CN117290605A - Vehicle-mounted intelligent scene recommendation method, device, equipment and medium - Google Patents
Vehicle-mounted intelligent scene recommendation method, device, equipment and medium Download PDFInfo
- Publication number
- CN117290605A CN117290605A CN202311485276.9A CN202311485276A CN117290605A CN 117290605 A CN117290605 A CN 117290605A CN 202311485276 A CN202311485276 A CN 202311485276A CN 117290605 A CN117290605 A CN 117290605A
- Authority
- CN
- China
- Prior art keywords
- user
- recommendation
- vehicle
- information
- target user
- 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 45
- 230000001815 facial effect Effects 0.000 claims abstract description 93
- 238000013136 deep learning model Methods 0.000 claims abstract description 48
- 230000006870 function Effects 0.000 claims abstract description 21
- 230000006399 behavior Effects 0.000 claims description 44
- 238000004590 computer program Methods 0.000 claims description 16
- 238000012549 training Methods 0.000 claims description 13
- 238000004378 air conditioning Methods 0.000 claims description 9
- 230000004044 response Effects 0.000 claims description 7
- 238000006243 chemical reaction Methods 0.000 claims description 6
- 230000036651 mood Effects 0.000 claims description 5
- 238000005457 optimization Methods 0.000 claims description 4
- 230000008447 perception Effects 0.000 abstract description 6
- 238000004891 communication Methods 0.000 description 8
- 238000012545 processing Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 4
- 230000001680 brushing effect Effects 0.000 description 3
- 230000003993 interaction Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000006872 improvement Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000003205 fragrance Substances 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 210000000697 sensory organ Anatomy 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000010408 sweeping Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 230000000007 visual effect 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
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/042—Knowledge-based neural networks; Logical representations of neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Biomedical Technology (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Databases & Information Systems (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The embodiment of the invention discloses a vehicle-mounted intelligent scene recommendation method, device, equipment and medium. The method comprises the following steps: responding to the facial feature information of the target user as non-first get-on, and acquiring user data information corresponding to the facial feature information; recommending the first vehicle-mounted intelligent scene to the target user according to the user attribute information and the optimal deep learning model; and responding to a voice operation instruction of the target user for the vehicle application service, and performing second intelligent scene recommendation on the target user according to the user permission information and the instruction field information of the voice operation instruction. According to the embodiment of the invention, through the technical scheme, the operation paths of the high-frequency scenes of the main driver and the passengers can be reduced, the overall user experience is improved, the perception of the common use and the new use of the automobile is improved by the user through the voice operation instruction function, the user participation degree is improved, the driving safety of the automobile is improved, and the excellent automobile operation experience is provided for the user.
Description
Technical Field
The invention relates to the technical field of vehicle scene recommendation, in particular to a vehicle-mounted intelligent scene recommendation method, device, equipment and medium.
Background
In the background of the increasing intellectualization of automobiles, current automobiles still know the automobile, rather than the mode of the automobile. With the rapid development of vehicle technology and the improvement of the living standard of people, vehicles have been popularized into thousands of households. However, as the usage rate of vehicles increases, the vehicles have gradually failed to meet the usage demands of users in the intelligent scene recommendation function. In the prior art, a user needs to select a theme store in limited wallpaper when switching desktop wallpaper, the user needs to repeatedly input and log in a car machine system or car machine application, the user frequently uses to select to buy an air ticket and find a parking space and find scenic spot information on a mobile phone because of inconvenient operation of the car machine, the whole car machine is not intelligent in use scene, different people get on the car, the car cannot distinguish main driving personnel, auxiliary driving personnel and passengers in the car, seat adjustment cannot be accurately and efficiently realized, the car is opened and the like, each operation needs manual clicking operation of the user, the whole interaction efficiency is very low, and the experience of the user is very poor.
Disclosure of Invention
In view of the above, the invention provides a vehicle-mounted intelligent scene recommendation method, device, equipment and medium, which can reduce the operation paths of main driving and passenger high-frequency scenes and improve the overall user experience; through the voice operation instruction function, the perception of the user on the common use and the new use of the vehicle is improved, the user participation degree is improved, the vehicle driving safety is improved, and excellent vehicle operation experience is provided for the user.
According to an aspect of the present invention, an embodiment of the present invention provides a vehicle-mounted intelligent scene recommendation method, including:
responding to the facial feature information of a target user as non-first getting on the vehicle, and acquiring user data information corresponding to the facial feature information; wherein, the user data information at least comprises user attribute information and user authority information;
performing first vehicle intelligent scene recommendation on the target user according to the user attribute information and a pre-trained optimal deep learning model; the optimal deep learning model is formed by training the collection of the target user behavior data based on a preset time granularity;
and responding to the voice operation instruction of the target user for the vehicle application service, and performing second intelligent scene recommendation on the target user according to the user permission information and the instruction field information of the voice operation instruction.
According to another aspect of the present invention, an embodiment of the present invention further provides a vehicle-mounted intelligent scene recommendation device, where the device includes:
the acquisition module is used for responding to the facial feature information of the target user as non-first get-on, and acquiring user data information corresponding to the facial feature information; wherein the user data information comprises user attribute information, user behavior information and user authority information;
The first recommendation module is used for recommending the first vehicle-mounted intelligent scene to the target user according to the user attribute information and a pre-trained optimal deep learning model; the optimal deep learning model is formed by training the collection of the target user behavior data based on a preset time granularity;
and the second recommendation module is used for responding to the voice operation instruction of the target user for the vehicle application service and recommending a second intelligent scene to the target user according to the user permission information and the instruction field information of the voice operation instruction.
