CN114995658A - Active interactive recommendation method applied to different emotions of driver - Google Patents
Active interactive recommendation method applied to different emotions of driver Download PDFInfo
- Publication number
- CN114995658A CN114995658A CN202210920590.4A CN202210920590A CN114995658A CN 114995658 A CN114995658 A CN 114995658A CN 202210920590 A CN202210920590 A CN 202210920590A CN 114995658 A CN114995658 A CN 114995658A
- Authority
- CN
- China
- Prior art keywords
- scene
- recommended
- action
- determining
- driver
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/011—Arrangements for interaction with the human body, e.g. for user immersion in virtual reality
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
- B60R16/00—Electric or fluid circuits specially adapted for vehicles and not otherwise provided for; Arrangement of elements of electric or fluid circuits specially adapted for vehicles and not otherwise provided for
- B60R16/02—Electric or fluid circuits specially adapted for vehicles and not otherwise provided for; Arrangement of elements of electric or fluid circuits specially adapted for vehicles and not otherwise provided for electric constitutive elements
- B60R16/023—Electric or fluid circuits specially adapted for vehicles and not otherwise provided for; Arrangement of elements of electric or fluid circuits specially adapted for vehicles and not otherwise provided for electric constitutive elements for transmission of signals between vehicle parts or subsystems
- B60R16/0231—Circuits relating to the driving or the functioning of the vehicle
-
- 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
- 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
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2203/00—Indexing scheme relating to G06F3/00 - G06F3/048
- G06F2203/01—Indexing scheme relating to G06F3/01
- G06F2203/011—Emotion or mood input determined on the basis of sensed human body parameters such as pulse, heart rate or beat, temperature of skin, facial expressions, iris, voice pitch, brain activity patterns
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Human Computer Interaction (AREA)
- Automation & Control Theory (AREA)
- Mechanical Engineering (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention provides an active interactive recommendation method applied to different emotions of a driver, which is characterized in that the emotional state of the driver is identified through a Driver Monitoring System (DMS); and identifying the date information of the day through the vehicle calendar; determining and generating scene information according to the emotional state and the date information; judging the scene information according to the recommended resistance model, and judging whether to trigger a first scene; according to the first scene, executing corresponding action recommendation, prompting a user and acquiring a user response; the user response includes a rejection or an acceptance. The method comprises the steps of performing scene decision by fusing multi-modal data such as vehicle, environment and in-vehicle user behaviors and voice, providing active interaction scene service, using DMS video data of a driver monitoring system in the vehicle to monitor different emotions of a driver in the vehicle, and using data such as date information and time of the day as input, and providing accurate active interaction action recommendation for the user.
Description
Technical Field
The invention relates to the technical field of interactive recommendation, in particular to an active interactive recommendation method applied to different emotions of a driver.
Background
The intelligent automobile is developed rapidly, the automobile becomes a third living space of people, along with the increase of automobile using scenes and time, the requirement of people on the function configuration of the automobile is more and more increased, the requirement dimension on the cabin function is continuously expanded for users, and except safety, the cabin needs to meet active intelligence and service plus content; for enterprises, the enterprises hope to break through the bottleneck of serious cabin product homogenization, and intelligent interactive service with brand modulation is formed through personalized scene definition and recommendation algorithm.
The current intelligent cockpit products still do not meet the requirements of user personalization and scene from the interaction level, the personalization is not enough, the intelligent degree of active interaction is not high, and the factors which are still the most unsatisfactory for consumers include: on one hand, the individuation is insufficient, the scene and customization capabilities are insufficient on one side of thousands of people, and the scene service lacks the continuous iteration capability; on the other hand, the service is not active, people find the service, and the selection is difficult.
Disclosure of Invention
In view of this, an object of the embodiments of the present invention is to provide an active interaction recommendation method applied to different emotions of a driver, which provides an active interaction scene service after performing scene decision by fusing multimodal data such as vehicle, environment, and in-vehicle user behavior and voice, and provides accurate active interaction action recommendation for a user.
A first aspect of the invention provides an active interaction recommendation method applied to different emotions of a driver, which comprises the following steps:
s1, recognizing the emotional state of the driver through the driver monitoring system DMS; and identifying the date information of the day through the vehicle calendar; determining and generating scene information according to the emotional state and the date information;
s2, judging the scene information according to the recommended resistance model, and judging whether to trigger a first scene;
s3, according to the first scene, executing corresponding action recommendation, and prompting the user to obtain a user response; the user response comprises a rejection or an acceptance;
s4, obtaining a mapping relation among the first scene, the recommended action and the user response in a historical preset time period, and generating or updating the recommended resistance model based on the mapping relation.
