CN115064244A - Method and system for reminding medicine taking for needleless injection based on voice recognition - Google Patents

Method and system for reminding medicine taking for needleless injection based on voice recognition Download PDF

Info

Publication number
CN115064244A
CN115064244A CN202210981481.3A CN202210981481A CN115064244A CN 115064244 A CN115064244 A CN 115064244A CN 202210981481 A CN202210981481 A CN 202210981481A CN 115064244 A CN115064244 A CN 115064244A
Authority
CN
China
Prior art keywords
medication
injection
reminding
needleless
user
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.)
Pending
Application number
CN202210981481.3A
Other languages
Chinese (zh)
Inventor
陈达权
肖晓
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.)
Shenzhen Fenda Intelligent Technology Co ltd
Original Assignee
Shenzhen Fenda Intelligent Technology Co ltd
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 Shenzhen Fenda Intelligent Technology Co ltd filed Critical Shenzhen Fenda Intelligent Technology Co ltd
Priority to CN202210981481.3A priority Critical patent/CN115064244A/en
Publication of CN115064244A publication Critical patent/CN115064244A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • 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
    • G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
    • G16H20/10—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to drugs or medications, e.g. for ensuring correct administration to patients
    • G16H20/17—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to drugs or medications, e.g. for ensuring correct administration to patients delivered via infusion or injection
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
    • A61M5/00—Devices for bringing media into the body in a subcutaneous, intra-vascular or intramuscular way; Accessories therefor, e.g. filling or cleaning devices, arm-rests
    • A61M5/178—Syringes
    • A61M5/30—Syringes for injection by jet action, without needle, e.g. for use with replaceable ampoules or carpules
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
    • A61M5/00—Devices for bringing media into the body in a subcutaneous, intra-vascular or intramuscular way; Accessories therefor, e.g. filling or cleaning devices, arm-rests
    • A61M5/178—Syringes
    • A61M5/31—Details
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01H—MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC OR INFRASONIC WAVES
    • G01H17/00—Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves, not provided for in the preceding groups
    • 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
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
    • G08B21/18—Status alarms
    • G08B21/24—Reminder alarms, e.g. anti-loss alarms
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
    • G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
    • G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
    • A61M2205/00—General characteristics of the apparatus
    • A61M2205/50—General characteristics of the apparatus with microprocessors or computers
    • A61M2205/502—User interfaces, e.g. screens or keyboards
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
    • A61M2205/00—General characteristics of the apparatus
    • A61M2205/50—General characteristics of the apparatus with microprocessors or computers
    • A61M2205/52—General characteristics of the apparatus with microprocessors or computers with memories providing a history of measured variating parameters of apparatus or patient
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61M—DEVICES FOR INTRODUCING MEDIA INTO, OR ONTO, THE BODY; DEVICES FOR TRANSDUCING BODY MEDIA OR FOR TAKING MEDIA FROM THE BODY; DEVICES FOR PRODUCING OR ENDING SLEEP OR STUPOR
    • A61M2205/00—General characteristics of the apparatus
    • A61M2205/58—Means for facilitating use, e.g. by people with impaired vision
    • A61M2205/581—Means for facilitating use, e.g. by people with impaired vision by audible feedback

Abstract

The application discloses a method and a system for reminding a patient of taking medicine for needleless injection based on voice recognition, which relate to the needleless injection technology, and comprise the following steps: a needle-free injection fitting for performing a needle-free injection, the needle-free injection fitting comprising an acoustic sensor for detecting a fitting status; an injection event detection module for detecting an injection event based on ambient sound detected by a sound sensor of the needleless injection accessory; and the medicine taking reminding terminal is used for storing the medicine taking information and generating the medicine taking reminding information aiming at the user according to the injection event and the medicine taking information detected by the injection event detection module. By the scheme, the injection condition of the user can be automatically recorded, the user does not need to carry out manual grade, and automatic reminding can be realized.

Description

Method and system for reminding medication for needleless injection based on voice recognition
Technical Field
The application relates to a needleless injection technology, in particular to a medicine-taking reminding method and a medicine-taking reminding system for needleless injection based on voice recognition.
Background
Needleless injection is also called as "gentle injection", and when medicine is injected, liquid medicine permeates skin at a high speed and diffuses into body tissues in a mode of superfine, high-speed and straight-line ejection of high-pressure jet flow by using instant high pressure generated by a pressure source without using a needle, and is gradually applied to clinic as a medical technology and a new injection technology.
For patients needing to inject hormones such as insulin or growth hormone, the injection frequency is high, the treatment time is long, when the needle-free injection is used, because the depth of the injected drugs entering a human body is limited, the injury to subcutaneous tissues is extremely small, and nerve endings are stimulated little, compared with the needle injection, the needle-free injection has no obvious pricking feeling, and the problems of fear, pain, needle breakage and the like caused by long-term injection are overcome easily, so that the compliance is greatly improved; in addition, the onset time when using needleless injection is fast at least 15 minutes compared with having the needle, to the injection of insulin, can save the dosage, can make the effect of medicine more steady simultaneously, reduce the risk of diabetic complication, and to the injection of auxin, have the periodic observation statistical result to show, have the needle to inject and increase 1.7 centimetres in a month, needleless injection increases 2.4 centimetres in a month, has shown the advantage of needleless injection in the aspect of macromolecule medicine injection. It is expected that, with the continuous and intensive research on medicine, needleless injection will become the mainstream of medicine injection in the future.
