Fragrance data processing method based on scene, computer equipment and storage medium

Abstract

The invention relates to the technical field of vehicle-mounted fragrance, and discloses a scene-based fragrance data processing method, computer equipment and a storage medium. The method comprises the following steps: acquiring a preset spice type ratio data table; acquiring scene environment information corresponding to the target scene; determining spice type information according to the scene environment information; and comparing the determined perfume type information with a set perfume type ratio data table, and determining a target perfume matched with the target scene. Scenarized application requirements of a vehicle are integrated into the development process of the vehicle-mounted fragrance, the vehicle scene reduction degree of the vehicle-mounted fragrance product in the sense of smell is improved, and meanwhile the fragrance of the vehicle-mounted fragrance product is more harmonious and richer based on the fragrance type matching data table; scenarized, healthy and intelligent requirements of the user on the vehicle are met, and the user experience is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of in-vehicle fragrance, and particularly to a method for processing fragrance data based on scenarios, a computer device, and a storage medium. Background Art

[0002] At present, most in-vehicle fragrance products are randomly formulated with perfume raw materials. Although there are many types of scents, there are few in-vehicle fragrances that meet the different scenario-based application requirements of vehicles. In related technologies, when developing in-vehicle fragrance products, developers often can only use the floral and fruity scents of spices, personal experiences, and abstract imaginations as the basis for formulating in-vehicle fragrances. The in-vehicle fragrances developed in the above manner usually only have the functions of purifying the air and increasing the fragrance in the vehicle, and cannot meet the requirements of scenario-based, healthy, and intelligent in terms of user experience. Summary of the Invention

[0003] Based on this, in view of the above technical problems, a method for processing fragrance data based on scenarios, a computer device, and a storage medium are provided to solve the problem that in-vehicle fragrances are difficult to meet the scenario-based requirements of vehicles.

[0004] A method for processing fragrance data based on scenarios includes:

[0005] Obtaining a pre-set data table of spice type ratios;

[0006] Obtaining scenario environment information corresponding to a target scenario;

[0007] Determining spice type information according to the scenario environment information;

[0008] Comparing the determined spice type information with the pre-set data table of spice type ratios to determine a target fragrance that matches the target scenario.

[0009] A computer device includes a memory, a processor, and computer-readable instructions stored in the memory and executable on the processor. When the processor executes the computer-readable instructions, the above method for processing fragrance data based on scenarios is implemented.

[0010] A computer-readable storage medium stores computer-readable instructions. When the computer-readable instructions are executed by one or more processors, the one or more processors are caused to execute the method for processing fragrance data based on scenarios as described above.

[0011] In the above-described scenario-based fragrance data processing method, computer device, and storage medium, the method determines the fragrance type information based on the scene environment information obtained for the target scene, increasing the relevance and matching degree between the fragrance of the vehicle-mounted fragrance and the target scene. The method also obtains a pre-set fragrance type ratio data table, and determines the target fragrance that matches the target scene based on the comparison between the fragrance type ratio data table and the determined fragrance type information, improving the harmony degree between different types of fragrances in the vehicle-mounted fragrance and emphasizing the user experience. The present invention integrates the scenario-based application requirements of the vehicle into the development process of the vehicle-mounted fragrance. Based on the analysis of the environmental information of different target scenes, different fragrance types are reversely matched and then the vehicle-mounted fragrance is formulated, so that the vehicle-mounted fragrance can more accurately restore the target scene in terms of olfactory senses, and at the same time make the aroma of the vehicle-mounted fragrance product more harmonious and rich, meeting the user's requirements for the vehicle in terms of scenario, health, and intelligence, and improving the user experience. Brief Description of the Drawings

[0012] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments of the present invention will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention, and those of ordinary skill in the art can obtain other drawings without creative efforts based on these drawings.

[0013] Figure 1 is a flowchart of a scenario-based fragrance data processing method according to an embodiment of the present invention;

[0014] Figure 2 is a structural diagram of a scenario-based fragrance data processing device according to an embodiment of the present invention;

[0015] Figure 3 is a schematic diagram of a computer device according to an embodiment of the present invention. Detailed Description of the Embodiments

[0016] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art without creative efforts based on the embodiments of the present invention belong to the scope of protection of the present invention.

[0017] In one embodiment, as Figure 1 shown, a scenario-based fragrance data processing method is provided, including the following steps S10-S40:

[0018] S10. Obtain a pre-set fragrance type ratio data table;

[0019] Understandably, the spice type ratio data table contains multiple spice groups and at least one ratio combination associated with each spice group. Among them, each spice group contains at least one spice, and the ratio combination refers to the proportional combination relationship among all types of spices in the spice group. Each spice group can be associated with one or more ratio combinations. For example, if the spice group includes three spices A, B, and C, the ratio combination can be A:B:C = 1:1:2; it can also be A:B:C = 1:0:1. That is, the ratios of various spices in the spice group can be preset according to actual needs to be greater than or equal to 0. When the ratio corresponding to a certain spice in a ratio combination is 0, it means that in this ratio combination, this spice will not be selected for use. The composition of the spice groups in the spice type ratio data table and the ratio combinations corresponding to each spice group can be preset according to requirements. Understandably, among the multiple ratio combinations corresponding to the same spice group, each ratio combination is associated with a priority. The higher the priority, the higher the possibility of being automatically selected in the spice type ratio data table (automatically selected according to the order of priority).

[0020] S20. Obtain the scene environment information corresponding to the target scene; Understandably, the target scene refers to one of the preset scenes that the vehicle cockpit can restore or simulate, and the preset scene is a scene preset to include specified objects with olfactory sensory stimulation effects (such as flowers, grass, trees, etc.). The target scene can be an objectively existing real scene, such as a live image collected in real time, a road image exported from the database of the vehicle navigation system, and a natural landscape video clip in a documentary. The target scene can also be an artificially synthesized virtual scene, such as an artificial intelligence painting work, a special effects composite image, and a text description segment, etc.

[0021] The environmental characteristics of the scene include background music environmental characteristics, odor environmental characteristics, light environmental characteristics, and color environmental characteristics. These environmental characteristics can affect the atmosphere of the scene and the sensory experience of the participants. In this embodiment, in order to strengthen the application of in-vehicle fragrance in terms of sceneization, it is necessary to pay attention to the olfactory sensory experience of the participants in the scene. Therefore, the scene environment information refers to the information extracted from the target scene and associated with the odor environmental characteristics. For example, the grass in the target scene is associated with the odor environmental characteristics. At this time, the scene environment information can include the proportion information of the grass in the entire scene.

[0022] In one embodiment, the target scene includes multiple scene quantization objects; the scene environment information includes environmental attribute information and environmental proportion information corresponding to each of the scene quantization objects one by one; step S20, that is, the obtaining of the scene environment information corresponding to the target scene, includes the following steps S201 - S204:

[0023] S201. Perform object recognition on the target scene to determine the scene quantization objects included therein and the environmental attribute information corresponding one by one to each of the scene quantization objects;

[0024] Understandably, the target scene is jointly composed of multiple scene quantization objects. A scene quantization object refers to one of the compositional elements having an olfactory sensory stimulation effect in the scene. For example, when the target scene is a grassland, the scene quantization objects include grass elements and land elements; when the target scene is a forest, the scene quantization objects include leaf elements and tree trunk elements.