Further, the first scenario corresponds to one or more recommended actions; determining the recommended action rejected by the user as a blacklist, and determining the recommended action accepted by the user as a whitelist;
the generating or updating the recommended resistance model based on the mapping relationship includes:
determining recommended actions in a first scene in the mapping relation as the proportion of a blacklist;
if the proportion exceeds a preset threshold value, determining that recommended resistance exists, and not recommending the recommended action; otherwise, it is determined that there is no recommended resistance and the recommended action is determined as the first recommended action.
Further, the determining the scene information according to the recommended resistance model and determining whether to trigger the first scene includes:
determining a corresponding first scene according to the scene information;
determining whether the first scene has a corresponding first recommended action in a recommended resistance model; if yes, triggering a first scene;
the controlling and executing corresponding action recommendation according to the first scene comprises: controlling the recommendation of the first recommended action to be performed.
Preferably, the emotional state comprises sadness, surprise, happiness and natural state; the date information includes a legal work day;
the obtaining a mapping relationship among a first scene, a recommended action and a user response in a historical predetermined time period, and generating or updating the recommended resistance model based on the mapping relationship includes:
acquiring time period information, a first scene, recommended actions and user responses at different time periods in a day in a historical preset time period, and establishing a mapping relation among the time period information, the first scene, the recommended actions and the user responses;
the judging the scene information according to the recommended resistance model and judging whether to trigger a first scene further comprises:
acquiring time information of current driving and determining a time period of the current driving;
determining whether the first scene has the corresponding first recommended action in the corresponding current time period in the recommended resistance model; if yes, triggering a first scene.
Further, the main body for controlling and executing the corresponding action recommendation comprises a main driving seat and/or a central control screen and/or TTS broadcast;
the action recommendation of the main driving seat comprises the front-back adjustment and/or the backrest adjustment of the seat;
and triggering the TTS broadcast to synchronously execute the broadcast when the central control screen executes the display of the picture.
Furthermore, a second aspect of the present invention provides an active interaction recommendation system applied to different emotions of a driver, the system comprising:
the identification module is used for identifying the emotional state of the driver through the driver monitoring system DMS; and identifying the date information of the day through the vehicle calendar; determining and generating scene information according to the emotional state and the date information;
the judging module is used for judging the scene information according to the recommended resistance model and judging whether to trigger a first scene or not;
the recommendation module executes corresponding action recommendation according to the first scene, prompts a user and acquires a user response; the user response comprises a rejection or an acceptance;
the generation and update module acquires a mapping relation among a first scene, recommended actions and user responses in a historical preset time period, and generates or updates the recommended resistance model based on the mapping relation.
Further, the first scenario corresponds to one or more recommended actions; determining the recommended action rejected by the user as a blacklist, and determining the recommended action accepted by the user as a whitelist;
the generating or updating the recommended resistance model based on the mapping relationship includes: determining recommended actions in a first scene in the mapping relation as the proportion of a blacklist;
if the proportion exceeds a preset threshold value, determining that recommended resistance exists, and not recommending the recommended action; otherwise, it is determined that there is no recommended resistance and the recommended action is determined as the first recommended action.
Further, the determining the scene information according to the recommended resistance model to determine whether to trigger the first scene includes:
determining a corresponding first scene according to the scene information;
determining whether the first scene has a corresponding first recommended action in a recommended resistance model; if yes, triggering a first scene;
the controlling and executing corresponding action recommendation according to the first scene comprises the following steps: controlling the recommendation of the first recommended action to be performed.
Preferably, the emotional state comprises sadness, surprise, happiness and natural state; the date information includes legal working days;
the obtaining a mapping relationship among a first scene, a recommended action and a user response in a historical predetermined time period, and generating or updating the recommended resistance model based on the mapping relationship includes:
acquiring time interval information, a first scene, recommended actions and user responses at different time intervals in a day in a historical preset time interval, and establishing a mapping relation among the time interval information, the first scene, the recommended actions and the user responses;
the judging the scene information according to the recommended resistance model, judging whether to trigger a first scene, further comprising:
acquiring time information of current driving and determining a time period of the current driving;
determining whether the first scene has the corresponding first recommended action in the corresponding current time period in the recommended resistance model; and if so, triggering the first scene.
Further, a third aspect of the present invention provides a storage medium, the computer storage medium storing a program; the program is loaded and executed by a processor to implement the active interactive recommendation method steps as described above, applied to different emotions of a driver.
