frequency, wherein the more the number of keywords which can be matched, the most matching the target songs with the most keywords.
The song list appearance frequency can be sorted from high to low and output to the vehicle terminal for selection by a user.
It should be noted that in other embodiments, other keyword searching methods may be used, for example, all keywords are input to perform searching output, and a song list is output, where the number of matching songs is more when the number of keywords is less, and the corresponding song list may not be searched when the number of keywords is more, at this time, the conventional technology generally reduces the keywords until the corresponding song list is searched, and at this time, a large number of keywords are lost, and the matching accuracy is not high.
According to the method, a large number of songs can be ensured to be searched certainly through a mode of forming a search phrase, the occurrence frequency of the songs is counted through improving the searching breadth of the songs, and the song with the highest priority can be determined.
In yet another embodiment of the present invention, after responding to the music playing request input by the occupant, the method further includes:
acquiring a destination and current time of current car navigation, and judging the destination and the current time;
when the destination is not a place in a preset conventional address library and the current time is not the preset conventional working time, starting a corresponding music recommendation function, acquiring environment data, driving state data and passenger data in the vehicle, and performing keyword recognition according to the acquired data to complete music recommendation;
and when the destination is a place in a preset conventional address library or the current time is a preset conventional working time, acquiring a latest play song list, and playing the acquired latest play song list.
When the embodiment is implemented, after receiving a music playing request input by a user, a destination and current time of current car navigation are acquired at the moment, and the destination and the current time are judged;
when the destination is not a place in a preset conventional address library and the current time is not the preset conventional working time, the passenger is not in a working state at this time, and the music recommendation function can be started; responding to a music playing request input by an occupant, and acquiring environment data, driving state data and occupant data in the vehicle; respectively analyzing the acquired environment data, driving state data and passenger data in the vehicle, and determining corresponding scene keywords, driving keywords and passenger keywords to form a keyword group; and searching the song list according to the generated keyword groups, and determining a target song list according to the number of the matched keywords of the song list.
When the destination is a place in a preset conventional address library or the current time is a preset conventional working time, the passengers may be in a working state and not suitable for excessive entertainment so as not to influence the state, and when the passengers are required to listen to music, the passengers acquire the latest play list and randomly play the acquired latest play list.
It should be noted that, the conventional address library may be preset as a company or a frequent job site; the preset regular working time may be set to 8 a.m. to 7 a.m. of the working day, during which time the passenger may be in working time.
By identifying the navigation destination and the current time, whether the corresponding music recommendation function is started or not can be judged, and the influence on the working state of the passenger is avoided.
Still another embodiment of the present invention provides a vehicle-end music recommendation device, referring to fig. 2, which is a schematic structural diagram of the vehicle-end music recommendation device provided by the embodiment of the present invention, where the device includes:
the data acquisition module is used for responding to a music playing request input by an occupant and acquiring environment data, driving state data and occupant data in the vehicle;
the keyword analysis module is used for respectively analyzing the acquired environmental data, the running state data and the passenger data in the vehicle, and determining corresponding scene keywords, running keywords and passenger keywords to form a keyword group;
and the song list searching module is used for searching the song list according to the generated keyword groups and determining a target song list according to the number of the matched keywords.
The vehicle-end music recommendation device provided in this embodiment can execute all the steps and functions of the vehicle-end music recommendation method provided in any one of the above embodiments, and specific functions of the device are not described herein.
Referring to fig. 3, a schematic structural diagram of a terminal device according to an embodiment of the present invention is provided. The terminal device includes: a processor, a memory, and a computer program stored in the memory and executable on the processor, such as a car-end music recommendation program. The steps in each of the foregoing embodiments of the vehicle-side music recommendation method are implemented when the processor executes the computer program, for example, steps S1 to S3 shown in fig. 1. Alternatively, the processor may implement the functions of the modules in the above-described device embodiments when executing the computer program.
The computer program may be divided into one or more modules, which are stored in the memory and executed by the processor to accomplish the present invention, for example. The one or more modules may be a series of computer program instruction segments capable of performing the specified functions, which instruction segments describe the execution of the computer program in the one terminal device. For example, the computer program may be divided into several modules, and specific functions of each module are described in detail in a vehicle-end music recommendation method provided in any of the foregoing embodiments, and specific functions of the device are not described herein.
The terminal equipment can be computing equipment such as a desktop computer, a notebook computer, a palm computer, a cloud server and the like. The terminal device may include, but is not limited to, a processor, a memory. It will be appreciated by those skilled in the art that the schematic diagram is merely an example of one type of terminal device and is not limiting of one type of terminal device, and may include more or fewer components than shown, or may combine certain components, or different components, e.g., the one type of terminal device may also include input-output devices, network access devices, buses, etc.