According to another aspect of the present invention, an embodiment of the present invention further provides an electronic device, including:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the vehicle-mounted intelligent scene recommendation method according to any of the embodiments of the present invention.
According to another aspect of the present invention, an embodiment of the present invention further provides a computer readable storage medium, where the computer readable storage medium stores computer instructions, where the computer instructions are configured to cause a processor to execute the method for recommending a vehicle-mounted intelligent scene according to any one of the embodiments of the present invention.
According to the technical scheme, the user data information corresponding to the facial feature information is acquired through the fact that a target user gets on the vehicle for the first time; performing first vehicle intelligent scene recommendation on the target user according to the user attribute information and a pre-trained optimal deep learning model; responding to a voice operation instruction of a target user for vehicle application service, and recommending a second intelligent scene to the target user according to user permission information and instruction field information of the voice operation instruction, so that operation paths of high-frequency scenes of a main driver and passengers can be reduced, and overall user experience is improved; through the voice operation instruction function, the perception of the user on the common use and the new use of the vehicle is improved, the user participation degree is improved, the vehicle driving safety is improved, and excellent vehicle operation experience is provided for the user.
It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the invention or to delineate the scope of the invention. Other features of the present invention will become apparent from the description that follows.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart of a vehicle-mounted intelligent scene recommendation method according to an embodiment of the present invention;
FIG. 2 is a flowchart of another vehicle-mounted intelligent scene recommendation method according to an embodiment of the present invention;
FIG. 3 is a block diagram illustrating a vehicle-mounted intelligent scene recommendation device according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and the claims of the present invention and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
In an embodiment, fig. 1 is a flowchart of a vehicle-mounted intelligent scene recommendation method according to an embodiment of the present invention, where the method may be performed by a vehicle-mounted intelligent scene recommendation device, and the vehicle-mounted intelligent scene recommendation device may be implemented in hardware and/or software, and the vehicle-mounted intelligent scene recommendation device may be configured in an electronic device.
As shown in fig. 1, the vehicle-mounted intelligent scene recommendation method in this embodiment includes the specific steps of:
s110, responding to the facial feature information of a target user as non-first get-on, and acquiring user data information corresponding to the facial feature information; the user data information at least comprises user attribute information and user authority information.
Wherein the target user may include a car owner and/or a passenger. Facial feature information may also be referred to as face data information and may be understood as relevant facial feature information of the user, exemplary facial contour features, features of the five sense organs, and so forth.
In this embodiment, if the target user is not first boarding, the user data information of the target user may be stored in a corresponding preset database, where the user data information may include related attribute information and user authority information of the user, and of course, the user attribute information is basic information of the user, and may include, but is not limited to, user basic information that may be disclosed by gender, age, preference, and the like of the user; the user rights information may be understood as the user's voice control rights to the vehicle, which may include, but is not limited to, voice map generation rights, voice payment rights, and rights to third party application services in the voice controlled vehicle, and the embodiment is not limited herein.
In this embodiment, in response to the fact that the facial feature information of the target user is not the first get-on, that is, in the case that the user is not the first taking or driving of the vehicle, the user attribute information and the user permission information corresponding to the facial feature information may be obtained from the database in which the facial feature information is stored in the vehicle. It should be noted that, when the user attribute information and the user authority information corresponding to the facial feature information are the information of the face data of the user detected when the target user gets on the vehicle for the first time, the collected facial feature information is presented in a central control screen in the vehicle for display after the collected facial feature information is collected, and the owner can add the corresponding public information such as the user authority, the preference of the user, the age and the sex of the user, etc. to the facial feature information displayed in the central control screen.
S120, recommending a first vehicle-mounted intelligent scene to a target user according to user attribute information and a pre-trained optimal deep learning model; the optimal deep learning model is formed by training the collection of target user behavior data based on a preset time granularity.
The first vehicle intelligent scene recommendation may be understood as a vehicle intelligent application scene recommended to a user through an optimal deep learning model, and the first vehicle intelligent scene recommendation may include, but is not limited to, scene recommendation of seat adjustment, air conditioning mode, music preference, vehicle atmosphere lamp mode, movie watching mode, volume size, navigation, common desktop wallpaper, and the like.
In this embodiment, the optimal deep learning model may be a ChatGPT model or a convolutional neural network model, where the optimal deep learning model is formed by training the collection of the target user behavior data based on a preset time granularity.
In some embodiments, training of the optimal deep learning model includes: collecting user behavior data of a target user according to a preset second time granularity; wherein, the user behavior data at least comprises: seat adjustment, air conditioning mode, music preference, vehicle atmosphere lamp mode, movie viewing mode, volume size, navigation and common desktop wallpaper; associating the user behavior data with the facial feature information according to the user identification of the target user to obtain a corresponding association result; wherein, the user behavior data of the target user corresponds to the facial feature information one by one; and inputting the correlation result into the deep learning model for training until the loss function corresponding to the deep learning model reaches the minimum to obtain a trained optimal deep learning model. In this embodiment, behavior data of a target user is collected, and the behavior data is associated with basic data information; the marks (users a, b and car owners) are arranged at the beginning of collection, the marks can be combined, and the behavior habits of each person in driving and other seats can be collected by means of the marks, for example, the main driving is used for adjusting the seats forwards in three habits, the back is adjusted backwards slightly, the car is liked to start a 26-degree air conditioner, music is liked to start, rock-and-roll type tracks are played, and atmosphere lamps and fragrance are liked to start. For example, li IV likes to turn on a rest mode in noon to rest on the vehicle. For example, the king likes to watch the child interface in the back row, turns off the air conditioner and turns down the volume.