In the scheme of the invention, the emotional state of the driver is identified through a driver monitoring system DMS; and identifying the date information of the day through the vehicle calendar; determining and generating scene information according to the emotional state and the date information; judging the scene information according to the recommended resistance model, and judging whether to trigger a first scene; according to the first scene, executing corresponding action recommendation, prompting a user and acquiring a user response; the user response comprises a rejection or an acceptance; wherein a mapping relationship between the first scene, the recommended action, and the user response over a historical predetermined time period is also obtained, and the recommended resistance model is generated or updated based on the mapping relationship. The method comprises the steps of performing scene decision by fusing multi-modal data such as vehicle, environment, in-vehicle user behavior and voice, providing active interaction scene service, using DMS video data of a driver monitoring system in the vehicle to monitor different emotions of a driver in the vehicle, using data such as the date information and the time of the day as input, and providing accurate active interaction action recommendation for a user.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
FIG. 1 is a schematic flow chart of an active interactive recommendation method applied to different emotions of a driver according to an embodiment of the present invention;
FIG. 2 is a flowchart of interactive recommendation for a sad + statutory workday scenario according to an embodiment of the present invention;
FIG. 3 is a flowchart of interactive recommendation of happy + weekday scenarios disclosed by embodiments of the present invention;
FIG. 4 is a flowchart of interactive recommendation in a natural + workday off-duty scenario as disclosed in an embodiment of the present invention;
FIG. 5 is a schematic structural diagram of an active interaction recommendation system applied to different emotions of a driver according to an embodiment of the present invention.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many different forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art.
Furthermore, the described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the application. One skilled in the relevant art will recognize, however, that the subject matter of the present application can be practiced without one or more of the specific details, or with other methods, components, devices, steps, and so forth. In other instances, well-known methods, devices, implementations, or operations have not been shown or described in detail to avoid obscuring aspects of the application.
The block diagrams shown in the figures are functional entities only and do not necessarily correspond to physically separate entities. I.e. these functional entities may be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor means and/or microcontroller means.
The flow charts shown in the drawings are merely illustrative and do not necessarily include all of the contents and operations/steps, nor do they necessarily have to be performed in the order described. For example, some operations/steps may be decomposed, and some operations/steps may be combined or partially combined, so that the actual execution sequence may be changed according to the actual situation.
It should be noted that: reference herein to "a plurality" means two or more.
The implementation details of the technical solution of the embodiment of the present application are set forth in detail below:
referring to fig. 1, fig. 1 is a schematic flowchart illustrating an active interactive recommendation method applied to different emotions of a driver according to an embodiment of the present invention. As shown in fig. 1, an active interactive recommendation method applied to different emotions of a driver according to an embodiment of the present invention includes:
s1, recognizing the emotional state of the driver through the driver monitoring system DMS; and identifying the date information of the day through the vehicle calendar; and determining and generating scene information according to the emotional state and the date information.
Specifically, in the embodiment, the driver monitoring system is a dms (driver Monitor system), which mainly utilizes the system sensing capability to Monitor and understand the driving state of the driver, and perform timely multidimensional intervention on the irregular driving behavior, so as to provide an auxiliary function beneficial to driving safety. Recognizing the emotional state of a driver through a Driver Monitoring System (DMS); and identifying the date information of the day through the vehicle calendar; wherein the emotional state comprises sadness, surprise, happiness and natural state; the date information includes legal working days. And determining and generating scene information according to the emotional state and the date information, such as a sadness + legal work day scene, a surprise + legal work day scene, a happy + work day and a nature + work day.
And S2, judging the scene information according to the recommended resistance model, and judging whether to trigger the first scene.
Specifically, in this embodiment, the recommended resistance model is used to determine whether there is a first recommended action that can be recommended and is easily accepted by the user in the corresponding scenario.
S3, according to the first scene, executing corresponding action recommendation, and prompting the user to obtain user response; the user response includes a rejection or an acceptance.
S4, obtaining a mapping relation among the first scene, the recommended action and the user response in a historical preset time period, and generating or updating the recommended resistance model based on the mapping relation.
Further, the first scenario corresponds to one or more recommended actions; recommended actions rejected by the user are determined as a black list, and recommended actions accepted by the user are determined as a white list.
The generating or updating the recommended resistance model based on the mapping relationship includes: determining recommended actions in a first scene in the mapping relation as the proportion of a blacklist; if the proportion exceeds a preset threshold value, determining that recommended resistance exists, and not recommending the recommended action; otherwise, it is determined that there is no recommended resistance and the recommended action is determined as the first recommended action.
