CN111671408B - User drinking safety monitoring method, user terminal and server - Google Patents

User drinking safety monitoring method, user terminal and server Download PDF

Info

Publication number
CN111671408B
CN111671408B CN202010648618.4A CN202010648618A CN111671408B CN 111671408 B CN111671408 B CN 111671408B CN 202010648618 A CN202010648618 A CN 202010648618A CN 111671408 B CN111671408 B CN 111671408B
Authority
CN
China
Prior art keywords
data
user
alcohol
inputting
terminal
Prior art date
Legal status (The legal status 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 status listed.)
Active
Application number
CN202010648618.4A
Other languages
Chinese (zh)
Other versions
CN111671408A (en
Inventor
方滨
李冰玉
陈雨晞
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Individual
Original Assignee
Individual
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 Individual filed Critical Individual
Priority to CN202010648618.4A priority Critical patent/CN111671408B/en
Publication of CN111671408A publication Critical patent/CN111671408A/en
Application granted granted Critical
Publication of CN111671408B publication Critical patent/CN111671408B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
    • A61B5/0205—Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
    • A61B5/02055—Simultaneously evaluating both cardiovascular condition and temperature
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
    • A61B5/6801—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient specially adapted to be attached to or worn on the body surface
    • A61B5/6802—Sensor mounted on worn items
    • A61B5/681—Wristwatch-type devices
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7235—Details of waveform analysis
    • A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
    • A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/74—Details of notification to user or communication with user or patient ; user input means
    • A61B5/746—Alarms related to a physiological condition, e.g. details of setting alarm thresholds or avoiding false alarms
    • 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
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
    • A61B5/021—Measuring pressure in heart or blood vessels
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/145—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue
    • A61B5/14546—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue for measuring analytes not otherwise provided for, e.g. ions, cytochromes
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/145—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue
    • A61B5/1455—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue using optical sensors, e.g. spectral photometrical oximeters
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
    • Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation

Landscapes

  • Health & Medical Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Medical Informatics (AREA)
  • Public Health (AREA)
  • Physics & Mathematics (AREA)
  • Biomedical Technology (AREA)
  • General Health & Medical Sciences (AREA)
  • Pathology (AREA)
  • Molecular Biology (AREA)
  • Biophysics (AREA)
  • Veterinary Medicine (AREA)
  • Physiology (AREA)
  • Animal Behavior & Ethology (AREA)
  • Surgery (AREA)
  • Artificial Intelligence (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Data Mining & Analysis (AREA)
  • Cardiology (AREA)
  • Primary Health Care (AREA)
  • Mathematical Physics (AREA)
  • Epidemiology (AREA)
  • Databases & Information Systems (AREA)
  • Evolutionary Computation (AREA)
  • Theoretical Computer Science (AREA)
  • Computing Systems (AREA)
  • General Physics & Mathematics (AREA)
  • Psychiatry (AREA)
  • Signal Processing (AREA)
  • Computational Linguistics (AREA)
  • Pulmonology (AREA)
  • General Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Software Systems (AREA)
  • Fuzzy Systems (AREA)
  • Measuring And Recording Apparatus For Diagnosis (AREA)
  • Medical Treatment And Welfare Office Work (AREA)
  • Emergency Alarm Devices (AREA)
  • Alarm Systems (AREA)
  • Telephonic Communication Services (AREA)

Abstract

The invention discloses a user drinking safety monitoring method, a user terminal and a server, wherein the monitoring method applied to the user terminal comprises the following steps: collecting positioning information and various physiological characteristic data of a user in real time; comparing the physiological characteristic data acquired at the current moment with the data at the previous moment, and judging whether the front-rear difference value of each data is larger than a first preset threshold value or not; when the front-back difference value of at least one data is larger than a first preset threshold value, all the collected data are sent to a server for further analysis; the invention acquires the influence degree data of the alcohol in the user body on the user at the current moment sent by the server, and the influence degree data is acquired and primarily judged by the data of the user terminal, then the data is sent to the server terminal to analyze the influence level of the alcohol in the user body on the user at the current moment based on fitting of various data, and the analysis result is informed to the guardian terminal, so that the safety monitoring of the drinking process of the drinker is realized in real time.