[0025] In one embodiment, in step S201, that is, performing object recognition on the target scene to determine the scene quantization objects included therein and the environmental attribute information corresponding one by one to each of the scene quantization objects, includes the following steps S2011 - S2012:

[0026] S2011. Obtain the scene image corresponding to the target scene, perform object recognition on the scene image through a preset image recognition model, and obtain at least one image type information included in the scene image output by the preset image recognition model and its corresponding image element features; Understandably, the preset image recognition model is a pre - trained neural network model used to perform image recognition processing on the scene image, and respectively obtain the image type information corresponding to different image element features, and output the image type information and the image element features. Among them, each image type information corresponds to a regional image block in the scene information. A regional image block is a small area with a certain size and shape in the scene image. All the image region blocks jointly form the scene image. Each regional image block contains several pixel points with different colors and coordinates. Therefore, each regional image block also has different color attributes and position attributes due to the different pixel points it contains. The different color attributes and position attributes corresponding to each regional image block are its corresponding image element features. And the image type information is the name of the scene quantization object that the preset image recognition model can determine based on the above - mentioned regional image block and its image element features. For example, the scene quantization objects (image type information) corresponding to a forest scene can include leaves, tree trunks, ferns, mosses, river water, flowers and fruits, animals, and soil, etc. The scene quantization objects (image type information) corresponding to a cherry - blossom viewing scene can include cherry blossoms, tree trunks, leaves, river water, wooden bridges, animals, grass, soil, and mosses, etc.

[0027] Understandably, the training process of the preset image recognition model can include:

[0028] Obtain a scene sample data set, where the scene sample data set includes at least one scene sample data and a sample label; among them, the scene sample data includes historical scene images; the sample label includes historical image type information and historical image element features corresponding to the historical scene sample.

[0029] Obtain a preset training model, and perform probability prediction on the scene sample data through the preset training model to obtain a prediction label; the preset training model is a neural network model; the prediction label includes predicted image type information and predicted image element features.

[0030] Determine the prediction loss value of the preset training model according to the sample label and the prediction label corresponding to the same image element feature sample data; that is, when the predicted image type information matches the historical image type information and the predicted image element features match the historical image element features, it is considered that the prediction loss value reaches the preset convergence condition; otherwise, when the predicted image type information does not match the historical image type information, or the predicted image element features do not match the historical image element features, it is considered that the prediction loss value does not reach the preset convergence condition. When the prediction loss value reaches the preset convergence condition, the preset training model after convergence is determined as the preset image recognition model. If the preset convergence condition is not reached, simply return to the step of performing probability prediction on the next scene sample data through the preset training model.

[0031] S2012. Record each piece of the image type information as a scene quantization object, and record the image element features corresponding to each piece of the image type information as the environmental attribute information of the scene quantization object corresponding to it. Referring to the above, the image type information recognized by the preset image recognition model is the name of the scene quantization object. Therefore, each piece of the image type information can be directly recorded as a scene quantization object. And the image element features corresponding to each piece of the image type information are the color attributes and position attributes corresponding to all pixel points in the regional image block corresponding to the scene quantization object. Therefore, the image element features can be used to describe and identify the regional image block corresponding to the scene quantization object, and the image element features are recorded as the environmental attribute information of the scene quantization object.

[0032] In this embodiment, the preset image recognition model is used to perform recognition processing on the scene image corresponding to the target scene. Not only the scene quantization object in the scene image is recognized, but also the environmental attribute information of the scene quantization object is further extracted, improving the information richness and contributing to further analysis and application.

[0033] S202. Split the target scene according to the environmental attribute information to obtain environmental proportion information corresponding to each scene quantization object one by one. In one embodiment, the image element features include the color attribute of the scene quantization object and the position attribute of the scene quantization object in the scene image. The color attribute is an important presentation form of the scene quantization object. Different scene quantization objects can be identified and distinguished through the color attribute, and the color attribute can be represented by RGB values. The position attribute records the distribution and arrangement information of the scene quantization object in the scene image, and the position attribute can refer to the coordinates of the pixel points in the scene image.

[0034] Further, in step S202, that is, splitting the target scene according to the environmental attribute information to obtain environmental proportion information corresponding to each scene quantization object one by one, includes:

[0035] S2021. In the scene image of the target scene, record the pixel points with the same color attribute as the scene quantization object as the target pixel points corresponding to this scene quantization object. Understandably, the image element features include the color attribute of the scene quantization object and the position attribute of the scene quantization object in the scene image. Therefore, all target pixel points corresponding to each scene quantization object can be determined first according to the color attribute.

[0036] S2022. Obtain the position attributes of all target pixel points corresponding to the same scene quantization object, and split the scene quantization object from the scene image according to the obtained all position attributes to obtain the object area corresponding to this scene quantization object. That is, after all target pixel points corresponding to each scene quantization object have been determined, determine the object area corresponding to this scene quantization object in the scene image according to the position attributes of all target pixel points and split it from the scene image. Understandably, in one embodiment, when splitting, a selection box with a specific shape (such as a rectangle) can be used to enclose the target pixel points corresponding to each scene quantization object to the greatest extent (while not including too many target pixel points corresponding to other scene quantization objects), and then determine the object area according to the position attributes of all pixel points in the selection box. In another embodiment, when splitting, the shape of the object area is not restricted. At this time, the object area can be directly determined by using the outermost target pixel points among the target pixel points corresponding to each scene quantization object as the boundary, and then determining the object area according to the position attributes of these outermost target pixel points.

[0037] S2023. Determine the proportion of the area of each object region in the scene image as the environmental proportion information of the scene quantization object corresponding to this object region. That is to say, the environmental proportion information refers to the proportion of the olfactory sensory stimulation effect of a scene quantization object compared to the olfactory sensory stimulation effects of all scene quantization objects. For example, in a grassland scene, the environmental proportion information of the grass element is 80%, and the environmental proportion information of the land element is 20%. In this embodiment, after all object regions in the scene object are split, the proportion of the area of the object region in the scene image is the environmental proportion information.

[0038] S203. Generate a set of environmental data according to each scene quantization object and its corresponding environmental proportion information. Specifically, after determining the environmental proportion information of the scene quantization object according to the color attribute and position attribute in the environmental attribute information, generate a set of environmental data according to the scene quantization object and its corresponding environmental proportion information. For example, a forest scene image includes the scene quantization object leaves, and a set of environmental data corresponding to the leaves can be [leaves, 30%].

[0039] S204. Generate the scene environmental information corresponding to the target scene according to all sets of the environmental data. That is to say, the scene environmental information contains multiple sets of environmental data corresponding one by one to each scene quantization object, and each set of environmental data includes the environmental proportion information of the scene quantization object.

[0040] This embodiment realizes the quantitative analysis of the target scene from the dimension of the scene quantization object, generates multiple sets of environmental data based on the environmental attribute information and the environmental proportion information, can more accurately understand the content and layout of the target scene, extract the scene environmental information of the target scene, and improves the accuracy of information extraction. Moreover, this embodiment realizes the precise splitting of the scene image according to the color attribute and position attribute in the environmental attribute information, determines the environmental proportion information, and then generates the environmental data associated with the scene quantization object according to the environmental proportion information, ensuring that the scene environmental information containing multiple sets of environmental data can more comprehensively describe the content and layout in the scene image corresponding to the target scene, thereby providing more accurate and comprehensive data support for subsequent analysis and applications.

[0041] In one embodiment, the target scene is an image of a forest scene. Through object recognition, it is determined that the scene quantization objects include leaves, tree trunks, ferns, moss, river water, flowers and fruits, animals, and soil. After splitting the forest scene image according to the color attribute and position attribute in the environmental attribute information, the environmental proportion information corresponding to each scene quantization object is obtained. Among them, the environmental proportion information corresponding to leaves, tree trunks, ferns, moss, river water, flowers and fruits, animals, and soil is 30%, 10%, 10%, 10%, 25%, 5%, 5%, and 5% respectively. Finally, environmental data associated with the scene quantization object is generated according to each scene quantization object and its corresponding environmental proportion information. The scene environmental information of the forest scene image consists of 8 sets of environmental data, including: [leaves, 30%], [tree trunks, 10%], [ferns, 10%], [moss, 10%], [river water, 25%], [flowers and fruits, 5%], [animals, 5%], and [soil, 5%].