In this embodiment, user data information corresponding to facial feature information may be input into an optimal deep learning model to obtain a user behavior habit of a target user in a preset time period, and a first vehicle-mounted intelligent scene recommendation is performed on the target user according to the user behavior habit of the target user in the preset time period; in this embodiment, the first vehicle-mounted intelligent scene recommendation may include, but is not limited to: seat adjustment recommendation, air conditioning mode recommendation, music preference recommendation, vehicle mood light mode recommendation, movie mode recommendation, volume size recommendation, navigation recommendation, and desktop wallpaper recommendation. In some embodiments, vehicle data of a vehicle, user face images and user portrait data can be collected, and the vehicle data, the user face images and the user portrait data are identified by using a graph roll-up neural network to obtain expression information of a user so as to recommend a first vehicle intelligent scene to a target user based on the expression data of the user; in other embodiments, the correlation analysis may be performed on the scene information corresponding to the current driving scene of the user to be recommended to obtain the preference information of the user to be recommended, a plurality of preference similar users close to the preference of the user to be recommended are determined according to the preference information, and a recommendation list is constructed through the preference similar users to perform the first vehicle-mounted intelligent scene recommendation on the target user.
S130, responding to a voice operation instruction of the target user for the vehicle application service, and recommending a second intelligent scene to the target user according to the user permission information and instruction field information of the voice operation instruction; the voice operation instruction comprises the following steps: voice graphics instructions, voice payment instructions, and third party application service instructions.
The vehicle application service refers to a third party application service in the vehicle, and the third party application service may include, but is not limited to, a desktop wallpaper application, a ticket purchasing related application, a related map application, and the like. Instruction field information may be understood as the field content in a voice operation instruction.
In this embodiment, the second intelligent scene recommendation may be understood as an intelligent scene recommendation performed according to a voice operation instruction of a user after the user gets on a vehicle, and in this embodiment, the second intelligent scene recommendation may include, but is not limited to, a wallpaper picture recommendation corresponding to a voice generation picture, a payment scene recommendation corresponding to a voice payment, and a recommendation of a related application service.
In this embodiment, the execution sequence of S120 and S130 is not separately and S120 may be executed first after S110 is executed, and then S130 is executed; after S110 is performed, S130 may be performed first, and S120 may be performed later; after S110 is executed, S120 and S130 may be in a parallel execution state, which is not limited herein.
In this embodiment, the voice operation permission status in the user permission information may be searched according to the facial feature information of the target user, and whether the target user has the voice operation permission may be determined according to the voice operation permission status, so as to perform corresponding operation processing according to whether the target user has the voice operation permission. In some embodiments, the current demand may also be obtained after the voice data of the target user is parsed, the current demand is sent to the cloud and a second intelligent scene obtained based on the matching of the current demand and sent by the cloud is received; when the recommended second intelligent scene meets the preset starting condition, loading voice operation content corresponding to the second intelligent scene on the vehicle screen, wherein the embodiment is not limited.
According to the technical scheme, the user data information corresponding to the facial feature information is acquired through the fact that a target user gets on the vehicle for the first time; performing first vehicle intelligent scene recommendation on the target user according to the user attribute information and a pre-trained optimal deep learning model; responding to a voice operation instruction of a target user for vehicle application service, and recommending a second intelligent scene to the target user according to user permission information and instruction field information of the voice operation instruction, so that operation paths of high-frequency scenes of a main driver and passengers can be reduced, and overall user experience is improved; through the voice operation instruction function, the perception of the user on the common use and the new use of the vehicle is improved, the user participation degree is improved, the vehicle driving safety is improved, and excellent vehicle operation experience is provided for the user.
In an embodiment, the method further comprises:
checking the scene utilization rate and the scene rejection rate of the optimal deep learning model for performing the scene recommendation function on the target user according to the preset first time granularity;
if the target user meets the first condition within the preset time period, intelligent optimization is performed on the optimal deep learning model according to the behavior habit, the scene utilization rate or the scene rejection rate of the target user; wherein the first condition comprises one of: the number of times that the target user changes the scene recommendation function reaches a preset number of times threshold; the scene usage is lower than a preset first threshold; the scene rejection rate is higher than a preset second threshold.
The preset first threshold value refers to a scene use rate threshold value, and if the scene use rate is lower than the preset first threshold value, the use rate of a certain recommended scene is represented as not high by a user; the preset second threshold refers to a rejection rate of a certain recommended scene by the user, and if the scene rejection rate is higher than the preset second threshold, the user does not want to use the currently recommended scene.
In this embodiment, the preset first time granularity may include time granularity of day, week, and month. In the embodiment, the model can be continuously trained according to the day, the week and the month, the usage rate of the regular multi-disc model recommending function and the scene, the rejection rate can be reduced more comprehensively through the model, and the operation behavior and the operation habit of each user can be restored more naturally and intelligently for the whole user. Specifically, a first time granularity can be preset to check the scene utilization rate and the scene rejection rate of the optimal deep learning model for performing the scene recommendation function on the target user; if the target user meets the first condition within the preset time period, intelligent optimization is performed on the optimal deep learning model according to the behavior habit, the scene utilization rate or the scene rejection rate of the target user; wherein the first condition comprises one of: the number of times that the target user changes the scene recommendation function reaches a preset number of times threshold; the scene usage is lower than a preset first threshold; the scene rejection rate is higher than a preset second threshold.