Description

User drinking safety monitoring method, user terminal and server
Technical Field
The invention relates to the technical field of safety monitoring, in particular to a user drinking safety monitoring method, a user terminal and a server.
Background
Alcohol can excite or inhibit the central nervous system of human body, and can gradually decrease judgment ability and cognition ability of human body during drinking, thereby reducing touch ability, producing vision disorder, and causing fatigue. The influence of drinking amount on the central nervous system of human body is not only related to the alcohol content in blood, but also to sex, age, weight, drinking habit, drinking time, mood, etc. The judgment capability and the cognition capability of the human blood alcohol concentration reaching 50mg/100mL are seriously affected, and the normal function damage of the central nervous system reaching 400mg/100mL even for other people is not serious, and the blood alcohol concentration is 8 times different.
And when the central nervous system of the drinker is affected by drinking to a certain extent, the judgment capability and the cognitive ability are reduced, and the drinker cannot accurately recognize the mental state of the drinker on one hand and can not timely inform the relevant guardianship or friends on the other hand, so that the safety state of the drinker cannot be ensured.
Disclosure of Invention
Aiming at the problems existing in the prior art, the invention provides a user drinking safety monitoring method, a user terminal and a server, wherein the user terminal is used for collecting various physiological characteristic data of a user in the drinking process in real time, the physiological characteristic data are sent to the server after preliminary judgment is carried out, the influence degree of alcohol in the user at the current moment on the user is further analyzed, and the current state information of a drinker is sent to the monitoring terminal, so that the real-time safety monitoring on the drinking process of the drinker is realized, and the method is specific:
the invention provides a user drinking safety monitoring method, which is applied to a user terminal and comprises the following steps:
(11) Collecting positioning information and various physiological characteristic data of a user in real time, wherein the physiological characteristic data comprise infrared spectrum data of body temperature, blood pressure, pulse and skin tissues;
(12) Acquiring blood alcohol concentration through a preset analysis method based on infrared spectrum data;
(13) Comparing the physiological characteristic data acquired at the current moment with the data at the previous moment, and judging whether the front-rear difference value of each data is larger than a first preset threshold value or not;
(14) When the front-back difference value of at least one data is larger than a first preset threshold value, all the collected data are sent to a server for further analysis;
(15) And acquiring influence degree data and influence level alarm information of the alcohol in the user body on the user at the current moment sent by the server.
As a further optimization of the above scheme, the step (13) further comprises judging whether drunk driving and drunk driving standards are met based on the acquired blood alcohol concentration, and sending alarm prompt information to the guardian terminal when the corresponding standards are met.
The invention provides a user terminal for monitoring drinking safety of a user, which is an intelligent bracelet and comprises:
the data acquisition module is used for acquiring positioning information and various physiological characteristic data of a user in real time and comprises a GPS unit, a body temperature acquisition unit, a blood pressure acquisition unit, a pulse acquisition unit and an infrared spectrum data acquisition unit;
the infrared spectrum data analysis module is used for acquiring the blood alcohol concentration through a preset analysis method based on the acquired infrared spectrum data;
the data comparison judging module is used for comparing the data acquired at the current moment with the data at the previous moment, judging whether the difference value of each data is larger than a first preset threshold value, and transmitting the acquired data to the server when the difference value is larger than the first preset threshold value;
the first communication module is used for sending the acquired data to the server, receiving the influence degree data and the influence level alarm information of the alcohol in the user body on the user at the current moment sent by the server.
As a further optimization of the above scheme, the data comparison and judgment module is further used for judging whether drunk driving and drunk driving standards are met or not based on the analyzed blood alcohol concentration, and sending alarm prompt information to the guardian terminal when the corresponding standards are met.
The invention discloses a user drinking safety monitoring method, which is applied to a server side and comprises the following steps:
the method comprises the steps of receiving collected data of a user terminal, fitting various physiological characteristic data with user basic health information stored in a database, obtaining the influence degree of alcohol in a user body on the user at the current moment, and sending the obtained influence degree grade and influence grade alarm information to the user terminal;
judging whether the acquired influence degree level reaches a second preset value, and when the influence degree level reaches the second preset value, sending GPS positioning data of the user terminal and current drinking state data to the corresponding monitoring terminal.
As a further optimization of the above, the user basic health information includes gender, height, weight, age, and physical health status.
As a further optimization of the above scheme, the second preset value is set by the guardian terminal for different user terminals and sent to the server.
As a further optimization of the above scheme, the step of obtaining the influence degree of the alcohol in the user body on the user at the current moment specifically includes:
building a deep neural network model;
acquiring big data including blood pressure, body temperature, pulse, blood alcohol concentration, gender, age, weight and body health data of a human body, and marking the influence level of alcohol on a user on each training sample;
inputting sample data into a built network model for training, acquiring an output value through a forward propagation network, measuring the difference between the labeling data and the output data of the input samples based on a preset loss function, performing reverse propagation to adjust parameters of the network model, inputting the next sample until the difference value is smaller than a third threshold value, and stopping the training process;
inputting the test sample into a network, obtaining the accuracy of an output result, and completing a training process when the accuracy of the output of the neural network is greater than a fourth threshold;
and inputting the acquired data of the user terminal at the current moment and the user basic health information stored in the database into the deep neural network model, and outputting the influence level of the alcohol in the body on the user.