[0042] In another embodiment, the target scene is an image of a cherry blossom viewing scene. Through object recognition, it is determined that the scene quantization objects include cherry blossoms, tree trunks, leaves, river water, wooden bridges, animals, grass, soil, and moss. After splitting the forest scene image according to the color attribute and position attribute in the environmental attribute information, the environmental proportion information corresponding to each scene quantization object is obtained. Among them, the environmental proportion information corresponding to cherry blossoms, tree trunks, leaves, river water, wooden bridges, animals, grass, soil, and moss is 35%, 5%, 10%, 10%, 10%, 5%, 15%, 5%, and 5% respectively. Finally, environmental data associated with the scene quantization object is generated according to each scene quantization object and its corresponding environmental proportion information. The scene environmental information of the cherry blossom viewing scene image consists of 9 sets of environmental data, including: [cherry blossoms, 35%], [tree trunks, 5%], [leaves, 10%], [river water, 10%], [wooden bridges, 10%], [animals, 5%], [grass, 15%], [soil, 5%], and [moss, 10%].

[0043] S30. Determine the spice type information according to the scene environmental information.

[0044] Understandably, the spice type information includes the spice types for restoring the odor environmental characteristics of the target scene from the olfactory sensory experience. Specifically, the spice type information includes multiple sets of spice type data, and each set of spice type data contains at least one type of spice; the aroma produced by each type of spice can create an environmental atmosphere of a constituent element (such as a scene quantization object) in the target scene on the olfactory sense, that is, the aroma of one spice corresponds to the odor environmental characteristics of one constituent element. The aromas produced by different types of spices may be different, or may be similar or the same, that is, the odor environmental characteristics of one constituent element can correspond to the aromas of one or more spices.

[0045] In one embodiment, in step S30, that is, determining the spice type information according to the scenario environment information includes:

[0046] S301. Obtain an environmental aroma association table; Understandably, the environmental aroma association table is a pre-generated data table representing the association relationship between the environmental type characteristics data of environmental composition elements and aroma types. The environmental aroma association table includes multiple groups of environment-aroma data groups; each group of the environment-aroma data groups includes standard environmental information and the aroma type associated with the standard environmental information.

[0047] Understandably, the standard environmental information refers to the information used to describe the environmental composition elements in different scenarios in the environmental aroma association table. For example, the standard environmental information includes: the environmental composition element is a leaf. And the aroma type associated with the standard environmental information is used to describe the aroma characteristics corresponding to the standard environmental information. For example, the aroma type corresponding to the leaf is a green aroma.

[0048] In this embodiment, the environmental aroma association table records multiple groups of environment-aroma data groups for characterizing the association relationship between the standard environmental information and the aroma type. For example, a group of environment-aroma data groups includes: the standard environmental information is soil, and the aroma type corresponding to the soil is a spicy aroma and / or a turbid aroma; another group of environment-aroma data groups includes: the standard environmental information is soil, and the aroma type corresponding to the soil is a spicy aroma and a turbid aroma; another group of environment-aroma data groups includes: the standard environmental information is soil, and the aroma type corresponding to the soil is a turbid aroma.

[0049] When generating the environmental aroma association table, environmental sample data can be collected in advance. The environmental sample data includes environmental composition elements and the aroma types corresponding to each environmental composition element; then, establish the association relationship between each environmental composition element and its corresponding aroma type, and generate the environmental aroma association table according to all the association relationships.

[0050] S302. Determine the scenario aroma information corresponding to the scenario environment information according to the environmental aroma association table; In one embodiment, step S302 includes the following steps S3021-S3024:

[0051] S3021. Search for the fragrance type information corresponding to the scene quantization objects of each group of the environmental data in the environmental fragrance association table. Further, step S3021 includes: obtaining the environmental attribute information in each group of the environmental data; searching for the standard environmental information that matches each of the scene quantization objects from all the environmental-fragrance data groups; and determining the fragrance type associated with the standard environmental information that matches each of the scene quantization objects and its corresponding environmental attribute information as the fragrance type information corresponding to the scene quantization object. That is, according to the above embodiments, each group of environmental data is generated based on each of the scene quantization objects and their corresponding environmental proportion information. For example, a forest scene image includes a scene quantization object, a leaf, and a group of environmental data corresponding to the leaf can be [leaf, 30%]. Therefore, each group of environmental data contains a scene quantization object. After matching the scene quantization object with the standard environmental information in the environmental fragrance association table, the fragrance type corresponding to the matched standard environmental information can be obtained, and the obtained fragrance type is the fragrance type information. In this embodiment, the scene quantization objects of the environmental data are matched with the standard environmental information, and then the fragrance type information associated with the scene quantization objects is determined, ensuring the accuracy and applicability of the fragrance type information.

[0052] S3022. Determine the fragrance proportion information corresponding to each group of the environmental data according to the environmental proportion information of each group of the environmental data; the fragrance proportion information is used to represent the proportion of each fragrance in all the fragrances corresponding to the target scene. For example, a forest scene image includes a scene quantization object, a leaf, and a group of environmental data corresponding to the leaf can be [leaf, 30%]. At this time, the environmental proportion information of this group of environmental data is 30%, so it can be determined that the fragrance proportion information is also 30%. However, the expression form of the fragrance proportion information can be switched according to requirements. For example, if the total proportion is 1, the fragrance proportion information can be represented by 30%, but if the total proportion is 100 parts, the fragrance proportion information can be represented by 30 parts. That is, the fragrance proportion information is not necessarily represented by a percentage and can also be converted to be represented by parts. Understandably, since there are interactions between fragrances, a fragrance with a greater olfactory sensory stimulation effect (such as an animal fragrance) will suppress a fragrance with a smaller olfactory sensory stimulation effect (such as a fruit fragrance). Therefore, in some embodiments, after determining the actual proportion information corresponding to each group of the environmental data according to the environmental proportion information of each group of the environmental data, the proportion of the fragrance with a greater olfactory sensory stimulation effect can be appropriately reduced according to the preset special conditions, and then all the actual proportion information is correspondingly adjusted to the fragrance proportion information.

[0053] S3023. Generate aroma data corresponding to this set of environmental data according to the aroma type information and the aroma proportion information corresponding to the same set of the environmental data; that is, the scene aroma information includes multiple sets of aroma data, and each set of aroma data includes aroma type information and aroma proportion information. And each set of aroma data corresponds to a set of environmental data.

[0054] S3024. Generate scene aroma information corresponding to the scene environmental information according to all sets of the aroma data.

[0055] In this embodiment, first determine the aroma type information corresponding to the scene quantization object of each set of the environmental data according to the environmental aroma association table, and then determine the corresponding aroma proportion information according to the environmental proportion information in different environmental data. Finally, realize the conversion from the scene environmental information to the scene aroma information. This embodiment converts the quantified environmental data into quantified scene aroma information according to the preset environmental aroma association table, realizes the quantification process of the target scene at the aroma level, and provides an effective basis for the selection of spice types in the subsequent steps.

[0056] In one embodiment, the target scenario is an image of a forest scene. The scene environment information of the forest scene image consists of 8 sets of environmental data, and each set of environmental data is [leaves, 30%], [tree trunks, 10%], [ferns, 10%], [moss, 10%], [river water, 25%], [flowers and fruits, 5%], [animals, 5%], and [soil, 5%]. Thus, the aroma type information corresponding to the scene quantification objects of each set of environmental data is found from the environmental aroma association table, which are the green aroma of leaves, the woody aroma of tree trunks, the grassy aroma of ferns and moss, the aquatic aroma of river water, the floral aroma and fruity aroma of flowers and fruits, the animal aroma of animals, and the pungent aroma and turbid aroma of soil. Further, the aroma proportion information corresponding to this set of environmental data is determined according to the environmental proportion information of each set of environmental data, and the aroma type information and aroma proportion information corresponding to the same set of environmental data are generated into a set of aroma data. In the process of determining the aroma proportion information corresponding to this set of environmental data according to the environmental proportion information of each set of environmental data, the environmental proportion information can be adjusted according to the degree of the stimulating effect of the aroma type information on the sense of smell. For example, in this embodiment, when the aroma type information corresponding to the scene quantification object has a continuous and stable aroma (such as the aroma type information corresponding to leaves, tree trunks, ferns, moss, and river water), the actual proportion information determined according to the environmental proportion information of the environmental data can be directly determined as the aroma proportion information without adjustment; when the aroma type information corresponding to the scene quantification object has a large stimulating effect on the olfactory sense (such as the animal aroma corresponding to animals and the pungent aroma and turbid aroma corresponding to soil), the actual proportion information determined according to the environmental proportion information of the environmental data can be down-regulated, and the actual proportion information after reduction is determined as the aroma proportion information. When the aroma type information corresponding to the scene quantification object has a small stimulating effect on the olfactory sense (such as the floral aroma and fruity aroma corresponding to flowers and fruits), the fragrance is easily suppressed, and the actual proportion information determined according to the environmental proportion information of the environmental data can be up-regulated, and the actual proportion information after increase is determined as the aroma proportion information. Furthermore, it can be obtained from the above that in this embodiment, the target scenario includes a forest scene; the scene aroma information corresponding to the forest scene includes: 30 parts of green aroma; 10 parts of woody aroma; 20 parts of grassy aroma; 25 parts of aquatic aroma; 5 parts of floral aroma; 2 parts of fruity aroma; 2 parts of animal aroma; 2 parts of pungent aroma; 2 parts of turbid aroma.