In an embodiment, fig. 2 is a flowchart of another vehicle-mounted intelligent scene recommendation method provided by an embodiment of the present invention, where, based on the above embodiments, before the step of obtaining user data information corresponding to facial feature information in response to the facial feature information of the target user being not first on-vehicle, and before the step of obtaining user data information corresponding to the facial feature information, and according to user attribute information and a pre-trained optimal deep learning model, the first vehicle-mounted intelligent scene recommendation is performed on the target user, and, in response to a voice operation instruction of the target user for a vehicle application service, the second intelligent scene recommendation is further refined on the target user according to user permission information and instruction field information of the voice operation instruction.
As shown in fig. 2, the vehicle-mounted intelligent scene recommendation method in this embodiment may specifically include the following steps:
s210, acquiring facial information of a target user through at least two acquisition devices to obtain facial feature information, and performing feature matching on the facial feature information and candidate facial feature information in a preset user database.
The preset user database comprises collected facial feature information of a plurality of users. The candidate facial feature information is all facial feature information of a preset user database.
In this embodiment, facial feature information is obtained by collecting facial information of a target user through at least two collecting devices, and feature matching is performed on the facial feature information and candidate facial feature information in a preset user database. In this embodiment, the collecting device in the vehicle collects face data respectively, and after face scanning, the owner can define basic information (age, character, preference) of each person and corresponding authority content on the vehicle. (sweeping faces corresponds to the process of registering an account, and basic information is filled in during registration, wherein each face corresponds to one id.)
S220, if the matching degree between the facial feature information and the candidate facial feature information reaches a preset matching degree threshold, determining that the target user is not getting on the vehicle for the first time.
In this embodiment, if the matching degree between the facial feature information and the candidate facial feature information reaches the preset matching degree threshold, it is determined that the target user is not getting on the vehicle for the first time.
S230, if the matching degree between the facial feature information and the candidate facial feature information does not reach the preset matching degree threshold, determining that the target user is the last time, configuring user data information corresponding to the facial feature information, and inputting the user data information into a preset database.
In this embodiment, if the matching degree between the facial feature information and the candidate facial feature information does not reach the preset matching degree threshold, it is determined that the target user is the last time, the user data information corresponding to the facial feature information is configured, and the user data information is input into a preset database. It can be understood that, when the car owner and the passenger get on the car for the first time, face data are collected, basic user information is input, face data initialization is completed, and face feature information of each person, and contents such as basic information, preference, authority and the like disclosed can be known. Basic information of each person and some operation rights which each person can carry out on a vehicle complete some basic inputs, the basic information of a target user is known only by the input, and relevant rights and the like exist.
S240, responding to the facial feature information of the target user as the non-first get-on, and acquiring the user data information corresponding to the facial feature information.
In this embodiment, in response to the facial feature information of the target user being the non-first get-on, user data information corresponding to the facial feature information is acquired.
S250, inputting user data information corresponding to the facial feature information into an optimal deep learning model to obtain user behavior habits of a target user in a preset time period.
The preset time period may be understood as a period of time, such as a week, a day, two weeks, etc.
In this embodiment, user data information corresponding to facial feature information is input into an optimal deep learning model to obtain a user behavior habit of a target user in a preset time period. It can be understood that a series of user behaviors of a user at a specific time are standardized to generate an intelligent scene through user data information and an optimal deep learning model, and the intelligent scene is automatically executed at regular intervals under the condition of obtaining user consent, so that an operation chain of the high-frequency behaviors of the user is reduced. Exemplary: the user a gets on the car, faces the identity of the person, automatically adjusts the seat habit corresponding to the user a according to the use habit of the user a, automatically adjusts the air conditioner use habit corresponding to the user a, and automatically plays the music preference corresponding to the user a.
S260, recommending a first vehicle-mounted intelligent scene to the target user according to the behavior habit of the user; wherein the first vehicle-mounted intelligent scene recommendation at least comprises: seat adjustment recommendation, air conditioning mode recommendation, music preference recommendation, vehicle mood light mode recommendation, movie mode recommendation, volume size recommendation, navigation recommendation, and desktop wallpaper recommendation.
In this embodiment, the first vehicle-mounted intelligent scene recommendation may be performed on the target user according to the user behavior habit; wherein the first vehicle-mounted intelligent scene recommendation at least comprises: seat adjustment recommendation, air conditioning mode recommendation, music preference recommendation, vehicle mood light mode recommendation, movie mode recommendation, volume size recommendation, navigation recommendation, and desktop wallpaper recommendation.
S270, responding to a voice operation instruction of the target user for the vehicle application service, and searching whether the voice operation authority in the user authority information is in an open state or not according to the facial feature information.
In this embodiment, the voice operation instruction may include, but is not limited to: voice graphics instructions, voice payment instructions, and third party application service instructions. In this embodiment, in response to a voice operation instruction of a target user for a vehicle application service, whether the voice operation authority in the user authority information is in an on state is searched according to facial feature information.
S280, under the condition that the voice operation authority is in an open state, analyzing the voice operation instruction to obtain corresponding operation field content, and recommending a second intelligent scene to the target user according to the operation field content; wherein, the content of the operation field at least comprises: voice generation, voice payment, and voice application services.