Most of the existing medicine-taking reminding related products realize the reminding function based on alarm clock setting, are complex to operate, lack of humanization and low in intelligentization level, have high possibility of wrong reminding and missed reminding due to unreasonable alarm clock reminding set by human factors, and particularly for old people with high medicine-taking frequency, the alarm clock reminding logic relation required to be set is complex, and the possibility of the wrong reminding and the missed reminding is greatly increased; in addition, special products for needle-free injection medication reminders are more rare in the market.
Disclosure of Invention
The present invention is directed to solving at least one of the problems of the prior art. Therefore, the invention provides a method and a system for reminding a user of needleless injection medication based on voice recognition, so as to automatically remind the user of injection.
The embodiment of the application provides a method for reminding a patient to take medicine for needleless injection based on voice recognition, which comprises the following steps:
acquiring medication information;
calculating the time of next medication of the user according to the medication information and the last medication time of the user;
if the time for next medication is reached, reminding the user to take the medication through the medication reminding terminal;
when the needleless injection accessory is installed on a needleless injector, acquiring an environmental sound signal periodically through a sound sensor, and detecting an injection event according to the environmental sound signal;
and recording the medication time of the user according to the timestamp corresponding to the injection event.
In some embodiments, periodically acquiring an ambient sound signal by a sound sensor and detecting an injection event according to the ambient sound signal specifically includes:
acquiring an ambient sound signal;
setting frame length and frame shift, and performing framing processing on the sound signal;
windowing the rated signal after framing processing;
performing fast Fourier transform on the windowed signal to obtain an energy spectrum of the sound signal;
calculating a mel energy spectrum of the energy spectrum;
and inputting the Mel energy spectrum into a needleless injection voice recognition model to obtain a recognition result.
In some embodiments, periodically acquiring an ambient sound signal by a sound sensor and detecting an injection event according to the ambient sound signal specifically includes:
obtaining an ambient sound signal
Figure DEST_PATH_IMAGE002
To the signal
Figure DEST_PATH_IMAGE003
Pre-emphasis processing is carried out to obtain the sound signal with improved signal-to-noise ratio
Figure DEST_PATH_IMAGE005
；
Setting frame length
Figure DEST_PATH_IMAGE007
And frame shifting
Figure DEST_PATH_IMAGE009
For sound signals
Figure DEST_PATH_IMAGE010
Performing frame division processing to obtain
Figure DEST_PATH_IMAGE012
And to the signal
Figure DEST_PATH_IMAGE013
Performing windowing to obtain signal
Figure DEST_PATH_IMAGE015
Wherein, T is a period,
Figure DEST_PATH_IMAGE017
is the sampling rate;
to the signal
Figure DEST_PATH_IMAGE018
Performing fast Fourier transform to obtain an ambient sound signal
Figure 100002_DEST_PATH_IMAGE019
Energy spectrum of
Figure 100002_DEST_PATH_IMAGE021
And setting the number of Mel filters
Figure 100002_DEST_PATH_IMAGE023
Lowest frequency of ambient sound
Figure 100002_DEST_PATH_IMAGE025
And maximum frequency of ambient sound
Figure DEST_PATH_IMAGE027
Building a Mel Filter set to calculate the ambient sound signal
Figure 100002_DEST_PATH_IMAGE028
Mel energy spectrum of
Figure DEST_PATH_IMAGE030
；
Mapping said mel-energy spectrum
Figure 100002_DEST_PATH_IMAGE031
Inputting the needleless injection sound identification model to obtain an identification result
Figure DEST_PATH_IMAGE033
Wherein the recognition result
Figure 529034DEST_PATH_IMAGE033
The value range is {0,1}, and 0 represents the environmental sound signal
Figure DEST_PATH_IMAGE034
Wherein no needleless injection sound is present, 1 represents an ambient sound signal
Figure 570808DEST_PATH_IMAGE034
Where a needle-free injection sound is present.
In some embodiments, the needleless injection sound recognition model comprises an input layer, a hidden layer and an output layer, the number of channels of the input layer is 1, and the input size and the Mel energy spectrum are integrated into a Mel energy spectrum
Figure DEST_PATH_IMAGE035
The size of the output layer is 1, the number of channels of the output layer is 1, the size of the output layer is 1, and the output layer and the last hidden layer are connected in a full connection mode.
