WO2019144658A1 - 智能便器及电器系统 - Google Patents

智能便器及电器系统 Download PDF

Info

Publication number
WO2019144658A1
WO2019144658A1 PCT/CN2018/111476 CN2018111476W WO2019144658A1 WO 2019144658 A1 WO2019144658 A1 WO 2019144658A1 CN 2018111476 W CN2018111476 W CN 2018111476W WO 2019144658 A1 WO2019144658 A1 WO 2019144658A1
Authority
WO
WIPO (PCT)
Prior art keywords
smart toilet
metabolite
information
smart
user
Prior art date
Application number
PCT/CN2018/111476
Other languages
English (en)
French (fr)
Inventor
谌进
宋德超
陈翀
何贤俊
Original Assignee
格力电器（武汉）有限公司
珠海格力电器股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 格力电器（武汉）有限公司, 珠海格力电器股份有限公司 filed Critical 格力电器（武汉）有限公司
Priority to JP2020554346A priority Critical patent/JP7091471B2/ja
Priority to US16/965,286 priority patent/US11655622B2/en
Publication of WO2019144658A1 publication Critical patent/WO2019144658A1/zh

Links

Images

Classifications

    • E—FIXED CONSTRUCTIONS
    • E03—WATER SUPPLY; SEWERAGE
    • E03D—WATER-CLOSETS OR URINALS WITH FLUSHING DEVICES; FLUSHING VALVES THEREFOR
    • E03D9/00—Sanitary or other accessories for lavatories ; Devices for cleaning or disinfecting the toilet room or the toilet bowl; Devices for eliminating smells
    • E—FIXED CONSTRUCTIONS
    • E03—WATER SUPPLY; SEWERAGE
    • E03D—WATER-CLOSETS OR URINALS WITH FLUSHING DEVICES; FLUSHING VALVES THEREFOR
    • E03D11/00—Other component parts of water-closets, e.g. noise-reducing means in the flushing system, flushing pipes mounted in the bowl, seals for the bowl outlet, devices preventing overflow of the bowl contents; devices forming a water seal in the bowl after flushing, devices eliminating obstructions in the bowl outlet or preventing backflow of water and excrements from the waterpipe
    • E—FIXED CONSTRUCTIONS
    • E03—WATER SUPPLY; SEWERAGE
    • E03D—WATER-CLOSETS OR URINALS WITH FLUSHING DEVICES; FLUSHING VALVES THEREFOR
    • E03D5/00—Special constructions of flushing devices, e.g. closed flushing system
    • E03D5/10—Special constructions of flushing devices, e.g. closed flushing system operated electrically, e.g. by a photo-cell; also combined with devices for opening or closing shutters in the bowl outlet and/or with devices for raising/or lowering seat and cover and/or for swiveling the bowl
    • E03D5/105—Special constructions of flushing devices, e.g. closed flushing system operated electrically, e.g. by a photo-cell; also combined with devices for opening or closing shutters in the bowl outlet and/or with devices for raising/or lowering seat and cover and/or for swiveling the bowl touchless, e.g. using sensors
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G06F18/232—Non-hierarchical techniques
    • G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
    • G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/161—Detection; Localisation; Normalisation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/168—Feature extraction; Face representation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/172—Classification, e.g. identification
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N7/00—Computing arrangements based on specific mathematical models
    • G06N7/01—Probabilistic graphical models, e.g. probabilistic networks