In this embodiment, under the condition that the voice operation authority is in an on state, analyzing the voice operation instruction to obtain corresponding operation field content, and recommending a second intelligent scene to the target user according to the operation field content; wherein, the content of the operation field at least comprises: voice generation, voice payment, and voice application services. Specifically, when the voice operation instruction is a voice image generation instruction, the voice image generation instruction is analyzed to obtain first field content, and the first field content is automatically converted into characters and converted into pictures through the characters so as to recommend picture scenes. When the voice operation instruction is a voice payment instruction, analyzing the voice payment instruction to obtain second field content, searching payment application service in the vehicle according to the second field content, and paying through the payment application service to recommend a payment scene. And when the voice operation instruction is a third-party application service instruction, analyzing keywords and events included in the third-party application service instruction, and searching target application services meeting the conditions in the third-party application service according to the keywords and the events for comprehensive display so as to recommend the application service.
In an embodiment, S280 may include: s2801 to S2804:
S2801, under the condition that the voice operation authority is in an on state, analyzing the voice operation instruction to obtain corresponding operation field content, when the voice operation instruction is a voice image generation instruction, analyzing the voice image generation instruction to obtain first field content, automatically converting the first field content into characters, automatically converting the characters into a picture form through a picture conversion tool, displaying the picture into a vehicle center control frequency, and recommending picture scenes.
The first field content is the field content corresponding to the voice generating instruction.
In this embodiment, when the voice operation instruction is a voice image generation instruction, the voice image generation instruction is analyzed to obtain a first field content, the first field content is automatically converted into characters, the characters are automatically converted into a picture form by a picture conversion tool, and the picture is displayed in a vehicle center frequency control for picture scene recommendation. In this embodiment, the image conversion tool may be a conventional image conversion tool, and the detailed description of this embodiment is omitted here. By way of example, the desktop wallpaper picture is directly generated through voice dialogue, the user can automatically turn the text by speaking, and the text automatically generates the picture to be used as the desktop wallpaper of the vehicle.
And S2802, when the voice operation instruction is a voice payment instruction, analyzing the voice payment instruction to obtain second field content, searching payment application service in the vehicle according to the second field content, and paying through the payment application service to recommend a payment scene.
The second field content is the field content corresponding to the voice payment instruction.
In this embodiment, when the voice operation instruction is a voice payment instruction, the voice payment instruction is parsed to obtain a second field content, and a payment application service in the vehicle is searched according to the second field content, and payment is performed through the payment application service, so as to perform payment scene recommendation. Illustratively, the vehicle leaves the parking lot and pays by brushing the face; the three-party ecological application in the vehicle needs the scene of payment, and the face brushing can also be directly paid.
And S2803, when the voice operation instruction is a third party application service instruction, analyzing keywords and events included in the third party application service instruction, searching the keywords according to an API (application program interface) of the third party application service included in the vehicle, and searching target application services meeting the conditions in the third party application service according to the keywords and the events for comprehensive display so as to recommend the application services.
In this embodiment, when the voice operation instruction is a third party application service instruction, the keywords and the events included in the third party application service instruction are analyzed, the keywords are retrieved according to the API interface of the third party application service included in the vehicle, and the target application service meeting the conditions in the third party application service is searched for comprehensive display according to the keywords and the events, so as to recommend the application service. Illustratively, through voice conversations, the application service is directly reached, reducing the intermediate links. For example, voice saying that I want to subscribe to an airplane from Huizhou to Beijing around 2 pm on tomorrow, automatically listing eligible shifts, and voice ordering can be done directly. For example, voice saying that me is to find a parking lot nearby here, automatically recommending a suitable parking lot, and recommending a parking floor nearest to the destination, specifically to a certain free parking space.
Besides, after the car owner gets on the car, the face brushing second login can be performed: the main driver gets on the car, automatically logs in the account of the car machine, automatically logs in the accounts of the three parties such as music, video and the like, and automatically gets off the car.
S2804, taking the picture scene recommendation, the payment scene recommendation, and the application service recommendation as the second intelligent scene recommendation.
In this embodiment, the picture scene recommendation, the payment scene recommendation, and the application service recommendation are taken as the second intelligent scene recommendation.
According to the technical scheme, the user behavior habit of the target user in the preset time period is obtained by inputting the user data information corresponding to the facial feature information into the optimal deep learning model; according to the user behavior habit, a first vehicle-mounted intelligent scene recommendation is carried out on a target user, whether a voice operation authority in user authority information is in an on state or not is searched according to facial feature information, when a voice operation instruction is a voice image generation instruction, the voice image generation instruction is analyzed to obtain first field content, the first field content is automatically converted into characters, the characters are automatically converted into a picture form through a picture conversion tool, and the picture is displayed in a vehicle center frequency control mode to carry out picture scene recommendation; when the voice operation instruction is a voice payment instruction, analyzing the voice payment instruction to obtain second field content, searching payment application service in the vehicle according to the second field content, and paying through the payment application service to recommend a payment scene; when the voice operation instruction is a third party application service instruction, analyzing keywords and events included in the third party application service instruction, searching the keywords according to an API (application program interface) of the third party application service included in the vehicle, searching target application services meeting the conditions in the third party application service according to the keywords and the events, and comprehensively displaying the target application services to perform application service recommendation, so that the operation paths of a main driver and a passenger in a high-frequency scene can be further reduced, the overall user experience is improved, the perception of a user on a vehicle machine in a normal use is improved through the voice operation function, the user participation is improved, the driving safety of the vehicle is improved through intelligent application operation, and the extremely product experience is brought to the user.