The invention provides a user drinking safety monitoring server, comprising:
the basic information storage module is used for storing basic health information and monitoring terminal information of a user;
the data primary analysis module is used for receiving the acquired data of the user terminal, fitting various physiological characteristic data with the user basic health information stored in the database, acquiring the influence degree of the alcohol in the user body on the user at the current moment, and sending the acquired influence grade and influence grade alarm information to the user terminal;
the data secondary analysis module is used for judging whether the acquired influence degree level reaches a second preset value, and sending GPS positioning data of the user terminal and current drinking state data to the corresponding monitoring terminal when the acquired influence degree level reaches the second preset value;
and the second communication module is used for carrying out data transmission with the user terminal and the monitoring terminal respectively.
As a further optimization of the above solution, the data primary analysis module includes:
the big data acquisition unit is used for acquiring big data comprising blood pressure, body temperature, pulse, blood alcohol concentration, gender, age, weight and body health data of a human body, and labeling the influence level of alcohol on a user for each training sample;
the deep neural network training unit is used for inputting sample data into the built network model for training, acquiring an output value through a forward propagation network, measuring the difference between the labeling data of the input sample and the output data based on a preset loss function, and performing backward propagation to adjust the parameters of the network model until the difference value is smaller than a third threshold value, and stopping the training process;
the model test unit is used for inputting the test sample into the network, obtaining the accuracy of the output result, and completing the training process when the accuracy of the output of the neural network is greater than a fourth threshold value;
and the real-time result analysis unit is used for inputting the acquired data of the user terminal at the current moment and the user basic health information stored in the database into the deep neural network model and outputting the influence level of the alcohol in the user body at the current moment to the user.
The user drinking safety monitoring method, the user terminal and the server have the following beneficial effects:
1. according to the invention, the wearing terminal monitors various physiological state data such as the body temperature, the blood pressure, the pulse and the blood alcohol concentration of the user in real time, and sends the acquired data to the server for analysis, and the server accurately analyzes the influence degree of the alcohol in the user on the central nervous system of the user at the current moment based on the combination of various acquired data and the basic information of the height, the weight, the age and the body health state of the user, and can remind and inform the terminal user of the current drinking safety state in real time, and the monitoring terminal is informed by the monitoring terminal when the influence degree reaches a certain degree, so that the monitoring terminal user monitors the user terminal and the safety state of a drinker is ensured.
2. According to the invention, the first data processing module is arranged on the wearing terminal, so that the collected data can be subjected to preliminary processing, the blood alcohol content data is obtained based on the infrared light data, whether the physiological state data of the user has variation is judged, the collected data is sent to the server for further analysis when the variation range exceeds a first preset threshold value, otherwise, the server is not uploaded, and the transmission of invalid data and the processing process of the server on the invalid data are reduced.
3. The first data processing module of the wearing terminal also can send alarm prompt information to the monitoring terminal when the acquired blood alcohol concentration data reach drunk driving and drunk driving standards, so that whether the central nervous system of a user wearing the terminal is affected or not reaches the degree of informing the monitoring terminal, the monitoring terminal is informed when the current alcohol content in the drinker affects the safe driving of the user terminal, and the monitoring terminal monitors the user wearing the terminal more comprehensively.
Drawings
FIG. 1 is a block diagram of an overall flow chart of a user drinking safety monitoring method applied to a user terminal of the invention;
FIG. 2 is a block diagram showing the overall construction of a user terminal for safety monitoring of drinkers in accordance with the present invention;
FIG. 3 is a block diagram showing the overall flow of a method for monitoring safety of drinking of a user applied to a server side;
FIG. 4 is a flowchart of a method for obtaining the influence degree of alcohol in a user body on the user at the current moment in FIG. 3;
fig. 5 is a block diagram showing the overall structure of a server for monitoring safety of drinkers according to the present invention.
Detailed Description
The technical scheme of the invention is further described below with reference to specific embodiments and drawings.
The invention realizes the real-time acquisition of physiological characteristic data in the drinking process of the user terminal, the analysis of the influence level of cognitive ability, judgment ability and the like of the user during drinking and timely informs the guardian to ensure the drinking safety of the user terminal user through the monitoring system formed among the user terminal, the monitoring terminal and the server.
The invention provides a user drinking safety monitoring method, which is applied to a user terminal and comprises the following steps:
(11) Collecting positioning information and various physiological characteristic data of a user in real time, wherein the physiological characteristic data comprise infrared spectrum data of body temperature, blood pressure, pulse and skin tissues;
in the step, the infrared spectrum data of the body temperature, the blood pressure, the pulse and the skin tissue can be respectively obtained through various sensors arranged in the user terminal, the user terminal is an intelligent bracelet and is worn on the wrist and other parts, and the infrared spectrum data are obtained through various sensors.
(12) Acquiring blood alcohol concentration through a preset analysis method based on infrared spectrum data;
specifically, the preset analysis method can establish a fitting model by using the collected spectrum data as an independent variable and the alcohol content as a dependent variable through a least square method, and specifically comprises the following steps:
carrying out wavelet analysis denoising and smooth processing on the collected infrared spectrum data;
calculating a correlation coefficient matrix of the independent variable by adopting a corrcoef function in MATLAB;
