Fragrance release method and apparatus, fragrance release system, and storage medium

Abstract

The present application relates to a fragrance release method and apparatus, a fragrance release system, and a storage medium. The method comprises: acquiring multi-modal data of a target object in a target medical space of a medical device, wherein the multi-modal data comprises at least one of physiological information, facial expression information, and vocal information; processing the multi-modal data using an emotion recognition model to obtain an emotion recognition result of the target object; and determining, on the basis of examination information and the emotion recognition results of the target object, a target fragrance release mode for releasing fragrance for the target object.

Description

Fragrance releasing method, device, fragrance releasing system and storage medium

[0001] Related applications

[0002] This application claims priority to Chinese patent application number 2023118048038, filed on December 25, 2023, entitled “Fragrance release method, device, fragrance release system and storage medium,” the entire text of which is hereby incorporated by reference. Technical Field

[0003] The present application relates to the field of medical device technology, and in particular to a fragrance release method, device, fragrance release system, storage medium, and computer program product. Background Art

[0004] With the advancement of medical device technology, treatment and diagnostic equipment, such as magnetic resonance imaging (MRI) and computed tomography (CT), have emerged. These devices are quite large, requiring subjects to enter treatment or diagnostic areas, such as the aperture of large medical imaging equipment, for extended scans. Many subjects, due to tension and anxiety, find it difficult to remain calm in these spaces. This can lead to movements that affect the scan, or, more seriously, to intense emotions such as dizziness, or even claustrophobia.

[0005] However, the current treatment / diagnosis process suffers from insufficient breathing guidance. Summary of the Invention

[0006] Based on this, the present application provides a fragrance release method, device, fragrance release system, storage medium and computer program product.

[0007] In a first aspect, the present application provides a method for releasing fragrance, the method comprising:

[0008] Collecting multimodal data of a target object in a target medical space of a medical device; the multimodal data includes at least one of physiological information, facial expression information, and voice information;

[0009] Use emotion recognition models to process multimodal data and obtain emotion recognition results of the target object;

[0010] A target fragrance release mode for releasing fragrance for the target object is determined based on the inspection information of the target object and the emotion recognition result.

[0011] In one embodiment, determining a target fragrance release mode for releasing fragrance to the target object based on the inspection information of the target object and the emotion recognition result includes:

[0012] Obtain inspection information of the target object, and obtain a preset interaction mode based on the inspection information matching;

[0013] Based on the emotion recognition results and the preset interaction mode, the target fragrance release mode is determined.

[0014] In one embodiment, the examination information includes treatment / diagnosis information of the medical device for the target subject; the target fragrance release pattern includes a target fragrance release time, a target fragrance release intensity, and a target fragrance type; and the method further includes:

[0015] Adjusting the target fragrance release time and / or the target fragrance release intensity according to the treatment / diagnosis information;

[0016] Based on the emotion recognition results, the target fragrance type is determined.

[0017] In one embodiment, obtaining inspection information of a target object and obtaining a preset interaction mode based on the inspection information matching include:

[0018] Based on the obtained inspection information, determining whether to release fragrance to the target object;

[0019] In response to determining to release fragrance for the target object, a preset interaction mode is obtained based on the inspection information matching.

[0020] In one embodiment, the method further comprises:

[0021] Under the target fragrance release mode, multimodal data is acquired and processed to obtain feedback information from the target object regarding the target fragrance release mode;

[0022] The target fragrance release pattern is dynamically adjusted based on feedback information.

[0023] In one embodiment, the method further comprises:

[0024] Obtain feature information obtained by processing multimodal data with an emotion recognition model;

[0025] Based on the feature information, the emotion recognition model is enhanced and trained to obtain the enhanced trained emotion recognition model and updated feature information;

[0026] The updated feature information is used to calibrate the emotion recognition model after enhanced training to obtain an updated emotion recognition model.

[0027] In one embodiment, the emotion recognition model includes a facial emotion model; and the emotion recognition result includes a facial emotion magnitude.

[0028] In one embodiment, the method further comprises:

[0029] The convolutional layer based on the facial emotion model processes facial expression information to obtain facial emotion features;

[0030] The facial emotion features are processed according to the pooling layer of the facial emotion model to obtain the facial emotion magnitude.

[0031] In a second aspect, the present application provides a fragrance release device, comprising:

[0032] An information acquisition module, configured to acquire multimodal data of a target object within a target medical space of the medical device; the multimodal data including at least one of physiological information, facial expression information, and voice information;

[0033] The emotion recognition module is used to process multimodal data using an emotion recognition model to obtain emotion recognition results of the target object;

[0034] The mode determination module is used to determine a target fragrance release mode for releasing fragrance for the target object based on the inspection information of the target object and the emotion recognition result.