[0057] In another embodiment, the target scene is an image of a cherry blossom viewing scene. The scene environment information of the cherry blossom viewing scene image is composed of 9 sets of environment data. Each set of environment data is respectively [cherry blossom, 35%], [tree trunk, 5%], [leaves, 10%], [river water, 10%], [wooden bridge, 10%], [animals, 5%], [grass, 15%], [soil, 5%] and [moss, 10%]. Similar to the above embodiment, in the environmental fragrance association table, the fragrance type information corresponding to the scene quantization objects of each set of environment data is found to be the sweet floral fragrance, fresh floral fragrance, honey-sweet floral fragrance and wine-like floral fragrance of cherry blossoms, the woody fragrance of the tree trunk and the wooden bridge, the green fragrance of the leaves, the water fragrance of the river water, the animal fragrance of the animals, the turbid fragrance of the soil, and the grass fragrance of the grass and moss. Further, according to the environmental proportion information of each set of environment data, the fragrance proportion information corresponding to this set of environment data is determined, and the fragrance type information and the fragrance proportion information corresponding to the same set of environment data are generated into a set of fragrance data. In the process of determining the fragrance proportion information corresponding to each set of environment data according to the environmental proportion information of each set of environment data, when the environmental type attribute of the scene quantization object is a specific type of flower (such as cherry blossoms), the fragrance type information of the floral fragrance is richer (such as sweet floral fragrance, fresh floral fragrance and honey-sweet floral fragrance). At this time, compared with the environmental proportion information of the environment data, the fragrance proportion of the floral fragrance in the fragrance proportion information of the fragrance data will increase, and the fragrance proportion of other fragrances will decrease. Furthermore, it can be obtained from the above that, in this embodiment, the target scene includes a cherry blossom viewing scene; the scene fragrance information corresponding to the cherry blossom viewing scene includes: 30 parts of sweet floral fragrance, 20 parts of fresh floral fragrance, 2 parts of honey-sweet floral fragrance, 5 parts of wine-like floral fragrance, 5 parts of woody fragrance, 10 parts of green fragrance, 5 parts of water fragrance, 2 parts of animal fragrance, 2 parts of turbid fragrance, and 2 parts of grass fragrance.

[0058] S303. Determine the spice type information according to the scene fragrance information. Among them, each set of environment data in the scene environment information corresponds to a scene quantization object. Fragrance is used to describe the tone of one of the various fragrances when combined (such as the green fragrance of grass, the woody fragrance of the tree trunk and the animal fragrance of animals, etc.), which reflects not the characteristics of the overall fragrance, but a part of it. Scene fragrance information refers to the set of scene fragrance information possessed by all scene quantization objects in the target scene. Different types of spices show different fragrances in terms of olfactory sensory stimulation when volatilized. One spice generally has only one fragrance, and one fragrance can correspond to one or more spices. For example, the three spices of cedarwood oil, sandalwood oil and terpineol all show a woody fragrance. There is a corresponding relationship between the scene quantization object and the fragrance type, and there is also a corresponding relationship between the fragrance of the spice and the fragrance type. Through the conversion of the above corresponding relationships, the scene environment information can be converted into spice type information, thereby increasing the relevance between the fragrance and the target scene.

[0059] In one embodiment, in step S303, that is, determining the spice type information according to the scenario fragrance information includes the following steps S3031 - S3033:

[0060] S3031. Obtain a fragrance - spice mapping table; wherein, the fragrance - spice mapping table includes multiple groups of fragrance - spice data groups; in each group of the fragrance - spice data groups, there is included a fragrance comparison type and a spice list associated with the fragrance comparison type; in each of the spice lists, there are included at least one type of spice; understandably, the fragrance comparison type is the fragrance type that serves as the matching object in the fragrance - spice mapping table. One fragrance comparison type can be associated with one or more spices. Therefore, the spice list corresponding to each fragrance comparison type contains at least one type of spice.

[0061] S3032. Determine the spice type data corresponding to each group of the fragrance data according to the fragrance - spice mapping table; each spice type data includes at least one type of spice; that is, match the fragrance type information in the fragrance data with each fragrance comparison type in the fragrance - spice mapping table. After successful matching, the spice list corresponding to the successfully matched fragrance comparison type can be determined as the spice type data corresponding to the fragrance data.

[0062] In one embodiment, step S3032 includes:

[0063] Obtain the fragrance type information in each group of the fragrance data.

[0064] Determine the fragrance comparison types that match each of the fragrance type information from all the fragrance - spice data groups; that is, search for the fragrance comparison types that match each fragrance type information in all the fragrance - spice data groups.

[0065] Determine the spice list associated with the fragrance comparison type that matches each of the fragrance type information as the spice type data corresponding to the fragrance data to which the fragrance type information belongs. That is, each fragrance comparison type has an associated spice list. Therefore, the spice list associated with the successfully matched fragrance comparison type can be determined as a set of spice type data corresponding to the fragrance data corresponding to it. Understandably, when a set of spice type data includes multiple spices, one or more of the spices can be selected as needed when formulating the fragrance so that the fragrance product has the corresponding fragrance.

[0066] This embodiment realizes the rapid search of fragrance type information based on the fragrance - spice mapping table, improves the search efficiency and accuracy. At the same time, a set of spice type data is determined according to the fragrance type information and the spice list, retaining the corresponding relationship between the fragrance and the spice type, which is beneficial to subsequent spice selection and fragrance formulation.

[0067] S3033. Generate spice type information corresponding to the target scenario based on all the spice type data. Understandably, the spice type information includes all the spice type data corresponding to each group of fragrance data.

[0068] In this embodiment, the quantified fragrance data is converted into spice type data according to the preset fragrance-spice mapping table, and the spice type information that can meet the requirements of restoring the target scenario is determined based on the fragrance data, which helps to quickly formulate a fragrance that meets the requirements.

[0069] In one embodiment, the target scenario is an image of a forest scene. The scene fragrance information of the forest scene image consists of 9 groups of fragrance data. Each group of fragrance data is respectively [green fragrance, 30 parts], [wood fragrance, 10 parts], [grass fragrance, 20 parts], [water fragrance, 25 parts], [flower fragrance, 5 parts], [fruit fragrance, 2 parts], [animal fragrance, 2 parts], [spicy fragrance, 2 parts] and [cloudy fragrance, 2 parts]. Determine each group of spice type data according to the fragrance-spice mapping table. Finally, the spice type information of the forest scene image includes the following spice type data: [green fragrance spices: leaf acetate, α-pinene, leaf alcohol, trans-2-cis-6-nonadienal], [wood fragrance spices: cypress oil, sandalwood oil, birch tar, terpineol], [grass fragrance spices: patchouli oil, citronellol, citronellyl acetate, linalool, linalyl acetate, green phenol, oakmoss extract], [water fragrance spices: benzaldehyde, ketone, Asian peppermint oil], [flower fragrance spices: geraniol, geranyl acetate, geranium oil, benzyl acetate],

[0070] [fruit fragrance spices: peach aldehyde, coconut aldehyde], [animal fragrance spices: galaxolide], [spicy fragrance spices: eugenol, isoeugenol] and [cloudy fragrance spices: indole].