determining the optimal principal component number in least square modeling by adopting a leave-one-out cross validation method to obtain a least square fitting model, and finishing fitting until the Root Mean Square Error (RMSEC) of the alcohol content and the true value of the fitting result and the correlation coefficient R meet preset conditions based on the fitting model;
inputting infrared spectrum data for verifying the accuracy of the model into a fitting model, comparing the output blood alcohol concentration analysis result with an actual value, and completing the construction of the fitting model when a predicted Root Mean Square Error (RMSEP) of the two meets a preset value;
and analyzing the spectrum data acquired in real time based on the fitting model to acquire the relation of alcohol content.
(13) Comparing the physiological characteristic data acquired at the current moment with the data at the previous moment, and judging whether the front-rear difference value of each data is larger than a first preset threshold value or not; and when the front-back difference value, namely the change range exceeds a first preset threshold value, sending the acquired data to a server for further analysis, otherwise, not uploading the acquired data to the server, and reducing the transmission of invalid data and the processing process of the server on the invalid data.
(14) When the front-back difference value of at least one data is larger than a first preset threshold value, all the collected data are sent to a server for further analysis;
specifically, the data classification used for real-time collection of the terminal is respectively stored, when the data collected at the moment t reaches the data processing part after being transmitted, the data of the corresponding type at the moment t-1 is calculated with the difference value at the moment t, when the value difference value of at least one data at the two moments is larger than a first preset threshold value, the characteristic data is judged to be abnormal in change, the characteristic data is required to be input into a server to further judge the influence of the alcohol in the current user on the cognitive ability, judgment ability and the like of the human body, and if all the types of data do not change beyond the first preset threshold value, the functions of the central nerve of the user at the current moment are maintained in a normal state.
(15) And acquiring influence degree data and influence level alarm information of the alcohol in the user body on the user at the current moment sent by the server.
In the step, the user terminal is enabled to sense the degree of influence of alcohol in the drinking process in real time, when the user drinks the wine initially, the body temperature, the blood pressure, the pulse and the infrared spectrum data of skin tissues of the user are basically unchanged, and along with the continuation of the drinking process, the user terminal can know the state of the user terminal in real time through grade alarm information, and stop the drinking process in time, so that safety hazard caused by excessive drinking is avoided.
Considering that the influence degree of drinking amount on the central nervous system of a human body is not only related to the quantity of alcohol in blood, but also related to factors such as gender, age, weight, drinking habit, drinking time, mood and the like, the national standards for drunk driving and drunk driving are based on the measurement of the alcohol content in the body, and when the alcohol content of the blood of a driver per 100 milliliters is more than or equal to 20 milligrams and less than 80 milligrams are drunk driving; the drunk driving is carried out by the drunk driving method with the blood alcohol content of more than or equal to 80 mg per 100ml, so the method further comprises the steps of judging whether drunk driving and drunk driving standards are met based on the analyzed blood alcohol concentration, and sending alarm prompt information to a guardian terminal when the corresponding standards are met. Whether the influence degree of the alcohol on the user of the user terminal reaches the degree of informing the monitoring terminal or not can be caused, when the current alcohol content in the drinker influences the safe driving of the user terminal, the user terminal and the monitoring terminal can be timely passed through, and drunk driving is avoided.
Based on the above-mentioned user drinking safety monitoring method, the embodiment of the invention provides a user drinking safety monitoring user terminal, the user terminal is an intelligent bracelet, comprising:
the data acquisition module is used for acquiring positioning information and various physiological characteristic data of a user in real time and comprises a GPS unit, a body temperature acquisition unit, a blood pressure acquisition unit, a pulse acquisition unit and an infrared spectrum data acquisition unit;
the infrared spectrum data analysis unit is used for acquiring the blood alcohol concentration through a preset analysis method based on the acquired infrared spectrum data;
the data comparison judging module is used for comparing the data acquired at the current moment with the data at the previous moment, judging whether the difference value of each data is larger than a first preset threshold value, and transmitting the acquired data to the server when the difference value is larger than the first preset threshold value;
the first communication module is used for sending the acquired data to the server, receiving the influence degree data and the influence level alarm information of the alcohol in the user body on the user at the current moment sent by the server.
Preferably, the data comparison judging module is further used for judging whether drunk driving and drunk driving standards are met based on the analyzed blood alcohol concentration, sending alarm prompt information to the guardian terminal when the corresponding standards are met, and the first communication module is further used for realizing communication between the user terminal and the guardian terminal.
The embodiment of the invention also provides a user drinking safety monitoring method which is applied to the server side: the method comprises the following steps:
the method comprises the steps of receiving collected data of a user terminal, fitting various physiological characteristic data with user basic health information stored in a database, obtaining the influence degree of alcohol in a user body on the user at the current moment, and sending the obtained influence degree grade and influence grade alarm information to the user terminal;
specifically, the user basic health information includes gender, height, weight, age and health status, and further includes monitoring terminal information corresponding to the user terminal, where the monitoring terminal may be multiple, so as to ensure that the user terminal can contact at least one of its guardianship person, friends or family when drunk.
Fitting various physiological characteristic data and user basic health information stored in a database, obtaining the influence degree of alcohol in a user body on the user at the current moment, and adopting a training-completed deep neural network, wherein the training process of the deep neural network comprises the following steps:
building a deep neural network model;