[0035] In a third aspect, the present application provides a fragrance release system, which includes a processing unit, which is used to implement the steps of the above method; the fragrance release system also includes an information acquisition module and a fragrance release device, the information acquisition module includes an image acquisition module, a sound acquisition module and an information input module, all of which are connected to the processing unit; the image acquisition module is used to collect facial expression information, the sound acquisition module is used to collect voice information, and the information input module is used to receive physiological information; the fragrance release device includes a fragrance module and a fragrance diffusion module, both of which are connected to the processing unit.

[0036] In a fourth aspect, the present application provides a fragrance release control device, which is used to respectively connect to the image acquisition module, sound acquisition module and information input module in the information acquisition module, wherein the image acquisition module is used to collect facial expression information, the sound acquisition module is used to collect voice information, and the information input module is used to receive physiological information; the fragrance release control device is also used to respectively connect to the fragrance module and the fragrance diffusion module in the fragrance release device; the fragrance release control device includes a memory and a processor, the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0037] In a fifth aspect, the present application provides a medical device, comprising a treatment / diagnostic device and a support device for carrying a target object, wherein the treatment / diagnostic device is used to perform medical treatment / diagnosis on the target object; the medical device comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0038] In a sixth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of the above-mentioned method when the computer program is executed by a processor.

[0039] In a seventh aspect, the present application provides a computer program product, comprising a computer program, which implements the steps of the above method when executed by a processor.

[0040] The details of one or more embodiments of the present application are set forth in the accompanying drawings and the description below. Other features, objects, and advantages of the present application will become apparent from the description, drawings, and claims. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the conventional technology, the following briefly introduces the drawings required for use in the embodiments or the conventional technology descriptions. Obviously, the drawings described below are merely embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the disclosed drawings without any creative work.

[0042] FIG1 is a schematic diagram of a flow chart of a fragrance release method in one embodiment of the present application;

[0043] FIG2 is a schematic diagram of a flow chart of a fragrance release step in one embodiment of the present application;

[0044] FIG3 is a schematic diagram of a flow chart of a fragrance release method according to another embodiment of the present application;

[0045] FIG4 is a schematic diagram of a flow chart of a fragrance release method in another embodiment of the present application;

[0046] FIG5 is a schematic diagram of a flow chart of a fragrance release method in another embodiment of the present application;

[0047] FIG6 is a schematic diagram of a flow chart of a fragrance release step in another embodiment of the present application;

[0048] FIG7 is a structural block diagram of a fragrance release device in one embodiment of the present application;

[0049] FIG8 is a structural block diagram of a fragrance release system in one embodiment of the present application;

[0050] FIG9 is a diagram showing the internal structure of a fragrance release control device in one embodiment of the present application;

[0051] FIG10 is a diagram showing the internal structure of a fragrance release control device in another embodiment of the present application. DETAILED DESCRIPTION

[0052] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0053] Currently, within the treatment / diagnostic spaces provided by medical equipment for subjects, such as imaging scanning rooms, care for subjects primarily focuses on visual and auditory aspects. Regarding the sense of smell, one-way fragrance systems are typically used. These systems release fragrances to engage the subject's olfactory senses for a long time, without any interaction between the fragrance system and the subject. This solution still lacks sufficient respiratory guidance for the subject.

[0054] In one embodiment, as shown in FIG1 , a fragrance release method is provided, the method comprising:

[0055] Step 110: collecting multimodal data of a target object in a target medical space of a medical device; the multimodal data includes at least one of physiological information, facial expression information, and voice information;

[0056] Specifically, the fragrance release method can be applied to the processing unit of the fragrance release system, and can also be applied to medical equipment. The medical equipment may include a treatment / diagnostic device and a support device for carrying a target object. The treatment / diagnostic device is used to perform medical treatment / diagnosis on the target object. The treatment / diagnostic equipment may include medical imaging equipment, such as X-ray scanning equipment, computer tomography equipment, magnetic resonance imaging equipment, positron emission tomography equipment, and gamma cameras; the treatment / diagnostic equipment may also include radiotherapy equipment, ultrasonic diagnostic equipment, dialyzers, laser treatment equipment, blood glucose monitors, and electrocardiographs. The support device can be used to support the target object and can also support medical equipment. For example, the support device may include a scanning table, a hospital bed, a wheelchair, and a bracket to ensure that the target object can maintain an appropriate posture or a safe position when receiving treatment or diagnosis. The treatment space or diagnostic area can accommodate the support device. The target medical space may include the treatment space or diagnostic area of ​​the medical equipment. When a subject is undergoing medical treatment / diagnosis on a medical device, the subject enters a treatment space or a diagnostic area. For example, the subject lies on a scanning table inside the aperture of a large medical imaging device. The subject can be identified as a target object, and multimodal data of the target object can be collected. The multimodal data may include at least one of physiological information, facial expression information, and voice information; wherein the physiological information of the target object may include the target object's electrocardiogram data, respiratory data, and blood pressure data; the facial expression information of the target object may include the target object's expressions such as smiling, frowning, and blinking, as well as the activity of facial muscles; the voice information of the target object may include the target object's speaking speed, pitch, voice emotion, and other information.