Definitions

  • the application relates to the field of electrical appliances, in particular to a smart toilet and an electrical system.
  • the toilet is also a very important necessities in people's daily life.
  • the traditional toilet has only a single flushing function, which is far from satisfying people's pursuit of healthy life.
  • an intelligent detection system and method for an intelligent health toilet which uses fingerprint recognition and key recognition to identify a user identity.
  • This method requires the user to first press a button with a finger to perform fingerprint recognition before using the toilet, which is inconvenient to use. Unsanitary.
  • a toilet having an identification function is also proposed in the prior art.
  • the proposal identifies the user identity of the current toilet according to the weight carried on the toilet seat. Obviously, if there are multiple people of the same weight to use the toilet at the same time, The proposed solution does not accurately identify the true identity of the user.
  • a smart toilet with voice control function is also proposed. The proposal proposes to perform the function of controlling the toilet through the user voice, such as: “flushing”, “coming to the first music”, etc., but not for the user. Identification.
  • one of the objects of the present application is to provide a smart toilet and an electrical system having the same that can conveniently and accurately perform user identification.
  • a smart toilet including:
  • An information collecting device configured to collect feature information of the smart toilet in a use state, where the feature information includes at least voiceprint information and/or smell information of a human body using the smart toilet;
  • the control device includes an identity recognition module, configured to identify the human body using the smart toilet according to the feature information.
  • the smart toilet can automatically synthesize the user's various characteristic information to automatically perform accurate operation on the user. Identification greatly improves the ease of use.
  • the feature information further includes image information of the face, a weight of the human body, a position of the human body relative to the smart toilet, and/or a usage time of the smart toilet.
  • the identity recognition module uses an artificial neural network algorithm to identify a human body using the smart toilet according to the feature information.
  • the smart toilet further comprises a metabolite sampling device for sampling a metabolite discharged into the smart toilet by a human body;
  • the control device also includes a metabolite analysis module for performing component analysis on the metabolite sampled by the metabolite sampling device.
  • the metabolite analysis module is for analyzing pH in urine, urine specific gravity, urobilinogen, occult blood, white blood cell content, urine protein content, bilirubin content, ketone body content, urinary red blood cell content and/or urine. Liquid color; and / or,
  • the metabolite analysis module is used to analyze red blood cell count, white blood cell content, pus cell content, and/or the type and content of parasite eggs in the feces.
  • the smart toilet further includes a storage device, wherein the control device is configured to store the component analysis result of the metabolite analysis module in the storage device in a manner corresponding to the identity recognized by the identity recognition module. .
  • the smart toilet further includes a communication module, wherein the control device is communicably connected to the server and/or the terminal through the communication module, and the control device is configured to use the communication module to perform the metabolite analysis module
  • the component analysis result and the identity information identified by the corresponding identity recognition module are uploaded to the server and/or the terminal.
  • the smart toilet further comprises a prompting device
  • the storage device further stores a standard range of metabolite components corresponding to different ranges of body feature parameters
  • the control device is configured to be recognized according to the identity recognition module The identity obtains the range of body characteristic parameters to which it belongs, and compares the component analysis result of the metabolite analysis module with the standard range of the metabolite component corresponding to the range of the body feature parameters, when the component analysis result is within the standard range
  • the control device controls the prompting device to make a prompt.
  • the smart toilet further includes an information entry module for inputting identity information
  • the identity recognition module is configured to use the smart toilet body according to the feature information and the identity information entered by the information entry module. Identify.
  • An electrical system comprising a smart toilet as described above, the electrical system further comprising a smart device, the smart device comprising a wearable device, a home exercise device and/or a household appliance,
  • the smart toilet can be communicatively coupled to the smart device; and/or,
  • the smart toilet and the smart device are both in communication with a server.
  • the household appliance includes an air conditioner, a cooking appliance, an air purifier, a humidifier, and/or a refrigerator.
  • the smart toilet further comprises a metabolite sampling device and a metabolite analysis module, wherein the metabolite sampling device is configured to sample a metabolite discharged into the smart toilet by a human body, and the metabolite analysis module is used for Performing component analysis on metabolites sampled by the metabolite sampling device;
  • the control device of the smart toilet or the server pushes the prompt information to the smart device according to the component analysis result of the metabolite analysis module.
  • the prompt information includes a dietary recommendation, a fitness plan, and/or a recommended environmental parameter setting.
  • the smart toilet provided by the present application can collect characteristic information such as voiceprint information and scent information of the user through the information collecting device, so that the control device of the smart toilet can integrate various characteristic information of the user to the user without any operation. Users perform accurate identification.
  • FIG. 1 is a schematic diagram of a system of a smart toilet provided by a specific embodiment of the present application
  • FIG. 2 is a structural diagram of a neural network algorithm provided by a specific embodiment of the present application.
  • FIG. 3 is a schematic structural view of an electrical system provided by an embodiment of the present application.
  • 100 smart toilet; 110, information collection device; 111, voiceprint recognition device; 112, odor scanner; 113, face recognition module; 114, weighing module; 115, position detection module; 116, timing module; 120, control device; 121, identity recognition module; 130, information entry module; 140, prompt device; 150, storage device; 160, communication module; 170, metabolite sampling device; 180, metabolite analysis module; 300, online diagnostic platform; 400, mobile terminal; 500, household appliances; 600, home fitness equipment; 700, wearable equipment.
  • the application provides a smart toilet, which improves the user experience by intelligently processing the toilet.
  • the smart toilet can be, for example, a squat or a toilet (ie a toilet).
  • the information collecting device 110 is configured to collect feature information of the smart toilet 100 in a use state, and the feature information includes, for example, a voiceprint of a human body using the smart toilet 100.
  • Information, scent information, etc., the so-called voiceprint is a sound wave spectrum that carries speech information displayed by an electroacoustic instrument.
  • the generation of human language is a complex physiological and physical process between the human language center and the vocal organs.
  • the vocal organs used by people in speech--tongue, teeth, throat, lungs, and nasal cavity vary greatly in size and shape. , so the soundprints of any two people are different.
  • the control device 120 includes an identity recognition module 121 for performing identity recognition according to the feature information of the human body using the smart toilet 100 collected by the information collection device 110.
  • the identity of the user can be pre-recorded into the control device 120.
  • the smart phone includes an information entry module 130, and the user can enter the personal information through the information entry module 130.
  • the identity recognition module 121 can be entered into the module 130 according to the feature and the entry information.
  • the identity information identifies the human body using the smart toilet 100, that is, the user can first enter his/her personal information in the smart toilet 100, including name, age, gender, weight, height, etc., to facilitate the subsequent metabolites of the smart toilet to the user. After the detection, the detection result is matched with the user.
  • the personal information of the user can also be established by the smart toilet 100.
  • the smart toilet 100 when a certain user uses the smart toilet 100, the smart toilet 100 automatically selects the user.
  • the file is archived, and the subsequent detection result is stored in the user's file, and the user can also name it later, and when the smart toilet 100 detects another user's use, the user is separately filed. .
  • the voiceprint information and the scent information can be detected by a specific sensor, and the control device 120 is connected to each sensor, and can be connected by wire or wirelessly.
  • the information collecting device 110 includes The voiceprint recognition device 111 of the voiceprint information, the process of voiceprint recognition includes:
  • acoustic features related to the anatomical structure of the human's pronunciation mechanism eg Spectrum, cepstrum, formant, pitch, reflection coefficient, etc.
  • the features currently available for the voiceprint automatic recognition model include: (1) acoustic features (cepstrum); (2) lexical features (speaker-related word n-gram, phoneme n -gram); (3) prosodic features (pitch and energy "postures” described by n-gram); (4) language, dialect and accent information; (5) channel information (what channel is used).
  • the method includes:
  • template matching method using dynamic time warping (DTW) to align training and test feature sequences, mainly used for fixed phrase applications (usually text-related tasks);
  • DTW dynamic time warping
  • Neural network methods There are many forms, such as multi-layer sensing, radial basis function (RBF), etc., which can be explicitly trained to distinguish between the speaker and its background speaker;
  • RBF radial basis function
  • HMM Hidden Markov Model
  • VQ clustering method (such as LBG): preferably used in conjunction with the HMM method;
  • the information collection device also includes an odor scanner 112 (ie, an electronic nose) for collecting user odors, the electronic nose being an electronic system that utilizes a response pattern of the gas sensor array to identify odors, primarily by odor sampling operators, gas sensor arrays, and signals.
  • the processing system consists of three functional devices. The main mechanism by which the electronic nose recognizes the odor is that each sensor in the array has different sensitivities to the gas being measured. For example, gas No. 1 produces a high response on one sensor and low response to other sensors. The No. 2 gas produces a highly responsive sensor that is insensitive to No. 1 gas. The entire sensor array has different response patterns to different gases. It is this difference that allows the system to identify odors based on the sensor's response pattern.
  • an odor is presented to a sensor of an active material that converts the chemical input into an electrical signal, and the response of the plurality of sensors to an odor constitutes a response spectrum of the sensor array to the scent.
  • the various chemical components in the odor interact with the sensitive material, so this response spectrum is the broad spectrum response spectrum of the odor.
  • the sensor signal In order to achieve qualitative or quantitative analysis of the odor, the sensor signal must be properly preprocessed (eliminating noise, feature extraction, signal amplification, etc.) and then processed using appropriate pattern recognition analysis methods.
  • each odor has its characteristic response spectrum, which can be distinguished according to its characteristic response spectrum.
  • the gas sensor can be used to form an array to measure the cross sensitivity of various gases, and the mixed gas analysis can be realized by an appropriate analysis method.
  • the feature information may further include image information of the face, the weight of the human body, the position of the human body relative to the smart toilet, the usage time of the smart toilet, and the like.
  • the information collection device further includes a face recognition module. 113, the weighing module 114, the position detecting module 115, the timing module 116, and the like, the face recognition module 113 performs face recognition on the user who uses the smart toilet, and the face recognition module 113 includes a face image collecting part and a face image.
  • the preprocessing part, the face image feature extraction part, and the face image matching and recognition part wherein in the face image acquisition part, the face image is collected by the camera lens, such as a still image, a moving image, different positions, and different Expressions and other aspects can be well collected.
  • the acquisition device automatically searches for and captures the user's face image.
  • the image preprocessing for the face is based on the face detection result, the image is processed and finally serves the feature extraction process.
  • the original image acquired by the system is often not directly used due to various conditions and random interference. It must be pre-processed with grayscale correction and noise filtering in the early stage of image processing.
  • the preprocessing process mainly includes ray compensation, gradation transformation, histogram equalization, normalization, geometric correction, filtering and sharpening of face images.
  • the features that can be used are generally classified into visual features, pixel statistical features, face image transform coefficient features, face image algebra features, and the like.
  • Face feature extraction is performed on certain features of the face.
  • Face feature extraction also known as face representation, is a process of character modeling a face. The methods of face feature extraction are summarized into two categories: one is based on knowledge representation methods; the other is based on algebraic features or statistical learning.
  • the knowledge-based representation method mainly obtains the feature data which is helpful for face classification according to the shape description of the face organs and the distance characteristics between them.
  • the feature components usually include the Euclidean distance, curvature and angle between the feature points.
  • the human face is composed of parts such as eyes, nose, mouth, chin, etc. The geometric description of these parts and the structural relationship between them can be used as important features for recognizing human faces. These features are called geometric features.
  • Knowledge-based face representation mainly includes geometric feature-based methods and template matching methods. In the face image matching and recognition part, the feature data of the extracted face image is searched and matched with the feature template stored in the database, and a threshold is set, and when the similarity exceeds the threshold, the result of the matching is output. Face recognition is to compare the face features to be recognized with the obtained face feature templates, and judge the identity information of the faces according to the degree of similarity.