acquiring big data including blood pressure, body temperature, pulse, blood alcohol concentration, gender, age, weight and body health data of a human body, and marking the influence level of alcohol on a user on each training sample;
inputting sample data into a built network model for training, acquiring an output value through a forward propagation network, measuring the difference between the labeling data and the output data of the input samples based on a preset loss function, performing reverse propagation to adjust parameters of the network model, inputting the next sample until the difference value is smaller than a third threshold value, and stopping the training process; the preset loss function adopts a cross entropy loss function, and an Adam optimization algorithm is adopted when the back propagation is carried out.
Inputting the test sample into a network, obtaining the accuracy of an output result, and completing a training process when the accuracy of the output of the neural network is greater than a fourth threshold;
and inputting the acquired data of the user terminal at the current moment and the user basic health information stored in the database into the deep neural network model, and outputting the influence level of the alcohol in the body on the user.
The deep neural network comprises an input layer, a hidden layer and an output layer, wherein the output layer comprises a preset regression function, after the acquired data of a user terminal at the current moment and the basic health information of a user stored in a database are input into the deep neural network model, the regression function outputs the probability that the drinking state at the current moment of the user belongs to each preset influence level, and the influence level with the maximum probability value is output as the influence level analysis result of the alcohol in the user body of the user terminal at the current moment on the cognition capability, the judgment capability and the like.
Specifically, the process from building to training completion of the deep neural network comprises the following steps:
firstly presetting super parameters of a deep neural network to obtain a built network model;
after the training process of the training sample and the testing process of the testing sample are sequentially carried out, judging whether the accuracy of the output result is larger than a fourth threshold value;
when the value is smaller than the fourth threshold value, adjusting the super-parameter combination of the network, and particularly, a grid search method based on cross verification: inputting the candidate values of the parameters to be searched into a searcher, traversing each combination of parameter values by the searcher, comparing the performance of the model under each parameter combination by using cross verification, and returning the parameter value of the model with the best performance;
and forming a network model based on the best super parameters, inputting a training sample into the network model, performing a training process, and judging whether the accuracy of the network model meets the preset conditions or not through the input of a test sample until the network model parameters with the accuracy meeting the preset conditions are obtained.
Judging whether the acquired influence degree level reaches a second preset value, and when the influence degree level reaches the second preset value, sending GPS positioning data of the user terminal and current drinking state data to the corresponding monitoring terminal.
The second preset value is set by the guardian terminal for different user terminals and is sent to the server, the guardian terminal flexibly sets the second preset value according to the specific physical condition of the corresponding user terminal, the guardian terminal monitors the requirements of the user wearing the terminal, and the like, and the guardian terminal reasonably sets the drinking safety state of the user terminal according to the specific physical and personal conditions of the user wearing the terminal.
In addition, the server in this embodiment also periodically performs a secondary statistical analysis based on the stored historical collected data of the user and the historical drinking state influence level analysis data, so as to obtain the overall situation and drinking trend data of the user terminal in a period, and provide the user of the user terminal and the monitoring terminal with reference to each other.
The embodiment of the invention also provides a user drinking safety monitoring server which is respectively communicated with the monitoring terminal and the user terminal, and specifically comprises the following steps:
the basic information storage module is used for storing basic health information and monitoring terminal information of a user;
the data primary analysis module is used for receiving the acquired data of the user terminal, fitting various physiological characteristic data with the user basic health information stored in the database, acquiring the influence degree of the alcohol in the user body on the user at the current moment, and sending the acquired influence grade and influence grade alarm information to the user terminal;
specifically, the module adopts a deep neural network model to carry out data analysis, and the module comprises:
the big data acquisition unit is used for acquiring big data comprising blood pressure, body temperature, pulse, blood alcohol concentration, gender, age, weight and body health data of a human body, and labeling the influence level of alcohol on a user for each training sample;
the deep neural network training unit is used for inputting sample data into the built network model for training, acquiring an output value through a forward propagation network, measuring the difference between the labeling data of the input sample and the output data based on a preset loss function, and performing backward propagation to adjust the parameters of the network model until the difference value is smaller than a third threshold value, and stopping the training process;
the model test unit is used for inputting the test sample into the network, obtaining the accuracy of the output result, and completing the training process when the accuracy of the output of the neural network is greater than a fourth threshold value;
and the real-time result analysis unit is used for inputting the acquired data of the user terminal at the current moment and the user basic health information stored in the database into the deep neural network model and outputting the influence level of the alcohol in the user body at the current moment to the user.
The data secondary analysis module is used for judging whether the acquired influence degree level reaches a second preset value, and sending GPS positioning data of the user terminal and current drinking state data to the corresponding monitoring terminal when the acquired influence degree level reaches the second preset value;
and the second communication module is used for carrying out data transmission with the user terminal and the monitoring terminal respectively.
The present invention is not limited to the above-described specific embodiments, and various modifications may be made by those skilled in the art without inventive effort from the above-described concepts, and are within the scope of the present invention.