[0057] In some examples, physiological information of the target object can be collected and processed using an emotion recognition model to obtain an emotion recognition result of the target object. The emotion recognition model can include a physiological emotion model, which can process at least one of the target object's electrocardiogram data, respiratory data, and blood pressure data to obtain an emotion recognition result of the target object.

[0058] In some examples, facial expression information of the target object can be collected and processed using an emotion recognition model to obtain an emotion recognition result of the target object, wherein the emotion recognition model may include a facial emotion model, and the facial emotion model can process at least one of the target object's expressions such as smiling, frowning, blinking, and facial muscle activity to obtain the emotion recognition result of the target object, and the emotion recognition result may include the magnitude of the facial emotion.

[0059] In some examples, voice information of the target object can be collected and processed using an emotion recognition model to obtain an emotion recognition result of the target object. The emotion recognition model may include a voice emotion model, which can process at least one of the target object's speech speed, pitch, voice emotion and other information to obtain an emotion recognition result of the target object.

[0060] In some examples, multiple information including physiological information, facial expression information and voice information of the target object can be collected, and corresponding emotion recognition models can be used to process different information separately, or a trained emotion recognition model that can comprehensively process multiple information can be used to obtain the emotion recognition results of the target object.

[0061] By acquiring the above-mentioned multimodal data, the status of the target object in the treatment space or diagnostic area can be obtained in real time, and the released fragrance can be adjusted according to the status of the target object, thereby improving the interactivity with the target object during the fragrance release process and improving the effect of breathing guidance.

[0062] In some examples, the target subject's physiological information, facial expression information, and voice information can be collected by an information collection module of the fragrance release system. The information collection module can include an image acquisition module, a sound acquisition module, and an information input module, all connected to a processing unit. The image acquisition module can collect facial expression information. This can be implemented using at least one of a spatial camera, an aperture camera, and a millimeter-wave radar. For example, the aperture camera can capture facial expression information, and the processing unit can then perform facial expression analysis and facial micro-movement recognition on the target subject, including but not limited to the target subject's level of tension, fatigue, breathing rate, and whether or not they are asleep. Based on the image information captured by the spatial camera, the processing unit can collect and identify the target subject's location and use this location as part of activating / controlling the fragrance release system. The sound acquisition module can collect voice information from the target subject. The sound acquisition module can include a microphone, which can capture voice information from the target subject, such as subconscious responses such as "What a stinky smell!" or "What's that smell?". The information input module can be connected to corresponding data interfaces, such as various sensors worn by the target subject during the scan, to collect physiological information including respiration, electrocardiogram, blood pressure, and other information.

[0063] Step 120: Process the multimodal data using an emotion recognition model to obtain an emotion recognition result of the target object;

[0064] Specifically, the acquired multimodal data can be processed using an emotion recognition model. This model can be a convolutional neural network model used to identify the target subject's comprehensive emotional state. The target subject's emotion recognition results can include various emotional states, such as happiness, sadness, anger, anxiety, and more. These results can also include an emotional magnitude, which can be a quantitative representation of the corresponding emotional state. This approach can identify the target subject's comprehensive emotional state, including their current underlying emotions, and can then control the release of fragrance based on the target subject's comprehensive emotional state.

[0065] In some examples, the acquired multimodal data can be stored in a corresponding database. For example, physiological information is stored in a physiological information database, facial expression information is stored in a facial expression information database, and voice information is stored in a voice information database. The databases can be linked to each other. The emotion recognition model can combine multiple databases to comprehensively analyze the real-time emotional information of the target object from the perspective of vision and sound. Physiological information, facial expression information, and voice information can be the input of the emotion recognition model, and the emotion recognition result of the target object can be the output of the emotion recognition model. The emotion recognition model can also be combined with big data and enhanced through artificial intelligence (AI) to obtain the emotional state and emotional level of the target object. For example, a corresponding index can be specified to enhance the emotional state and emotional level. When the index is reached, it is a certain emotional state. The output emotional level is enhanced within the corresponding range. For example, the emotional recognition result of the target object can be anxiety, 70%. The emotional level can include the facial emotional level.