  • This process is divided into two categories: one is confirmation, one-to-one image comparison process, and the other is recognition, which is a one-to-many image matching process. Since the user is required to align the camera of the face recognition module when performing face recognition, in order to facilitate the acquisition of the face image, preferably, the camera of the face recognition module is disposed at a position corresponding to the height of the human head on the opposite side of the toilet. In this way, the user does not need to deliberately find the camera, and the user can automatically recognize the face when the user normally uses the smart toilet.
  • the weight of the user using the smart toilet is weighed by the weighing module 114.
  • the weighing module 114 is, for example, a weight sensor.
  • the weight sensor is preferably disposed under the toilet seat.
  • the weight is The sensor is preferably placed below the ground on which the user steps.
  • the position detection module 115 detects the position of the human body relative to the smart toilet 100. Since different users usually have their own unique toilet habits, different users may have slight changes in the position of the smart toilet 100 when using the smart toilet 100.
  • the identity recognition module 121 can find these subtle changes according to the user location analysis detected by the location detection module 115, thereby using it as a factor for the user to identify the user identity. Of course, the location detection module 115 may not be provided, but in the smart toilet.
  • a plurality of weight sensors are disposed at different positions of 100. When the positions of the users are different, the weights detected by the plurality of weight sensors are also different, and the position of the user relative to the smart toilet 100 can be analyzed according to the detection amount of the plurality of weight sensors.
  • the use time of the smart toilet 100 is detected by the timing module. Since different users have their own unique toilet habits, for example, some users like to play mobile phones when they are going to the toilet or have constipation problems, the toilet time is usually longer.
  • the identity module 121 can use the user's toilet time as counted by the timing module 116 as a factor in identifying the identity of the user.
  • the timing module 116 starts timing until the weighing module 114 When no weight is detected within a predetermined time (for example, 10 s) (or when the user is detected to flush), the user ends the toilet, and the timing module 116 stops counting.
  • a predetermined time for example, 10 s
  • the identity module 121 preferably uses an artificial neural network algorithm to identify the human body using the smart toilet 100 based on the feature information.
  • the user identity data is obtained through a large number of different usage environments (including but not limited to one or more of the following: user's voiceprint information, user smell information, user's toilet time, user's weight, etc.) Collecting and collecting several physical feature state parameters as sample data, learning and training the neural network, adjusting the network structure and the weight between network nodes, so that the neural network fits the relationship between the user's identity and its characteristic information, and finally The neural network can accurately fit the correspondence between the user identity and the feature information.
  • the specific implementation steps are as follows:
  • the specific collection methods include, but are not limited to, the characteristic parameters in the laboratory simulation environment (ie, the user actively makes the smart toilet obtain its characteristic information, including voiceprint information, smell, weight, facial image, etc.), through the Internet of Things technology. Collecting characteristic information parameters when the actual user is used (that is, the user passively collects the characteristic information parameters of the various appliances in the Internet of Things).
  • Input parameters include, but are not limited to, one or more of the following: user's voiceprint information, user's scent information, user's toilet time, user's weight, etc., treadmill return health plan, life appliance return recipe information Wait.
  • the input parameters are not only a single parameter, but also a one-dimensional or multi-dimensional array of input parameters composed of features extracted according to a certain rule.
  • the obtained input and output parameter pairs are used as part of training sample data and as part of test sample data.
  • the basic structure of the network According to the user's characteristic information and the rules it contains, the basic structure of the network, the number of input and output nodes of the network, the number of hidden layers of the network, the number of hidden nodes, and the initial weight of the network can be initially determined.
  • a schematic diagram of the neural network algorithm of the present application is shown in FIG. 2.
  • the training sample data is needed to train the network.
  • the training method can be adjusted according to the actual network structure and the problems found in the training. Only one of the methods of this application is illustrated here as follows:
  • ⁇ y(x)-a(x) ⁇ , ⁇ is the target minimum error.
  • test sample is used to test the network.
  • test error does not meet the requirements, repeat the above steps to retrain the network; if the test error meets the requirements, the network training test is completed.
  • each sensor can also be controlled by the control device 120.
  • the control device 120 Control each sensor to open for user characteristic parameter acquisition, and the weighing module 114 does not detect the weight within a predetermined time (for example, 10s) (or when the user flushes water is detected), indicating that the user ends the toilet, and the control device controls each The sensor is off.
  • the human body absorbs nutrients from the outside every day, and at the same time discharges the wastes of its own metabolism out of the body. Metabolism is a cyclical dynamic process. The human body maintains the normal operation of the body in such a dynamic balance. When a disease occurs in the body, this dynamic balance is broken, and the waste of the human body is abnormal.
  • the smart toilet further includes a metabolite sampling device 170 and a metabolite analysis module 180, wherein the metabolite
  • the sampling device 170 is configured to sample the metabolites discharged into the smart toilet 100 by the human body
  • the metabolite analysis module 180 is configured to perform component analysis on the metabolites sampled by the metabolite sampling device 170, for example, analyzing the pH in the urine of the user, Urine specific gravity, urinary biliary, occult blood, white blood cell content, urine protein content, bilirubin content, ketone body content, urinary red blood cell content and/or urine color, for example, analysis of red blood cell count, white blood cell content, pus in user feces Cell content and / or the type and content of parasite eggs.
  • users do not need to go to the hospital to queue and register to easily know their own health.
  • the control device 120 can determine the health status of the user according to the user metabolite component of the metabolite analysis module analysis 180.
  • the smart toilet 100 further includes a prompting device 140 and a storage device 150, which are different ages, genders, and occupations.
  • the standard range of the corresponding metabolite components is different. Therefore, the storage device 150 stores a standard range of metabolite components corresponding to different body feature parameter ranges, and the control device 120 is configured to identify the identity according to the identity recognition module 121.
  • the control device 120 may control the prompting device 140 to perform a corresponding prompt, and the prompting device 140 may perform corresponding reminding, for example, by voice, text display, etc., for example, in the smart A display device is disposed on the toilet 100, and the control device 120 determines When the current user has a health hazard, the analysis result that the user indicator is out of the standard range may be displayed on the display device.
  • the control device 120 can display the analysis result on the display device even if the user does not have a health hazard. On, so that users can understand their physical health.
  • the smart toilet 100 further includes a communication module 160, and the control device 120 can communicate with the server 200 through the communication module 160, and the metabolite analysis module
  • the component analysis result of 180 and the identity information identified by the corresponding identity recognition module 121 are uploaded to the server 200, and the health status of the user is determined by the server 200, and the server 200 is further stored with different detection results.
  • the server 200 can pre-judgize the health status according to the user's metabolite detection result, for example, predict which part of the body the user has a problem, and send the predicted result to the smart toilet 100 to display the prompt.
  • the corresponding APP can also be installed on the terminal (for example, a mobile terminal such as a mobile phone or an iPad), and the server 200 transmits the predicted result to the terminal for display.
  • the server 200 can also be in communication with the online diagnostic platform 300.
  • the server 200 can send the metabolite detection result of the user to the online diagnostic platform 300 by obtaining the user authorization.
  • the online doctor diagnoses it online and gives a diagnosis result to the server 200, and is forwarded by the server 200 to the smart toilet 100 or the mobile terminal 400 for viewing by the user.
  • the server 200 can also analyze the diagnosis results and push the conditioning and improvement scheme to the user.
  • the component analysis result of the metabolite analysis module 180 is stored in the storage device 150 in a manner corresponding to the identity recognized by the identity recognition module 121, so that the user's vital parameters can be recorded when the user needs to go to the hospital to see a doctor.
  • the data stored in the storage device 150 can be extracted for reference by the doctor so that the doctor can make a good judgment on the condition of the user.
  • the present application further provides an electrical system, as shown in FIG. 3, which includes the smart toilet 100 described above, and further includes a smart device, for example, including a wearable device 700 (eg, a smart bracelet), home fitness
  • a smart device for example, including a wearable device 700 (eg, a smart bracelet), home fitness
  • the equipment 600, the household appliance 500, and the household appliance 500 include, for example, an air conditioner, a cooking appliance, an air purifier, a humidifier, a refrigerator, etc.
  • the smart toilet 100 can be communicably connected with the smart device, and both the smart toilet 100 and the smart device can communicate with the server 200. connection.
  • the smart toilet 100 can exchange information with the smart device.
  • the smart device can send information that can reflect the user's living habits to the smart toilet 100, and the smart toilet 100 can combine the living habits to identify the user's identity.
  • the information reflecting the user's living habits includes, for example, the user's fitness habits, the user's eating habits, the frequency with which the user uses the air conditioner, the set temperature of the air conditioner, the type of food in the refrigerator, and the like.
  • the smart toilet 100 can determine the physical health condition of the user according to the components of the user metabolite, and push the prompt information to the smart device according to the physical health condition of the user, for example, pushing the appropriate temperature setting value to the air conditioner and pushing the cooking appliance.
  • the wearable device 700 can also send the detected heart rate, blood pressure, sleep condition, and motion condition of the user to the smart toilet 100, and the smart toilet 100 can combine the user metabolite component with the user's heart rate, blood pressure, sleep condition, and exercise.
  • the information detected by the wearable device 700 comprehensively judges the health status of the user, and improves the accuracy of the diagnosis of the user's health condition.
  • the smart toilet 100 and the smart device can also perform information interaction with the server 200.
  • the smart device can send information that can reflect the user's living habits to the server 200, and the server 200 sends the information to the smart toilet 100, and the smart toilet 100 can Combining these habits to identify the user's identity, the information reflecting the user's living habits includes, for example, the user's fitness habits, the user's eating habits, the frequency with which the user uses the air conditioner, the set temperature of the air conditioner, the type of food in the refrigerator, etc. Wait.
  • the smart toilet 100 transmits the component information of the user metabolite detected by the smart toilet 100 to the server 200.
  • the server 200 determines the physical health condition of the user according to the component of the user metabolite, and pushes the prompt to the smart device according to the physical health condition of the user.
  • Information such as pushing a suitable temperature setting value to the air conditioner, pushing a diet recommendation to the cooking appliance, dietary restrictions, etc., pushing the air purification degree information to the air purifier, pushing the appropriate humidity setting value to the humidifier, and pushing the food recommendation to the refrigerator.
  • the user 200 is urged to exercise on time, and the server 200 can also formulate matching recipes and send them to the cooking appliance, reminding the user to preferably arrange their own diet according to the recommended recipe to improve the condition of the user's fatty liver.
  • the server 200 may send a control signal to the air purifier to control the air purifier to automatically purify the indoor air periodically, and the server 200 may also send the recommended recipe to the home fitness equipment 600.
  • the server 200 can push information to the cooking appliance.
  • the cooking appliance reminds the user not to put chili, pepper, alcoholic food in the process of cooking the food. Tips.
  • the wearable device 700 can also send the detected heart rate, blood pressure, sleep condition, and exercise condition of the user to the server, and the server 200 combines the user metabolite component with the user's heart rate, blood pressure, sleep condition, and exercise condition.
  • the information detected by the device 700 comprehensively judges the health status of the user, and improves the accuracy of the diagnosis of the user's health condition.
  • the terminal or the wearable device 700 may send a notice to the user, for example, sending a reminder to the fasting for metabolite detection in the early morning, in a preferred embodiment
  • the smart bracelet detects that the user wakes up, it automatically reminds the user by sound or text, reminding the user to go to the toilet to check metabolites, of course, the smart bracelet
  • the information may also be transmitted to the mobile terminal 400 such as a mobile phone, and the mobile terminal 400 transmits the reminder information to the user.
  • the smart toilet 100 provided by the present application can collect feature information such as voiceprint information and scent information of the user through the information collecting device 110, so that the control device 120 of the smart toilet 100 can integrate various kinds of users without any operation by the user. Feature information to accurately identify the user.
  • the program may be stored in a computer readable storage medium, and the storage medium may include: Read Only Memory (ROM), Random Access Memory (RAM), disk or optical disk.
  • ROM Read Only Memory
  • RAM Random Access Memory