Claims (9)

1. A user drinking safety monitoring method is applied to a user terminal and is characterized in that: the method comprises the following steps:
(11) Collecting positioning information and various physiological characteristic data of a user in real time, wherein the physiological characteristic data comprise infrared spectrum data of body temperature, blood pressure, pulse and skin tissues;
(12) Acquiring blood alcohol concentration through a preset analysis method based on infrared spectrum data;
(13) Comparing the physiological characteristic data acquired at the current moment with the data at the previous moment, and judging whether the front-rear difference value of each data is larger than a first preset threshold value or not;
(14) When the front-back difference value of at least one data is larger than a first preset threshold value, all the collected data are sent to a server for further analysis;
(15) Acquiring influence degree data of alcohol in a user body on the user at the current moment sent by a server and influence grade alarm information;
the method for obtaining the influence degree data of the alcohol in the user body on the user at the current moment by the server comprises the following steps:
building a deep neural network model;
acquiring big data including blood pressure, body temperature, pulse, blood alcohol concentration, gender, age, weight and body health data of a human body, and marking the influence level of alcohol on a user on each training sample;
inputting sample data into a built network model for training, acquiring an output value through a forward propagation network, measuring the difference between the labeling data and the output data of the input samples based on a preset loss function, performing reverse propagation to adjust parameters of the network model, inputting the next sample until the difference value is smaller than a third threshold value, and stopping the training process;
inputting the test sample into a network, obtaining the accuracy of an output result, and completing a training process when the accuracy of the output of the neural network is greater than a fourth threshold;
and inputting the acquired data of the user terminal at the current moment and the user basic health information stored in the database into the deep neural network model, and outputting the influence level of the alcohol in the body on the user.
2. The method for monitoring safety of drinking of a user according to claim 1, wherein: and (13) judging whether drunk driving and drunk driving standards are met based on the acquired blood alcohol concentration, and sending alarm prompt information to the guardian terminal when the corresponding standards are met.
3. A user terminal for monitoring drinking safety of a user is characterized in that: the user terminal is an intelligent bracelet, and comprises:
the data acquisition module is used for acquiring positioning information and various physiological characteristic data of a user in real time and comprises a GPS unit, a body temperature acquisition unit, a blood pressure acquisition unit, a pulse acquisition unit and an infrared spectrum data acquisition unit;
the infrared spectrum data analysis module is used for acquiring the blood alcohol concentration through a preset analysis method based on the acquired infrared spectrum data;
the data comparison judging module is used for comparing the data acquired at the current moment with the data at the previous moment, judging whether the difference value of each data is larger than a first preset threshold value, and transmitting the acquired data to the server when the difference value is larger than the first preset threshold value;
the first communication module is used for sending the acquired data to the server, receiving the influence degree data and the influence level alarm information of the alcohol in the user body on the user at the current moment sent by the server;
the method for obtaining the influence degree data of the alcohol in the user body on the user at the current moment by the server comprises the following steps:
building a deep neural network model;
acquiring big data including blood pressure, body temperature, pulse, blood alcohol concentration, gender, age, weight and body health data of a human body, and marking the influence level of alcohol on a user on each training sample;
inputting sample data into a built network model for training, acquiring an output value through a forward propagation network, measuring the difference between the labeling data and the output data of the input samples based on a preset loss function, performing reverse propagation to adjust parameters of the network model, inputting the next sample until the difference value is smaller than a third threshold value, and stopping the training process;
inputting the test sample into a network, obtaining the accuracy of an output result, and completing a training process when the accuracy of the output of the neural network is greater than a fourth threshold;
and inputting the acquired data of the user terminal at the current moment and the user basic health information stored in the database into the deep neural network model, and outputting the influence level of the alcohol in the body on the user.
4. A user terminal for safety supervision of drinking according to claim 3, wherein: the data comparison judging module is also used for judging whether drunk driving and drunk driving standards are met or not based on the analyzed blood alcohol concentration, and sending alarm prompt information to the guardian terminal when the corresponding standards are met.
5. A user drinking safety monitoring method is applied to a server side and is characterized in that: the method comprises the following steps:
the method comprises the steps of receiving collected data of a user terminal, fitting various physiological characteristic data with user basic health information stored in a database, obtaining the influence degree of alcohol in a user body on the user at the current moment, and sending the obtained influence degree grade and influence grade alarm information to the user terminal;
judging whether the acquired influence degree level reaches a second preset value, and when the influence degree level reaches the second preset value, transmitting GPS positioning data of the user terminal and current drinking state data to the corresponding monitoring terminal;
the method for acquiring the influence degree data of the alcohol in the user body on the user at the current moment comprises the following steps:
building a deep neural network model;
acquiring big data including blood pressure, body temperature, pulse, blood alcohol concentration, gender, age, weight and body health data of a human body, and marking the influence level of alcohol on a user on each training sample;
inputting sample data into a built network model for training, acquiring an output value through a forward propagation network, measuring the difference between the labeling data and the output data of the input samples based on a preset loss function, performing reverse propagation to adjust parameters of the network model, inputting the next sample until the difference value is smaller than a third threshold value, and stopping the training process;
inputting the test sample into a network, obtaining the accuracy of an output result, and completing a training process when the accuracy of the output of the neural network is greater than a fourth threshold;
and inputting the acquired data of the user terminal at the current moment and the user basic health information stored in the database into the deep neural network model, and outputting the influence level of the alcohol in the body on the user.
6. The method for monitoring safety of drinking of a user according to claim 5, wherein: the user basic health information includes gender, height, weight, age, and physical health status.
7. The method for monitoring safety of drinking of a user according to claim 5, wherein: and the second preset value is set by the guardian terminal for different user terminals and is sent to the server.
8. A user drinking safety monitoring server is characterized in that: comprising the following steps:
the basic information storage module is used for storing basic health information and monitoring terminal information of a user;
the data primary analysis module is used for receiving the acquired data of the user terminal, fitting various physiological characteristic data with the user basic health information stored in the database, acquiring the influence degree of the alcohol in the user body on the user at the current moment, and sending the acquired influence grade and influence grade alarm information to the user terminal;
the data secondary analysis module is used for judging whether the acquired influence degree level reaches a second preset value, and sending GPS positioning data of the user terminal and current drinking state data to the corresponding monitoring terminal when the acquired influence degree level reaches the second preset value;
the second communication module is used for carrying out data transmission with the user terminal and the monitoring terminal respectively;
the method for acquiring the influence degree data of the alcohol in the user body on the user at the current moment comprises the following steps:
building a deep neural network model;
acquiring big data including blood pressure, body temperature, pulse, blood alcohol concentration, gender, age, weight and body health data of a human body, and marking the influence level of alcohol on a user on each training sample;
inputting sample data into a built network model for training, acquiring an output value through a forward propagation network, measuring the difference between the labeling data and the output data of the input samples based on a preset loss function, performing reverse propagation to adjust parameters of the network model, inputting the next sample until the difference value is smaller than a third threshold value, and stopping the training process;
inputting the test sample into a network, obtaining the accuracy of an output result, and completing a training process when the accuracy of the output of the neural network is greater than a fourth threshold;
and inputting the acquired data of the user terminal at the current moment and the user basic health information stored in the database into the deep neural network model, and outputting the influence level of the alcohol in the body on the user.
9. The user drinking safety monitoring server of claim 8, wherein: the data primary analysis module comprises:
the big data acquisition unit is used for acquiring big data comprising blood pressure, body temperature, pulse, blood alcohol concentration, gender, age, weight and body health data of a human body, and labeling the influence level of alcohol on a user for each training sample;
the deep neural network training unit is used for inputting sample data into the built network model for training, acquiring an output value through a forward propagation network, measuring the difference between the labeling data of the input sample and the output data based on a preset loss function, and performing backward propagation to adjust the parameters of the network model until the difference value is smaller than a third threshold value, and stopping the training process;
the model test unit is used for inputting the test sample into the network, obtaining the accuracy of the output result, and completing the training process when the accuracy of the output of the neural network is greater than a fourth threshold value;
and the real-time result analysis unit is used for inputting the acquired data of the user terminal at the current moment and the user basic health information stored in the database into the deep neural network model and outputting the influence level of the alcohol in the user body at the current moment to the user.
CN202010648618.4A 2020-07-07 2020-07-07 User drinking safety monitoring method, user terminal and server Active CN111671408B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010648618.4A CN111671408B (en) 2020-07-07 2020-07-07 User drinking safety monitoring method, user terminal and server