In an embodiment, fig. 3 is a block diagram of a vehicle-mounted intelligent scene recommendation device according to an embodiment of the present invention, where the device is suitable for a situation when intelligent recommendation is performed on a vehicle-mounted scene, and the device may be implemented by hardware/software. The vehicle-mounted intelligent scene recommendation method can be configured in the electronic equipment to realize the vehicle-mounted intelligent scene recommendation method in the embodiment of the invention.
As shown in fig. 3, the apparatus includes: an acquisition module 310, a first recommendation module 320, and a second recommendation module 330.
The acquiring module 310 is configured to acquire user data information corresponding to facial feature information of a target user in response to the facial feature information being a non-first boarding; wherein the user data information comprises user attribute information, user behavior information and user authority information;
the first recommendation module 320 is configured to recommend a first vehicle-mounted intelligent scene to the target user according to the user attribute information and a pre-trained optimal deep learning model; the optimal deep learning model is formed by training the collection of the target user behavior data based on a preset time granularity;
a second recommendation module 330, configured to respond to a voice operation instruction of the target user for the vehicle application service, and perform a second intelligent scene recommendation on the target user according to the user permission information and instruction field information of the voice operation instruction; wherein the voice operation instruction comprises: voice graphics instructions, voice payment instructions, and third party application service instructions.
According to the embodiment of the invention, the first recommendation module recommends a first vehicle-mounted intelligent scene for a target user through an optimal deep learning model trained in advance according to user attribute information; the second recommendation module responds to a voice operation instruction of the target user for the vehicle application service, and carries out second intelligent scene recommendation on the target user according to user permission information and instruction field information of the voice operation instruction, so that the operation paths of high-frequency scenes of a main driver and passengers can be reduced, and the overall user experience is improved; through the voice operation instruction function, the perception of the user on the common use and the new use of the vehicle is improved, the user participation degree is improved, the vehicle driving safety is improved, and excellent vehicle operation experience is provided for the user.
In an embodiment, the apparatus further comprises:
the feature matching module is used for acquiring the facial information of the target user through at least two acquisition devices to obtain the facial feature information before the facial feature information of the target user is not the first driving, and carrying out feature matching on the facial feature information and candidate facial feature information in a preset user database;
The first determining module is used for determining that the target user is not on the vehicle for the first time if the matching degree between the facial feature information and the candidate facial feature information reaches a preset matching degree threshold;
and the second determining module is used for determining that the target user is the last time if the matching degree between the facial feature information and the candidate facial feature information does not reach the preset matching degree threshold value, configuring user data information corresponding to the facial feature information and inputting the user data information into the preset database.
In an embodiment, the apparatus further comprises:
the verification module is used for verifying the scene utilization rate and the scene rejection rate of the optimal deep learning model for performing the scene recommendation function on the target user according to the preset first time granularity;
the optimization module is used for intelligently optimizing the optimal deep learning model according to the behavior habit of the target user, the scene utilization rate or the scene rejection rate if the target user meets a first condition within a preset time period; wherein the first condition includes one of: the number of times that the target user changes the scene recommendation function reaches a preset number of times threshold; the scene usage rate is lower than a preset first threshold value; the scene rejection rate is higher than a preset second threshold.
In an embodiment, the training of the optimal deep learning model includes:
collecting user behavior data of the target user according to a preset second time granularity; wherein the user behavior data at least comprises: seat adjustment, air conditioning mode, music preference, vehicle atmosphere lamp mode, movie viewing mode, volume size, navigation and common desktop wallpaper;
associating the user behavior data with the facial feature information according to the user identification of the target user to obtain a corresponding association result; wherein, the user behavior data of the target user corresponds to the facial feature information one by one;
and inputting the correlation result into a deep learning model for training until a loss function corresponding to the deep learning model reaches minimum, thereby obtaining a trained optimal deep learning model.
In an embodiment, the first recommendation module 320 includes:
the input unit is used for inputting the user data information corresponding to the facial feature information into the optimal deep learning model to obtain the user behavior habit of the target user in a preset time period;
the first recommendation unit is used for recommending the first vehicle-mounted intelligent scene to the target user according to the user behavior habit; wherein, the first vehicle-mounted intelligent scene recommendation at least includes: seat adjustment recommendation, air conditioning mode recommendation, music preference recommendation, vehicle mood light mode recommendation, movie mode recommendation, volume size recommendation, navigation recommendation, and desktop wallpaper recommendation.
In an embodiment, the second recommendation module includes:
the permission determining unit is used for searching whether the voice operation permission in the user permission information is in an open state or not according to the facial feature information;
the second recommending unit is used for analyzing the voice operation instruction to obtain corresponding operation field content under the condition that the voice operation authority is in an open state, and recommending a second intelligent scene to the target user according to the operation field content; wherein, the operation field content at least comprises: voice generation, voice payment, and voice application services.
In an embodiment, the voice operation instructions include: a voice map generation instruction, a voice payment instruction and a third party application service instruction; correspondingly, the second recommendation unit comprises:
the picture scene recommending subunit is used for analyzing the voice image generating instruction to obtain first field content when the voice operation instruction is the voice image generating instruction, automatically converting the first field content into characters, automatically converting the characters into a picture form through a picture converting tool and displaying the picture form in a vehicle center frequency control for picture scene recommending;
The payment scene recommendation subunit is used for analyzing the voice payment instruction to obtain second field content when the voice operation instruction is the voice payment instruction, searching a payment application service in the vehicle according to the second field content, and paying through the payment application service to recommend the payment scene;
the application service recommending subunit is used for analyzing keywords and events included in the third-party application service instruction when the voice operation instruction is the third-party application service instruction, searching the keywords according to an API interface of the third-party application service included in the vehicle, and searching target application services meeting the conditions in the third-party application service according to the keywords and the events for comprehensive display so as to recommend the application service;
and the composition subunit is used for taking the picture scene recommendation, the payment scene recommendation and the application service recommendation as second intelligent scene recommendation.