Abstract

一种智能便器（100），包括信息采集装置（110）和控制装置（120）。信息采集装置（110）用于采集处于使用状态的智能便器（100）的特征信息，特征信息至少包括使用智能便器（100）的人体的声纹信息和/或气味信息；控制装置（120）包括身份识别模块（121），用于根据特征信息对使用智能便器（100）的人体进行身份识别。还包括一种具有智能便器（100）的电器系统。

Description

智能便器及电器系统
相关申请
本申请要求2018年01月29日申请的，申请号为201810082073.8，名称为“智能便器及电器系统”的中国专利申请的优先权，在此将其全文引入作为参考。
技术领域
本申请涉及电器领域，特别是一种智能便器及电器系统。
背景技术
伴随物联网技术的发展，智慧生活会成为一种健康、时尚的潮流。马桶也是人们日常生活中一个很重要的生活必需品，传统的马桶仅具备单一的冲水功能，远远不能够满足人们对健康生活追求的需求。
现有技术中提出一种智能健康马桶的智能检测系统和方法，利用指纹识别和按键识别来识别用户身份，这种方式需要用户在使用马桶之前首先用手指按动按键进行指纹识别，使用不便且不卫生。现有技术中还提出了一种具有身份识别功能的马桶，该提案根据马桶圈上承载的重量来识别当下马桶的使用者身份，显然如果有体重完全相同的多个人来同时使用该马桶时，该提案方案并不能够准确地识别出用户的真实身份。现有技术中还提出了一种具有语音控制功能的智能便器，该提案提出了通过用户语音控制马桶的功能执行，比如：“冲水”、“来首音乐”等等，但并不能进行用户身份识别。
发明内容
有鉴于此，本申请的目的之一是提供一种能够方便准确地进行用户身份识别的智能便器及具有其的电器系统。
为达上述目的，一方面，本申请采用如下技术方案：
一种智能便器，包括：
信息采集装置，用于采集处于使用状态的所述智能便器的特征信息，所述特征信息至少包括使用所述智能便器的人体的声纹信息和/或气味信息；
控制装置，包括身份识别模块，用于根据所述特征信息对使用所述智能便器的人体进行身份识别。
由于是采集人体特有的声纹信息、气味信息等特征信息进行身份识别，因此，无需用 户进行任何操作，当用户使用智能便器时，智能便器能够综合用户的各种特征信息自动对用户进行准确的身份识别，大大提高了使用便捷性。
优选地，所述特征信息还包括人脸的图像信息、所述人体的体重、人体相对所述智能便器的位置和/或所述智能便器的使用时间。
优选地，所述身份识别模块采用人工神经网络算法根据所述特征信息对使用所述智能便器的人体进行身份识别。
优选地，所述智能便器还包括代谢物取样装置，用于对人体排入所述智能便器内的代谢物进行取样；
所述控制装置还包括代谢物分析模块，用于对所述代谢物取样装置取样的代谢物进行成分分析。
优选地，所述代谢物分析模块用于分析尿液中的酸碱度、尿比重、尿胆原、隐血、白细胞含量、尿蛋白含量、胆红素含量、酮体含量、尿红细胞含量和/或尿液颜色；和/或，
所述代谢物分析模块用于分析粪便中的红细胞计数、白细胞含量、脓细胞含量和/或寄生虫卵的种类和含量。
优选地，所述智能便器还包括存储装置，所述控制装置用于将所述代谢物分析模块的成分分析结果以与所述身份识别模块识别的身份相对应的方式存储于所述存储装置中。
优选地，所述智能便器还包括通讯模块，所述控制装置能够通过所述通讯模块与服务器和/或终端通讯连接，所述控制装置用于通过所述通讯模块将所述代谢物分析模块的成分分析结果以及与相对应的所述身份识别模块识别的身份信息上传至所述服务器和/或所述终端。
优选地，所述智能便器还包括提示装置，所述存储装置中还存储有与不同的身体特征参数范围对应的代谢物成分的标准范围，所述控制装置用于根据所述身份识别模块识别的身份得到其所属的身体特征参数范围，并将所述代谢物分析模块的成分分析结果与所属的身体特征参数范围对应的代谢物成分的标准范围比较，当所述成分分析结果在所述标准范围之外时，所述控制装置控制所述提示装置进行提示。
优选地，所述智能便器还包括信息录入模块，用于录入身份信息，所述身份识别模块用于根据所述特征信息和经所述信息录入模块录入的身份信息对使用所述智能便器的人体进行身份识别。
另一方面，本申请采用如下技术方案：
一种电器系统，包括如上所述的智能便器，所述电器系统还包括智能设备，所述智能设备包括可穿戴设备、家用健身器材和/或家用电器，
所述智能便器能够与所述智能设备通讯连接；和/或，
所述智能便器和所述智能设备均与服务器通讯连接。
优选地，所述家用电器包括空调、烹饪器具、空气净化器、加湿器和/或冰箱。
优选地，所述智能便器还包括代谢物取样装置和代谢物分析模块，所述代谢物取样装置用于对人体排入所述智能便器内的代谢物进行取样，所述代谢物分析模块用于对所述代谢物取样装置取样的代谢物进行成分分析；
所述智能便器的控制装置或者所述服务器根据所述代谢物分析模块的成分分析结果向所述智能设备推送提示信息。
优选地，所述提示信息包括饮食建议、健身计划和/或推荐环境参数设定值。
本申请提供的智能便器能够通过信息采集装置进行用户的声纹信息、气味信息等特征信息的采集，如此，无需用户进行任何操作，智能便器的控制装置即可综合用户的各种特征信息来对用户进行准确的身份识别。
附图说明
通过以下参照附图对本申请实施例的描述，本申请的上述以及其它目的、特征和优点将更为清楚，在附图中：
图1示出本申请具体实施方式提供的智能便器的系统示意图；
图2示出本申请具体实施方式提供的神经网络算法结构图；
图3示出本申请具体实施方式提供的电器系统的结构示意图。
其中，100、智能便器；110、信息采集装置；111、声纹识别装置；112、气味扫描仪；113、人脸识别模块；114、称重模块；115、位置检测模块；116、计时模块；120、控制装置；121、身份识别模块；130、信息录入模块；140、提示装置；150、存储装置；160、通讯模块；170、代谢物取样装置；180、代谢物分析模块；200、服务器；300、在线诊断平台；400、移动终端；500、家用电器；600、家用健身器材；700、可穿戴设备。
具体实施方式
以下基于实施例对本申请进行描述，但是本申请并不仅仅限于这些实施例。为了避免混淆本申请的实质，公知的方法、过程、流程、元件并没有详细叙述。
此外，本领域普通技术人员应当理解，在此提供的附图都是为了说明的目的，并且附图不一定是按比例绘制的。
除非上下文明确要求，否则整个说明书和权利要求书中的“包括”、“包含”等类似词 语应当解释为包含的含义而不是排他或穷举的含义；也就是说，是“包括但不限于”的含义。
在本申请的描述中，需要理解的是，术语“第一”、“第二”等仅用于描述目的，而不能理解为指示或暗示相对重要性。此外，在本申请的描述中，除非另有说明，“多个”的含义是两个或两个以上。
在描述本申请的概念的过程中使用了术语“一”和“所述”以及类似的词语(尤其是在所附的权利要求书中)，应该将这些术语解释为既涵盖单数又涵盖复数。此外，除非本文中另有说明，否则在本文中叙述数值范围时仅仅是通过快捷方法来指代属于相关范围的每个独立的值，而每个独立的值都并入本说明书中，就像这些值在本文中单独进行了陈述一样。另外，除非本文中另有指明或上下文有明确的相反提示，否则本文中所述的所有方法的步骤都可以按任何适当次序加以执行。本申请的改变并不限于描述的步骤顺序。除非另外主张，否则使用本文中所提供的任何以及所有实例或示例性语言(例如，“例如”)都仅仅为了更好地说明本申请的概念，而并非对本申请的概念的范围加以限制。在不脱离精神和范围的情况下，所属领域的技术人员将易于明白多种修改和适应。
本申请提供了一种智能便器，通过对便器的智能化处理，提高用户体验。智能便器例如可以是蹲便或者坐便器(即马桶)。
如图1所示，其包括信息采集装置110和控制装置120，其中，信息采集装置110用于采集处于使用状态的智能便器100的特征信息，特征信息例如包括使用智能便器100的人体的声纹信息、气味信息等，所谓声纹(Voiceprint)，是用电声学仪器显示的携带言语信息的声波频谱。人类语言的产生是人体语言中枢与发音器官之间一个复杂的生理物理过程，人在讲话时使用的发声器官--舌、牙齿、喉头、肺、鼻腔在尺寸和形态方面每个人的差异很大，所以任何两个人的声纹图谱都有差异。每个人的语音声学特征既有相对稳定性，又有变异性，不是绝对的、一成不变的。这种变异可来自生理、病理、心理、模拟、伪装，也与环境干扰有关。尽管如此，由于每个人的发音器官都不尽相同，因此，通过声纹识别装置仍能区别不同的人的声音或判断是否是同一人的声音。由于不同的个体具有独特的声纹以及气味(例如，当某一用户喜欢抽烟时，通常身上会有烟味)，因此，通过获取声纹信息、气味信息能够准确的对正在使用智能便器100的用户进行准确的身份识别。例如，控制装置120包括身份识别模块121，身份识别模块121用于根据信息采集装置110采集的使用智能便器100的人体的特征信息来进行身份识别。
用户的身份可以预先录入到控制装置120中，例如，智能便器包括信息录入模块130，用户可以通过信息录入模块130将个人信息录入进去，身份识别模块121可根据特征和录 入信息录入模块130中的身份信息对使用智能便器100的人体进行身份识别，即，用户可以首先在智能便器100中录入自己的个人信息，包括姓名、年龄、性别、体重、身高等，方便智能便器后续对用户的代谢物进行检测后将检测结果与用户相匹配，当然，可以理解的是，用户的个人信息也可以由智能便器100自主建立，例如，当某一用户使用智能便器100时，智能便器100自动对该用户建档，并将其后续的检测结果存入该用户的档案中，用户还可以后续对其进行相应的命名，而当智能便器100检测到另一用户使用时，则另外单独对该用户建档。