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010648618.4A CN111671408B (en) 2020-07-07 2020-07-07 User drinking safety monitoring method, user terminal and server

Publications (2)

Publication Number Publication Date
CN111671408A CN111671408A (en) 2020-09-18
CN111671408B true CN111671408B (en) 2023-05-30

Family

ID=72457344

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010648618.4A Active CN111671408B (en) 2020-07-07 2020-07-07 User drinking safety monitoring method, user terminal and server

Country Status (1)

Country Link
CN (1) CN111671408B (en)

Families Citing this family (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115151182B (en) * 2020-10-10 2023-11-14 豪夫迈·罗氏有限公司 Method and system for diagnostic analysis
CN112315465B (en) * 2020-10-23 2022-12-09 歌尔智能科技有限公司 Alcohol detection ring and alcohol detection method
CN113069093B (en) * 2021-03-18 2023-01-10 北京雪扬科技有限公司 Non-sensory drinking verification method and system based on wearable equipment
CN114190916B (en) * 2021-12-07 2023-05-23 河南省儿童医院郑州儿童医院 Fabric sensor-based child respiration monitoring method and system
CN115035680A (en) * 2022-04-22 2022-09-09 深圳市华盛昌科技实业股份有限公司 Alcohol early warning method
CN115024690A (en) * 2022-04-24 2022-09-09 深圳市华盛昌科技实业股份有限公司 Alcohol metabolism detection method, computer device and storage medium
CN115051354A (en) * 2022-05-19 2022-09-13 深圳市创诺新电子科技有限公司 Household power utilization system management method
CN116543903B (en) * 2023-04-28 2024-02-27 广州逆熵电子科技有限公司 Alcohol concentration prediction method and alcohol concentration prediction device
CN117481615A (en) * 2023-12-27 2024-02-02 网思科技股份有限公司 Drunk recognition method and device, storage medium and computer equipment

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2007295946A (en) * 2006-04-27 2007-11-15 Konica Minolta Holdings Inc Detection system for alcohol influence and method
CN101808273A (en) * 2010-03-18 2010-08-18 华为终端有限公司 Intoxication prompting method, system, mobile terminal and server
CN106510726A (en) * 2016-11-08 2017-03-22 惠州Tcl移动通信有限公司 Wearable device, intelligent alcohol detection method and intelligent alcohol detection system
CN109091126A (en) * 2018-09-14 2018-12-28 李思楠 A kind of human body physiological state differentiation method for visualizing and equipment based on multisensor

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2018204914A1 (en) * 2017-05-05 2018-11-08 Balajadia Leah Fe Personal healthcare device

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2007295946A (en) * 2006-04-27 2007-11-15 Konica Minolta Holdings Inc Detection system for alcohol influence and method
CN101808273A (en) * 2010-03-18 2010-08-18 华为终端有限公司 Intoxication prompting method, system, mobile terminal and server
CN106510726A (en) * 2016-11-08 2017-03-22 惠州Tcl移动通信有限公司 Wearable device, intelligent alcohol detection method and intelligent alcohol detection system
CN109091126A (en) * 2018-09-14 2018-12-28 李思楠 A kind of human body physiological state differentiation method for visualizing and equipment based on multisensor

Also Published As

Publication number Publication date
CN111671408A (en) 2020-09-18

Similar Documents

Publication Publication Date Title
CN111671408B (en) User drinking safety monitoring method, user terminal and server
US20230270345A1 (en) Seizure detection methods, apparatus, and systems using an autoregression algorithm
CN102098955B (en) Method and device for the detection of microsleep events
US20190295729A1 (en) Universal non-invasive blood glucose estimation method based on time series analysis
RU2757048C1 (en) Method and system for assessing the health of the human body based on the large-volume sleep data
CN109953763A (en) A kind of vehicle carried driving behavioral value early warning system and method based on deep learning
Chen et al. Non‐invasive detection of alcohol concentration based on photoplethysmogram signals
CN115910346A (en) Monitoring and early warning system and method for diabetic patient
CN107913075B (en) Mental stress assessment device based on multiple parameters and assessment method thereof
CN109620263B (en) Physical sign safety analysis method for post workers in enterprises and public institutions
CN109300546A (en) A kind of individual sub-health state appraisal procedure based on big data and artificial intelligence
CN111317458A (en) Blood pressure detection system based on deep learning
Byrnes et al. On Using Drivers' Eyes to Predict Accident-Causing Drowsiness Levels
WO2023207678A1 (en) Alcohol metabolism detection method, computer device, and storage medium
CN117423455A (en) User health management system and method based on data analysis
Ma et al. Research on drowsy-driving monitoring and warning system based on multi-feature comprehensive evaluation
CN116978510A (en) Nursing grading evaluation system for home cerebral apoplexy patient
Zhendong et al. Mobile Healthcare System for Driver Based on Drowsy Detection Using EEG Signal Analysis.
CN114224359A (en) Electroencephalogram fatigue index determination method for high-speed rail dispatcher
JPH09294729A (en) Drinking monitoring device
CN110801205A (en) Human body data monitoring method based on Internet technology
CN107007292A (en) Method for knowing fatigue
CN109589100A (en) Medical examination device and health evaluating method based on topsis algorithm
CN115429262B (en) Lactic acid threshold prediction method, device, equipment and medium for motion data analysis
CN113069093B (en) Non-sensory drinking verification method and system based on wearable equipment

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant