Environment peculiar smell monitoring and multi-mode fragrance AI cooperative processing system and use method

Abstract

The invention relates to the technical field of fragrance generation, and particularly discloses an environment peculiar smell monitoring and multi-mode fragrance AI cooperative processing system which is characterized by comprising a detection module used for detecting environment data, generating a detection signal when a peculiar smell value is larger than the national standard, triggering a peculiar smell removing system of the system at the same time, and sending the detection signal when the peculiar smell value meets the national standard. The system can automatically switch the fragrance mode; the fragrance synthesis module is used for adjusting the proportion of essential oil according to the instruction; a processing module; the AI module comprises an automatic adjustment module and a fragrance instruction module, the automatic adjustment module generates an LSTM neural network training model, and the fragrance instruction module is internally provided with an NLP mechanism and an attention mechanism. The fragrance cooperative processing system overcomes the defects that in the prior art, a fragrance cooperative processing system is low in automation degree, unable to decompose peculiar smell, turbid in fragrance, lack of an intelligent matching mechanism for emotional state interaction with users, insufficient in user experience and the like.

Description

Technical Field

[0001] The present invention relates to the field of fragrance generation, and in particular to an environmental odor monitoring and multimodal fragrance AI collaborative processing system and a method for using the system. Background Art

[0002] Environmental odor problems are widespread in industrial, medical, home, hotel rooms and public space scenarios. It is necessary to comprehensively manage the odors generated by the environment and take proactive measures to improve user happiness.

[0003] Existing fragrance devices typically rely solely on atomizers to atomize actively added essential oils. This approach offers limited user experience, low automation, and poor convenience, and is unable to automatically adjust the fragrance type based on the user's voice. Furthermore, existing fragrance generation is affected by environmental factors, resulting in mixed odors, unpleasant odors, and turbid fragrance. Summary of the Invention

[0004] (1) Technical issues to be resolved The problem to be solved by the present invention is to provide an environmental odor monitoring and multimodal fragrance AI collaborative processing system and a method of use, so as to overcome the defects of the existing fragrance collaborative processing system in the art, such as low degree of automation, inaccurate fragrance generation, and insufficient user experience.

[0005] (2) Technical solution To solve the above technical problems, the first aspect of the present invention provides an environmental odor monitoring and multimodal fragrance AI collaborative processing system and a method for use, which includes: A detection module, configured to detect environmental data and generate a detection signal; A fragrance synthesis module stores a variety of essential oils and adjusts the proportions of different essential oils according to instructions; a processing module, the processing module being connected to the detection module and the fragrance synthesis module, the processing module being configured to receive detection data, perform corresponding processing based on the detection data, and send adjustment instructions to the fragrance synthesis module; An AI module is built into the processing module and includes an automatic adjustment module and a fragrance instruction module. The automatic adjustment module collects user selection data to generate an LSTM neural network training model and generates a recommendation strategy. The fragrance instruction module has a built-in NLP mechanism and an attention mechanism. The NLP mechanism is used to extract user input language keywords and generate an adversarial network based on the attention mechanism. The adversarial network generates and judges the feasibility and accuracy of different essential oil ratios.

[0006] As in the aforementioned collaborative processing system, optionally, the processing module has a feature database, and the feature database stores feature data of different essential oils of multiple fragrances.

[0007] As described above, in the collaborative processing system, optionally, the feature database is connected to the fragrance instruction module, the language keywords extracted by the NLP mechanism in the fragrance instruction module correspond to the feature database to generate feature data, the adversarial network forms essential oil ratio data based on the feature data, and the essential oil ratio data is used to synthesize the fragrance in the fragrance synthesis module.

[0008] As for the collaborative processing system described above, optionally, the processing module is connected to a visual interface, and the visual interface is used to support user input of language, adjustment of fragrance mode and adjustment of fragrance ratio.

[0009] As described above, in the collaborative processing system, optionally, the fragrance synthesis module is connected to the engine module, the engine module includes a plasma decomposition device and a fragrance atomization device, the fragrance atomization device has an output quantity output classification, and the processing module controls the output of the fragrance atomization device.

[0010] As in the aforementioned collaborative processing system, optionally, the fragrance atomization device automatically adjusts the fragrance output based on the detection module.

[0011] As in the aforementioned collaborative processing system, optionally, the fragrance atomization device has a three-channel output, and a PID-Smith predictor is provided in the fragrance atomization device to compensate for atomization delay.