声纹信息、气味信息均可以通过特定的传感器进行检测，控制装置120与各个传感器均相连，可以通过有线或者无线的方式通讯连接，在一个具体的实施例中，信息采集装置110包括用于采集声纹信息的声纹识别装置111，声纹识别的过程包括：
A、特征提取，提取并选择对说话人的声纹具有可分性强、稳定性高等特性的声学或语言特征。与语音识别不同，声纹识别的特征必须是“个性化”特征，而说话人识别的特征对说话人来讲必须是“共性特征”。虽然目前大部分声纹识别系统用的都是声学层面的特征，但是表征一个人特点的特征应该是多层面的，包括：(1)与人类的发音机制的解剖学结构有关的声学特征(如频谱、倒频谱、共振峰、基音、反射系数等等)、鼻音、带深呼吸音、沙哑音、笑声等；(2)受社会经济状况、受教育水平、出生地等影响的语义、修辞、发音、言语习惯等；(3)个人特点或受父母影响的韵律、节奏、速度、语调、音量等特征。从利用数学方法可以建模的角度出发，声纹自动识别模型目前可以使用的特征包括：(1)声学特征(倒频谱)；(2)词法特征(说话人相关的词n-gram，音素n-gram)；(3)韵律特征(利用n-gram描述的基音和能量“姿势”)；(4)语种、方言和口音信息；(5)通道信息(使用何种通道)。
B、模式匹配
在该过程中进行模式的识别，其方法包括：
(1)模板匹配方法：利用动态时间弯折(DTW)以对准训练和测试特征序列，主要用于固定词组的应用(通常为文本相关任务)；
(2)最近邻方法：训练时保留所有特征矢量，识别时对每个矢量都找到训练矢量中最近的K个，据此进行识别；
(3)神经网络方法：有很多种形式，如多层感知、径向基函数(RBF)等，可以显式训练以区分说话人和其背景说话人；
(4)隐式马尔可夫模型(HMM)方法：通常使用单状态的HMM，或高斯混合模型(GMM)；
(5)VQ聚类方法(如LBG)：优选与HMM方法配合使用；
(6)多项式分类器方法。
信息采集装置还包括用于采集用户气味的气味扫描仪112(即电子鼻)，电子鼻是利用气体传感器阵列的响应图案来识别气味的电子系统，主要由气味取样操作器、气体传感器阵列和信号处理系统三种功能器件组成。电子鼻识别气味的主要机理是在阵列中的每个传感器对被测气体都有不同的灵敏度，例如，一号气体可在某个传感器上产生高响应，而对其他传感器则是低响应，同样，二号气体产生高响应的传感器对一号气体则不敏感，整个传感器阵列对不同气体的响应图案是不同的，正是这种区别，才使系统能根据传感器的响应图案来识别气味。具体地，某种气味呈现在一种活性材料的传感器面前，传感器将化学输入转换成电信号，由多个传感器对一种气味的响应便构成了传感器阵列对该气味的响应谱。显然，气味中的各种化学成分均会与敏感材料发生作用，所以这种响应谱为该气味的广谱响应谱。为实现对气味的定性或定量分析，必须将传感器的信号进行适当的预处理(消除噪声、特征提取、信号放大等)后采用合适的模式识别分析方法对其进行处理。理论上，每种气味都会有它的特征响应谱，根据其特征响应谱可区分不同的气味。同时还可利用气敏传感器构成阵列对多种气体的交叉敏感性进行测量，通过适当的分析方法，实现混合气体分析。
为了进一步提高身份识别的准确性，特征信息还可以包括人脸的图像信息、人体的体重、人体相对智能便器的位置、智能便器的使用时间等等，例如，信息采集装置还包括人脸识别模块113、称重模块114、位置检测模块115、计时模块116等等，通过人脸识别模块113对使用智能便器的用户进行人脸识别，人脸识别模块113包括人脸图像采集部分、人脸图像预处理部分、人脸图像特征提取部分以及人脸图像匹配与识别部分，其中，人脸图像采集部分中，通过摄像镜头对人脸图像进行采集，比如静态图像、动态图像、不同的位置、不同表情等方面都可以得到很好的采集。当用户在采集设备的拍摄范围内时，采集设备会自动搜索并拍摄用户的人脸图像。人脸图像预处理部分中，对于人脸的图像预处理是基于人脸检测结果，对图像进行处理并最终服务于特征提取的过程。系统获取的原始图像由于受到各种条件的限制和随机干扰，往往不能直接使用，必须在图像处理的早期阶段对它进行灰度校正、噪声过滤等图像预处理。对于人脸图像而言，其预处理过程主要包括人脸图像的光线补偿、灰度变换、直方图均衡化、归一化、几何校正、滤波以及锐化等。人脸图像特征提取部分中，其可使用的特征通常分为视觉特征、像素统计特征、人脸图像变换系数特征、人脸图像代数特征等。人脸特征提取就是针对人脸的某些特征进行的。人脸特征提取，也称人脸表征，它是对人脸进行特征建模的过程。人脸特征提取的方法归纳起来分为两大类：一种是基于知识的表征方法；另外一种是基于代数特征或统计学习的表征方法。基于知识的表征方法主要是根据人脸器官的形状描述以及他们之间的距离特性来 获得有助于人脸分类的特征数据，其特征分量通常包括特征点间的欧氏距离、曲率和角度等。人脸由眼睛、鼻子、嘴、下巴等局部构成，对这些局部和它们之间结构关系的几何描述，可作为识别人脸的重要特征，这些特征被称为几何特征。基于知识的人脸表征主要包括基于几何特征的方法和模板匹配法。人脸图像匹配与识别部分中，提取的人脸图像的特征数据与数据库中存储的特征模板进行搜索匹配，通过设定一个阈值，当相似度超过这一阈值，则把匹配得到的结果输出。人脸识别就是将待识别的人脸特征与已得到的人脸特征模板进行比较，根据相似程度对人脸的身份信息进行判断。这一过程又分为两类：一类是确认，是一对一进行图像比较的过程，另一类是辨认，是一对多进行图像匹配对比的过程。由于在进行人脸识别时需要用户对准人脸识别模块的摄像头，为了方便人脸图像的获取，优选地，人脸识别模块的摄像头设置在便器的对侧与人头部高度相对应的位置，如此，用户无需刻意地去找摄像头，当用户正常使用智能便器时即可自动对用户进行人脸识别。
通过称重模块114称取使用智能便器的用户的体重，称重模块114例如为重量传感器，当智能便器为马桶时，重量传感器优选设置在马桶圈的下方，当智能便器为蹲便器时，重量传感器优选设置在用户踩踏的地面的下方。
通过位置检测模块115检测人体相对智能便器100的位置，由于不同的用户通常具有自己独特的如厕习惯，因此不同的用户在使用智能便器100时相对智能便器100的位置也会有细微的变化，身份识别模块121可以根据位置检测模块115检测到的用户位置分析发现这些细微的变化，从而将其作为用户识别用户身份的一个因素，当然，也可以不设置位置检测模块115，而是在智能便器100的不同位置设置多个重量传感器，用户的位置不同，则多个重量传感器所检测到的重量也各不相同，可以根据多个重量传感器的检测量来分析得到用户相对智能便器100的位置。
通过计时模块来检测智能便器100的使用时间，由于不同的用户具有自己独特的如厕习惯，比如有些用户喜欢在如厕时玩手机或者有便秘的问题，则其如厕时间通常会较长，身份识别模块121可以将计时模块116统计的用户如厕时间作为识别用户身份的一个因素。在一个具体的实施例中，当称重模块114检测到重量增加较大并持续预定时间(例如10s)时，说明有用户开始使用智能便器，此时计时模块116开始计时，直至称重模块114在预定时间(例如10s)内均检测不到重量时(或者是检测到用户冲水时)，说明用户结束如厕，计时模块116停止计时。
身份识别模块121优选采用人工神经网络算法根据特征信息对使用智能便器100的人体进行身份识别。具体地，通过对大量不同使用环境下(包括但不限于如下的一种或多种：用户的声纹信息、用户气味信息、用户的如厕时间、用户的体重等综合方式等)用户身份 数据汇总收集，选取若干身体特征状态参数作为样本数据，对神经网络进行学习和训练，通过调整网络结构及网络节点间的权值，使神经网络拟合用户的身份与其特征信息之间的关系，最终使神经网络能准确拟合出用户身份与特征信息的对应关系。具体实施步骤如下：
S001、数据搜集；
搜集用户在不同使用环境下的自身的特征信息参数及对应的确定身份信息情况。具体搜集方式包括但不限于在实验室模拟环境下的特征参数(即用户主动地让智能便器对其特征信息进行获取，包括声纹信息、气味、体重、脸部图像等)、通过物联网技术搜集实际用户使用时的特征信息参数(即用户被动地由处于物联网中的各个电器对其特征信息参数进行采集)等方式。
S002、样本数据选择；
通过对数据的分析和结合专家经验知识，选取对用户身份状态有影响的参数作为输入参数，将确定用户身份信息状态作为输出参数。输入参数包括但不限于如下的一种或多种：用户的声纹信息、用户的气味信息、用户的如厕时间、用户的体重等综合方式、跑步机返回的健康计划、生活电器返回食谱信息等。输入参数不仅为单一参数，也包括按一定规律提取特征组成的输入参数一维或多维数组。
将得到的输入、输出参数对，一部分用作训练本样数据，一部分用作测试样本数据。
S003、网络结构设计；
根据用户的特征信息及其所蕴含的规律，可初步确定网络的基本结构、网络的输入、输出节点数、网络隐层数、隐节点数、网络初始权值等。本申请的神经网络算法示意图如图2所示。
S004、网络训练与测试；
网络设计完成后，需用训练样本数据，对网络进行训练。
训练方法可根据实际的网络结构及训练中发现的问题进行调整。此处仅针对本申请的其中一种方法举例说明如下：
导入输入数据x，根据激活函数、初始化的权值及偏置计算出网络的实际输出a(x)，即a(x)＝1/(1+e-z),其中Z＝Wk*x+bl。
判断网络的期望输出y(x)与实际输出a(x)是否满足输出精度要求即：
‖y(x)-a(x)‖<∈，∈为目标最小误差。
网络训练完成后，再用测试样本正向测试网络。当测试误差不满足要求时，则重复以上步骤，重新训练网络；若测试误差满足要求，则网络训练测试完成。
进一步地，通过控制装置120还可以控制各个传感器的启停，例如，当称重模块114 检测到重量增加较大并持续预定时间(例如10s)时，说明有用户开始使用智能便器，控制装置120控制各个传感器开启进行用户特征参数的获取，称重模块114在预定时间(例如10s)内均检测不到重量时(或者是检测到用户冲水时)，说明用户结束如厕，控制装置控制各个传感器关闭。
进一步地，人体每天都在从外界吸收营养物质，同时又将自身代谢的废物排出身体之外。新陈代谢是一个循环往复的动态过程。人体就是在这样一个动态平衡中维持机体的正常运转。当身体中出现了疾病时，这个动态的平衡就会被打破，进而人体代谢的废物就会出现异常，基于此，智能便器还包括代谢物取样装置170和代谢物分析模块180，其中，代谢物取样装置170用于对人体排入智能便器100内的代谢物进行取样，代谢物分析模块180用于对代谢物取样装置170取样的代谢物进行成分分析，例如，分析用户尿液中的酸碱度、尿比重、尿胆原、隐血、白细胞含量、尿蛋白含量、胆红素含量、酮体含量、尿红细胞含量和/或尿液颜色，再例如，分析用户粪便中的红细胞计数、白细胞含量、脓细胞含量和/或寄生虫卵的种类和含量。如此，用户不需要去医院排队和挂号即可方便的获知自身的健康状况。
控制装置120可根据代谢物分析模块分析180的用户代谢物成分来判断用户的健康状况，例如，智能便器100还包括提示装置140和存储装置150，由于不同年龄阶段、不同性别、不同的职业其所对应的代谢物成分的标准范围是不同的，因此，存储装置150中存储有与不同的身体特征参数范围对应的代谢物成分的标准范围，控制装置120用于根据身份识别模块121识别的身份得到其所属的身体特征参数范围，并将所述代谢物分析模块180的成分分析结果与所属的身体特征参数范围对应的代谢物成分的标准范围比较，当所述成分分析结果在所述标准范围之外时，说明该用户可能会存在健康问题，此时，控制装置120可以控制所述提示装置140进行相应提示，提示装置140例如可以通过语音、文字显示等方式进行相应提醒，例如，在智能便器100上设置显示装置，当控制装置120判断当前用户存在健康隐患时，可以将用户指标不在标准范围内的分析结果显示在显示装置上，当然，可以理解的是，即使用户不存在健康隐患，控制装置120也可以将分析结果显示在显示装置上，使得用户可以了解自己的身体健康状况。
为了降低控制装置120的预算量以及减小对存储装置的存储量的要求，优选地，智能便器100还包括通讯模块160，控制装置120能够通过通讯模块160与服务器200通讯连接，代谢物分析模块180的成分分析结果以及与相对应的身份识别模块121识别的身份信息上传至服务器200中，通过服务器200来对用户的健康状况进行判断，在服务器200中还存储有分别与不同的检测结果相对应的病理分析，服务器200可以根据用户的代谢物检 测结果对其健康状况进行预判，例如预判用户是身体的哪部分出现了问题，并将预判的结果发送至智能便器100显示在提示装置140中，当然，可以理解的是，也可以在终端(例如手机、ipad等移动终端)上安装相应的APP，服务器200将预判的结果发送到终端上进行显示。进一步优选地，服务器200还可以与在线诊断平台300通讯连接，当检测到用户存在健康隐患时，在获得用户授权的情况下，服务器200可以将用户的代谢物检测结果发送到在线诊断平台300由在线医生对其进行在线诊断并给出诊断结果反馈到服务器200，并由服务器200转发到智能便器100或者移动终端400供用户进行查看。另外，服务器200还可以对诊断结果进行分析，并向用户推送调理和改善的方案。
进一步地，代谢物分析模块180的成分分析结果以与身份识别模块121识别的身份相对应的方式存储于存储装置150中，从而能够对用户的体征参数进行记录，当用户需要去医院看医生时，可以提取存储装置150中存储的数据供医生参考，以便医生对用户的病情进行很好的判断。
进一步优选地，本申请还提供了一种电器系统，如图3所示，其包括上述的智能便器100，还包括智能设备，智能设备例如包括可穿戴设备700(例如智能手环)、家用健身器材600、家用电器500，家用电器500例如包括空调、烹饪器具、空气净化器、加湿器、冰箱等等，智能便器100能够与智能设备通讯连接，智能便器100和智能设备均能够与服务器200通讯连接。
如此，智能便器100能够与智能设备之间进行信息交互，例如，智能设备可以将其能够体现用户生活习惯的信息发送至智能便器100，智能便器100可以结合这些生活习惯来对用户的身份进行识别，体现用户生活习惯的信息例如包括用户的健身习惯、用户的饮食习惯、用户使用空调的频率、使用空调的设定温度高低、冰箱内的食品种类等等。再例如，智能便器100可以根据用户代谢物的成分来判断用户的身体健康状况，并根据用户的身体健康状况来向智能设备推送提示信息，例如向空调推送适宜温度设定值、向烹饪器具推送饮食建议、饮食禁忌等信息，向空气净化器推送空气净化程度信息、向加湿器推送适宜湿度设定值、向冰箱推送饮食建议、向家用健身器材600推送健身计划等等。另外，可穿戴设备700还可以将其检测到的用户的心率、血压、睡眠状况、运动情况发送给智能便器100，智能便器100能够结合用户代谢物成分以及用户的心率、血压、睡眠状况、运动情况这些可穿戴设备700检测的信息对用户的健康状况进行综合判断，提高对用户健康状况诊断的准确性。
智能便器100和智能设备也可以与服务器200进行信息交互，例如，智能设备可以将其能够体现用户生活习惯的信息发送至服务器200，由服务器200将这些信息发送至智能 便器100，智能便器100可以结合这些生活习惯来对用户的身份进行识别，体现用户生活习惯的信息例如包括用户的健身习惯、用户的饮食习惯、用户使用空调的频率、使用空调的设定温度高低、冰箱内的食品种类等等。再例如，智能便器100将其检测的用户代谢物的成分信息发送至服务器200，服务器200根据用户代谢物的成分来判断用户的身体健康状况，并根据用户的身体健康状况来向智能设备推送提示信息，例如向空调推送适宜温度设定值、向烹饪器具推送饮食建议、饮食禁忌等信息，向空气净化器推送空气净化程度信息、向加湿器推送适宜湿度设定值、向冰箱推送饮食建议、向家用健身器材600推送健身计划等等。例如，当通过分析判断用户患有脂肪肝时，服务器200可以拟定与用户的体重、年龄相匹配的健身计划并向家用健身器材600发送，还可同时控制家用健身器材600定时对用户进行提醒，督促用户按时锻炼身体，服务器200还可以拟定匹配的菜谱并向烹饪器具发送，提醒用户优选按推荐的菜谱安排自己的饮食，以改善用户脂肪肝的状况。再例如，当通过分析判断用户患有呼吸道疾病时，服务器200可以向空气净化器发送控制信号，控制空气净化器定期对室内空气进行自动净化，服务器200同时也可以向家用健身器材600发送推荐食谱，以提高用户的呼吸环境，提高用户的舒适度。再例如，当通过分析判断用户患有慢性肾炎时，服务器200可以向烹饪器具推送信息，当用户开启烹饪器具，烹饪器具会提醒用户在烹饪食品的过程中不要放入辣椒、胡椒、酒类食品的提示。另外，可穿戴设备700还可以将其检测到的用户的心率、血压、睡眠状况、运动情况发送给服务器，服务器200结合用户代谢物成分以及用户的心率、血压、睡眠状况、运动情况这些可穿戴设备700检测的信息对用户的健康状况进行综合判断，提高对用户健康状况诊断的准确性。
进一步优选地，为了提高智能马桶100对用户代谢物检测的准确性，终端或者可穿戴设备700可以向用户发送注意事项，例如在清早发送建议空腹进行代谢物检测的提醒，在一个优选的实施例中，具有检测用户睡眠状况的可穿戴设备700例如智能手环检测到用户醒来时，其自动以声音或者文字的方式向用户提醒，提醒用户空腹如厕以检验代谢物，当然，智能手环也可以将信息发送至手机等移动终端400，由移动终端400向用户发送提醒信息。
本申请提供的智能便器100能够通过信息采集装置110进行用户的声纹信息、气味信息等特征信息的采集，如此，无需用户进行任何操作，智能便器100的控制装置120即可综合用户的各种特征信息来对用户进行准确的身份识别。
本领域的技术人员容易理解的是，在不冲突的前提下，上述各优选方案可以自由地组合、叠加。
应当理解，上述的实施方式仅是示例性的，而非限制性的，在不偏离本申请的基本原 理的情况下，本领域的技术人员可以针对上述细节做出的各种明显的或等同的修改或替换，都将包含于本申请的权利要求范围内。
本领域普通技术人员可以理解上述实施例的各种方法中的全部或部分步骤是可以通过程序来指令相关的硬件来完成，该程序可以存储于一计算机可读存储介质中，存储介质可以包括：只读存储器(ROM，Read Only Memory)、随机存取记忆体(RAM，Random Access Memory)、磁盘或光盘等。
在描述本申请的概念的过程中使用了术语“一”和“所述”以及类似的词语(尤其是在所附的权利要求书中)，应该将这些术语解释为既涵盖单数又涵盖复数。此外，除非本文中另有说明，否则在本文中叙述数值范围时仅仅是通过快捷方法来指代属于相关范围的每个独立的值，而每个独立的值都并入本说明书中，就像这些值在本文中单独进行了陈述一样。另外，除非本文中另有指明或上下文有明确的相反提示，否则本文中所述的所有方法的步骤都可以按任何适当次序加以执行。本申请的改变并不限于描述的步骤顺序。除非另外主张，否则使用本文中所提供的任何以及所有实例或示例性语言(例如，“例如”)都仅仅为了更好地说明本申请的概念，而并非对本申请的概念的范围加以限制。在不脱离精神和范围的情况下，所属领域的技术人员将易于明白多种修改和适应。

Claims (13)

  1. 一种智能便器，其特征在于，包括：
    信息采集装置，用于采集处于使用状态的所述智能便器的特征信息，所述特征信息至少包括使用所述智能便器的人体的声纹信息和/或气味信息；
    控制装置，包括身份识别模块，用于根据所述特征信息对使用所述智能便器的人体进行身份识别。
  2. 根据权利要求1所述的智能便器，其特征在于，所述特征信息还包括人脸的图像信息、所述人体的体重、人体相对所述智能便器的位置和/或所述智能便器的使用时间。
  3. 根据权利要求1或2所述的智能便器，其特征在于，所述身份识别模块采用人工神经网络算法根据所述特征信息对使用所述智能便器的人体进行身份识别。
  4. 根据权利要求1或2所述的智能便器，其特征在于，所述智能便器还包括代谢物取样装置，用于对人体排入所述智能便器内的代谢物进行取样；
    所述控制装置还包括代谢物分析模块，用于对所述代谢物取样装置取样的代谢物进行成分分析。
  5. 根据权利要求4所述的智能便器，其特征在于，所述代谢物分析模块用于分析尿液中的酸碱度、尿比重、尿胆原、隐血、白细胞含量、尿蛋白含量、胆红素含量、酮体含量、尿红细胞含量和/或尿液颜色；和/或，
    所述代谢物分析模块用于分析粪便中的红细胞计数、白细胞含量、脓细胞含量和/或寄生虫卵的种类和含量。
  6. 根据权利要求4所述的智能便器，其特征在于，所述智能便器还包括存储装置，所述控制装置用于将所述代谢物分析模块的成分分析结果以与所述身份识别模块识别的身份相对应的方式存储于所述存储装置中。
  7. 根据权利要求6所述的智能便器，其特征在于，所述智能便器还包括通讯模块，所述控制装置能够通过所述通讯模块与服务器和/或终端通讯连接，所述控制装置用于通过所述通讯模块将所述代谢物分析模块的成分分析结果以及与相对应的所述身份识别模块识别的身份信息上传至所述服务器和/或所述终端。
  8. 根据权利要求6所述的智能便器，其特征在于，所述智能便器还包括提示装置，所述存储装置中还存储有与不同的身体特征参数范围对应的代谢物成分的标准范围，所述控制装置用于根据所述身份识别模块识别的身份得到其所属的身体特征参数范围，并将所述 代谢物分析模块的成分分析结果与所属的身体特征参数范围对应的代谢物成分的标准范围比较，当所述成分分析结果在所述标准范围之外时，所述控制装置控制所述提示装置进行提示。
  9. 根据权利要求1所述的智能便器，其特征在于，所述智能便器还包括信息录入模块，用于录入身份信息，所述身份识别模块用于根据所述特征信息和经所述信息录入模块录入的身份信息对使用所述智能便器的人体进行身份识别。
  10. 一种电器系统，其特征在于，包括如权利要求1至9之一所述的智能便器，所述电器系统还包括智能设备，所述智能设备包括可穿戴设备、家用健身器材和/或家用电器，
    所述智能便器能够与所述智能设备通讯连接；和/或，
    所述智能便器和所述智能设备均与服务器通讯连接。
  11. 根据权利要求10所述的电器系统，其特征在于，所述家用电器包括空调、烹饪器具、空气净化器、加湿器和/或冰箱。
  12. 根据权利要求10所述的电器系统，其特征在于，所述智能便器还包括代谢物取样装置和代谢物分析模块，所述代谢物取样装置用于对人体排入所述智能便器内的代谢物进行取样，所述代谢物分析模块用于对所述代谢物取样装置取样的代谢物进行成分分析；
    所述智能便器的控制装置或者所述服务器根据所述代谢物分析模块的成分分析结果向所述智能设备推送提示信息。
  13. 根据权利要求12所述的电器系统，其特征在于，所述提示信息包括饮食建议、健身计划和/或推荐环境参数设定值。
PCT/CN2018/111476 2018-01-29 2018-10-23 智能便器及电器系统 WO2019144658A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
JP2020554346A JP7091471B2 (ja) 2018-01-29 2018-10-23 スマート・トイレ及び電気器具システム
US16/965,286 US11655622B2 (en) 2018-01-29 2018-10-23 Smart toilet and electric appliance system

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810082073.8A CN108360630B (zh) 2018-01-29 2018-01-29 智能便器及电器系统
CN201810082073.8 2018-01-29

Publications (1)

Publication Number Publication Date
WO2019144658A1 true WO2019144658A1 (zh) 2019-08-01

Family

ID=63007144

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/111476 WO2019144658A1 (zh) 2018-01-29 2018-10-23 智能便器及电器系统

Country Status (4)

Country Link
US (1) US11655622B2 (zh)
JP (1) JP7091471B2 (zh)
CN (1) CN108360630B (zh)
WO (1) WO2019144658A1 (zh)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110441504A (zh) * 2019-08-22 2019-11-12 王鹂辉 一种马桶用人体排泄物气味检测分析仪及分析系统
TWI711746B (zh) * 2019-11-07 2020-12-01 南開科技大學 整合物聯網的免治馬桶座之控制系統及其方法
CN112859652A (zh) * 2021-01-20 2021-05-28 青岛海尔空调器有限总公司 室内抽烟监控方法及监控装置