The vehicle-mounted intelligent scene recommendation device provided by the embodiment of the invention can execute the vehicle-mounted intelligent scene recommendation processing method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.
In an embodiment, fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present invention. The electronic device 10 is intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. Electronic equipment may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.
As shown in fig. 4, the electronic device 10 includes at least one processor 11, and a memory, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, etc., communicatively connected to the at least one processor 11, in which the memory stores a computer program executable by the at least one processor, and the processor 11 may perform various appropriate actions and processes according to the computer program stored in the Read Only Memory (ROM) 12 or the computer program loaded from the storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 may also be stored. The processor 11, the ROM 12 and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to bus 14.
Various components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, etc.; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.
The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, digital Signal Processors (DSPs), and any suitable processor, controller, microcontroller, etc. The processor 11 performs the various methods and processes described above, such as the in-vehicle intelligent scene recommendation method.
In some embodiments, the in-vehicle intelligent scene recommendation processing method may be implemented as a computer program tangibly embodied on a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 10 via the ROM 12 and/or the communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the in-vehicle intelligent scene recommendation method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the in-vehicle intelligent scene recommendation method in any other suitable manner (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
A computer program for carrying out methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable vehicle-mounted intelligent scene recommendation device, such that the computer programs, when executed by the processor, cause the functions/operations specified in the flowchart and/or block diagram block or blocks to be implemented. The computer program may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.
The computing system may include clients and servers. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service are overcome.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present invention may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution of the present invention are achieved, and the present invention is not limited herein.
The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.
Claims (10)
1. The vehicle-mounted intelligent scene recommendation method is characterized by comprising the following steps of:
responding to the facial feature information of a target user as non-first getting on the vehicle, and acquiring user data information corresponding to the facial feature information; wherein, the user data information at least comprises user attribute information and user authority information;
performing first vehicle intelligent scene recommendation on the target user according to the user attribute information and a pre-trained optimal deep learning model; the optimal deep learning model is formed by training the collection of the target user behavior data based on a preset time granularity;
Responding to a voice operation instruction of the target user for vehicle application service, and performing second intelligent scene recommendation on the target user according to the user permission information and instruction field information of the voice operation instruction; wherein the voice operation instruction comprises: voice graphics instructions, voice payment instructions, and third party application service instructions.
2. The method of claim 1, further comprising, prior to the obtaining user data information corresponding to the facial feature information in response to the target user facial feature information being a non-first-time drive-in,:
acquiring facial information of the target user through at least two acquisition devices to obtain facial feature information, and performing feature matching on the facial feature information and candidate facial feature information in a preset user database;
if the matching degree between the facial feature information and the candidate facial feature information reaches a preset matching degree threshold value, determining that the target user is not on the vehicle for the first time;
if the matching degree between the facial feature information and the candidate facial feature information does not reach the preset matching degree threshold value, determining that the target user is the last time, configuring user data information corresponding to the facial feature information, and inputting the user data information into the preset database.
3. The method according to claim 1, characterized in that the method further comprises:
checking the scene utilization rate and the scene rejection rate of the optimal deep learning model for performing a scene recommendation function on the target user according to a preset first time granularity;
if the target user meets a first condition within a preset time period, intelligent optimization is performed on the optimal deep learning model according to the behavior habit of the target user, the scene utilization rate or the scene rejection rate; wherein the first condition includes one of: the number of times that the target user changes the scene recommendation function reaches a preset number of times threshold; the scene usage rate is lower than a preset first threshold value; the scene rejection rate is higher than a preset second threshold.
4. The method of claim 1, wherein the training of the optimal deep learning model comprises:
collecting user behavior data of the target user according to a preset second time granularity; wherein the user behavior data at least comprises: seat adjustment, air conditioning mode, music preference, vehicle atmosphere lamp mode, movie viewing mode, volume size, navigation and common desktop wallpaper;
Associating the user behavior data with the facial feature information according to the user identification of the target user to obtain a corresponding association result; wherein, the user behavior data of the target user corresponds to the facial feature information one by one;
and inputting the correlation result into a deep learning model for training until a loss function corresponding to the deep learning model reaches minimum, thereby obtaining a trained optimal deep learning model.
5. The method of claim 1, wherein said performing a first vehicle-mounted intelligent scene recommendation on said target user based on said user attribute information and a pre-trained optimal deep learning model comprises:
inputting user data information corresponding to the facial feature information into the optimal deep learning model to obtain user behavior habits of the target user in a preset time period;
performing first vehicle-mounted intelligent scene recommendation on the target user according to the user behavior habit; wherein, the first vehicle-mounted intelligent scene recommendation at least includes: seat adjustment recommendation, air conditioning mode recommendation, music preference recommendation, vehicle mood light mode recommendation, movie mode recommendation, volume size recommendation, navigation recommendation, and desktop wallpaper recommendation.