Specifically, in this embodiment, feedback information or interaction information of a vehicle owner on a scene and a corresponding recommended action can be collected through a cloud, for example, four scenes including happy scenes, surprised scenes, natural sadness and the like under a large scene of an emotion mode are divided, and scenes in each type of emotion correspond to small scenes of different categories (for example, happy scenes + working days, natural days + working days working off, natural days + legal days working off the day before), the feedback information under the corresponding scene is obtained, a long-vector black-and-white list is formed, blacklist ratios under various scenes of the scenes are calculated every day, a recommended resistance model is formed, the feedback information is issued to a vehicle end every day, and the vehicle end queries the recommended resistance model to select whether to push the action. By acquiring a current scene, determining recommendation resistance corresponding to the current scene (that is, determining whether a first recommendation action which is worth recommending to a user and is not easy to reject by the user exists because the proportion of the blacklist matched with the current scene is smaller than a certain threshold), and if the recommendation resistance is smaller, determining that the recommendation action can be executed.
Further, the determining the scene information according to the recommended resistance model to determine whether to trigger the first scene includes: determining a corresponding first scene according to the scene information; determining whether the first scene has a corresponding first recommended action in a recommended resistance model; if yes, triggering a first scene; the controlling and executing corresponding action recommendation according to the first scene comprises the following steps: controlling the recommendation of the first recommended action to be performed.
Preferably, the emotional state comprises sadness, surprise, happiness and natural state; the date information includes legal working days.
Specifically, in this embodiment, for example, the scenario information may be sadness + legal working day. FIG. 2 is a flowchart illustrating the interactive recommendation process for the sad + statutory workday scenario of the present embodiment. After the vehicle-mounted device is started, a driver monitoring system DMS identifies a main driving emotion, if the driving emotion is a sad emotion, whether the current date is a legal working day is continuously detected, and if not, the current date is detected again. Under the conditions that the driver is sad and the current time is legal working day, judging recommended resistance, if the recommended resistance exists, ending triggering, and not triggering the scene; if there is no recommended resistance, the following recommended action is executed according to the recommendation. Wherein, include: TTS report "whether sad or sad, followed me deep breath relax Bar! ", realizing the guiding broadcast of deep breathing for 6 times in one minute; 2. the large screen is synchronous with the 1 minute deep breathing guide picture and TTS broadcast; 3. the main driving chair is adjusted, the front and back are adjusted to the end, and the backrest is adjusted to the end. In addition, if the endurance is less than 30km, in order to save electric energy, the recommended action is not executed, and the triggering is finished.
Further, the obtaining a mapping relationship among a first scene, a recommended action, and a user response within a historical predetermined time period, and generating or updating the recommended resistance model based on the mapping relationship includes:
acquiring time interval information, a first scene, recommended actions and user responses at different time intervals in a day in a historical preset time interval, and establishing a mapping relation among the time interval information, the first scene, the recommended actions and the user responses;
the judging the scene information according to the recommended resistance model, judging whether to trigger a first scene, further comprising: acquiring time information of current driving and determining a time period of the current driving; determining whether the first scene has the corresponding first recommended action in the corresponding current time period in the recommended resistance model; and if so, triggering the first scene.
Further, the main body for controlling and executing the corresponding action recommendation comprises a main driving seat and/or a central control screen and/or TTS broadcast; the action recommendation of the main driving seat comprises the front-back adjustment and/or the backrest adjustment of the seat; and triggering the TTS broadcast to synchronously execute the broadcast when the central control screen executes the display of the picture.
Specifically, in this embodiment, scene information is determined to be generated according to the emotional state and the date information, for example, a natural + workday scene or a natural + workday off-duty scene may be formed. In this embodiment, for the natural + workday scene, action recommendations in different time periods may be set. Therefore, in the generation process of the recommended resistance model, under the condition that the period information of different periods in a day in a historical preset time period is collected and acquired, the corresponding first scene, recommended action and user response are needed, and the mapping relation among the period information, the first scene, the recommended action and the user response is established.