In some embodiments, the needleless injection sound recognition model is obtained by:
s101, initializing a needleless injection sound recognition model; the method comprises the following steps: creating a deep convolutional network for identifying the needleless injection sound, and initializing the deep convolutional network;
s102, acquiring duration through microphone moduleTTaking the internal environment sound signal as the data of one sample in the data set, marking whether the environment sound signal has the needleless injection sound as the label of the sample, if the environment sound signal has the needleless injection sound, marking the environment sound signal as 1, otherwise marking the environment sound signal as 0, and repeating the step
Figure 100002_DEST_PATH_IMAGE037
To obtain
Figure 304540DEST_PATH_IMAGE037
The calibrated samples form a data setDWherein
Figure DEST_PATH_IMAGE038
Is a settable positive integer;
s103, from the data setDIn selection
Figure 100002_DEST_PATH_IMAGE040
The calibrated samples form a training setPAnd collecting the dataDWherein the remaining calibrated samples constitute a test setQWherein
Figure DEST_PATH_IMAGE041
Is a settable positive integer;
s104, from the training setPIn the random selection
Figure DEST_PATH_IMAGE043
1 branch training sample consisting of the calibrated samples is input into the deep convolutional network, and corresponding network output is calculated according to a forward propagation formula; calculating the error between the network output of the calibrated sample after being input into the deep convolutional network and the label of the calibrated sample according to an error formula, and updating all weights and thresholds of the deep full convolutional network according to a back propagation algorithm based on the error, wherein the weights and the thresholds are all calculated according to the back propagation algorithm
Figure DEST_PATH_IMAGE044
Is a settable positive integer;
s105, repeating S104
Figure DEST_PATH_IMAGE046
Next, from the test setQIn the random selection
Figure DEST_PATH_IMAGE048
The calibrated samples form 1 branch test sample and are input into the deep convolution network, and corresponding network output is calculated according to a forward propagation formula, wherein
Figure DEST_PATH_IMAGE049
And
Figure DEST_PATH_IMAGE050
the error between the network output of the calibrated test sample after being input into the deep convolutional network and the label of the calibrated test sample can be calculated according to the error formulaMIf, ifMThe target loss function threshold ml of the network is larger than, and the repetition times of the step are smaller than the maximum training times of the network
Figure DEST_PATH_IMAGE052
Then, jumping to S104; otherwise, jumping to S106;
s106, completing the training of the deep convolutional network, and selecting the trained deep convolutional network as the needleless injection sound recognition model.
In some embodiments, the needleless injection accessory is a circular cylinder, and the surface of the circular cylinder is provided with a clamping groove for fixing with the needleless injector and a detection switch for detecting the installation state of the needleless injection accessory and the needleless injector, and the detection switch is closed when the needleless injection accessory and the needleless injector are installed so as to be communicated with power supply of the needleless injection accessory.
In some embodiments, the medication reminding terminal comprises a display module and a sound module, and is used for playing reminding information in an image or sound mode.
In some embodiments, the calculating the time of the next medication of the user according to the medication information and the last medication time of the user specifically includes:
s201, acquiring medication according to medication information of a user, wherein the dosage of each medication and the interval time required for each medication are long
Figure DEST_PATH_IMAGE054
Time period for prohibiting drug administration
Figure DEST_PATH_IMAGE056
And inquiring the last time of taking medicine
Figure DEST_PATH_IMAGE058
；
S202, obtaining the timestamp of the current moment from the medication reminding terminal
Figure DEST_PATH_IMAGE060
；
S203, if
Figure DEST_PATH_IMAGE062
Then, then
Figure DEST_PATH_IMAGE064
And if not, the step (B),
Figure DEST_PATH_IMAGE066
；
s204, the next medication timetConversion to 24 hours system time
Figure DEST_PATH_IMAGE068
；
S205, if
Figure DEST_PATH_IMAGE070
Then, then
Figure DEST_PATH_IMAGE072
And jumping to S204, otherwise, jumping to S206;
s206, outputting the next medication timet。
In another aspect, an embodiment of the present application provides a method for reminding a patient of needleless injection based on voice recognition, including the following steps:
the method comprises the following steps: the medicine taking reminding terminal acquires user medicine taking information of a user through the input moduleDAnd medication prohibition period
Figure DEST_PATH_IMAGE074
And storing the time stamp into a data storage module B, and setting the system time stamp at the moment as the first time medication time of the usert0；
Step two: the medication reminding terminal uses the medicine according to the user medication information stored in the data storage module BDThe time of the last administration is calculated by the calculating module Bt；
Step three: the medication reminding terminal is used for reminding the user of the next medication time if the system time reaches the next medication timetPrompting the user to take medicine in time through the display module and the sound module, or continuing to wait;
step four: mounting a needle-free injector fitting to a needle-free injector;
step five: if the needleless injector accessory does not work normally, jumping to the step two, otherwise, enabling the needleless injector accessory to start the needleless injector accessory through the Bluetooth module ASTo said applicationThe medicine reminding terminal comprises a Bluetooth module B receiving signalSThereafter, activating the injection event detection module;
step six: if the injection event detection module is activated, the calculation module B acquires the period through the microphone moduleTInternal environment sound signal
Figure DEST_PATH_IMAGE076
And applying the ambient sound signal
Figure DEST_PATH_IMAGE077
Inputting the injection event detection module, wherein the sampling rate of the microphone module is
Figure DEST_PATH_IMAGE079
(ii) a If the needleless injector accessory is detached from the needleless injector, the signal of closing the needleless injector accessory is sent through the Bluetooth module A before the normally open switch is switched from the closed state to the open state
Figure DEST_PATH_IMAGE081
Sending the information to the medication reminding terminal;
step seven: if the Bluetooth module B of the medication reminding terminal receives the signal
Figure 493557DEST_PATH_IMAGE081
Jumping to the second step, otherwise, jumping to the eighth step;
step eight: if the injection event detection module does not detect the injection event, skipping to the step six, otherwise, taking the system time stamp at the moment as the medication time of the user at the timet1And recording the data to a data storage module B, converting the injection event detection module from an activated state to a closed state, and jumping to the step two.
In another aspect, embodiments of the present application provide a needle-free injection system, including:
a memory for storing a program;
a processor for loading the program to perform the method.