6. The method according to claim 1, wherein said performing a second intelligent scene recommendation on said target user according to said user authority information and instruction field information of said voice operation instruction comprises:
searching whether the voice operation authority in the user authority information is in an open state or not according to the facial feature information;
under the condition that the voice operation authority is in an open state, analyzing the voice operation instruction to obtain corresponding operation field content, and recommending a second intelligent scene to the target user according to the operation field content; wherein, the operation field content at least comprises: voice generation, voice payment, and voice application services.
7. The method of claim 6, wherein the parsing the voice operation command to obtain corresponding operation field content and performing a second intelligent scene recommendation for the target user according to the operation field content comprises:
when the voice operation instruction is a voice picture generation instruction, analyzing the voice picture generation instruction to obtain first field content, automatically converting the first field content into characters, automatically converting the characters into a picture form through a picture conversion tool, and displaying the picture into a vehicle center frequency control for picture scene recommendation;
When the voice operation instruction is a voice payment instruction, analyzing the voice payment instruction to obtain second field content, searching a payment application service in the vehicle according to the second field content, and paying through the payment application service to recommend a payment scene;
when the voice operation instruction is a third party application service instruction, analyzing keywords and events included in the third party application service instruction, searching the keywords according to an API (application program interface) of third party application service included in a vehicle, and searching target application services meeting the conditions in the third party application service according to the keywords and the events for comprehensive display so as to recommend the application services;
and taking the picture scene recommendation, the payment scene recommendation and the application service recommendation as second intelligent scene recommendation.
8. An on-board intelligent scene recommendation device, characterized in that the device comprises:
the acquisition module is used for responding to the facial feature information of the target user as non-first get-on, and acquiring user data information corresponding to the facial feature information; wherein the user data information comprises user attribute information, user behavior information and user authority information;
The first recommendation module is used for recommending the first vehicle-mounted intelligent scene to the target user according to the user attribute information and a pre-trained optimal deep learning model; the optimal deep learning model is formed by training the collection of the target user behavior data based on a preset time granularity;
the second recommendation module is used for responding to the voice operation instruction of the target user for the vehicle application service and recommending a second intelligent scene to the target user according to the user permission information and the instruction field information of the voice operation instruction; wherein the voice operation instruction comprises: voice graphics instructions, voice payment instructions, and third party application service instructions.
9. An electronic device, the electronic device comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the in-vehicle intelligent scene recommendation method of any of claims 1-7.
10. A computer readable storage medium, characterized in that the computer readable storage medium stores computer instructions for causing a processor to implement the vehicle-mounted intelligent scene recommendation method according to any one of claims 1-7 when executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311485276.9A CN117290605A (en) | 2023-11-08 | 2023-11-08 | Vehicle-mounted intelligent scene recommendation method, device, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311485276.9A CN117290605A (en) | 2023-11-08 | 2023-11-08 | Vehicle-mounted intelligent scene recommendation method, device, equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117290605A true CN117290605A (en) | 2023-12-26 |
Family
ID=89239234
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311485276.9A Pending CN117290605A (en) | 2023-11-08 | 2023-11-08 | Vehicle-mounted intelligent scene recommendation method, device, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117290605A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117899492A (en) * | 2024-03-20 | 2024-04-19 | 成都帆点创想科技有限公司 | Real-time recommendation method and system for game playing scenes |
-
2023
- 2023-11-08 CN CN202311485276.9A patent/CN117290605A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117899492A (en) * | 2024-03-20 | 2024-04-19 | 成都帆点创想科技有限公司 | Real-time recommendation method and system for game playing scenes |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11893311B2 (en) | Virtual assistant configured to automatically customize groups of actions | |
| KR102050334B1 (en) | Automatic suggestion responses to images received in messages, using the language model | |
| US11295221B2 (en) | Learning user preferences in a conversational system | |
| CN110446057B (en) | Method, device and equipment for providing live auxiliary data and readable medium | |
| CN109308357B (en) | Method, device and equipment for obtaining answer information | |
| CN111666380A (en) | Intelligent calling method, device, equipment and medium | |
| CN110020022B (en) | Data processing method, device, equipment and readable storage medium | |
| US20200143000A1 (en) | Customized display of emotionally filtered social media content | |
| CN117290605A (en) | Vehicle-mounted intelligent scene recommendation method, device, equipment and medium | |
| US12014411B2 (en) | Vehicle listing generation and optimization system | |
| CN109996026A (en) | Video special effect interaction method, device, equipment and medium based on wearable equipment | |
| CN105824863A (en) | Desktop theme recommending method and terminal | |
| CN112052316A (en) | Model evaluation method, model evaluation device, storage medium and electronic equipment | |
| CN111967750A (en) | Vehicle matching method, device, terminal and storage medium | |
| CN116501432A (en) | Vehicle wallpaper generation method and device, electronic equipment and readable storage medium | |
| CN111866578A (en) | Data processing method and device, electronic equipment and computer readable storage medium | |
| CN117131270A (en) | Content generation method and system | |
| US20220382799A1 (en) | Recommending multimedia information | |
| CN115860829A (en) | Intelligent advertisement image generation method and device | |
| CN110287422B (en) | Information providing apparatus and control method thereof | |
| CN113890948A (en) | Resource allocation method based on voice outbound robot dialogue data and related equipment | |
| CN112148849A (en) | Dynamic interaction method, server, electronic device and storage medium | |
| CN116483310B (en) | In-vehicle volume adjusting method, device, equipment and medium | |
| CN114925108A (en) | Determination method, device and equipment of sequencing model and storage medium | |
| CN116166835A (en) | Intelligent recommendation method and system |
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 |