Families Citing this family (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108360630B (zh) * 2018-01-29 2019-08-13 珠海格力电器股份有限公司 智能便器及电器系统
CN109235590A (zh) * 2018-09-26 2019-01-18 深圳市博电电子技术有限公司 智能马桶控制方法与智能马桶
WO2020061787A1 (zh) * 2018-09-26 2020-04-02 深圳市博电电子技术有限公司 一种智能马桶控制方法与智能马桶
CN109549482A (zh) * 2018-11-15 2019-04-02 珠海格力电器股份有限公司 饮水机和饮水机控制方法
CN109610584A (zh) * 2018-12-20 2019-04-12 乳源南岭智能家用机械有限公司 一种具有人脸识别功能的智能坐便器及其智能调节方法
TR201820212A2 (tr) * 2018-12-24 2020-07-21 Eczacibasi Yapi Gerecleri Sanayi Ve Ticaret Anonim Sirketi Kullanici alişkanliklari tespi̇t ve kullanici tanimlama si̇stemi̇ ve yöntemi̇
CN113160936A (zh) * 2020-01-22 2021-07-23 青岛海尔电冰箱有限公司 饮食推荐方法、冰箱、计算机可读存储介质
TWM613735U (zh) * 2021-03-24 2021-06-21 美商紐倫百仕科技股份有限公司 影像辨識自動掀蓋智能馬桶
CN113359523A (zh) * 2021-06-03 2021-09-07 广东水护盾健康科技有限公司 智能马桶的控制方法以及智能马桶组件、智能马桶
WO2023145501A1 (ja) * 2022-01-27 2023-08-03 京セラ株式会社 ガス検出装置およびガス検出システム
CN114582451A (zh) * 2022-02-10 2022-06-03 湖南思码智链教育科技有限责任公司 一种智能如厕监测系统与方法

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2001265822A (ja) * 2000-03-23 2001-09-28 Toto Ltd 生体情報管理システム
CN1804859A (zh) * 2005-01-11 2006-07-19 吴水超 一种高效的生物特征认证系统
CN201328144Y (zh) * 2008-09-28 2009-10-14 宇龙计算机通信科技(深圳)有限公司 基于气味识别的移动终端
CN104452926A (zh) * 2014-12-25 2015-03-25 电子科技大学 一种基于智能马桶的健康监测系统
CN105374355A (zh) * 2015-12-17 2016-03-02 厦门科牧智能技术有限公司 一种电子坐便器的语音控制、交互系统及方法和电子坐便器
CN105951955A (zh) * 2016-05-09 2016-09-21 中科院合肥技术创新工程院 一种基于智能马桶的尿液检测仪控制系统及其控制方法
CN106400918A (zh) * 2016-07-19 2017-02-15 顾华 智能健康随访坐便器
CN108360630A (zh) * 2018-01-29 2018-08-03 珠海格力电器股份有限公司 智能便器及电器系统

Family Cites Families (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH05192269A (ja) * 1992-01-21 1993-08-03 Matsushita Electric Ind Co Ltd トイレ装置
JPH085631A (ja) * 1994-06-20 1996-01-12 Hidetoshi Wakamatsu 尿検査用便器およびその便器を用いた尿成分データの検出装置
JP2000148985A (ja) 1998-11-17 2000-05-30 Hitachi Ltd 個人認証システム
JP3539371B2 (ja) * 2000-08-24 2004-07-07 東陶機器株式会社 健康管理用生体情報収集記録システム
CN100496367C (zh) * 2002-12-03 2009-06-10 松下电器产业株式会社 检测人体的马桶装置以及人体检测方法
DE202012104219U1 (de) * 2012-11-02 2012-12-14 Bing-Ru Wu Desodorisierungseinrichtung für das Klosett
JP2016001838A (ja) * 2014-06-12 2016-01-07 シャープ株式会社 制御システム、制御装置、家電、家電制御方法、およびプログラム
US9646216B2 (en) * 2014-12-08 2017-05-09 Intel Corporation Multiple user biometric for authentication to secured resources
CN105256871A (zh) * 2015-10-29 2016-01-20 林文友 智能马桶
JP6951057B2 (ja) * 2016-03-22 2021-10-20 エコナビスタ株式会社 プログラム、情報処理方法および情報処理装置
US11091903B2 (en) * 2016-07-07 2021-08-17 As America, Inc. Systems to automate adjustment of water volume release to a toilet bowl to correspond to bowl contents, toilets including the system and related methods
US10888278B2 (en) * 2016-07-20 2021-01-12 Hall Labs, Llc Method of monitoring health while using a toilet
CN106567435A (zh) * 2016-11-09 2017-04-19 中科院合肥技术创新工程院 一种智能健康马桶的智能检测系统及方法
US11287415B2 (en) * 2016-12-30 2022-03-29 Withings Urine home analyser
CN106502120A (zh) * 2017-01-05 2017-03-15 珠海市横琴麒翔科技有限公司 一种收集用户健康信息并显示的智能家电
US10542937B2 (en) * 2017-07-07 2020-01-28 Hall Labs Llc Intelligent health monitoring toilet system with wand sensors
US10887125B2 (en) * 2017-09-15 2021-01-05 Kohler Co. Bathroom speaker

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2001265822A (ja) * 2000-03-23 2001-09-28 Toto Ltd 生体情報管理システム
CN1804859A (zh) * 2005-01-11 2006-07-19 吴水超 一种高效的生物特征认证系统
CN201328144Y (zh) * 2008-09-28 2009-10-14 宇龙计算机通信科技(深圳)有限公司 基于气味识别的移动终端
CN104452926A (zh) * 2014-12-25 2015-03-25 电子科技大学 一种基于智能马桶的健康监测系统
CN105374355A (zh) * 2015-12-17 2016-03-02 厦门科牧智能技术有限公司 一种电子坐便器的语音控制、交互系统及方法和电子坐便器
CN105951955A (zh) * 2016-05-09 2016-09-21 中科院合肥技术创新工程院 一种基于智能马桶的尿液检测仪控制系统及其控制方法
CN106400918A (zh) * 2016-07-19 2017-02-15 顾华 智能健康随访坐便器
CN108360630A (zh) * 2018-01-29 2018-08-03 珠海格力电器股份有限公司 智能便器及电器系统

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110441504A (zh) * 2019-08-22 2019-11-12 王鹂辉 一种马桶用人体排泄物气味检测分析仪及分析系统
TWI711746B (zh) * 2019-11-07 2020-12-01 南開科技大學 整合物聯網的免治馬桶座之控制系統及其方法
CN112859652A (zh) * 2021-01-20 2021-05-28 青岛海尔空调器有限总公司 室内抽烟监控方法及监控装置
CN112859652B (zh) * 2021-01-20 2022-03-29 青岛海尔空调器有限总公司 室内抽烟监控方法及监控装置

Also Published As

Publication number Publication date
JP7091471B2 (ja) 2022-06-27
JP2021508797A (ja) 2021-03-11
US20210071401A1 (en) 2021-03-11
CN108360630B (zh) 2019-08-13
CN108360630A (zh) 2018-08-03
US11655622B2 (en) 2023-05-23

Similar Documents

Publication Publication Date Title
WO2019144658A1 (zh) 智能便器及电器系统
US10573336B2 (en) System and method for assessing expressive language development of a key child
CN110556129B (zh) 双模态情感识别模型训练方法及双模态情感识别方法
US10223934B2 (en) Systems and methods for expressive language, developmental disorder, and emotion assessment, and contextual feedback
CN102498485B (zh) 用于有表现力的语言、发育失调和情绪评估的系统和方法
JP6435257B2 (ja) 患者音を処理するための方法および装置
CN109273085B (zh) 病理呼吸音库的建立方法、呼吸疾病的检测系统及处理呼吸音的方法
US9355651B2 (en) System and method for expressive language, developmental disorder, and emotion assessment
CN108899037A (zh) 动物声纹特征提取方法、装置及电子设备
CN109637674B (zh) 自动获取健康医疗问题答案的方法、系统、介质和设备
CN108197115A (zh) 智能交互方法、装置、计算机设备和计算机可读存储介质
WO2019242155A1 (zh) 基于声音识别的健康管理方法、装置和计算机设备
CN109036395A (zh) 个性化的音箱控制方法、系统、智能音箱及存储介质
CN110085220A (zh) 智能交互装置
JP7390268B2 (ja) 認知機能予測装置、認知機能予測方法、プログラム及びシステム
KR20220048381A (ko) 말 장애 평가 장치, 방법 및 프로그램
Feng Toward knowledge-driven speech-based models of depression: Leveraging spectrotemporal variations in speech vowels
CN114830257A (zh) 咳嗽检测系统和方法
WO2015168274A1 (en) System and method for expressive language, developmental disorder, and emotion assessment
Richards et al. The LENATM automatic vocalization assessment
CN110427848B (zh) 一种精神分析系统
Ning et al. Emotion Recognition of Depressive Patients Based on General Speech Information
CN110338747B (zh) 视力检查的辅助方法、存储介质、智能终端及辅助装置
Bou Zeidan Automatic Speech Recognition to Maintain the Elderly’s Autonomy in Signal Processing and Al Approaches
Pompe et al. Exploring Shapely Values for Blood Glucose Level Prediction from Speech

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18901870

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2020554346

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18901870

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 18901870

Country of ref document: EP

Kind code of ref document: A1

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 24/11/2020)