For example, for a happy + workday scene, interactive recommendation and action recommendation can be performed for the working hours and the working hours. Such as setting a go-to-work period: the time is more than or equal to 7:00 and less than 10: 00; the off duty period: the time is more than or equal to 17:30 and less than 21: 00. Then, when the mapping relationship is generated, time period information needs to be added, and the mapping relationship among the time period information, the first scene, the recommended action and the user response is established. That is, in this natural + workday scenario, the recommended actions differ from time period to time period. Action recommendations such as work hours may be: TTS broadcast, "open heart go to work, go home safely". The action recommendation for the off-hours period may be: TTS reports, "you are full every day as today". Based on the established mapping relation, determining recommended actions in corresponding time periods in corresponding scenes in the mapping relation as the proportion of a blacklist; if the proportion exceeds a preset threshold value, determining that recommended resistance exists, and not recommending the recommended action; otherwise, it is determined that there is no recommended resistance and the recommended action is determined as the first recommended action. The method also comprises the step of terminating the execution of the recommended action. Such as: 1. the pedestrian arbitrates once according to the outside of the vehicle: identifying a pedestrian, and ending the recommended TTS broadcast action; 2. arbitrate once according to vehicle direction: and recognizing the turning of the vehicle, and ending the recommended TTS broadcasting action.
As shown in fig. 3, it is an interactive recommendation flowchart of the happy + workday scenario of the present embodiment. After the vehicle-mounted device is started, a driver monitoring system DMS identifies a main driving emotion, if the driving emotion is a sad emotion, whether the current date is a legal working day is continuously detected, and if not, the current date is detected again. Under the conditions that the driver is identified to be sad and the current time is legal working day, judging recommended resistance, if the recommended resistance exists, ending triggering, and not triggering the scene; if the recommended resistance does not exist, the current time period is further judged to belong to 7:00 ≦ time ≦ 10:00 or 17:30 ≦ time ≦ 21: 00. If the time is more than or equal to 7:00 and less than 10:00, TTS broadcasting is performed in the working time period, and the user is in a safe and safe way to come home after leaving home; if the time is 17:30 ≦ time < 21:00, the TTS is reported in the off-duty period, and the user is filled up like today every day; for entertainment broadcasting, a happy song is played no matter commuting. In addition, identifying the pedestrian, and ending the recommended TTS broadcast action; and recognizing the turning of the vehicle and finishing the recommended TTS broadcasting action.
For another example, for a natural + workday scene, interactive recommendation may be performed only for the off-duty time period, that is, the scene is a natural + workday off-duty scene. Specifically, the period of acquiring the scene of nature + workday off duty is divided into two periods: time is more than or equal to 17:30 and less than 20: 00; the time is more than or equal to 20:00 and less than 24: 00. Then, when the mapping relationship is generated, time period information needs to be added, and the mapping relationship among the time period information, the first scene, the recommended action and the user response is established. That is, in the natural + workday scenario, recommended actions are different for different time periods. Further, on the basis, in the embodiment, different action recommendations can be executed under different scenes of working day off duty or normal working day off duty before the legal holiday.
In particular, the system may set different action recommendations for, among other things, the day of work before the legal holiday, typically for the off-hours of the day before the holiday, for the upcoming holiday. Of course, this requires that a recommended resistance model is established in advance, and the period of working day before the legal holiday in the scene of nature + working day is divided into two periods within the historical predetermined time period: the time is more than or equal to 17:30 and less than 20: 00; the time is more than or equal to 20:00 and less than 24:00, and the recommended action and the user response in the two time periods are carried out, and the mapping relation among the time period information, the first scene, the recommended action and the user response is established. As shown in fig. 4, it is an interactive recommendation flowchart of the natural + workday off-duty scene in this embodiment. The time interval information comprises whether the time interval belongs to a working day label of the day before the legal holiday and the time interval. Generally, the off-duty time is 5.30, and the overtime time is not more than 24:00 at the latest, so that the time period is divided into 17: 30-20: 00; 20: 00-24: 00; for the off-duty time period 17: 30-20: 00 of the working day in the scene of nature + working day one day before the legal holiday, the front road condition can be broadcasted through recommending TTS; TTS reports that the sleep late is the most respectful of holidays in the tomorrow, and the like; for the 20: 00-24: 00 off duty time period, traffic jam does not exist generally, the road condition can not be broadcasted, TTS broadcasting is ' hard, I ' can be drunk in the evening, and a good rest bar is good in the tomorrow '; for entertainment content may be the playing of random music. It should be noted that for a common working day (a working day one day before an illegal holiday) which may be overtime, the overtime period 17: 30-24: 00 may be set, and the recommended action may be TTS broadcast, "go to work, sleep in the morning tonight! "for entertainment may be the playing of a type of music that the user likes. In addition, if the mapping relation in a certain period of history exists in the system, when new mapping relation generation is performed again, updating can be performed on the basis of the mapping relation in a certain period of history, and the mapping relation in the latest period is updated, so that a new resistance model is generated.