[0071] In another embodiment, the target scenario is an image of a cherry blossom viewing scene. The scene fragrance information of the cherry blossom viewing scene image consists of 10 sets of fragrance data. Each set of fragrance data is respectively [sweet floral fragrance, 30 parts], [fresh floral fragrance, 20 parts], [honey-sweet fragrance, 2 parts], [wine fragrance, 5 parts], [wood fragrance, 5 parts], [green fragrance, 10 parts], [watery fragrance, 5 parts], [animal fragrance, 2 parts], [heavy fragrance, 2 parts] and [herbal fragrance, 2 parts]. Determine each set of spice type data according to the fragrance-spice mapping table. Finally, the spice type information of the cherry blossom viewing scene image includes the following spice type data: [sweet floral fragrance spice: geranium oil, phenylethyl alcohol, geraniol, geranyl acetate, methyl ionone], [fresh floral fragrance spice: benzyl acetate, damascenone, alpha-hexyl cinnamaldehyde, ylang-ylang oil], [honey-sweet fragrance spice: vanillin, ethyl vanillin], [wine fragrance spice: cognac oil, ethyl heptanoate], [wood fragrance spice: cedarwood oil, birch tar oil], [green fragrance spice: methyl dihydrojasmonate, alpha-pinene, leaf alcohol, nonanal], [watery fragrance spice: benzaldehyde, ketone, Asian peppermint oil], [animal fragrance spice: galaxolide, civetone], [heavy fragrance spice: indole] and [herbal fragrance spice: citronellol, citronellyl acetate, oakmoss extract].

[0072] S40. Compare the determined spice type information with the set spice type ratio data table to determine the target fragrance that matches the target scenario.

[0073] Understandably, a fragrance is formulated by different types of spices in proportion. Different types of spices have different degrees of stimulation to the olfactory senses. When two different types of spices are combined, the resulting odor may not interfere with each other, may enhance or weaken each other, or may even produce a new odor. When formulating a fragrance with spices, different types of spices have better effects within a specific proportion range. The spice type ratio data table contains multiple spice groups and at least one ratio combination associated with each spice group. Among them, each spice group contains at least one type of spice, and the ratio combination refers to the proportional combination relationship among all types of spices in the spice group. After determining the spice type information, the spice type ratio data table can be used to query the spice group corresponding to each set of spice type data in the spice type information, and then obtain all the ratio combinations corresponding to the queried spice group; according to the priority of the ratio combination and the required preset test quantity (the preset test quantity refers to the number of test fragrances to be formulated, which can be set according to requirements), select a set of ratio combinations for each spice group, and then determine all the selected ratio combinations as a set of ratio information. According to a set of ratio information, fragrance blending processing can be carried out to obtain a test fragrance.

[0074] Among them, the target fragrance refers to the fragrance that can maximize the restoration of the target scene in terms of olfactory sense among all the fragrances to be tested. The scenes created by each fragrance to be tested are different in terms of olfactory sense. Among all the fragrances to be tested, the degree of matching between the scenes restored by each fragrance to be tested and the target scene is different. Therefore, by conducting olfactory tests on all the fragrances to be tested, the fragrance to be tested that can maximize the restoration of the target scene in terms of olfactory sense can be found according to the obtained olfactory test results, and this fragrance to be tested is determined as the target fragrance.

[0075] In this embodiment, by obtaining the scene environment information corresponding to the target scene and determining the spice type information according to the scene environment information, the relevance and matching degree between the spice of the vehicle-mounted fragrance and the target scene are increased. This embodiment also obtains the pre-set spice type ratio data table, and based on the comparison between the spice type ratio data table and the determined spice type information, determines the target fragrance that matches the target scene, improves the matching of the vehicle-mounted fragrance with the target scene, and attaches importance to the user experience. This embodiment integrates the scene application requirements of the vehicle into the development process of the vehicle-mounted fragrance. Based on the analysis of the environmental information of different target scenes, it reversely matches different spice types and then formulates the vehicle-mounted fragrance, so that the vehicle-mounted fragrance can more accurately restore the target scene in terms of olfactory sense, and at the same time makes the aroma of the vehicle-mounted fragrance product more harmonious and rich, meeting the user's requirements for the scene, health and intelligence of the vehicle, and improving the user experience.

[0076] In one embodiment, in step S40, that is, comparing the determined spice type information with the pre-set spice type ratio data table to determine the target fragrance that matches the target scene includes the following steps S401 - S402:

[0077] S401. Compare the determined spice type information with the pre-set spice type ratio data table to determine at least one set of ratio information, and determine a fragrance to be tested according to each set of the ratio information; in one embodiment, the spice type ratio data table contains multiple spice groups and at least one ratio combination associated with each spice group; among them, each spice group contains at least one spice, and the ratio combination refers to the proportional combination relationship between all types of spices in the spice group. Each spice group can be associated with one or more ratio combinations. For example, if the spice group includes three spices A, B, and C, the ratio combination can be A:B:C = 1:1:2; it can also be A:B:C = 1:0:1. That is, the ratio of various spices in the spice group can be preset to be greater than or equal to 0 according to actual needs. When the ratio corresponding to a certain spice in a ratio combination is 0, it means that in this ratio combination, this spice will not be selected for use.

[0078] Further, in step S401, the step of comparing the determined spice type information with the set spice type ratio data table to determine at least one set of ratio information, and determining a test fragrance according to each set of the ratio information includes the following steps S4011 - S4015:

[0079] S4011, obtain each group of the spice type data in the spice type information; in this embodiment, after determining the spice type information, the spice group corresponding to each group of the spice type data in the spice type information can be queried by using the spice type ratio data table.

[0080] S4012, determine the spice group that matches each group of the spice type data from the spice type ratio data table; specifically, when the spice types in a group of spice type data are exactly the same as those in the spice group in the spice type ratio data table, it is considered that the two match, otherwise they do not match.

[0081] S4013, determine all the ratio combinations associated with the spice group that matches the spice type data as the combination ratio information corresponding to the spice type data; after determining the spice group corresponding to the spice type data, all the ratio combinations corresponding to the spice group obtained are the combination ratio information corresponding to the spice type data; the combination ratio information corresponding to a group of the spice type data includes one or more ratio combinations.

[0082] S4014. Select one proportion combination from the combination proportion information corresponding to each of the spice type data, and record all the selected proportion combinations as a set of the proportion information. That is, since the combination proportion information corresponding to one spice type data contains one or more proportion combinations, when it is necessary to prepare a test fragrance to be tested, only one proportion combination needs to be selected from the combination proportion information corresponding to each spice type data. Then, based on the selected proportion combinations corresponding to each group of spice type data, a set of proportion information is determined. When selecting one proportion combination from the combination proportion information corresponding to each group of spice type data, it can be selected according to the priority of the proportion combination and the required preset test quantity (the preset test quantity refers to the quantity of the test fragrance to be prepared, which can be set according to requirements). For example, if the combination proportion information corresponding to a group of spice type data contains two proportion combinations, but the preset test quantity is only one, only the proportion combination with the highest priority needs to be selected at this time. If the combination proportion information corresponding to a group of spice type data contains only one proportion combination, but the preset test quantity is three, then this unique proportion combination is selected three times. The same applies to other cases, which are selected according to the order from high to low priority and the preset test quantity. Among them, the priority of the above proportion combination can be directly preset in advance, or can be adjusted according to the degree of preference feedback by the user after the actual use of the proportion combination in the fragrance, etc.

[0083] S4015. Perform fragrance blending processing according to each set of the proportion information to obtain a test fragrance to be tested. In this embodiment, a test fragrance to be tested can be obtained by performing fragrance blending processing according to a set of proportion information.

[0084] S402. Determine the target fragrance that matches the target scenario from all the test fragrances to be tested. In this embodiment, based on the comparison of the spice type proportion data table, at least one set of proportion information can be determined. The test fragrance to be tested can be quickly prepared based on the proportion information, and then the target fragrance that has the highest matching degree with the target scenario is determined from all the test fragrances to be tested. Furthermore, the target fragrance that meets the user's expectations can be accurately determined, and it can also provide reference and guidance for other similar target scenarios. In this embodiment, the proportion information of the test fragrance corresponding to the spice type information can be quickly searched and determined by using the spice type proportion data table, which broadens the richness of the proportion scheme between the spices in the test fragrance to be tested, ensures the rationality of the selected spice types and the combination proportion, and improves the efficiency of the fragrance product development.

[0085] In one embodiment, the target scenario is an image of a forest scene. The scene aroma information of the forest scene image consists of 9 sets of aroma data, and each set of aroma data is respectively [green aroma, 30 parts], [wood aroma, 10 parts], [grass aroma, 20 parts], [water aroma, 25 parts], [flower aroma, 5 parts], [fruit aroma, 2 parts], [animal aroma, 2 parts], [spicy aroma, 2 parts] and [muddled aroma, 2 parts].

[0086] The spice type information of the forest scene image includes the following spice type data: [green aroma spice: leaf acetate, α-pinene, leaf alcohol, trans-2-cis-6-nonadienal], [wood aroma spice: cedarwood oil, sandalwood oil, birch tar, terpineol], [grass aroma spice: patchouli oil, citronellol, citronellyl acetate, linalool, linalyl acetate, green flower phenol, oakmoss extract], [water aroma spice: benzaldehyde, ketone, Asian peppermint oil], [flower aroma spice: geraniol, geranyl acetate, geranium oil, benzyl acetate], [fruit aroma spice: peach aldehyde, coconut aldehyde], [animal aroma spice: galaxolide], [spicy aroma spice: eugenol, isoeugenol] and [muddled aroma spice: indole].

[0087] Thus, when determining a set of formulation information as follows (the numerical unit in the formulation combination is part):

[0088] The formulation combination corresponding to the spice type data [green aroma spice: leaf acetate, α-pinene, leaf alcohol, trans-2-cis-6-nonadienal] is "leaf acetate: α-pinene: leaf alcohol: trans-2-cis-6-nonadienal = 30:0:0:0";

[0089] The formulation combination corresponding to the spice type data [wood aroma spice: cedarwood oil, sandalwood oil, birch tar, terpineol] is "cedarwood oil: sandalwood oil: birch tar: terpineol = 0:0:0:10";

[0090] The formulation combination corresponding to the spice type data [grass aroma spice: patchouli oil, citronellol, citronellyl acetate, linalool, linalyl acetate, green flower phenol, oakmoss extract] is "patchouli oil: citronellol: citronellyl acetate: linalool: linalyl acetate: green flower phenol: oakmoss extract = 0:0:20:0:0:0:0";

[0091] The formulation combination corresponding to the spice type data [water aroma spice: benzaldehyde, ketone, Asian peppermint oil] is "benzaldehyde: ketone: Asian peppermint oil = 25:0:0";

[0092] The formulation combination corresponding to the spice type data [flower aroma spice: geraniol, geranyl acetate, geranium oil, benzyl acetate] is "geraniol: geranyl acetate: geranium oil: benzyl acetate = 0:0:0:5";

[0093] The ratio combination corresponding to the spice type data [fruity spice: peach aldehyde, coconut aldehyde] is "peach aldehyde: coconut aldehyde = 2:0";

[0094] The ratio combination corresponding to the spice type data [animalic spice: galaxolide] is "galaxolide = 2";

[0095] The ratio combination corresponding to the spice type data [spicy spice: eugenol, isoeugenol] is "eugenol: isoeugenol = 2:0";

[0096] The ratio combination corresponding to the spice type data [mellow spice: indole] is "indole = 2";

[0097] At this time, the ratio information composed of the above ratio combinations can be obtained as "leaf acetate: terpineol: citronellyl acetate: benzaldehyde: benzyl acetate: coconut aldehyde: galaxolide: eugenol and indole = 30:10:20:25:5:2:2:2:2". At this time, the ratio information of a test fragrance to be obtained includes [leaf acetate, 30 parts], [terpineol, 10 parts], [citronellyl acetate, 20 parts], [benzaldehyde, 25 parts], [benzyl acetate, 5 parts], [coconut aldehyde, 2 parts], [galaxolide, 2 parts], [eugenol, 2 parts] and [indole, 2 parts].

[0098] In one embodiment, in step S40, that is, determining the target fragrance matching the target scene image from all the test fragrances to be tested includes:

[0099] S403. Obtain the olfactory test results of all the test fragrances to be tested;

[0100] S404. Determine the scene reproduction scores of each of the test fragrances to be tested according to the olfactory test results;

[0101] S405. Determine the test fragrances to be tested with scene reproduction scores greater than the preset score as the target fragrances matching the target scene.

[0102] Understandably, among different types of spices in a set of spice type data corresponding to an aroma type, there are differences in the intensity of olfactory sensory stimulation. For example, cedarwood oil, sandalwood oil, and terpineol all exhibit a woody aroma, but the olfactory sensory stimulation degree of sandalwood oil is stronger than that of cedarwood oil and terpineol. Therefore, the olfactory test results for different test fragrances to be tested may be completely different. Therefore, in this embodiment, samples of each test fragrance to be tested need to be subjected to an olfactory test, and the personnel undergoing the test include people of different ages and genders. The personnel undergoing the test take turns entering the driver's seat of the same vehicle and perform a round of olfactory tests using smelling strips of the same test fragrance to be tested. Each test fragrance to be tested is tested for 3 rounds, 5 seconds each time, with an interval of more than 15 seconds. After the test, the subjective feeling results of the personnel undergoing the test on the preference for the test fragrance to be tested and the description of the scene restoration (such as floral fragrance, grass fragrance, and wood fragrance, etc.) are statistically recorded as the olfactory test results. The scene reproduction score is a score used to evaluate the degree of overlap between the restored scene and the target scene in the olfactory test results. The preset score is the critical value of the scene reproduction score preset for determining whether the test fragrance to be tested meets the target scene restoration requirement. The default value can be set according to empirical data, or it can be adjusted as needed. When there are multiple test fragrances to be tested, there may be more than one test fragrance to be tested whose scene reproduction score is greater than the preset score. At this time, the test fragrance to be tested with the highest scene reproduction score can be determined as the target fragrance matching the target scene, or all test fragrances to be tested whose scene reproduction scores are greater than the preset score can be determined as the target fragrances matching the target scene, obtaining a series of target fragrances. When there are multiple test fragrances to be tested, it is possible that the scene reproduction scores of all test fragrances to be tested are less than or equal to the preset score. At this time, it is necessary to re-perform the olfactory test on all test fragrances to be tested, obtain the updated olfactory test results of all test fragrances to be tested and determine the updated scene reproduction scores, and judge whether each updated scene reproduction score is greater than the preset score until the target fragrance is confirmed from all test fragrances to be tested.

[0103] In this embodiment, the scene reproduction score is obtained based on the olfactory test results of the test fragrance samples to be tested, and the target fragrance is determined from the test fragrances to be tested by judging the threshold of the scene reproduction score, ensuring that the target fragrance can more accurately restore the target scene in terms of olfactory sense.

[0104] In one embodiment, the target scene includes a forest scene;

[0105] The scene aroma information corresponding to the forest scene includes:

[0106] Green aroma, 30 parts;

[0107] Woody aroma, 10 parts;

[0108] Grass aroma, 20 parts;

[0109] Water fragrance note, 25 portions;

[0110] Flower fragrance note, 5 portions;

[0111] Fruit fragrance note, 2 portions;

[0112] Animal fragrance note, 2 portions;

[0113] Spicy fragrance note, 2 portions;

[0114] Muddy fragrance note, 2 portions.

[0115] Understandably, this embodiment describes the scene fragrance note information corresponding to the forest scene when the target scene is specifically the forest scene. The forest scene usually has its unique atmosphere and characteristics, such as freshness, naturalness, vitality, etc. The scene fragrance note information of the forest scene specifically includes green fragrance note, wood fragrance note, grass fragrance note, water fragrance note, flower fragrance note, fruit fragrance note, animal fragrance note, spicy fragrance note and muddy fragrance note, and each fragrance note has a corresponding portion value. These portion values represent the olfactory stimulation degree of different fragrance notes in the forest scene, and can provide guidance for subsequent fragrance formulation. This embodiment lists the scene fragrance note information of the forest scene, which helps to further design a fragrance formula to restore the forest scene to meet the desired atmosphere effect.

[0116] In one embodiment, the target scene includes a cherry blossom viewing scene;

[0117] The scene fragrance note information corresponding to the cherry blossom viewing scene includes:

[0118] Sweet flower fragrance note, 30 portions;

[0119] Fresh flower fragrance note, 20 portions;

[0120] Honey-sweet fragrance note, 2 portions;

[0121] Wine fragrance note, 5 portions;

[0122] Wood fragrance note, 5 portions;

[0123] Green fragrance note, 10 portions;

[0124] Water fragrance note, 5 portions;

[0125] Animal fragrance note, 2 portions;

[0126] Muddy fragrance note, 2 portions;

[0127] Grass fragrance note, 2 portions.

[0128] Understandably, this embodiment describes the scene fragrance information corresponding to the cherry blossom viewing scene when the target scene is specifically the cherry blossom viewing scene. The cherry blossom viewing scene usually has its unique atmosphere and characteristics, such as romantic, fresh, intoxicating, etc. The scene fragrance information of the cherry blossom viewing scene specifically includes sweet floral fragrance, fresh floral fragrance, honey-sweet fragrance, wine fragrance, woody fragrance, green fragrance, aquatic fragrance, animal fragrance, turbid fragrance, and herbaceous fragrance, and each fragrance has a corresponding fractional value. These fractional values represent the olfactory stimulation degree of different fragrances in the cherry blossom viewing scene, which can provide guidance for subsequent fragrance formulation. This embodiment lists the scene fragrance information of the cherry blossom viewing scene, which helps to further design a fragrance formula to restore the cherry blossom viewing scene to meet the desired atmosphere effect.

[0129] In one embodiment, in step S40, that is, after determining the target fragrance that matches the target scene image from all the to-be-tested fragrances, it further includes:

[0130] S404. Send the scene environment information corresponding to the target scene to the target vehicle-mounted terminal loaded with the target fragrance, so that the target vehicle-mounted terminal establishes an association relationship between the target scene and the target fragrance according to the scene environment information;

[0131] S405. When the target vehicle-mounted terminal receives a fragrance release instruction corresponding to the target scene, perform a fragrance release operation on the target fragrance.

[0132] Understandably, the target vehicle-mounted terminal refers to the fragrance system control terminal of the vehicle loaded with the target fragrance, such as the vehicle computer terminal. The fragrance system control terminal of the vehicle is built-in with multiple scene modes for selection, and one mode can correspond to one vehicle-mounted fragrance product (all vehicle-mounted fragrance products are target fragrances). In one embodiment, when the target fragrance is a forest scene fragrance product and the vehicle is loaded with this forest scene fragrance product, the fragrance system control terminal receives the scene environment information and forest scene image of the forest scene, and establishes an association relationship between the forest scene image and the forest scene fragrance product, and sets the forest scene image as the preview screen of the forest scene mode. When the driver and passengers of the vehicle select the forest scene mode through the central control display screen or buttons, the fragrance system control terminal receives a fragrance release instruction corresponding to the forest scene image and performs a fragrance release operation on the forest scene fragrance product.

[0133] This embodiment sets a fragrance release mode corresponding to the target scene on the target vehicle-mounted terminal loaded with the target fragrance, so as to facilitate the release of the target fragrance, meet the user's scene-based requirements for the vehicle, and enhance the user's olfactory sensory experience.

[0134] It should be understood that the sequence numbers of the steps in the above embodiments do not indicate the order of execution, and the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0135] In one embodiment, a scene-based fragrance data processing device is provided. The scene-based fragrance data processing device corresponds one-to-one with the scene-based fragrance data processing method in the above embodiment. As Figure 2 shown, the scene-based fragrance data processing device includes a proportion data table acquisition module 10, an environmental information acquisition module 20, a fragrance type determination module 30, and a target fragrance determination module 40. The detailed description of each functional module is as follows:

[0136] The proportion data table acquisition module 10 is configured to acquire a preset fragrance type proportion data table;

[0137] The environmental information acquisition module 20 is configured to acquire scene environmental information corresponding to the target scene;

[0138] The fragrance type determination module 30 is configured to determine fragrance type information according to the scene environmental information;

[0139] The target fragrance determination module 40 is configured to compare the determined fragrance type information with the preset fragrance type proportion data table to determine a target fragrance matching the target scene.

[0140] For the specific limitations of the scene-based fragrance data processing device, reference can be made to the limitations of the scene-based fragrance data processing method in the foregoing text, which will not be elaborated here. Each module in the above scene-based fragrance data processing device can be implemented in whole or in part by software, hardware, and their combination. The above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0141] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as Figure 3As shown. The computer device includes a processor, a memory, a network interface, and a database connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a readable storage medium and an internal memory. The readable storage medium stores an operating system, computer-readable instructions, and a database. The internal memory provides an environment for the operation of the operating system and computer-readable instructions in the readable storage medium. The database of the computer device is used to store the data involved in the method for processing fragrance data based on scenarios. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer-readable instructions are executed by the processor, a method for processing fragrance data based on scenarios is implemented. The readable storage medium provided in this embodiment includes a non-volatile readable storage medium and a volatile readable storage medium.

[0142] In one embodiment, a computer device is provided, including a memory, a processor, and computer-readable instructions stored on the memory and executable on the processor. When the processor executes the computer-readable instructions, the following steps are implemented:

[0143] Obtain a pre-set fragrance type ratio data table;

[0144] Obtain the scenario environment information corresponding to the target scenario;

[0145] Determine the fragrance type information according to the scenario environment information;

[0146] Compare the determined fragrance type information with the pre-set fragrance type ratio data table to determine the target fragrance that matches the target scenario.

[0147] In one embodiment, one or more computer-readable storage media storing computer-readable instructions are provided. The readable storage media provided in this embodiment include non-volatile readable storage media and volatile readable storage media. Computer-readable instructions are stored on the readable storage media. When the computer-readable instructions are executed by one or more processors, the following steps are implemented:

[0148] Obtain a pre-set fragrance type ratio data table;

[0149] Obtain the scenario environment information corresponding to the target scenario;

[0150] Determine the fragrance type information according to the scenario environment information;

[0151] Compare the determined fragrance type information with the pre-set fragrance type ratio data table to determine the target fragrance that matches the target scenario.

[0152] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through computer-readable instructions. The computer-readable instructions can be stored in a non-volatile readable storage medium or a volatile readable storage medium. When the computer-readable instructions are executed, they can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the embodiments provided by the present invention can include non-volatile and / or volatile memories. Non-volatile memories can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memories can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0153] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, only the above division of each functional unit and module is used as an example. In actual applications, the above functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0154] The above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments or perform equivalent replacements for some of the technical features. These modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention and should all be included in the protection scope of the present invention.

Claims

1. A scenario-based fragrance data processing method, characterized in that, Including: Obtain a preset data table of spice type ratios; Obtain scene environment information corresponding to the target scene; Determine spice type information according to the scene environment information; Compare the determined spice type information with the preset data table of spice type ratios to determine the target fragrance that matches the target scene.

2. The method for processing fragrance data based on scenarios according to claim 1, characterized in that The target scene includes multiple scene quantification objects; the scene environment information includes environment attribute information and environment proportion information corresponding one-to-one to each of the scene quantification objects; The obtaining of the scene environment information corresponding to the target scene includes: Perform object recognition on the target scene to determine environment attribute information corresponding one-to-one to each of the scene quantification objects; Perform splitting processing on the target scene according to the environment attribute information to obtain environment proportion information corresponding one-to-one to each of the scene quantification objects; Generate a set of environment data according to each scene quantification object and its corresponding environment proportion information; Generate the scene environment information corresponding to the target scene according to all sets of the environment data.

3. The method for processing fragrance data based on scenarios according to claim 2, wherein The performing of object recognition on the target scene to determine the included scene quantification objects and the environment attribute information corresponding one-to-one to each of the scene quantification objects includes: Obtain a scene image corresponding to the target scene, perform object recognition on the scene image through a preset image recognition model, and obtain at least one image type information included in the scene image output by the preset image recognition model and its corresponding image element features; Record each of the image type information as a scene quantification object, and record the image element features corresponding to each of the image type information as the environment attribute information corresponding to it.

4. The method for processing fragrance data based on scenarios according to claim 3, wherein, The image element features include the color attribute of the scene quantification object and the position attribute of the scene quantification object in the scene image; The performing of splitting processing on the target scene according to the environment attribute information to obtain environment proportion information corresponding one-to-one to each of the scene quantification objects includes: In the scene image of the target scene, record the pixel points with the same color attribute as the scene quantification object as the target pixel points corresponding to the scene quantification object; Obtain the position attributes of all the target pixel points corresponding to the same scene quantification object, and split out the scene quantification object from the scene image according to the obtained all position attributes to obtain an object area corresponding to the scene quantification object; Determine the area proportion of each object area in the scene image as the environment proportion information of the scene quantification object corresponding to the object area.

5. The method for processing fragrance data based on scenarios according to claim 2, wherein The determining of the spice type information according to the scene environment information includes: Obtain an environmental fragrance association table; Determine scene fragrance information corresponding to the scene environment information according to the environmental fragrance association table; Determine spice type information according to the scene fragrance information.

6. The method for processing fragrance data based on a scenario according to claim 5, wherein The determining of the scene fragrance information corresponding to the scene environment information according to the environmental fragrance association table includes: Search for the fragrance type information corresponding to the scene quantification objects of each group of the environment data in the environmental fragrance association table; Determine the fragrance proportion information corresponding to the environmental data of each group according to the environmental proportion information of the environmental data of each group; Generate fragrance data corresponding to the environmental data of each group according to the fragrance type information and the fragrance proportion information corresponding to the environmental data of the same group; Generate scene fragrance information corresponding to the scene environment information according to the fragrance data of all groups.

7. The method for processing fragrance data based on a scenario according to claim 6, wherein The environmental fragrance association table includes multiple groups of environment-fragrance data groups; each group of the environment-fragrance data groups includes standard environmental information and the fragrance types associated with the standard environmental information; The step of finding out the fragrance type information corresponding to the scene quantization object of each group of the environmental data in the environmental fragrance association table includes: Obtain the environmental attribute information in each group of the environmental data; Search for the standard environmental information that matches each of the scene quantization objects from all the environment-fragrance data groups; Determine the fragrance type associated with the standard environmental information that matches each scene quantization object and its corresponding environmental attribute information as the fragrance type information corresponding to the scene quantization object.

8. The method for processing aroma data based on scenarios according to claim 5, wherein, The step of determining the spice type information according to the scene fragrance information includes: Obtain the fragrance-spice mapping table; Determine the spice type data corresponding to each group of the fragrance data according to the fragrance-spice mapping table; each spice type data includes at least one type of spice; Generate the spice type information corresponding to the target scene according to all the spice type data.

9. The method for processing fragrance data based on scenarios according to claim 8, wherein, The fragrance-spice mapping table includes multiple groups of fragrance-spice data groups; each group of the fragrance-spice data groups includes a fragrance comparison type and a spice list associated with the fragrance comparison type; Each spice list contains at least one type of spice; The step of determining the spice type data corresponding to each group of the fragrance data according to the fragrance-spice mapping table includes: Obtain the fragrance type information in each group of the fragrance data; Determine the fragrance comparison type that matches each of the fragrance type information from all the fragrance-spice data groups; Determine the spice list associated with the fragrance comparison type that matches each of the fragrance type information as the spice type data corresponding to the fragrance data to which the fragrance type information belongs.

10. The method for processing fragrance data based on scenarios according to claim 8, wherein The step of comparing the determined spice type information with the set spice type ratio data table to determine the target fragrance that matches the target scene includes: Compare the determined spice type information with the set spice type ratio data table to determine at least one set of ratio information, and determine a test fragrance to be tested according to each set of the ratio information; Determine the target fragrance that matches the target scene from all the test fragrances to be tested.

11. The scene-based fragrance data processing method according to claim 10, wherein The spice type ratio data table contains multiple spice groups and at least one ratio combination associated with each spice group; The step of comparing the determined spice type information with the set spice type ratio data table to determine at least one set of ratio information, and determining a test fragrance to be tested according to each set of the ratio information includes: Obtain each group of the spice type data in the spice type information; Determine the spice group that matches each group of the spice type data from the spice type ratio data table; Determine all the ratio combinations associated with the spice group that matches the spice type data as the combination ratio information corresponding to the spice type data; Select one ratio combination from the combination ratio information corresponding to each spice type data respectively, and record all the selected ratio combinations as a group of the ratio information; Perform perfume blending processing according to each group of the ratio information to obtain a to-be-tested fragrance.

12. The scene-based fragrance data processing method according to claim 10, wherein The determining the target fragrance that matches the target scenario from all the to-be-tested fragrances includes: Obtain the olfactory test results of all the to-be-tested fragrances; Determine the scenario reproduction scores of each to-be-tested fragrance according to the olfactory test results; Determine the to-be-tested fragrances with the scenario reproduction scores greater than the preset score as the target fragrances that match the target scenario.

13. The method for processing fragrance data based on scenarios according to claim 6, characterized in that The target scenario includes a forest scenario; The scenario fragrance rhyme information corresponding to the forest scenario includes: Green fragrance rhyme, 30 parts; Woody fragrance rhyme, 10 parts; Grassy fragrance rhyme, 20 parts; Watery fragrance rhyme, 25 parts; Floral fragrance rhyme, 5 parts; Fruity fragrance rhyme, 2 parts; Animalic fragrance rhyme, 2 parts; Spicy fragrance rhyme, 2 parts; Cloudy fragrance rhyme, 2 parts.

14. The method for processing fragrance data based on scenarios according to claim 6, wherein The target scenario includes a cherry blossom viewing scenario; The scenario fragrance rhyme information corresponding to the cherry blossom viewing scenario includes: Sweet floral fragrance rhyme, 30 parts; Fresh floral fragrance rhyme, 20 parts; Honey-sweet fragrance rhyme, 2 parts; Wine fragrance rhyme, 5 parts; Woody fragrance rhyme, 5 parts; Green fragrance rhyme, 10 parts; Watery fragrance rhyme, 5 parts; Animalic fragrance rhyme, 2 parts; Cloudy fragrance rhyme, 2 parts; Grassy fragrance rhyme, 2 parts.

15. The method for processing fragrance data based on scenarios according to any one of claims 1-14, characterized in that After determining the target fragrance that matches the target scenario, it further includes: Send the scenario environment information corresponding to the target scenario to the target vehicle-mounted terminal loaded with the target fragrance, so that the target vehicle-mounted terminal establishes an association relationship between the target scenario and the target fragrance according to the scenario environment information; When the target vehicle-mounted terminal receives a fragrance release instruction corresponding to the target scenario, perform a fragrance release operation on the target fragrance.

16. A computer device, comprising a memory, a processor, and computer-readable instructions stored in the memory and executable on the processor, characterized in that, When the processor executes the computer-readable instructions, it implements the scenario-based fragrance data processing method according to any one of claims 1 to 15.

17. A computer-readable storage medium storing computer-readable instructions, characterized in that, When the computer-readable instructions are executed by one or more processors, the one or more processors are caused to execute the scenario-based fragrance data processing method according to any one of claims 1 to 15.

Images