Thereby the sound sensor of this application embodiment needleless injection accessory gathers the detection of environment sound realization injection incident, then generates the warning of using medicine to the user based on injection incident and the information module of using medicine, can indicate the user in time to use medicine on the one hand, need not the user and manually carry out the record when using medicine simultaneously, convenience of customers' use more.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a block diagram of a needle-free injection system according to an embodiment of the present application;
FIG. 2 is a flow chart of a method for detecting a needle-free injection event by ambient sound according to an embodiment of the present application;
FIG. 3 is another flow chart for detecting a needle-free injection event by ambient sound provided by an embodiment of the present application;
FIG. 4 is a flow chart illustrating the training of a needleless injection voice recognition model according to an embodiment of the present application;
FIG. 5 is a flow chart providing medication time determination according to an embodiment of the present application;
fig. 6 is a flowchart of another method for reminding a patient to take a medicine for a needleless injection based on voice recognition according to an embodiment of the present application.
Detailed Description
In order to make the purpose, technical solutions and advantages of the present application clearer, the technical solutions of the present application will be clearly and completely described below through embodiments with reference to the accompanying drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
In the description of the present invention, the meaning of a plurality is one or more, the meaning of a plurality is two or more, and the above, below, exceeding, etc. are understood as excluding the present numbers, and the above, below, within, etc. are understood as including the present numbers. If there is a description of first and second for the purpose of distinguishing technical features only, this is not to be understood as indicating or implying a relative importance or implicitly indicating the number of technical features indicated or implicitly indicating the precedence of technical features indicated.
In the description of the present invention, unless otherwise explicitly defined, terms such as set, etc. should be broadly construed, and those skilled in the art can reasonably determine the specific meanings of the above terms in the present invention in combination with the detailed contents of the technical solutions.
In the description of the present invention, reference to the description of the terms "one embodiment," "some embodiments," "an illustrative embodiment," "an example," "a specific example," or "some examples," etc., means that a particular feature or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
Referring to fig. 1, the embodiment of the present application discloses a system for needle-free injection, which mainly implements a method for reminding a patient to take medicine for needle-free injection based on voice recognition: acquiring medication information; calculating the time of next medication of the user according to the medication information and the last medication time of the user; if the time for next medication is reached, reminding the user to take the medication through the medication reminding terminal; when the needleless injection accessory is installed on the needleless injector, acquiring an environmental sound signal periodically through a sound sensor, and detecting an injection event according to the environmental sound signal; and recording the medication time of the user according to the timestamp corresponding to the injection event.
The system comprises:
a needle-free injection fitting for performing a needle-free injection, the needle-free injection fitting comprising an acoustic sensor for detecting a state of the fitting. The needleless injection accessory comprises a normally open switch, a Bluetooth module A, a calculation module A, a data storage module A, a power supply module A and a capacitive sensor (optional); the needle-free injection accessory is a circular cylinder, a clamping groove used for being fixed with the needle-free injector and a detection switch used for detecting the installation state of the needle-free injection accessory and the needle-free injector are formed in the surface of the circular cylinder, and the detection switch is closed when the needle-free injection accessory and the needle-free injector are installed so as to be communicated with power supply of the needle-free injection accessory. The capacitance sensor is arranged on the bottom surface of the circular cylinder, which is used for contacting the skin, and is used for detecting whether the needleless injection accessory contacts the skin. The sound detection may be performed upon detecting that the capacitive sensor is in contact with the skin, thereby reducing the time for sound detection.
Referring to fig. 2, an injection event detection module for detecting an injection event based on ambient sound detected by the sound sensor of the needleless injection accessory. Detecting an injection event, including in particular:
and S11, acquiring the environmental sound signal. The ambient sound signal is acquired by a sound sensor, and it is mainly desired to acquire recorded data at the time of injection.
And S12, setting frame length and frame shift, and performing framing processing on the sound signal.
And S13, performing windowing processing on the rated signal after the framing processing. Because the length of the model is fixed, and the length of the speech recognized in the detection process may not be fixed, the frame length and the frame shift need to be set for the sliding process.
And S14, carrying out fast Fourier transform on the windowed signal to obtain an energy spectrum of the sound signal.
And S15, calculating a Mel energy spectrum of the energy spectrum. Processing the signals into mel-energy spectra can facilitate analysis of the characteristic signals.
And S16, inputting the Mel energy map into a needleless injection voice recognition model to obtain a recognition result. The needleless injection sound recognition model is a trained deep neural network model, and is mainly trained to recognize characteristic signals in a Mel energy map so as to judge whether an injection event occurs.
And the medicine taking reminding terminal is used for storing the medicine taking information and generating the medicine taking reminding information aiming at the user according to the injection event and the medicine taking information detected by the injection event detection module. The medicine-taking reminding terminal comprises an input module, a display module, a sound module, a microphone module, a Bluetooth module B, a calculation module B, a data storage module B and a power supply module B. And the display module and the sound module are used for playing the reminding information in an image or sound mode.
Referring to fig. 3, in some embodiments, in parallel with the arrangement of fig. 2, the detecting an injection event based on the ambient sound detected by the sound sensor of the needleless injection accessory specifically includes:
s21, acquiring the environment sound signal
Figure 839088DEST_PATH_IMAGE034
To the signal
Figure DEST_PATH_IMAGE082
Pre-emphasis processing is carried out to obtain the sound signal with improved signal-to-noise ratio
Figure DEST_PATH_IMAGE083
；
S22, setting the frame length
Figure DEST_PATH_IMAGE084
And frame shifting
Figure DEST_PATH_IMAGE085
For sound signals
Figure DEST_PATH_IMAGE086
Performing frame division processing to obtain
Figure DEST_PATH_IMAGE087
And to the signal
Figure 878195DEST_PATH_IMAGE086
Performing windowing to obtain signal
Figure DEST_PATH_IMAGE088
(ii) a Wherein the content of the first and second substances,Tin order to be a period of time,
Figure DEST_PATH_IMAGE089
is the sampling rate.
S23, pair signal
Figure DEST_PATH_IMAGE090
Performing fast Fourier transform to obtain an ambient sound signal
Figure DEST_PATH_IMAGE091
Energy spectrum of
Figure 161540DEST_PATH_IMAGE021
And setting the number of Mel filters
Figure DEST_PATH_IMAGE092
Lowest frequency of ambient sound
Figure DEST_PATH_IMAGE093
And maximum frequency of ambient sound
Figure DEST_PATH_IMAGE094
Building a Mel Filter set to calculate the ambient sound signal
Figure DEST_PATH_IMAGE095
Mel energy map
Figure DEST_PATH_IMAGE096
；
S24, mapping the Mel energy map
Figure DEST_PATH_IMAGE097
Inputting the needleless injection sound identification model to obtain an identification result
Figure DEST_PATH_IMAGE099
Wherein the recognition result
Figure DEST_PATH_IMAGE100
The value range is {0,1}, 0 represents the environment sound signal
Figure 701718DEST_PATH_IMAGE095
Wherein no needleless injection sound is present, 1 represents an ambient sound signal
Figure 403220DEST_PATH_IMAGE082
Where a needle-free injection sound is present.
It can be understood that, by performing the transformation in the above manner, on one hand, the signal can be characterized without being limited by the length of the audio data, and in addition, the interference factors in the environmental sound can be filtered by the mel filter bank. In addition, by identifying the acoustic features by the model to identify the occurrence between needle-free injections, the time occurrence can be automatically determined so that the user does not have to manually register.
Referring to fig. 4, in some embodiments, the needleless injection sound recognition model is obtained by:
s101, initializing a needleless injection voice recognition model. The method comprises the following steps: creating a deep convolutional network for identifying the needleless injection sound, and initializing the deep convolutional network; the needleless injection sound identification model comprises an input layer, a hidden layer and an output layer, the number of channels of the input layer is 1, and the input size and the Mel energy spectrum are
Figure DEST_PATH_IMAGE102
The size of the output layer is 1, the number of channels of the output layer is 1, the size of the output layer is 1, and the output layer and the last hidden layer are connected in a full connection mode. In addition, all weights and thresholds of the deep convolutional network are initialized by Gaussian distribution random numbers, the learning rate is initialized to le, the target Loss (arithmetic function) threshold of the network is set to ml, and the maximum training times of the network is set to ml
Figure DEST_PATH_IMAGE104
The optimizer algorithm selects a Bayes regularization algorithm or a momentum gradient descent algorithm or Adam and the like, and the Loss function selects Bintake Cross Engine, Focal local or MSE, etc., wherein, le, ml,
Figure 255638DEST_PATH_IMAGE104
can be customized according to the actual application needs of users.
S102, acquiring duration through microphone moduleTTaking the internal environment sound signal as the data of one sample in the data set, marking whether the environment sound signal has the needleless injection sound as the label of the sample, if the environment sound signal has the needleless injection sound, marking the environment sound signal as 1, otherwise marking the environment sound signal as 0, and repeating the step
Figure DEST_PATH_IMAGE106
To obtain
Figure DEST_PATH_IMAGE107
The calibrated samples form a data setDWherein
Figure DEST_PATH_IMAGE108
Is a settable positive integer;
s103, from the data setDIn selection
Figure DEST_PATH_IMAGE110
The calibrated samples form a training setPAnd collecting the dataDWherein the remaining calibrated samples constitute a test setQWherein
Figure DEST_PATH_IMAGE111
Is a settable positive integer;
s104, from the training setPIn the random selection
Figure DEST_PATH_IMAGE113
1 branch training sample consisting of the calibrated samples is input into the deep convolutional network, and corresponding network output is calculated according to a forward propagation formula; calculating the error between the network output of the calibrated sample after being input into the deep convolutional network and the label of the calibrated sample according to an error formula, and performing back propagation on the basis of the errorThe algorithm updates all the weight values and threshold values of the deep full convolution network, wherein
Figure DEST_PATH_IMAGE114
Is a settable positive integer;
s105, repeating S104
Figure DEST_PATH_IMAGE116
Next, from the test setQIn the random selection
Figure DEST_PATH_IMAGE118
The calibrated samples form 1 branch test sample input to the deep convolutional network, and the corresponding network output is calculated according to a forward propagation formula, wherein
Figure 915027DEST_PATH_IMAGE116
And
Figure DEST_PATH_IMAGE119
the error between the network output of the calibrated test sample after being input into the deep convolutional network and the label of the calibrated test sample can be calculated according to the error formulaMIf, ifMThe target loss function threshold ml of the network is larger than, and the repetition times of the step are smaller than the maximum training times of the network
Figure DEST_PATH_IMAGE121
Then, jumping to S104; otherwise, jumping to S106;
s106, completing the training of the deep convolutional network, and selecting the trained deep convolutional network as the needleless injection sound recognition model.
It can be understood that the model can be trained by collecting data samples in combination with the sound sensor of the hardware, and the model is trained in such a way, so that the recognition result of the model is more suitable for the hardware environment.
Referring to fig. 5, in some embodiments, the generating medication reminding information for a user according to the injection event and the medication information detected by the injection event detection module specifically includes:
s201, acquiring medication according to medication information of a user, wherein the dosage of each medication and the interval time required for each medication are long
Figure DEST_PATH_IMAGE122
Time period for prohibiting drug administration
Figure DEST_PATH_IMAGE123
And inquiring the last time of taking medicine
Figure DEST_PATH_IMAGE124
. It will be appreciated that by setting the medication prohibition period
Figure DEST_PATH_IMAGE125
The user may be reminded to take medication at the wrong time, or at a rest time.
S202, obtaining the timestamp of the current moment from the medication reminding terminal
Figure DEST_PATH_IMAGE126
。
S203, if
Figure DEST_PATH_IMAGE127
Then, then
Figure DEST_PATH_IMAGE128
And if not, the step (B),
Figure DEST_PATH_IMAGE129
. In the step, if the medication time is not reached, the reminding time is determined according to the time difference, and if the medication time is exceeded, the reminding is delayed for a time after the reminding.
S204, the next medication timetConversion to 24 hours system time
Figure DEST_PATH_IMAGE130
. The step converts the time into a 24-hour system, so that the operation is convenient.
S205, if
Figure DEST_PATH_IMAGE131
Then, then
Figure DEST_PATH_IMAGE132
And jumping to S204, otherwise, jumping to S206; in this step, if the measured time is within the medication prohibition period, a delay is made for a time.
S206, outputting the next medication timet。
Referring to fig. 6, the present application provides a method for reminding a user of needleless injection based on voice recognition, which includes the following steps:
a1, acquiring medication information;
a2, detecting an injection event according to the environment sound detected by the sound sensor of the needleless injection accessory;
and A3, generating medication reminding information aiming at the user according to the injection event and the medication information detected by the injection event detection module.
In some embodiments, detecting an injection event based on ambient sound detected by a sound sensor of a needleless injection accessory includes:
s21, acquiring the environment sound signal
Figure 947312DEST_PATH_IMAGE034
To the signal
Figure 736277DEST_PATH_IMAGE028
Pre-emphasis processing is carried out to obtain the sound signal with improved signal-to-noise ratio
Figure DEST_PATH_IMAGE133
；
S22, setting the frame length
Figure 320448DEST_PATH_IMAGE084
Frame shift
Figure DEST_PATH_IMAGE134
For sound signals
Figure DEST_PATH_IMAGE135
Performing frame division processing to obtain
Figure DEST_PATH_IMAGE136
And to the signal
Figure 217866DEST_PATH_IMAGE013
Performing windowing to obtain signal
Figure 820886DEST_PATH_IMAGE088
；
S23, pair signal
Figure 496980DEST_PATH_IMAGE018
Performing fast Fourier transform to obtain an ambient sound signal
Figure DEST_PATH_IMAGE137
Energy spectrum of
Figure 894463DEST_PATH_IMAGE021
And setting the number of Mel filters
Figure DEST_PATH_IMAGE138
Lowest frequency of ambient sound
Figure 420122DEST_PATH_IMAGE025
Maximum frequency of ambient sound
Figure 30095DEST_PATH_IMAGE094
Building a Mel Filter set to calculate the ambient sound signal
Figure 59231DEST_PATH_IMAGE003
Mel energy spectrum of
Figure DEST_PATH_IMAGE139
；
S24, mapping the Mel energy map
Figure 539801DEST_PATH_IMAGE031
Inputting the needleless injection sound identification model to obtain an identification result
Figure DEST_PATH_IMAGE140
Wherein the recognition result
Figure 552757DEST_PATH_IMAGE140
The value range is {0,1}, and 0 represents the environmental sound signal
Figure 966421DEST_PATH_IMAGE019
Wherein no needleless injection sound is present, 1 represents an ambient sound signal
Figure 351528DEST_PATH_IMAGE003
Where a needle-free injection sound is present.
The embodiment discloses a needleless injection oriented medicine taking reminding method based on data fusion, which comprises the following steps of:
the method comprises the following steps: the medicine taking reminding terminal acquires user medicine taking information of a user through the input moduleDAnd medication prohibition period
Figure DEST_PATH_IMAGE142
And storing the time stamp into a data storage module B, and setting the system time stamp at the moment as the first time medication time of the usert0；
Step two: the medication reminding terminal uses the medicine according to the user medication information stored in the data storage module BDThe time of the last administration is calculated by the calculating module Bt；
Step three: the medication reminding terminal is used for reminding the user of the next medication time if the system time reaches the next medication timetPrompting the user to take medicine in time through the display module and the sound module, or continuing to wait;
step four: a user mounting a needleless syringe accessory to a needleless syringe;
step five: if the needleless injector accessory cannot work normally, jumping to the step two, otherwise, enabling the needleless injector accessory to be free of the operation through the Bluetooth module ASignal for opening of needle syringe accessorySThe Bluetooth module B of the medication reminding terminal receives the signalSThereafter, activating the injection event detection module;
step six: if the injection event detection module is activated, the calculation module B acquires the period through the microphone moduleTInternal environment sound signal
Figure DEST_PATH_IMAGE144
And applying the ambient sound signal
Figure DEST_PATH_IMAGE145
Inputting the injection event detection module, wherein the sampling rate of the microphone module isf(ii) a If the needleless injector accessory is detached from the needleless injector, the signal of closing the needleless injector accessory is sent through the Bluetooth module A before the normally open switch is switched from the closed state to the open state
Figure DEST_PATH_IMAGE147
Sending the information to the medication reminding terminal;
step seven: if the Bluetooth module B of the medication reminding terminal receives the signal
Figure 838616DEST_PATH_IMAGE147
Jumping to the second step, otherwise, jumping to the eighth step;
step eight: if the injection event detection module does not detect the injection event, skipping to the step six, otherwise, taking the system time stamp at the moment as the medication time of the user at the timet1And recording the data to a data storage module B, converting the injection event detection module from an activated state to a closed state, and jumping to the step two.