In this embodiment, the main body of the action recommendation output may be a main seat, a center control screen, a TTS reporting system and/or an entertainment system, wherein the action output of the main seat includes a front-back position and a backrest position; TTS broadcasts specific voice content or plays music; entertainment systems may be used to play music; the central control screen automatically plays the interactive content suitable for the specific emotion.
Further, as shown in fig. 5, a second aspect of the present embodiment provides an active interaction recommendation system applied to different emotions of a driver, the system including:
the identification module 10 is used for identifying the emotional state of the driver through a driver monitoring system DMS; and identifying the date information of the day through the vehicle calendar; determining and generating scene information according to the emotional state and the date information;
the judging module 20 judges the scene information according to the recommended resistance model, and judges whether to trigger a first scene;
the recommending module 30 executes corresponding action recommendation according to the first scene, prompts a user and obtains a user response; the user response comprises a rejection or an acceptance;
the generation and update module 40 obtains a mapping relationship between the first scene, the recommended action, and the user response within a historical predetermined time period, and generates or updates the recommended resistance model based on the mapping relationship.
Further, the first scenario corresponds to one or more recommended actions; determining the recommended action rejected by the user as a blacklist, and determining the recommended action accepted by the user as a whitelist;
the generating or updating the recommended resistance model based on the mapping relationship includes: determining recommended actions in a first scene in the mapping relation as the proportion of a blacklist;
if the proportion exceeds a preset threshold value, determining that recommended resistance exists, and not recommending the recommended action; otherwise, it is determined that there is no recommended resistance and the recommended action is determined as the first recommended action.
Further, the determining the scene information according to the recommended resistance model to determine whether to trigger the first scene includes:
determining a corresponding first scene according to the scene information;
determining whether the first scene has a corresponding first recommended action in a recommended resistance model; if yes, triggering a first scene;
the controlling and executing corresponding action recommendation according to the first scene comprises the following steps: controlling the recommendation of the first recommended action to be performed.
Preferably, the emotional state comprises sadness, surprise, happiness and natural state; the date information includes legal working days;
the obtaining a mapping relationship among a first scene, a recommended action and a user response in a historical predetermined time period, and generating or updating the recommended resistance model based on the mapping relationship, includes:
acquiring time interval information, a first scene, recommended actions and user responses at different time intervals in a day in a historical preset time interval, and establishing a mapping relation among the time interval information, the first scene, the recommended actions and the user responses;
the judging the scene information according to the recommended resistance model, judging whether to trigger a first scene, further comprising:
acquiring time information of current driving and determining a time period of the current driving;
determining whether the first scene has the corresponding first recommended action in the corresponding current time period in the recommended resistance model; if yes, triggering a first scene.
In addition, this application embodiment also discloses an electronic device, electronic device includes: one or more processors, memory for storing one or more computer programs; characterized in that said computer program is configured to be executed by said one or more processors, said program comprising means for performing the active interactive recommendation steps applied to different emotions of the driver as described above.
In addition, the embodiment of the application also provides a computer storage medium, wherein the computer storage medium stores a program; the program is loaded and executed by a processor to implement the active interactive recommendation steps applied to different emotions of the driver as described above.
Those of ordinary skill in the art will appreciate that the elements and algorithm steps of the examples described in connection with the embodiments disclosed herein may be embodied in electronic hardware, computer software, or combinations of both, and that the components and steps of the examples have been described in a functional general in the foregoing description for the purpose of illustrating clearly the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may also be an electric, mechanical or other form of connection.
The elements described as separate parts may or may not be physically separate, as one of ordinary skill in the art would appreciate that the elements and algorithm steps of the examples described in connection with the embodiments disclosed herein may be embodied in electronic hardware, computer software, or combinations of both, and that the components and steps of the examples have been described in a functional general sense in the foregoing description for clarity of explanation of the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention essentially or partially contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a grid device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are merely exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (10)
1. An active interactive recommendation method applied to different emotions of a driver, characterized by comprising the following steps:
s1, recognizing the emotional state of the driver through the driver monitoring system DMS; and identifying the date information of the day through the vehicle calendar; determining and generating scene information according to the emotional state and the date information;
s2, judging the scene information according to the recommended resistance model, and judging whether to trigger a first scene;
s3, according to the first scene, executing corresponding action recommendation, and prompting the user to obtain a user response; the user response comprises a rejection or an acceptance;
s4, obtaining a mapping relation among the first scene, the recommended action and the user response in a historical preset time period, and generating or updating the recommended resistance model based on the mapping relation.
2. The active interactive recommendation method applied to different emotions of a driver according to claim 1, wherein said first scene corresponds to one or more recommended actions; determining the recommended action rejected by the user as a blacklist, and determining the recommended action accepted by the user as a whitelist;
the generating or updating the recommended resistance model based on the mapping relationship comprises:
determining recommended actions in a first scene in the mapping relation as the proportion of a blacklist;
if the proportion exceeds a preset threshold value, determining that recommended resistance exists, and not recommending the recommended action; otherwise, it is determined that there is no recommended resistance and the recommended action is determined as the first recommended action.
3. The active interactive recommendation method applied to different emotions of a driver according to claim 2, wherein the judging the scene information according to the recommendation resistance model and whether to trigger the first scene comprises:
determining a corresponding first scene according to the scene information;
determining whether the first scene has a corresponding first recommended action in a recommended resistance model; if yes, triggering a first scene;
the controlling and executing corresponding action recommendation according to the first scene comprises the following steps: controlling the recommendation of the first recommended action to be performed.
4. The active interactive recommendation method applied to different emotions of a driver according to claim 3, wherein the emotional state comprises sadness, surprise, happiness and nature; the date information includes legal working days;
the obtaining a mapping relationship among a first scene, a recommended action and a user response in a historical predetermined time period, and generating or updating the recommended resistance model based on the mapping relationship includes:
acquiring time interval information, a first scene, recommended actions and user responses at different time intervals in a day in a historical preset time interval, and establishing a mapping relation among the time interval information, the first scene, the recommended actions and the user responses;
the judging the scene information according to the recommended resistance model, judging whether to trigger a first scene, further comprising:
acquiring time information of current driving and determining a time period of the current driving;
determining whether the first scene has the corresponding first recommended action in the corresponding current time period in the recommended resistance model; and if so, triggering the first scene.
5. The active interactive recommendation method applied to different emotions of a driver according to claim 3, wherein the main body for controlling to execute the corresponding action recommendation comprises a main driving seat and/or a central control screen and/or TTS broadcast;
the action recommendation of the main driving seat comprises the front-back adjustment and/or the backrest adjustment of the seat;
and triggering the TTS broadcast to synchronously execute the broadcast when the central control screen executes the display of the picture.
6. An active interactive recommendation system applied to different emotions of a driver, the system comprising:
the identification module is used for identifying the emotional state of the driver through the driver monitoring system DMS; and identifying the date information of the day through the vehicle calendar; determining and generating scene information according to the emotional state and the date information;
the judging module is used for judging the scene information according to the recommended resistance model and judging whether to trigger a first scene or not;
the recommending module executes corresponding action recommendation according to the first scene, prompts a user and obtains a user response; the user response comprises a rejection or an acceptance;
the generation and update module acquires a mapping relation among a first scene, recommended actions and user responses in a historical preset time period, and generates or updates the recommended resistance model based on the mapping relation.
7. The active interactive recommendation system applied to different emotions of a driver according to claim 6, wherein said first scene corresponds to one or more recommended actions; determining the recommended action rejected by the user as a blacklist, and determining the recommended action accepted by the user as a whitelist;
the generating or updating the recommended resistance model based on the mapping relationship includes: determining recommended actions in a first scene in the mapping relation as the proportion of a blacklist;
if the proportion exceeds a preset threshold value, determining that recommended resistance exists, and not recommending the recommended action; otherwise, it is determined that there is no recommended resistance and the recommended action is determined as the first recommended action.
8. The active interaction recommendation system applied to different emotions of a driver as claimed in claim 7, wherein said determining the scene information according to the recommendation resistance model and whether to trigger the first scene comprises:
determining a corresponding first scene according to the scene information;
determining whether the first scene has a corresponding first recommended action in a recommended resistance model; if yes, triggering a first scene;
the controlling and executing corresponding action recommendation according to the first scene comprises the following steps: controlling the recommendation of the first recommended action to be performed.
9. The active interactive recommendation system applied to different emotions of a driver according to claim 8, wherein said emotional state comprises sadness, surprise, happiness, natural state; the date information includes legal working days;
the obtaining a mapping relationship among a first scene, a recommended action and a user response in a historical predetermined time period, and generating or updating the recommended resistance model based on the mapping relationship includes:
acquiring time interval information, a first scene, recommended actions and user responses at different time intervals in a day in a historical preset time interval, and establishing a mapping relation among the time interval information, the first scene, the recommended actions and the user responses;
the judging the scene information according to the recommended resistance model, judging whether to trigger a first scene, further comprising:
acquiring time information of current driving and determining a time period of the current driving;
determining whether the first scene has the corresponding first recommended action in the corresponding current time period in the recommended resistance model; if yes, triggering a first scene.