[0066] Step 130 : determining a target fragrance release mode for releasing fragrance to the target object based on the inspection information of the target object and the emotion recognition result.

[0067] Specifically, the target fragrance release mode for releasing fragrance for the target object can be determined based on the target object's inspection information and emotion recognition results. The target object's inspection information may include the target object's age, gender, medical history, scan content, scan time, and whether there is a history of fragrance allergies. Fragrance release modes for different target objects and different protocols can be pre-set to interact with the target object to achieve breathing guidance. For example, different fragrance release modes can be set to target the difference in olfaction between the elderly and young people, and then a personalized target fragrance release mode can be matched for the current target object, thereby improving the effectiveness of breathing guidance.

[0068] The embodiment of the present application collects multimodal data of a target object in a target medical space of a medical device, where the multimodal data includes at least one of physiological information, facial expression information, and voice information, so as to obtain in real time the status of the target object in a treatment space or a diagnostic area of ​​the medical device; an emotion recognition model is used to process the multimodal data to obtain an emotion recognition result of the target object, so as to identify the comprehensive emotional state of the target object including the current potential emotion; and based on the inspection information of the target object and the emotion recognition result, a target fragrance release mode for releasing fragrance to the target object is determined, so as to improve the interactivity with the target object during the fragrance release process, thereby improving the effect of breathing guidance.

[0069] In one embodiment, as shown in FIG2 , determining a target fragrance release mode for releasing fragrance to the target object based on the inspection information of the target object and the emotion recognition result includes:

[0070] Step 210: Obtain inspection information of the target object, and obtain a preset interaction mode based on the inspection information matching;

[0071] Step 220 : Determine a target fragrance release mode based on the emotion recognition result and the preset interaction mode.

[0072] Specifically, the target subject's examination information may include the target subject's age, gender, medical history, scan content, scan duration, and whether they have a history of fragrance allergies. The preset interaction mode obtained based on the examination information matching may be one of a plurality of pre-stored olfactory interaction modes. The pre-stored plurality of olfactory interaction modes may be preset for historical examination information of different historical subjects to accommodate different target subjects. Furthermore, based on the emotion recognition result and the preset interaction mode, a target fragrance release mode corresponding to the emotion recognition result under the preset interaction mode may be determined, and the processing unit may then control the fragrance release device to operate in the target fragrance release mode.

[0073] In some examples, based on the acquired inspection information of the target object, it may be possible to first determine whether to release fragrance to the target object. If it is determined that the fragrance release system should be used for the target object, a preset interaction mode is then determined based on the inspection information. For example, if, based on the acquired inspection information of the target object, the target object is determined to be one of the following, the fragrance release system will not be used for the target object: those with allergies; those with asthma; those with sensitive skin; pregnant women; infants and young children; those with specific diseases, etc.

[0074] In one embodiment, the examination information includes treatment / diagnosis information of the medical device for the target subject; the target fragrance release pattern includes a target fragrance release time, a target fragrance release intensity, and a target fragrance type; as shown in FIG3 , the method further includes:

[0075] Step 310 , adjusting the target fragrance release time and / or target fragrance release intensity according to the treatment / diagnosis information;

[0076] Step 320: Determine the target fragrance type based on the emotion recognition result.

[0077] Specifically, the treatment / diagnosis information for the target object may include mode information and parameter information that need to be set for the treatment / diagnosis equipment for the target object. When the treatment / diagnosis equipment is a medical imaging device, the treatment / diagnosis information may include scanning information such as scanning mode and scanning parameters, for example, information such as scanning content and scanning time. When the treatment / diagnosis equipment is a radiotherapy equipment, the treatment / diagnosis information may include radiation dose, treatment site, treatment target, treatment cycle, and setting parameters of the radiotherapy equipment. When the treatment / diagnosis equipment is an ultrasound diagnostic equipment, the treatment / diagnosis information may include ultrasound parameters and inspection mode. Based on the treatment / diagnosis information, the processing unit may adjust the target fragrance release time and / or target fragrance release intensity. The target fragrance release time may be the time when the fragrance release device of the fragrance release system needs to release the fragrance, and the target fragrance release intensity may be the intensity at which the fragrance release device of the fragrance release system needs to release the fragrance. The target fragrance type can be determined based on the emotion recognition results. For example, different fragrance types can be pre-matched with different emotional states and emotional levels. Then, based on the acquired emotion recognition results, the corresponding target fragrance type can be matched. The target fragrance type can be the type of fragrance that the fragrance release device of the fragrance release system needs to release. In this way, the current emotional state and potential emotional trends of the target subject can be analyzed and matched with pre-designed fragrance types, thereby improving the efficiency of breathing guidance.

[0078] In one embodiment, as shown in FIG4 , the method further includes:

[0079] Step 410 , in the target fragrance release mode, acquiring and processing multimodal data to obtain feedback information of the target subject with respect to the target fragrance release mode;

[0080] Step 420: Dynamically adjust the target fragrance release pattern based on the feedback information.

[0081] Specifically, when the processing unit controls the fragrance release device to be in the target fragrance release mode, the target object may make corresponding feedback for the target fragrance release mode. For example, when the fragrance intensity of the fragrance released is 40% during the breathing guidance process, the target object around 50 years old may frown. The multimodal data of the target object in this process can be continuously obtained, and the above information can be processed to extract the feedback information of the target object for the target fragrance release mode; then, the target fragrance release mode can be dynamically adjusted based on the feedback information to improve the interactivity with the target object during the fragrance release process, thereby improving the effectiveness of the breathing guidance.

[0082] In one embodiment, as shown in FIG5 , the method further includes:

[0083] Step 510: Acquire feature information obtained by processing multimodal data with an emotion recognition model;

[0084] Step 520: Based on the feature information, the emotion recognition model is enhanced and trained to obtain the enhanced and trained emotion recognition model and updated feature information.

[0085] Step 530 : Calibrate the emotion recognition model after enhanced training using the updated feature information to obtain an updated emotion recognition model.

[0086] Specifically, when processing multimodal data, the convolutional network of the emotion recognition model can extract corresponding feature information, which can be used to reflect the emotional characteristics of the target object. This feature information can be used for enhanced training of the emotion recognition model. For example, enhanced training can be performed during the actual use of the emotion recognition model, or the emotion recognition model can be further trained after collecting various feature information and uploading it to a server. After the enhanced training of the emotion recognition model, the emotion recognition model obtained through enhanced training can update the feature information, and the updated feature information can be used to calibrate the enhanced trained emotion recognition model. For example, the calibrated enhanced trained emotion recognition model can be used as the updated emotion recognition model to improve the generalization ability and recognition accuracy of the emotion recognition model. The updated emotion recognition model can provide personalized fragrance release solutions for different target objects. Through enhanced training, the feature information obtained during the use of the emotion recognition model can be continuously used for training the emotion recognition model to improve the performance of the emotion recognition model.

[0087] In one embodiment, the emotion recognition model includes a facial emotion model; and the emotion recognition result includes a facial emotion magnitude.

[0088] Specifically, facial expression information includes the manifestation of each emotion on the face, which can be described by changes in various parts such as eyebrows, corners of the mouth, and eyes. By processing facial expression information, it is possible to evaluate the intensity of facial emotions, that is, to obtain the magnitude of facial emotions.

[0089] In one embodiment, as shown in FIG6 , the method further includes:

[0090] Step 610, processing facial expression information based on the convolutional layer of the facial emotion model to obtain facial emotion features;

[0091] Step 620 : Process the facial emotion features according to the pooling layer of the facial emotion model to obtain the facial emotion magnitude.

[0092] Specifically, the facial emotion model can be a pre-trained convolutional neural network model, for example, trained using fixed samples, which can be recorded during subsequent use and modified in conjunction with physiological data from other modalities. The convolutional layer of the facial emotion model can be used to process facial expression information and extract facial emotion features to identify emotions such as anger and rage. The pooling layer of the facial emotion model can further process the obtained facial emotion features to measure and output the magnitude of facial emotions. The pooling layer can include standardized pooling layers of different levels.

[0093] In some examples, a convolutional neural network model can be used to identify the target subject's facial emotional features and emotional intensity. Furthermore, the processing unit can combine visual and audio data to comprehensively analyze the target subject's emotional state and emotional intensity to characterize the target subject's underlying emotions beyond their facial expressions. For example, if the target subject is actually experiencing tension and pain but is enduring it, the processing unit can combine physiological information such as breathing data. For example, sensors can collect physiological information indicating that the target subject's breathing is consistently light and their heart rate is high. The processing unit determines the target subject's underlying condition based on physiological information, facial expression information, and voice information. After obtaining the target subject's emotional recognition results, the processing unit can determine a corresponding target fragrance release mode and control the fragrance release device of the fragrance release system to release fragrance in the target fragrance release mode, providing olfactory soothing to the target subject. This fully intelligent control process requires no technician intervention. Through this method, the fragrance release system can simultaneously perceive the target subject's emotional state and continuously adjust the target fragrance release mode based on the target subject's feedback, enhancing the target subject's comfort during the scanning process. This aligns with the personalized sensory characteristics of smell and improves the breathing guidance of the target subject during the scanning process.

[0094] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0095] Based on the same inventive concept, the present application also provides a fragrance release device for implementing the aforementioned fragrance release method. The solution provided by this device is similar to the solution described in the aforementioned method. Therefore, the specific limitations of one or more fragrance release device embodiments provided below can be found in the above-described limitations of the fragrance release method and will not be further elaborated here.

[0096] In one embodiment, as shown in FIG7 , a fragrance releasing device is provided, comprising:

[0097] An information acquisition module 710 is configured to acquire multimodal data of a target object within a target medical space of a medical device; the multimodal data includes at least one of physiological information, facial expression information, and voice information;

[0098] Emotion recognition module 720, used to process multimodal data using an emotion recognition model to obtain emotion recognition results of the target object;

[0099] The pattern determination module 730 is configured to determine a target fragrance release pattern for releasing fragrance to the target object based on the inspection information of the target object and the emotion recognition result.

[0100] In one embodiment, the mode determination module 730 is further configured to obtain inspection information of the target object, obtain a preset interaction mode based on the inspection information matching, and determine a target fragrance release mode based on the emotion recognition result and the preset interaction mode.

[0101] In one embodiment, the examination information includes treatment / diagnosis information of the medical device for the target subject; the target fragrance release pattern includes a target fragrance release time, a target fragrance release intensity, and a target fragrance type; and the device further includes:

[0102] A fragrance adjustment module, configured to adjust a target fragrance release time and / or a target fragrance release intensity according to treatment / diagnosis information;

[0103] The target fragrance type determination module is used to determine the target fragrance type based on the emotion recognition result.

[0104] In one embodiment, the mode determination module 730 is further configured to determine whether to release fragrance to the target object based on the acquired inspection information; in response to determining that fragrance is to be released to the target object, obtain a preset interaction mode based on the inspection information matching.

[0105] In one embodiment, the apparatus further comprises:

[0106] A feedback information acquisition module is used to acquire and process multimodal data in the target fragrance release mode to obtain feedback information from the target object for the target fragrance release mode;

[0107] The dynamic adjustment module is used to dynamically adjust the target fragrance release mode based on feedback information.

[0108] In one embodiment, the apparatus further comprises:

[0109] Feature information acquisition module, used to obtain feature information obtained by processing multimodal data by the emotion recognition model;

[0110] A feature information updating module is used to perform enhanced training on the emotion recognition model based on the feature information to obtain an enhanced trained emotion recognition model and updated feature information;

[0111] The emotion recognition model updating module is used to calibrate the emotion recognition model after enhanced training using the updated feature information to obtain an updated emotion recognition model.

[0112] In one embodiment, the emotion recognition model includes a facial emotion model; and the emotion recognition result includes a facial emotion magnitude.

[0113] In one embodiment, the apparatus further comprises:

[0114] Facial emotion feature acquisition module, used to process facial expression information based on the convolution layer of the facial emotion model to obtain facial emotion features;

[0115] The facial emotion magnitude acquisition module is used to process facial emotion features according to the pooling layer of the facial emotion model to obtain the facial emotion magnitude.

[0116] Each module in the fragrance release device described above can be implemented in whole or in part through software, hardware, or a combination thereof. Each module can be embedded in or independent of the processor in the fragrance release control device in hardware form, or stored in the memory of the fragrance release control device in software form, so that the processor can call and execute the corresponding operations of each module.

[0117] In one embodiment, as shown in Figure 8, a fragrance release system 80 is provided. The fragrance release system 80 includes a processing unit 810, which is used to implement the steps of the above method; the fragrance release system 80 also includes an information collection module 820 and a fragrance release device 830, and the information collection module 820 includes an image collection module 822, a sound collection module 824 and an information entry module 826, all of which are connected to the processing unit 810; the fragrance release device 830 includes a fragrance module 832 and a fragrance diffusion module 834, both of which are connected to the processing unit 810.

[0118] Specifically, the image acquisition module 822 can capture facial expression information. This can be implemented using at least one of a spatial camera, an aperture camera, and a millimeter-wave radar. The sound acquisition module 824 can capture voice information from the target subject. The sound acquisition module 824 can include a microphone that can capture the target subject's voice information. The information input module 826 can be used to connect to corresponding data interfaces, for example, to various sensors worn by the target subject during the scan, and to collect physiological information such as respiration, electrocardiogram, and blood pressure through the sensors. The fragrance release device 830 can store multiple fragrance agents and includes a fragrance dispensing module 832 and a fragrance dispersing module 834. The fragrance dispensing module 832 can include at least one of an integrator and a blender. The integrator can store multiple pre-arranged fragrance agents, and the blender can contain multiple fragrance base materials that can be mixed to create different scents. The fragrance dispersing module 834 can include an air supply and exhaust duct to enable rapid fragrance dispersal and exhaust under the control of the processing unit 810 within the treatment space or diagnostic area, such as within the aperture of the scanning device or other small spaces.

[0119] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above method are implemented.

[0120] In one embodiment, a computer program product is provided, comprising a computer program, which implements the steps of the above method when executed by a processor.

[0121] In one embodiment, a fragrance release control device is provided, which is used to respectively connect to an image acquisition module, a sound acquisition module, and an information entry module in an information acquisition module, wherein the image acquisition module is used to acquire facial expression information, the sound acquisition module is used to acquire voice information, and the information entry module is used to receive physiological information; the fragrance release control device is also used to respectively connect to a fragrance emission module and a fragrance diffusion module in a fragrance release device; the fragrance release control device includes a memory and a processor, the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0122] In one embodiment, a fragrance release control device is provided. The fragrance release control device may be a server, and its internal structure diagram may be shown in Figure 9. The fragrance release control device includes a processor, memory, an input / output (I / O) interface, and a communication interface. The processor, memory, and I / O interface are connected via a system bus, and the communication interface is connected to the system bus via the I / O interface. The processor of the fragrance release control device provides computing and control capabilities. The memory of the fragrance release control device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operating system and computer program in the non-volatile storage medium. The database of the fragrance release control device stores fragrance release data. The I / O interface of the fragrance release control device is used to exchange information between the processor and external devices. The communication interface of the fragrance release control device is used to communicate with external terminals via a network connection. When executed by the processor, the computer program implements a fragrance release method.

[0123] In one embodiment, a fragrance release control device is provided. The fragrance release control device may be a terminal, and its internal structure diagram may be shown in Figure 10. The fragrance release control device includes a processor, memory, an input / output interface, a communication interface, a display unit, and an input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are connected to the system bus via the input / output interface. The processor of the fragrance release control device provides computing and control capabilities. The memory of the fragrance release control device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and computer program stored in the non-volatile storage medium. The input / output interface of the fragrance release control device is used to exchange information between the processor and external devices. The communication interface of the fragrance release control device is used to communicate with external terminals via wired or wireless communication. The wireless communication may be achieved via Wi-Fi, a mobile cellular network, NFC (near field communication), or other technologies. When executed by the processor, the computer program implements a fragrance release method. The display unit of the fragrance release control device is used to produce a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display or an electronic ink display screen. The input device of the fragrance release control device can be a touch layer covering the display screen, a keypad, a trackball, or a touchpad provided on the device housing, or an external keyboard, touchpad, or mouse.

[0124] Those skilled in the art will understand that the structures shown in Figures 9 and 10 are merely block diagrams of partial structures related to the present application scheme, and do not constitute a limitation on the fragrance release control device to which the present application scheme is applied. The specific fragrance release control device may include more or fewer components than shown in the figures, or combine certain components, or have a different component arrangement.

[0125] It should be noted that the physiological information, facial expression information, voice information, examination information, treatment / diagnosis information and feedback information involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards of relevant countries and regions.

[0126] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchains. The processor involved in the various embodiments provided herein may be, but are not limited to, a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, and the like.

[0127] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0128] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. An aroma release method, the method comprising: Collecting multimodal data of a target object in a target medical space of a medical device; the multimodal data includes at least one of physiological information, facial expression information, and voice information; Processing the multimodal data using an emotion recognition model to obtain an emotion recognition result of the target object; Determining a target aroma release mode for releasing aroma for the target object according to the examination information of the target object and the emotion recognition result.

2. The method according to claim 1, wherein, The determining a target aroma release mode for releasing aroma for the target object according to the examination information of the target object and the emotion recognition result includes: Obtaining the examination information of the target object, and matching a preset interaction mode based on the examination information; Determining the target aroma release mode based on the emotion recognition result and the preset interaction mode.

3. The method according to any one of claims 1 to 2, wherein, The examination information includes treatment / diagnosis information of the medical device for the target object; The target aroma release mode includes a target aroma release time, a target aroma release intensity, and a target aroma type; The method further includes: Adjusting the target aroma release time and / or the target aroma release intensity according to the treatment / diagnosis information; Determining the target aroma type based on the emotion recognition result.

4. The method according to claim 2, wherein, The obtaining the examination information of the target object and matching a preset interaction mode based on the examination information includes: Based on the obtained examination information, determining whether to release aroma for the target object; In response to determining to release aroma for the target object, matching the preset interaction mode based on the examination information.

5. The method according to claim 2, wherein The method further includes: Under the target aroma release mode, obtaining and processing the multimodal data to obtain feedback information of the target object for the target aroma release mode; Dynamically adjusting the target aroma release mode based on the feedback information.

6. The method according to claim 5, wherein The method further includes: Obtaining feature information obtained by the emotion recognition model processing the multimodal data; Based on the feature information, performing enhanced training on the emotion recognition model to obtain the enhanced trained emotion recognition model and the updated feature information; Calibrating the enhanced trained emotion recognition model with the updated feature information to obtain the updated emotion recognition model.

7. The method according to any one of claims 1 to 6, wherein, The emotion recognition model includes a facial emotion model; the emotion recognition result includes a facial emotion magnitude.

8. According to the method of claim 7, the method further includes: Processing the facial expression information based on the convolutional layer of the facial emotion model to obtain facial emotion features; Processing the facial emotion features according to the pooling layer of the facial emotion model to obtain the facial emotion magnitude.

9. An aroma release device, the device comprising: An information collection module for collecting multimodal data of a target object in a target medical space of a medical device; the multimodal data includes at least one of physiological information, facial expression information, and voice information; An emotion recognition module, configured to process the multi-modal data by using an emotion recognition model to obtain an emotion recognition result of the target object; A mode determination module, configured to determine a target fragrance release mode for releasing fragrance to the target object according to the examination information of the target object and the emotion recognition result.

10. The device according to claim 9, wherein, The mode determination module is further configured to obtain the examination information of the target object, and match a preset interaction mode based on the examination information; and determine the target fragrance release mode based on the emotion recognition result and the preset interaction mode.

11. A fragrance release system, the fragrance release system includes a processing unit, and the processing unit is configured to implement the steps of the method according to any one of claims 1 to 8; the fragrance release system further includes an information acquisition module and a fragrance release device, and the information acquisition module includes an image acquisition module, a sound acquisition module, and an information entry module that are all connected to the processing unit; the image acquisition module is configured to acquire the facial expression information, the sound acquisition module is configured to acquire the voice information, and the information entry module is configured to receive the physiological information; the fragrance release device includes a fragrance emitting module and a fragrance diffusing module that are all connected to the processing unit.

12. The system according to claim 11, wherein, The image acquisition module includes at least one of a space camera, an aperture camera, and a millimeter wave radar.

13. The system according to claim 11 or 12, wherein, The sound acquisition module includes a microphone.

14. The system according to any one of claims 11 to 13, wherein The information entry module is configured to connect to a data interface of a sensor for acquiring the physiological information.

15. An aroma release control device, which is used to be respectively connected to an image acquisition module, a sound acquisition module and an information entry module in an information acquisition module, wherein, The image acquisition module is configured to acquire the facial expression information, the sound acquisition module is configured to acquire the voice information, and the information entry module is configured to receive the physiological information; the fragrance release control device is further configured to be respectively connected to the fragrance emitting module and the fragrance diffusing module in the fragrance release device; the fragrance release control device includes a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 8.

16. A medical device, including a treatment / diagnosis device and a support device for carrying a target object, the treatment / diagnosis device is configured to perform medical treatment / diagnosis on the target object; the medical device includes a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 8.

17. The medical device according to claim 16, wherein, The medical device further includes an information acquisition module and a fragrance release device, and the information acquisition module includes an image acquisition module, a sound acquisition module, and an information entry module that are all connected to the processing unit; the image acquisition module is configured to acquire the facial expression information, the sound acquisition module is configured to acquire the voice information, and the information entry module is configured to receive the physiological information; the fragrance release device includes a fragrance emitting module and a fragrance diffusing module that are all connected to the processing unit.

18. The medical device according to claim 16 or 17, wherein, The treatment / diagnosis device includes at least one of a radiotherapy device, an X-ray scanning device, a computed tomography device, a magnetic resonance imaging device, a positron emission tomography device, and an ultrasonic diagnosis device.

19. The medical device according to any one of claims 16 to 18, wherein, The support device includes at least one of a scanning table, a hospital bed, a wheelchair, and a bracket.

20. A computer-readable storage medium having a computer program stored thereon, the computer program, when executed by a processor, implementing the steps of the method according to any one of claims 1 to 8.

21. A computer program product comprising a computer program which, when executed by a processor, implements the steps of the method according to any one of claims 1 to 8.

Images