The processor may be a central processing unit (Central Processing Unit, CPU), other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. The general purpose processor may be a microprocessor or the processor may be any conventional processor or the like, which is a control center of the one terminal device, and which connects the respective parts of the entire one terminal device using various interfaces and lines.
The memory may be used to store the computer program and/or the module, and the processor may implement various functions of the vehicle-side music recommendation device by running or executing the computer program and/or the module stored in the memory and invoking data stored in the memory. The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program (such as a sound playing function, an image playing function, etc.) required for at least one function, and the like; the storage data area may store data (such as audio data, phonebook, etc.) created according to the use of the handset, etc. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as a hard disk, memory, plug-in hard disk, smart Media Card (SMC), secure Digital (SD) Card, flash Card (Flash Card), at least one disk storage device, flash memory device, or other volatile solid-state storage device.
Wherein the terminal device integrated module may be stored in a computer readable storage medium if implemented in the form of a software functional unit and sold or used as a stand alone product. Based on such understanding, the present invention may implement all or part of the flow of the method of the above embodiment, or may be implemented by a computer program to instruct related hardware, where the computer program may be stored in a computer readable storage medium, and when the computer program is executed by a processor, the computer program may implement the steps of each of the method embodiments described above. Wherein the computer program comprises computer program code which may be in source code form, object code form, executable file or some intermediate form etc. The computer readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), an electrical carrier signal, a telecommunications signal, a software distribution medium, and so forth.
It should be noted that modifications and adaptations to the invention may occur to one skilled in the art without departing from the principles of the present invention and are intended to be within the scope of the present invention.
Claims (10)
1. A car-end music recommendation method, the method comprising:
responding to a music playing request input by an occupant, and acquiring environment data, driving state data and occupant data in the vehicle;
respectively analyzing the acquired environment data, driving state data and passenger data in the vehicle, and determining corresponding scene keywords, driving keywords and passenger keywords to form a keyword group;
and searching the song list according to the generated keyword groups, and determining a target song list according to the number of the matched keywords of the song list.
2. The car-end music recommendation method according to claim 1, wherein the environmental data specifically includes an external car environmental image acquired through an external car camera;
the scene keyword generation process specifically comprises the following steps:
inputting the acquired external environment image into a pre-trained scene recognition model for feature analysis, outputting a corresponding scene tag, and adding the output scene tag into a scene keyword;
the scene recognition model training process specifically comprises the following steps:
inputting image data which are marked as different scene labels in advance as training data into a neural network model for training to obtain the scene recognition model;
the scene tag includes: cities, beaches, mountain roads and sunset.
3. The car-end music recommendation method according to claim 1, wherein the environmental data specifically includes an acquired temperature outside a car, a current time, a current date and a current location;
the scene keyword generation process specifically comprises the following steps:
automatically matching corresponding current time orders according to the acquired temperature, date and current positioning information, wherein the current time orders comprise spring, summer, autumn and winter;
matching a current region in a region matching table of a preset position and a corresponding current region according to the acquired positioning information, wherein the current region in the region matching table comprises the south and the north;
matching the current time in a time matching table of a preset time period and the corresponding current time according to the acquired current time, wherein the current time in the time matching table comprises early morning, late night, afternoon, evening and late night;
and adding the determined current time, the determined current area and the determined current time to the scene keyword.
4. The vehicle-end music recommendation method according to claim 1, wherein the running state data includes a current vehicle speed;
the driving keyword generation process specifically comprises the following steps:
matching corresponding vehicle speed grades in a state matching table of the corresponding vehicle speed grades in a preset vehicle speed section according to the current vehicle speed, and outputting the current vehicle speed grades as driving keywords;
the vehicle speed level in the state matching table comprises high speed, low speed and traffic jam.
5. The vehicle-end music recommendation method according to claim 1, wherein the occupant data includes an in-vehicle occupant image;
the occupant keyword generation process specifically includes:
extracting the facial features of each passenger according to the passenger images in the vehicle, and determining the gender information and the age bracket of each passenger according to the facial features of each passenger;
according to the passenger proportion of different age groups in all passengers and the sex information of all passengers, matching corresponding passenger relations from a preset database, and taking the matched passenger relations as the passenger keywords;
the occupant relationships in the database include: friends, lovers, girls, children and families;
the database comprises corresponding relations among different age groups of ratios, different sexes of ratios and passenger relations.
6. The car-end music recommendation method according to claim 1, wherein the step of searching the song list according to the generated keyword group and determining the target song list according to the number of matching keywords is specifically included:
selecting combination modes containing preset number of key word groups from the key word groups, and taking each combination mode as a search word group;
searching the song list by taking each search phrase as a target, and counting the occurrence frequency of each song list in the song list searched by all the search phrases;
the song with the highest appearance frequency is most matched with the target song with the most keywords.
7. The vehicle-side music recommendation method according to claim 1, wherein after responding to a music play request input by an occupant, the method further comprises:
acquiring a destination and current time of current car navigation, and judging the destination and the current time;
when the destination is not a place in a preset conventional address library and the current time is not the preset conventional working time, starting a corresponding music recommendation function, acquiring environment data, driving state data and passenger data in the vehicle, and performing keyword recognition according to the acquired data to complete music recommendation;
and when the destination is a place in a preset conventional address library or the current time is a preset conventional working time, acquiring a latest play song list, and playing the acquired latest play song list.
8. A car-end music recommendation device, characterized in that the device comprises:
the data acquisition module is used for responding to a music playing request input by an occupant and acquiring environment data, driving state data and occupant data in the vehicle;
the keyword analysis module is used for respectively analyzing the acquired environmental data, the running state data and the passenger data in the vehicle, and determining corresponding scene keywords, running keywords and passenger keywords to form a keyword group;
and the song list searching module is used for searching the song list according to the generated keyword groups and determining a target song list according to the number of the matched keywords.
9. A terminal device comprising a processor, a memory and a computer program stored in the memory and configured to be executed by the processor, the processor implementing the car-end music recommendation method according to any one of claims 1 to 7 when executing the computer program.
10. A computer readable storage medium, characterized in that the computer readable storage medium comprises a stored computer program, wherein the computer program when run controls a device in which the computer readable storage medium is located to perform the car-end music recommendation method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311580199.5A CN117573919A (en) | 2023-11-23 | 2023-11-23 | Car end music recommendation method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311580199.5A CN117573919A (en) | 2023-11-23 | 2023-11-23 | Car end music recommendation method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117573919A true CN117573919A (en) | 2024-02-20 |
Family
ID=89887810
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311580199.5A Pending CN117573919A (en) | 2023-11-23 | 2023-11-23 | Car end music recommendation method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117573919A (en) |
-
2023
- 2023-11-23 CN CN202311580199.5A patent/CN117573919A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3240258B1 (en) | System and method for presenting media contents in autonomous vehicles | |
| CN109841212B (en) | Speech recognition system and speech recognition method for analyzing commands with multiple intents | |
| US11200892B1 (en) | Speech-enabled augmented reality user interface | |
| WO2017003452A1 (en) | Method and apparatus for processing user input | |
| CN111833881B (en) | Stroke voice service generation method, stroke accompanying assistant system and electronic equipment | |
| US20180068659A1 (en) | Voice recognition device and voice recognition method | |
| CN110203154B (en) | Recommendation method and device for vehicle functions, electronic equipment and computer storage medium | |
| CN102175255B (en) | The automated prioritization of map object | |
| CN106101168A (en) | Car-mounted terminal, cloud service equipment, onboard system and information processing method and device | |
| JP6956232B2 (en) | Search system, search method, and search program | |
| CN117573919A (en) | Car end music recommendation method, device, equipment and storage medium | |
| CN108959387B (en) | Information acquisition method and device | |
| CN111831929A (en) | Method and device for acquiring POI information | |
| CN114861056A (en) | Information pushing method and device, electronic equipment and storage medium | |
| US11874129B2 (en) | Apparatus and method for servicing personalized information based on user interest | |
| CN115214696A (en) | Vehicle machine virtual image interaction method, system, vehicle and storage medium | |
| CN117216249A (en) | Data classification method, device, electronic equipment, medium and vehicle | |
| JP2022103675A (en) | Information processing device, information processing method, and program | |
| KR20220029217A (en) | Method and system for providing local search terms based on location | |
| CN112562668A (en) | Semantic information deviation rectifying method and device | |
| CN112561657B (en) | Vehicle information processing method and device, electronic equipment and storage medium | |
| CN116168704B (en) | Voice interaction guiding method, device, equipment, medium and vehicle | |
| US20230178071A1 (en) | Method for determining a vehicle domain and a speech recognition system for a vehicle | |
| CN114969224B (en) | Vehicle test driving reservation method and device, electronic equipment and medium | |
| CN114296680B (en) | Virtual test driving device, method and storage medium based on facial image recognition |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |