Fragrance control method, device, medium and system based on in-vehicle environment and vehicle
By collecting and comparing data in the vehicle, and using the fragrance habit characteristic model to intelligently regulate the fragrance, the problem of insufficient intelligence in fragrance control in the existing technology is solved and the user experience is improved.
Patent Information
- Application Number
- CN202310610218.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-05-26
- Publication Date
- 2024-11-26
AI Technical Summary
The existing car fragrance control methods cannot meet user needs in different scenarios, resulting in poor intelligence and poor user experience.
By collecting real-time interior environment data after the vehicle is turned on, inputting fragrance habit characteristic model, outputting predicted fragrance status data, and comparing it with real-time fragrance status data, controlling the interior fragrance device according to the comparison results. Achieve intelligent regulation.
Improves the intelligent control ability of fragrance and improves the user experience effect.
Smart Images

Figure CN119017906A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of vehicle technology, and in particular to a fragrance control method, device, medium, system and vehicle based on an in-vehicle environment. Background Art
[0002] At present, car fragrances are widely used in cars. They can kill bacteria in the air inside the car to keep the air inside the car clean and play a role in purifying the air. In addition, car fragrances can also create a fresh and pleasant air atmosphere in the narrow space inside the car to keep the driver and passengers in the car clear-headed and calm, which can effectively reduce the occurrence of traffic accidents and benefit driving safety.
[0003] The existing in-vehicle fragrance control method predicts and adjusts the concentration of the fragrance after the user starts the fragrance decision model by obtaining environmental characteristic values of temperature, humidity, infrared and luminosity, pet emotion characteristic values obtained from the pet sound spectrum in the car, and pet category characteristic values obtained from the pet images in the car. A single adjustment cannot meet the needs of users in different scenarios, resulting in poor intelligence and poor user experience. Therefore, how to improve the intelligent control of fragrance has become an urgent problem to be solved. Summary of the invention
[0004] Based on this, it is necessary to provide a fragrance control method, device, medium, system and vehicle based on the in-vehicle environment to address the above-mentioned technical problems, so as to solve the problem of poor user experience during the vehicle fragrance control process.
[0005] A first aspect of an embodiment of the present application provides a fragrance control method based on an in-vehicle environment, the fragrance control method comprising:
[0006] After the vehicle's air conditioner is turned on, the real-time in-vehicle environment data at the current moment is collected;
[0007] Inputting the real-time in-vehicle environment data into a fragrance habit feature model and outputting predicted fragrance state data;
[0008] The real-time fragrance state data at the current moment is compared with the predicted fragrance state data to obtain fragrance control data, and the fragrance device in the vehicle is controlled according to the fragrance control data.
[0009] A second aspect of an embodiment of the present application provides a control device, which includes a processor, a memory, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the fragrance control method described in the first aspect is implemented.
[0010] A third aspect of an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the fragrance control method based on the in-vehicle environment as described in the first aspect is implemented.
[0011] A fourth aspect of the embodiments of the present application provides a fragrance system based on an in-vehicle environment, the fragrance system comprising a control device and a fragrance device connected to the control device, the control device being used to collect real-time in-vehicle environment data at the current moment after the air conditioner of the vehicle is turned on;
[0012] The control device is used to input the real-time in-vehicle environment data into a fragrance habit feature model and output predicted fragrance state data;
[0013] The control device is used to compare the real-time fragrance status data at the current moment with the predicted fragrance status data to obtain fragrance control data, and control the fragrance system in the vehicle according to the fragrance control data.
[0014] A fifth aspect of an embodiment of the present application provides a vehicle, comprising the fragrance system described in the fourth aspect.
[0015] Compared with the prior art, the present invention has the following beneficial effects:
[0016] After the vehicle air conditioner is turned on, the real-time in-vehicle environment data at the current moment is collected, the real-time in-vehicle environment data is input into the fragrance habit feature model, the predicted fragrance state data is output, the real-time fragrance state data at the current moment is compared with the predicted fragrance state data, the fragrance control data is obtained, and the fragrance device in the vehicle is controlled according to the fragrance control data. In this application, the fragrance state data is predicted by a large amount of multi-dimensional data, and the fragrance state can be intelligently controlled according to the prediction results, thereby improving the user experience effect. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.
[0018] Figure 1 is a flow chart of a method for controlling a fragrance based on an in-vehicle environment provided in the first embodiment of the present invention;
[0019] Figure 2 is a structural schematic diagram of a fragrance system based on an in-vehicle environment provided by the first embodiment of the present invention;
[0020] Figure 3 It is a structural schematic diagram of a vehicle provided in Embodiment 2 of the present invention. DETAILED DESCRIPTION
[0021] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0022] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.
[0023] It should also be understood that the term "and / or" used in the present description and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.
[0024] As used in the present specification and the appended claims, the term "if" may be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" may be interpreted as meaning "upon determination" or "in response to determining" or "upon detection of [described condition or event]" or "in response to detecting [described condition or event]", depending on the context.
[0025] In addition, in the description of the present specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.
[0026] References to "one embodiment" or "some embodiments" etc. described in the present specification mean that one or more embodiments of the present invention include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.
[0027] It should be understood that the order of execution of the steps in the following embodiments does not imply a precedence of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.
[0028] In order to illustrate the technical solution of the present invention, specific embodiments are provided below for illustration.
[0029] See also Figure 1 , is a flow chart of a fragrance control method based on the in-vehicle environment provided in the first embodiment of the present invention. The fragrance control method is used in a vehicle to control a fragrance system provided in the vehicle, that is, to control the selection of fragrance flavors and whether the fragrance is turned on or not.
[0030] like Figure 1 As shown, the fragrance control method may include the following steps:
[0031] S101: After the vehicle air conditioner is turned on, real-time in-vehicle environment data at the current moment is collected.
[0032] In step S101, after the vehicle turns on the air conditioner, the air conditioner intelligent control system collects relevant data sets in real time through the vehicle controller area network bus.
[0033] In this embodiment, after the air conditioner is turned on in the vehicle, the air conditioner intelligent control system collects data such as the PM2.5 value in the vehicle, the temperature inside the vehicle, the percentage of window positions, the vehicle speed, the air conditioner outlet position, humidity, the number of passengers and the distribution of passenger positions.
[0034] S102: Input the real-time in-vehicle environment data into the fragrance habit feature model, and output the predicted fragrance status data.
[0035] In step S102, the real-time data of the fragrance status is predicted using the fragrance habit feature model, the real-time in-vehicle environment data collected by the air-conditioning system is input into the fragrance habit feature model, and the corresponding predicted fragrance status data is output.
[0036] In this embodiment, the real-time in-vehicle PM2.5, in-vehicle temperature, window position percentage, vehicle speed, air-conditioning outlet gear, humidity, number of passengers and passenger position distribution data collected by the air-conditioning system are input into the fragrance habit feature model, and the corresponding predicted fragrance status data is output, wherein the predicted fragrance status data includes the prediction of fragrance type, the prediction of fragrance concentration, the prediction of fragrance remaining data, etc.
[0037] Among them, the fragrance habit feature model is a fragrance habit feature model obtained by training with historical related data in the database of the fragrance system, wherein the historical related data include historical in-vehicle environment data and corresponding historical fragrance status data, wherein the historical in-vehicle environment data include PM2.5 values, in-vehicle temperature, window position percentage, vehicle speed, air-conditioning gear, humidity, number of passengers and passenger position distribution data corresponding to each historical time period, and the historical fragrance status data include fragrance concentration feedback, fragrance selection feedback, and different fragrance remaining values corresponding to each historical time period.
[0038] Optionally, the training process of the fragrance habit feature model includes:
[0039] Obtain historical fragrance status data and historical in-vehicle environment data within a preset historical time period;
[0040] According to the historical in-vehicle environment data, the attribute characteristics of each historical in-vehicle environment data are determined to obtain a corresponding attribute characteristic set;
[0041] Calculate the information gain value of each attribute feature in the attribute feature set, and determine the attribute feature corresponding to the maximum information gain value as the root node of the fragrance habit feature model;
[0042] Divide the historical in-vehicle environment data into different subsets according to preset conditions and root nodes;
[0043] Through a recursive algorithm, the child node corresponding to the root node in the fragrance habit feature model is calculated from each subset. When the child node meets the preset stopping condition, the recursive calculation of the child node is stopped, and the historical fragrance state data corresponding to the historical in-vehicle environment data in the child node is used as a leaf node to obtain the fragrance habit feature model.
[0044] In this embodiment, historical fragrance status data and historical vehicle interior environment data within a preset historical time period are obtained from a corresponding database. The preset historical time period may be a period of one month. When the vehicle is started, the fragrance system transmits its own status data, i.e., fragrance concentration feedback, fragrance selection feedback, and different fragrance remaining values, to the vehicle terminal of the vehicle through the vehicle controller area network. The vehicle terminal sends the fragrance status data received at a certain period to the corresponding database through a wireless network signal. The database stores fragrance status data of different periods, and adds a serial number mark i to each data, i=1, 2, 3..., n, where n is an integer greater than 1.
[0045] When the air conditioner is turned on in the vehicle, the air conditioner intelligent control system collects the usage time, PM2.5 value, temperature, window position, speed, air conditioner air outlet position, humidity, number of passengers and passenger position distribution data. The air conditioner intelligent control system transmits the collected in-vehicle environment data to the vehicle terminal through the vehicle controller area network. The vehicle terminal sends the received fragrance status data to the corresponding database through the wireless network signal according to a certain period. The database stores the fragrance status data of different periods and adds a serial number mark i to each data, i=1, 2, 3..., n, n is an integer greater than 1, and the corresponding historical in-vehicle environment data can be obtained from the corresponding database.
[0046] It should be noted that when the air-conditioning intelligent control system collects in-vehicle environmental data, the usage time of the air-conditioning can be collected, wherein the usage time of the air-conditioning can be calculated based on the time each time the fragrance is turned on and the time each time the fragrance is turned off. For example, the time each time the fragrance is turned on is recorded as t1, and the time when the fragrance is turned off is t2, and the usage time of the air-conditioning is T1=t2-t1; the time required for each fragrance to reach a steady state can be collected. For example, the time each time the fragrance is turned on is recorded as t1, the time when the fragrance index reaches a steady state is t3, and the time required for the fragrance to reach a steady state is T2=t3-t1.
[0047] It is also possible to collect the in-vehicle environmental data in each cycle each time the fragrance is used, wherein the in-vehicle environmental data in each cycle each time the fragrance is used is collected by constructing a data set of corresponding values for each cycle. When constructing the data set of corresponding values, a PM2.5 value data set A{P1, P2, ..., Pn} for each time the fragrance is used can be constructed, wherein n is an integer greater than 1, and the data set can be the average value of the PM2.5 value in the car in the corresponding cycle, or the maximum or minimum value of the PM2.5 value in the car in the corresponding cycle; a temperature data set B{W1, W2, ..., Wn} for each time the fragrance is used is constructed, wherein n is an integer greater than 1, and the temperature data set can be the average value of the temperature value in the car in the corresponding cycle, or the maximum or minimum value of the temperature value in the car in the corresponding cycle; a window position data set C{C1, C2, ..., Cn} for each time the fragrance is used is constructed. , where n is an integer greater than 1; construct a vehicle speed data set D{S1, S2, ..., Sn} each time the fragrance is used, where n is an integer greater than 1, and the vehicle speed data set may be the average value of the vehicle speed value in the car in the corresponding period, or the maximum or minimum value of the vehicle speed value in the car in the corresponding period; construct an air-conditioning outlet gear data set E{F1, F2, ..., Fn} each time the fragrance is used, where n is an integer greater than 1, and the air-conditioning outlet gear data set may be the average value of the number of air-conditioning outlet gears in the car in the corresponding period, or the maximum or minimum value of the number of air-conditioning outlet gears in the car in the corresponding period; construct a vehicle humidity value data set F{D1, D2, ..., Dn} each time the fragrance is used, where n is an integer greater than 1, and the vehicle humidity value data set may be the average value of the humidity value in the car in the corresponding period, or the maximum or minimum value of the humidity value in the car in the corresponding period.
[0048] When the vehicle is started, it is also possible to determine whether there is a passenger in each seat by collecting the mass Sn on the seat. When Sn>20kg, the seat is marked as 1, indicating that there is an occupant, otherwise it is marked as 0, indicating that there is no one, and a seat occupant data set P{Q1, Q2..., Qn} is constructed, where n is an integer greater than 1; Q1 is the main driver's position data, Q2 is the co-pilot's position data, and Q3...Qn are the data collected by the pressure sensors on the seats in the second row from left to right.
[0049] It should be noted that after the corresponding data set is constructed, the data set can be preprocessed when it is used, for example, missing values in the data set are supplemented, discrete values in the data set are deleted, the data in the data set are regularized or normalized, and the values in different data sets are converted to values in the same dimensional unit to facilitate the corresponding calculation. For example, when the data set A{P1, P2, ..., Pn} corresponding to the PM2.5 values in the car is preprocessed, when the corresponding data P2 is missing in the data set A, the data P2 is supplemented, and the supplement can be made by referring to the corresponding values before and after, or by referring to the values in the entire data set.
[0050] After obtaining the corresponding historical in-vehicle environment data, the attribute characteristics of each historical in-vehicle environment data are determined to obtain the corresponding attribute characteristic set. For example, when the in-vehicle environment data is 20 degrees Celsius, the attribute characteristic corresponding to the data is the in-vehicle temperature characteristic. When the in-vehicle environment data is 30 kilometers per hour, the attribute characteristic corresponding to the data is the vehicle speed characteristic. The attribute characteristic set may include in-vehicle PM2.5, in-vehicle temperature, window position, vehicle speed, air conditioning gear, humidity, number of occupants, and occupant position distribution and other attributes.
[0051] According to the decision tree algorithm, the information gain value of each attribute feature in the attribute feature set is calculated, and the attribute feature corresponding to the maximum information gain value is determined as the root node of the fragrance habit feature model. Among them, the decision tree algorithm is a method of approximating the value of a discrete function, and the decision tree is a tree structure that represents the classification of samples based on features. The classification process of the decision tree can be summarized as recursively selecting the optimal partitioning feature from a given data set based on the feature selection criteria, and dividing the data set according to the selected optimal partitioning feature so that each data subset has a best classification process. The process of selecting the optimal partitioning feature to divide the data set can also be called feature grouping. Therefore, the process of using the decision tree model for data classification can also be summarized as the process of iteratively selecting the optimal partitioning feature from the current data set to group the features contained in the current data set.
[0052] In this embodiment, the information gain value of each attribute feature is calculated, and the information gain is used to measure whether each division of the data set is optimal. The attribute feature corresponding to the maximum information gain value is determined as the root node of the fragrance habit feature model. According to the preset conditions and the root node, the historical in-vehicle environment data is divided into different subsets. For example, when the information gain value corresponding to the in-vehicle humidity attribute feature is the largest, the in-vehicle humidity attribute feature is used as the root node in the decision tree, and the historical in-vehicle environment data is divided into corresponding subsets according to the in-vehicle humidity attribute feature. In this embodiment, according to whether the fragrance system is turned on as the division basis, the historical in-vehicle environment data is divided into a subset containing the in-vehicle humidity attribute feature in the in-vehicle system turned on data and a subset containing the in-vehicle humidity attribute feature in the in-vehicle system turned off data.
[0053] After different subsets are determined, the child nodes corresponding to the root nodes in the fragrance habit feature model are calculated from each subset through a recursive algorithm. When the child nodes meet the preset stopping conditions, the recursive calculation of the child nodes is stopped, and the historical fragrance status data corresponding to the historical in-vehicle environment data in the child nodes are used as leaf nodes to obtain the fragrance habit feature model.
[0054] When a child node meets a preset stop condition, the recursive calculation of the child node is stopped. In this embodiment, when training the fragrance habit feature model, in order to improve the robustness of the fragrance habit feature model, the child node cannot be infinitely segmented and classified. When a child node meets a preset stop condition, the recursive calculation of the child node is stopped. The preset stop condition can be that when the historical fragrance status data corresponding to the historical in-car environment data in the child node is the same type of data, the recursive calculation of the child node is stopped. For example, when the historical fragrance status data corresponding to the historical in-car environment data in the node are all of the same fragrance type, the same fragrance concentration, and the same remainder, the recursive calculation of the child node is stopped; if the child node If the attribute characteristics of the historical in-car environment data are equal, the recursive calculation of the child node is stopped. For example, the attribute characteristics corresponding to the historical in-car environment data in the child node only include one of the attributes and have not been divided, then the recursive calculation of the child node is stopped; if the historical in-car environment data corresponding to the child node is an empty set, the recursive calculation of the child node is stopped. For example, if the segmentation is based on the fragrance type, the fragrance type includes three types, and the attribute characteristic corresponding to the segmentation node is the humidity in the car. If the node is segmented into 4 child nodes, each child node corresponds to a fragrance type, then the segmentation subset corresponding to one of the nodes is an empty set, then the recursive calculation of the child node is stopped to obtain the fragrance habit feature model.
[0055] It should be noted that the decision tree algorithm includes the ID3 model, the C4.5 decision tree model, the Classification And Regression Tree (CART) algorithm, etc., which is not limited in this embodiment.
[0056] Optionally, the real-time in-vehicle environment data is input into the fragrance habit feature model, and the output predicted fragrance state data includes:
[0057] The real-time in-vehicle environment data is input into the fragrance habit feature model for classification, the historical fragrance state data corresponding to the classified target leaf node is determined as the predicted fragrance state data, and the predicted fragrance state data is output.
[0058] In this embodiment, the real-time in-vehicle environment data is input into the fragrance habit feature model for classification, and the target leaf node corresponding to the real-time in-vehicle environment data and the historical in-vehicle environment data in the leaf node of the fragrance habit feature model is determined, and the historical fragrance state data in the target leaf node is output as the predicted fragrance state data.
[0059] Optionally, according to the historical in-vehicle environment data, the attribute characteristics of each historical in-vehicle environment data are determined to obtain a corresponding attribute characteristic set, including:
[0060] According to the historical in-vehicle environment data, determine the attribute characteristics corresponding to each historical in-vehicle environment data;
[0061] Calculate the value corresponding to each attribute feature, select the attribute features corresponding to the first N values with the largest values to construct an attribute feature set, where N is an integer greater than 0.
[0062] In this embodiment, in order to reduce the number of sub-nodes in the fragrance habit feature model and improve the training efficiency of the fragrance habit feature model, an appropriate amount of feature attributes are selected as nodes in the fragrance habit feature model, and the attribute features corresponding to each historical in-vehicle environment data are determined according to the historical in-vehicle environment data, and all the attribute features contained in the historical in-vehicle environment data are obtained. The number corresponding to each attribute feature is calculated, and the attribute features corresponding to the data with more same attribute features in the historical in-vehicle environment data are used as the basis for classification judgment in the corresponding nodes, so as to improve the classification accuracy of the nodes in the fragrance habit feature model.
[0063] In this embodiment, attribute features corresponding to the first N values with the largest values are selected to construct an attribute feature set, and a fragrance habit feature model is constructed based on the attribute feature set.
[0064] Optionally, before determining the attribute feature of each historical vehicle interior environment data according to the historical vehicle interior environment data and obtaining the corresponding attribute feature set, the method further includes:
[0065] If the vehicle starts navigation within the preset historical time period, the historical traffic environment data on the corresponding navigation planning path is obtained;
[0066] According to the historical in-vehicle environment data, the attribute characteristics of each historical in-vehicle environment data are determined, and the corresponding attribute characteristic set is obtained, including:
[0067] According to the historical in-vehicle environment data and the historical traffic environment data, the attribute characteristics of each historical in-vehicle environment data are determined to obtain a corresponding attribute characteristic set.
[0068] In this embodiment, if the navigation system is turned on after the vehicle is started, the fragrance system can collect the destination and planned path information set in the navigation, and obtain the corresponding traffic environment data through the network based on the collected destination and planned path information. The fragrance system can also transmit the acquired traffic environment data to the vehicle terminal of the whole vehicle through the vehicle control device area network. The vehicle terminal sends the fragrance status data received in a certain period to the corresponding database through the wireless network signal. Therefore, the corresponding database stores the traffic environment data corresponding to the navigation start time. Therefore, if the vehicle turns on the navigation within the preset historical time period, the historical traffic environment data on the corresponding navigation planning path can be obtained.
[0069] It should be noted that when obtaining the traffic environment data on the corresponding navigation planning path, the fragrance system obtains it by collecting data from the navigation system, collecting the destination and planned path information in the navigation system, and obtaining the road congestion coefficient of the area that needs to be passed in the traffic big data information based on the destination and path information. The current real-time weather and the weather forecast maximum ambient temperature, wind speed, wind direction, and sunshine value data set of the area that needs to be passed are obtained based on the destination and path information. When obtaining the congestion coefficient data set in each cycle, the traffic environment data within the cycle can be regularly obtained according to the set cycle. For example, the cycle can be set to three minutes.
[0070] Optionally, the fragrance control method further comprises:
[0071] After the vehicle starts navigation, collect real-time traffic environment data on the corresponding navigation planning path;
[0072] The real-time in-car environment data is input into the fragrance habit feature model, and the output predicted fragrance status data includes:
[0073] The real-time in-vehicle environment data and the real-time traffic environment data are input into the fragrance habit feature model for classification, and the historical fragrance state data corresponding to the classified target leaf node is determined as the predicted fragrance state data.
[0074] In this embodiment, a fragrance habit feature model is used to predict real-time data of the fragrance status. The real-time in-vehicle environment data collected by the air-conditioning system and the corresponding real-time traffic environment data on the navigation planning path collected by the navigation system are input into the fragrance habit feature model. The fragrance habit feature model is used for classification, and the target leaf node corresponding to the real-time in-vehicle environment data and the historical in-vehicle environment data and traffic environment data in the leaf node of the fragrance habit feature model is determined. The historical fragrance status data in the target leaf node is output as the predicted fragrance status data.
[0075] S103: Compare the real-time fragrance state data at the current moment with the predicted fragrance state data to obtain fragrance control data, and control the fragrance device in the vehicle according to the fragrance control data.
[0076] In step S103, corresponding control data is determined according to the predicted fragrance state data, and the fragrance device is controlled according to the control data. The fragrance device releases fragrance of the corresponding fragrance type according to the real-time in-vehicle data corresponding to the current moment, and releases the fragrance at an appropriate concentration.
[0077] In this embodiment, the fragrance device releases fragrance of corresponding concentration according to the received control data, and the fragrance device is automatically adjusted and controlled according to the received control data, wherein the control number is compared with the real-time fragrance status data at the current moment and the predicted fragrance status data. When the real-time fragrance status data at the current moment is equal to the predicted fragrance status data, the fragrance control data is 0. When the real-time fragrance status data at the current moment is not equal to the predicted fragrance status data, the difference between the real-time fragrance status data at the current moment and the predicted fragrance status data is calculated, and the fragrance device in the vehicle is controlled according to the difference, so that the fragrance status data released by the fragrance device conforms to the corresponding predicted fragrance status data.
[0078] After the vehicle air conditioner is turned on, the real-time in-vehicle environment data at the current moment is collected, the real-time in-vehicle environment data is input into the fragrance habit feature model, the predicted fragrance state data is output, the real-time fragrance state data at the current moment is compared with the predicted fragrance state data, the fragrance control data is obtained, and the fragrance device in the vehicle is controlled according to the fragrance control data. In this application, the fragrance state data is predicted by a large amount of multi-dimensional data, and the fragrance state can be intelligently controlled according to the prediction results, thereby improving the user experience effect.
[0079] Corresponding to the above embodiment, a fragrance control method based on the in-vehicle environment is provided. Figure 2 The structure diagram of a fragrance system based on the in-car environment provided by the first embodiment of the present application is shown. For the sake of convenience, only the part related to the embodiment of the present application is shown. Figure 2The structural diagram 20 of the fragrance system includes a control device 21 and a fragrance device 22 connected to the control device. The control device 21 is used to collect real-time in-vehicle environment data at the current moment after the vehicle air conditioner is turned on.
[0080] The control device 21 is used to input the real-time in-vehicle environment data into the fragrance habit feature model and output the predicted fragrance state data.
[0081] The control device 21 is used to compare the real-time fragrance state data at the current moment with the predicted fragrance state data to obtain fragrance control data, and control the fragrance system in the vehicle according to the fragrance control data.
[0082] See also Figure 3 , Figure 3 It is a structural schematic diagram of a vehicle provided in Embodiment 2 of the present invention. The structural schematic diagram 30 of the vehicle includes a fragrance system 20. The fragrance system 20 includes a control device 21 and a fragrance device 22 connected to the control device. The control device 21 is used to collect real-time in-vehicle environment data at the current moment after the vehicle air conditioner is turned on.
[0083] The control device 21 is used to input the real-time in-vehicle environment data into the fragrance habit feature model and output the predicted fragrance state data.
[0084] The control device 21 is used to compare the real-time fragrance state data at the current moment with the predicted fragrance state data to obtain fragrance control data, and control the fragrance system in the vehicle according to the fragrance control data.
[0085] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned device can refer to the corresponding process in the above-mentioned method embodiment, which will not be repeated here. If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned method embodiment when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may at least include: any entity or device capable of carrying computer program code, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.
[0086] The present application implements all or part of the processes in the above-mentioned embodiment method, and may also be completed through a computer program product. When the computer program product runs on a terminal device, the terminal device implements the steps in the above-mentioned method embodiment when executing the computer program product.
[0087] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0088] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.
[0089] In the embodiments provided in the present application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.
[0090] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0091] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.
Claims
1. A method for controlling the fragrance based on the in-vehicle environment, characterized in that: The fragrance control method comprises: After the vehicle's air conditioner is turned on, the real-time in-vehicle environment data at the current moment is collected; Inputting the real-time in-vehicle environment data into a fragrance habit feature model and outputting predicted fragrance state data; The real-time fragrance state data at the current moment is compared with the predicted fragrance state data to obtain fragrance control data, and the fragrance device in the vehicle is controlled according to the fragrance control data.
2. The fragrance control method according to claim 1, characterized in that: The training process of the fragrance habit feature model includes: Obtain historical fragrance status data and historical in-vehicle environment data within a preset historical time period; Determine the attribute characteristics of each historical in-vehicle environment data according to the historical in-vehicle environment data, and obtain a corresponding attribute characteristic set; Calculating the information gain value of each attribute feature in the attribute feature set, and determining the attribute feature corresponding to the maximum information gain value as the root node of the fragrance habit feature model; Dividing the historical in-vehicle environment data into different subsets according to preset conditions and the root node; The child node corresponding to the root node is calculated from each subset through a recursive algorithm. When the child node meets a preset stop condition, the recursive calculation of the child node is stopped, and the historical fragrance state data in the child node is used as a leaf node to obtain a fragrance habit feature model.
3. The fragrance control method according to claim 2, characterized in that: The step of inputting the real-time in-vehicle environment data into the fragrance habit feature model and outputting predicted fragrance state data comprises: The real-time in-vehicle environment data is input into the fragrance habit feature model for classification, the historical fragrance state data corresponding to the classified target leaf node is determined as the predicted fragrance state data, and the predicted fragrance state data is output.
4. The fragrance control method according to claim 2, characterized in that: The step of determining the attribute characteristics of each historical in-vehicle environment data according to the historical in-vehicle environment data to obtain a corresponding attribute characteristic set includes: Determine, based on the historical in-vehicle environment data, the attribute features corresponding to each historical in-vehicle environment data; The numerical value corresponding to each attribute feature is calculated, and the attribute features corresponding to the first N numerical values with the largest numerical values are selected to construct an attribute feature set, where N is an integer greater than 0.
5. The fragrance control method according to claim 2, characterized in that: Before determining the attribute feature of each historical in-vehicle environment data according to the historical in-vehicle environment data to obtain the corresponding attribute feature set, the method further includes: If the vehicle starts navigation within the preset historical time period, the historical traffic environment data on the corresponding navigation planning path is obtained; Determining the attribute characteristics of each historical in-vehicle environment data according to the historical in-vehicle environment data to obtain the corresponding attribute characteristic set includes: According to the historical in-vehicle environment data and the historical traffic environment data, attribute features of each historical in-vehicle environment data are determined to obtain a corresponding attribute feature set.
6. The fragrance control method according to claim 5, characterized in that: The fragrance control method also includes: After the vehicle starts navigation, collect real-time traffic environment data on the corresponding navigation planning path; Inputting the real-time in-vehicle environment data into the fragrance habit feature model and outputting the predicted fragrance state data comprises: The real-time in-vehicle environment data and the real-time traffic environment data are input into the fragrance habit feature model for classification, and the historical fragrance state data corresponding to the classified target leaf node is determined as the predicted fragrance state data.
7. A control device, characterized in that: The control device includes a processor, a memory, and a computer program stored in the memory and executable on the processor, and the processor implements the fragrance control method according to any one of claims 1 to 6 when executing the computer program.
8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the fragrance control method according to any one of claims 1 to 6 is implemented.
9. A fragrance system based on the in-car environment, characterized in that: The fragrance system includes a control device and a fragrance device connected to the control device, and the control device is used to collect real-time in-vehicle environment data at the current moment after the vehicle air conditioner is turned on; The control device is used to input the real-time in-vehicle environment data into a fragrance habit feature model and output predicted fragrance state data; The control device is used to compare the real-time fragrance status data at the current moment with the predicted fragrance status data to obtain fragrance control data, and control the fragrance system in the vehicle according to the fragrance control data.
10. A vehicle, characterized in that: The vehicle comprises the fragrance system of claim 9.
Citation Information
Cited By
Perfume spraying control method and intelligent perfume spraying machine
CN119705007A