10. A storage medium, the computer storage medium storing a program; the program is loaded and executed by a processor to implement the active interactive recommendation method steps applied to different emotions of a driver as claimed in any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210920590.4A CN114995658A (en) | 2022-08-02 | 2022-08-02 | Active interactive recommendation method applied to different emotions of driver |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210920590.4A CN114995658A (en) | 2022-08-02 | 2022-08-02 | Active interactive recommendation method applied to different emotions of driver |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114995658A true CN114995658A (en) | 2022-09-02 |
Family
ID=83020976
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210920590.4A Pending CN114995658A (en) | 2022-08-02 | 2022-08-02 | Active interactive recommendation method applied to different emotions of driver |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114995658A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106682090A (en) * | 2016-11-29 | 2017-05-17 | 上海智臻智能网络科技股份有限公司 | Active interaction implementing device, active interaction implementing method and intelligent voice interaction equipment |
| CN113076474A (en) * | 2021-03-22 | 2021-07-06 | 上海仙塔智能科技有限公司 | Driving behavior recommendation method and device, electronic equipment and storage medium |
| US20210380118A1 (en) * | 2020-06-09 | 2021-12-09 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method and apparatus for regulating user emotion, device, and readable storage medium |
| CN113961806A (en) * | 2021-10-19 | 2022-01-21 | 上海仙塔智能科技有限公司 | Processing method and device for driving feedback recommendation, electronic equipment and storage medium |
-
2022
- 2022-08-02 CN CN202210920590.4A patent/CN114995658A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106682090A (en) * | 2016-11-29 | 2017-05-17 | 上海智臻智能网络科技股份有限公司 | Active interaction implementing device, active interaction implementing method and intelligent voice interaction equipment |
| US20210380118A1 (en) * | 2020-06-09 | 2021-12-09 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method and apparatus for regulating user emotion, device, and readable storage medium |
| CN113076474A (en) * | 2021-03-22 | 2021-07-06 | 上海仙塔智能科技有限公司 | Driving behavior recommendation method and device, electronic equipment and storage medium |
| CN113961806A (en) * | 2021-10-19 | 2022-01-21 | 上海仙塔智能科技有限公司 | Processing method and device for driving feedback recommendation, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20110172873A1 (en) | Emotive advisory system vehicle maintenance advisor | |
| CN108629652A (en) | A kind of shared automobile operational version recommends method and server | |
| CN110929074A (en) | Vehicle-mounted voice broadcasting method and system | |
| JP4659754B2 (en) | Method and system for interaction between vehicle driver and multiple applications | |
| CN110286745A (en) | Dialog process system, the vehicle with dialog process system and dialog process method | |
| JP2007511414A6 (en) | Method and system for interaction between vehicle driver and multiple applications | |
| CN113076474A (en) | Driving behavior recommendation method and device, electronic equipment and storage medium | |
| CN114995658A (en) | Active interactive recommendation method applied to different emotions of driver | |
| CN114503133A (en) | Information processing apparatus, information processing method, and program | |
| CN117290605A (en) | Vehicle-mounted intelligent scene recommendation method, device, equipment and medium | |
| JP2013063747A (en) | Vehicle information display system | |
| CN109582271B (en) | Method, device and equipment for dynamically setting TTS (text to speech) playing parameters | |
| CN112141031A (en) | Cabin service method and cabin service system | |
| CN111178558B (en) | Network appointment order processing method and device, computer equipment and readable storage medium | |
| CN112109730A (en) | Reminding method based on interactive data, vehicle and readable storage medium | |
| CN115577173A (en) | Information pushing method, device, equipment and storage medium | |
| CN116049548A (en) | Vehicle service pushing method and device | |
| CN111907435B (en) | Control method, device and equipment of vehicle-mounted multimedia system and storage medium | |
| CN110796495A (en) | Method, device, computer storage medium and terminal for realizing information processing | |
| CN116483305A (en) | Intelligent network-connected automobile digital virtual person application system, application method thereof and vehicle | |
| Andreone et al. | Beyond context-awareness: driver-vehicle-environment adaptivity. from the comunicar project to the aide concept | |
| CN109166071A (en) | Adjust the method, apparatus and storage medium, electronic equipment of order status | |
| CN114710553A (en) | Information acquisition method, information push method and terminal equipment | |
| CN112172712A (en) | Cabin service method and cabin service system | |
| DE102019133133A1 (en) | Assistance system through which the output of at least one media content is controlled in a room, motor vehicle and operating method for the assistance 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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220902 |