[0012] As described above, the collaborative processing system, optionally, the detection module includes a VOC sensor array, a temperature and humidity sensor, and a PM2.5 detector. The VOC sensor array is used to detect fragrance, the temperature and humidity sensor is used to detect the temperature and humidity in the air, and the PM2.5 detector is used to detect small particulate pollutants in the air.

[0013] As described above in the collaborative processing system, optionally, the detection signal between the detection module and the processing module is connected using a star topology network, and the star topology network is constructed by the LoRaWAN protocol.

[0014] To achieve the aforementioned objective, a second aspect of the present invention provides a method for using the collaborative processing system according to any one of the first aspects of the present invention, wherein the method is as follows: S1: The user inputs a fragrance description into the visual interface, and the AI ​​module matches the fragrance based on the feature database; S2: The fragrance synthesis module generates fragrance and outputs it; S3: The detection module detects the external environment and adjusts and corrects the fragrance odor.

[0015] (3) Beneficial effects The environmental odor monitoring and multimodal fragrance AI collaborative processing system and usage method provided by the present invention have the following beneficial effects: The processing module of the present invention receives input from the user and automatically adjusts under the control of the AI ​​module to generate an LSTM neural network training model. It then generates a recommendation strategy based on the user's usage habits and adjusts the generation of fragrance. The fragrance instruction module can accept instructions from the user, summarize and extract features from the user instructions based on the NLP mechanism, and match these features in a feature database. The matched features are then matched to the feasibility and accuracy of the essential oil ratio through the action of an adversarial network. This design has an extremely high degree of automation and can achieve high-precision and high-matching fragrance output according to user needs.

[0016] The fragrance synthesis module of the present invention synthesizes fragrance based on the finalized data and outputs it to the fragrance atomizer. The fragrance atomizer atomizes the fragrance, while the PID-Smith predictor within the atomizer compensates for the atomization time. This design effectively improves the accuracy of fragrance output.

[0017] The detection module of the present invention detects the fragrance content and ratio in the air in real time and inputs this information into the AI ​​module, which then adjusts the output fragrance content and ratio to further meet user needs. This design can further correct the output amount and improve the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0019] Figure 1 This is a flow chart of the environmental odor monitoring and multimodal fragrance AI collaborative processing system and its usage method of the present invention.

[0020] The corresponding component names of the various figure marks in the figure are: 1. Detection module; 11. VOC sensor array; 12. Temperature and humidity sensor; 13. PM2.5 detector; 2. Fragrance synthesis module; 3. Processing module; 4. AI module; 41. Automatic adjustment module; 42. Fragrance instruction module; 5. Feature database; 6. Visual interface; 7. Engine module; 71. Ion decomposition device; 72. Fragrance atomization device. DETAILED DESCRIPTION

[0021] The present application is described in detail below with reference to the accompanying drawings and specific embodiments.

[0022] The following describes the embodiments of the present application through specific examples, and those skilled in the art can easily understand other advantages and effects of the present application from the contents disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The present application can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present application. It should be noted that, in the absence of conflict, the features in the following embodiments and embodiments can be combined with each other. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without making creative work are within the scope of protection of this application.

[0023] It should be noted that various aspects of the embodiments within the scope of the appended claims are described below. It should be apparent that the aspects described herein can be embodied in a wide variety of forms, and any specific structure and / or function described herein is merely illustrative. Based on this application, it should be understood by those skilled in the art that an aspect described herein can be implemented independently of any other aspect, and two or more of these aspects can be combined in various ways. For example, any number and aspect described herein can be used to implement an apparatus and / or practice a method. In addition, other structures and / or functionalities other than one or more of the aspects described herein can be used to implement this apparatus and / or practice this method.

[0024] It should also be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present application. The illustrations only show components related to the present application and are not drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component can be changed at will, and the component layout type may also be more complicated.

[0025] Additionally, in the following description, specific details are provided to provide a thorough understanding of the examples, however, one skilled in the art will appreciate that the examples can be practiced without these specific details.

[0026] The following describes the technical solutions provided by various embodiments of the present application in conjunction with the accompanying drawings.

[0027] See Figure 1 The present invention provides an environmental odor monitoring and multimodal fragrance AI collaborative processing system, comprising: a detection module 1, a fragrance synthesis module 2, a processing module 3, and an AI module 4. During operation, the detection module 1 can detect various airborne data, including but not limited to fragrance concentration data, ambient temperature and humidity data, and air pollution data; the processing module 3 receives and analyzes this data; and the processing module 3 can also control the fragrance synthesis module 2 to intelligently and collaboratively output fragrance.

[0028] exist Figure 1 In an optional embodiment, the detection module 1 is used to detect environmental data and generate a detection signal. Through the detection module 1, the user can understand the external environmental conditions in real time, which is an important judgment basis of the present invention.

[0029] Furthermore, the detection module 1 includes a VOC sensor array 11, a temperature and humidity sensor 12, and a PM2.5 detector 13. The VOC sensor array 11 is used to detect fragrance, the temperature and humidity sensor 12 is used to detect the temperature and humidity in the air, and the PM2.5 detector 13 is used to detect small particulate pollutants in the air. Users can also configure different types of sensors in the detection module 1 as needed to further improve data detection.

[0030] exist Figure 1 In an optional embodiment, the fragrance synthesis module 2 stores multiple essential oils and adjusts the proportions of different essential oils according to the instructions. By synthesizing different essential oils, the fragrance can emit different types of odors. Therefore, the fragrance synthesis module 2 can generate fragrances according to user needs.

[0031] Furthermore, the processing module 3 is connected to the detection module 1 and the fragrance synthesis module 2 . The processing module 3 is used to receive detection data, perform corresponding processing according to the detection data, and send adjustment instructions to the fragrance synthesis module 2 .

[0032] Furthermore, the AI ​​module 4 is built into the processing module 3 and includes an automatic adjustment module 41 and a fragrance instruction module 42. The AI ​​module 4 can process the data detected by the detection module 1 and provide support for the coordination processing of the processing module 3.

[0033] Specifically, the automatic adjustment module 41 collects user selection data to generate an LSTM neural network training model and generate a recommendation strategy. The automatic adjustment module 41 can adjust the present invention based on the user's habit data. It should be noted that it can automatically adjust the output of the fragrance according to the user's preferred fragrance type at different time periods, and it can also adjust the output of the fragrance according to the user's preferred output volume at different time periods.

[0034] Furthermore, the fragrance instruction module 42 has a built-in NLP mechanism and an attention mechanism. The NLP mechanism is used to extract user input language keywords and generate an adversarial network based on the attention mechanism. The adversarial network generates and judges the feasibility and accuracy of different essential oil ratios.

[0035] It should be noted that the processing module 3 includes a feature database 5 , which stores feature data of different essential oils of various fragrances.

[0036] Furthermore, the feature database 5 is connected to the fragrance instruction module 42. The NLP mechanism within the fragrance instruction module 42 extracts language keywords that correspond to the feature database 5 to generate feature data. These language keywords can be entered by the user into the visual interface 6. The keywords extracted by the NLP mechanism can be matched with the feature data of different essential oils. When the user enters a desired fragrance release instruction into the visual interface 6, the fragrance instruction module 42 issues the instruction, and the fragrance synthesis module 2 synthesizes the fragrance.

[0037] Furthermore, the adversarial network forms essential oil ratio data based on the feature data, and the essential oil ratio data is used to synthesize the fragrance in the fragrance synthesis module 2.

[0038] Furthermore, the fragrance synthesis module 2 is connected to the engine module 7, which includes a plasma decomposition device 71 and a fragrance atomization device 72. The plasma decomposition device 71 is used to break up and decompose the synthesized fragrance, and the fragrance atomization device 72 can atomize the broken fragrance and output it.

[0039] It should be noted that the fragrance atomizer device 72 automatically adjusts the fragrance output based on the detection module 1. The fragrance atomizer device 72 has an output level classification, which can be divided into levels 0-5. By adjusting in the visual interface 6, the processing module 3 can control the output power and output of the fragrance atomizer device 72.

[0040] Furthermore, the fragrance atomization device 72 has three-channel output, and a PID-Smith predictor is provided in the fragrance atomization device 72 to compensate for atomization delay.

[0041] The plasma decomposition device 71 has a high voltage field of 10-15 kV, and the fragrance atomization device 72 can emit fragrance particles with a diameter of 0.5-3 μm.

[0042] As described above, the processing module 3 is connected to the visual interface 6, which is used to support user input of language, adjustment of fragrance mode and adjustment of fragrance ratio. The visual interface 6 can be, but is not limited to, an APP platform.

[0043] Furthermore, the detection signal between the detection module 1 and the processing module 3 is connected using a star topology network built using the LoRaWAN protocol. This approach can maximize the savings in signal transmission losses and ensure that standby power consumption is ≤0.01W.

[0044] Another aspect of the present invention provides a method for using the collaborative processing system, which is as follows: S1: The user inputs a fragrance description into the visual interface 6 , and the AI ​​module 4 matches the fragrance based on the feature database 5 .

[0045] Processing module 3 receives user input and automatically adjusts under the control of AI module 4 to generate an LSTM neural network training model. It then generates a recommendation strategy based on the user's usage habits and adjusts the generation of fragrances. Fragrance instruction module 42 receives user instructions, summarizes and extracts features from the instructions using NLP mechanisms, and matches these features against feature database 5. The matched features are then used in an adversarial network to determine the feasibility and accuracy of the essential oil ratio.

[0046] S2: Fragrance synthesis module 2 generates fragrance and outputs it; The fragrance synthesis module 2 synthesizes the fragrance according to the data of the completed ratio and outputs it to the fragrance atomization device 72. The fragrance atomization device 72 can atomize the fragrance, and the PID-Smith predictor therein can compensate for the atomization time.

[0047] S3: The detection module 1 detects the external environment and adjusts and corrects the fragrance odor.

[0048] The detection module 1 detects the fragrance content and ratio in the air in real time and inputs it into the AI ​​module 4. The AI ​​module 4 can adjust the output fragrance content and ratio to further meet user needs.

[0049] The same or similar parts between the various embodiments in this specification can be referred to each other, and each embodiment focuses on the differences from other embodiments.

[0050] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present application should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. Environmental odor monitoring and multimodal fragrance AI collaborative processing system, characterized by: include: A detection module (1), the detection module (1) is used to detect environmental data and generate a detection signal; A fragrance synthesis module (2), wherein the fragrance synthesis module (2) stores a plurality of essential oils and adjusts the proportions of the different essential oils according to the instructions; a processing module (3), the processing module (3) being connected to the detection module (1) and the fragrance synthesis module (2), the processing module (3) being used to receive detection data, perform corresponding processing according to the detection data, and send adjustment instructions to the fragrance synthesis module (2); An AI module (4) is built into the processing module (3). The AI ​​module (4) includes an automatic adjustment module (41) and a fragrance instruction module (42). The automatic adjustment module (41) collects user selection data to generate an LSTM neural network training model and generates a recommendation strategy. The fragrance instruction module (42) has an NLP mechanism and an attention mechanism built in. The NLP mechanism is used to extract user input language keywords and generate an adversarial network based on the attention mechanism. The adversarial network generates and judges the feasibility and accuracy of different essential oil ratios.

2. The collaborative processing system according to claim 1, wherein: The processing module (3) has a feature database (5), and the feature database (5) stores feature data of different essential oils of various fragrances.

3. The collaborative processing system according to claim 2, wherein: The feature database (5) is connected to the fragrance instruction module (42), and the language keywords extracted by the NLP mechanism in the fragrance instruction module (42) correspond to the feature database (5) to generate feature data. The adversarial network forms essential oil ratio data based on the feature data, and the essential oil ratio data is used to synthesize the fragrance in the fragrance synthesis module (2).

4. The collaborative processing system according to claim 1, wherein: The processing module (3) is connected to a visual interface (6), and the visual interface (6) is used to support user input of language, adjustment of fragrance mode, and adjustment of fragrance ratio.

5. The collaborative processing system according to claim 1, wherein: The fragrance synthesis module (2) is connected to the engine module (7), and the engine module (7) includes a plasma decomposition device (71) and a fragrance atomization device (72). The fragrance atomization device (72) has an output quantity output classification, and the processing module (3) controls the output of the fragrance atomization device (72).

6. The collaborative processing system according to claim 5, wherein: The fragrance atomization device (72) automatically adjusts the fragrance output based on the detection module (1).

7. The collaborative processing system according to claim 5, wherein: The fragrance atomization device (72) has a three-channel output, and a PID-Smith predictor is provided in the fragrance atomization device (72) for compensating for atomization delay.

8. The collaborative processing system according to claim 7, wherein: The detection module (1) comprises a VOC sensor array (11), a temperature and humidity sensor (12), and a PM2.5 detector (13). The VOC sensor array (11) is used to detect fragrance, the temperature and humidity sensor (12) is used to detect the temperature and humidity in the air, and the PM2.5 detector (13) is used to detect small particle pollutants in the air.

9. The collaborative processing system according to claim 1, wherein: The detection signal between the detection module (1) and the processing module (3) is connected using a star topology network, and the star topology network is constructed by the LoRaWAN protocol.

10. A method for using the collaborative processing system according to any one of claims 1 to 9, characterized in that: The method of use is as follows: S1: The user inputs a fragrance description into the visual interface (6), and the AI ​​module (4) matches the fragrance based on the feature database (5); S2: the fragrance synthesis module (2) generates fragrance and outputs it; S3: The detection module (1) detects the external environment and adjusts and corrects the fragrance odor.

Images