The medication reminding terminal can be mounted on other equipment such as a smart phone or a tablet.
The integrated units described in this application may be stored in a computer-readable storage medium if they are implemented in the form of software functional units and sold or used as separate products. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present application and the technical principles employed. It will be understood by those skilled in the art that the present application is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the application. Therefore, although the present application has been described in more detail with reference to the above embodiments, the present application is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present application, and the scope of the present application is determined by the scope of the appended claims.

Claims (10)

1. A method for reminding a patient of taking medicine for needleless injection based on voice recognition is characterized by comprising the following steps:
acquiring medication information;
calculating the time of next medication of the user according to the medication information and the last medication time of the user;
if the time for next medication is reached, reminding the user to take the medication through the medication reminding terminal;
when the needleless injection accessory is installed on a needleless injector, acquiring an environmental sound signal periodically through a sound sensor, and detecting an injection event according to the environmental sound signal;
and recording the medication time of the user according to the timestamp corresponding to the injection event.
2. The method for reminding a user of needleless injection based on voice recognition of claim 1, wherein the sound sensor periodically obtains an environmental sound signal and detects an injection event according to the environmental sound signal, and the method comprises the following steps:
acquiring an ambient sound signal;
setting frame length and frame shift, and performing frame division processing on the sound signal;
windowing the rated signal after framing processing;
performing fast Fourier transform on the windowed signal to obtain an energy spectrum of the sound signal;
calculating a mel energy spectrum of the energy spectrum;
and inputting the Mel energy spectrum into a needleless injection voice recognition model to obtain a recognition result.
3. The method for reminding a user of needleless injection based on voice recognition of claim 1, wherein the sound sensor periodically obtains an environmental sound signal and detects an injection event according to the environmental sound signal, and the method comprises the following steps:
obtaining an ambient sound signal
Figure DEST_PATH_IMAGE001
To the signal
Figure 136685DEST_PATH_IMAGE002
Pre-emphasis processing is carried out to obtain the sound signal with improved signal-to-noise ratio
Figure 623161DEST_PATH_IMAGE003
；
Setting frame length
Figure DEST_PATH_IMAGE004
And frame shifting
Figure 852148DEST_PATH_IMAGE005
For sound signals
Figure DEST_PATH_IMAGE006
Performing frame division processing to obtain
Figure 525706DEST_PATH_IMAGE007
And for the signal
Figure DEST_PATH_IMAGE008
Performing windowing to obtain signal
Figure 396710DEST_PATH_IMAGE009
Wherein, T is a period,
Figure 534430DEST_PATH_IMAGE010
is the sampling rate;
to the signal
Figure DEST_PATH_IMAGE011
Performing fast Fourier transform to obtain an ambient sound signal
Figure 417809DEST_PATH_IMAGE002
Energy spectrum of
Figure 375400DEST_PATH_IMAGE012
And setting the number of Mel filters
Figure 581254DEST_PATH_IMAGE013
Lowest frequency of ambient sound
Figure DEST_PATH_IMAGE014
And maximum frequency of ambient sound
Figure 980005DEST_PATH_IMAGE015
Building a Mel Filter set to calculate the ambient sound signal
Figure DEST_PATH_IMAGE016
Mel energy spectrum of
Figure 550795DEST_PATH_IMAGE017
；
Mapping the mel-energy spectrum
Figure 995683DEST_PATH_IMAGE018
Inputting the needleless injection sound identification model to obtain an identification result
Figure DEST_PATH_IMAGE019
Wherein the recognition result
Figure 942910DEST_PATH_IMAGE020
The value range is {0,1}, and 0 represents the environmental sound signal
Figure DEST_PATH_IMAGE021
Wherein no needleless injection sound is present, 1 represents an ambient sound signal
Figure 255555DEST_PATH_IMAGE022
Where a needle-free injection sound is present.
4. The method for reminding a user of taking a medicine for needle-free injection based on voice recognition as claimed in claim 3, wherein the voice recognition model for needle-free injection comprises an input layer, a hidden layer and an output layer, the number of channels of the input layer is 1, and the input size and Mel energy spectrum are
Figure DEST_PATH_IMAGE023
The size of the output layer is 1, the number of channels of the output layer is 1, the size of the output layer is 1, and the output layer and the last hidden layer are connected in a full connection mode.
5. The method for reminding a user of injecting a medicine without needle based on voice recognition as claimed in claim 4, wherein the voice recognition model for needle-free injection is obtained by the following steps:
s101, creating a deep convolution network for identifying needleless injection sound, and initializing the deep convolution network;
s102, acquiring duration through microphone moduleTTaking the internal environment sound signal as the data of one sample in the data set, marking whether the environment sound signal has the needleless injection sound as the label of the sample, if the environment sound signal has the needleless injection sound, marking the environment sound signal as 1, otherwise marking the environment sound signal as 0, and repeating the step
Figure 262826DEST_PATH_IMAGE024
To obtain
Figure DEST_PATH_IMAGE025
The calibrated samples form a data setDWherein
Figure 663851DEST_PATH_IMAGE025
Is a settable positive integer;
s103, from the data setDIn selection
Figure 211507DEST_PATH_IMAGE026
The calibrated samples form a training setPAnd collecting the dataDWherein the remaining calibrated samples constitute a test setQWherein
Figure 912747DEST_PATH_IMAGE026
Is a settable positive integer;
s104, from the training setPIn the random selection
Figure 887656DEST_PATH_IMAGE027
1 branch training sample consisting of the calibrated samples is input into the deep convolutional network, and corresponding network output is calculated according to a forward propagation formula; calculating the calibrated sample input to the depth according to an error formulaAnd updating all weights and thresholds of the deep full convolution network according to a back propagation algorithm based on the error between the network output after the degree convolution network and the calibrated sample label, wherein the weights and the thresholds are all updated according to the back propagation algorithm
Figure DEST_PATH_IMAGE028
Is a settable positive integer;
s105, repeating S104
Figure 510398DEST_PATH_IMAGE029
Next, from the test setQIn the random selection
Figure 861745DEST_PATH_IMAGE030
The calibrated samples form 1 branch test sample and are input into the deep convolution network, and corresponding network output is calculated according to a forward propagation formula, wherein
Figure DEST_PATH_IMAGE031
And
Figure 889263DEST_PATH_IMAGE032
is a settable positive integer, and calculates the error between the network output of the calibrated test sample after being input into the deep convolutional network and the label of the calibrated test sample according to an error formulaMIf, ifMThe target loss function threshold ml of the network is larger than, and the repetition times of the step are smaller than the maximum training times of the network
Figure 35073DEST_PATH_IMAGE033
Then, jumping to S104; otherwise, jumping to S106;
s106, completing the training of the deep convolutional network, and selecting the trained deep convolutional network as the needleless injection sound recognition model.
6. The method for reminding the administration of a medicine to a needleless injector based on the voice recognition of claim 1, wherein the needleless injector is a circular cylinder, a slot for fixing with the needleless injector and a detection switch for detecting the installation state of the needleless injector and the needleless injector are arranged on the surface of the circular cylinder, and the detection switch is closed when the needleless injector and the needleless injector are installed so as to communicate the power supply of the needleless injector.
7. The needle-free injection-oriented medication reminding method based on voice recognition as claimed in claim 6, wherein the medication reminding terminal comprises a display module and a sound module, and is used for playing reminding information in an image or voice mode.
8. The method for reminding a user of taking medicine for needle-free injection based on voice recognition as claimed in claim 7, wherein the step of calculating the time of next medicine taking of the user according to the medicine taking information and the last medicine taking time of the user comprises the following specific steps:
s201, acquiring medication according to medication information of a user, wherein the medication dosage is one time, and the interval time of each medication is required
Figure 941850DEST_PATH_IMAGE034
Time period for prohibiting drug administration
Figure 565729DEST_PATH_IMAGE035
And inquiring the last time of taking medicine
Figure 241561DEST_PATH_IMAGE036
；
S202, obtaining the timestamp of the current moment from the medication reminding terminal
Figure DEST_PATH_IMAGE037
；
S203, if
Figure 27114DEST_PATH_IMAGE038
Then, then
Figure 421187DEST_PATH_IMAGE039
And if not, the step (B),
Figure DEST_PATH_IMAGE040
；
s204, the next medication timetConversion to 24 hours system time
Figure 317598DEST_PATH_IMAGE041
；
S205, if
Figure DEST_PATH_IMAGE042
Then, then
Figure 785620DEST_PATH_IMAGE043
And jumping to S204, otherwise, jumping to S206;
s206, outputting the next medication timet。
9. A method for reminding a patient of taking medicine for needleless injection based on voice recognition is characterized by comprising the following steps:
the method comprises the following steps: the medicine taking reminding terminal acquires user medicine taking information of a user through the input moduleDAnd medication prohibition period
Figure 270303DEST_PATH_IMAGE044
And storing the time stamp into a data storage module B, and setting the system time stamp at the moment as the first time medication time of the usert0；
Step two: the medication reminding terminal uses the medicine according to the user medication information stored in the data storage module BDThe time of the last administration is calculated by the calculating module Bt；
Step three: the medication reminding terminal is used for reminding the user of the next medication time if the system time reaches the next medication timetPrompting the user to take medicine in time through the display module and the sound module, or continuing to wait;
step four: mounting a needleless syringe accessory to a needleless syringe;
step five: if the needleless injector accessory does not work normally, jumping to the step two, otherwise, enabling the needleless injector accessory to start the needleless injector accessory through the Bluetooth module ASThe Bluetooth module B of the medication reminding terminal receives the signalSThereafter, activating the injection event detection module;
step six: if the injection event detection module is activated, the calculation module B acquires the period through the microphone moduleTInternal environment sound signal
Figure DEST_PATH_IMAGE045
And applying the ambient sound signal
Figure 27038DEST_PATH_IMAGE046
Inputting the injection event detection module, wherein the sampling rate of the microphone module is
Figure DEST_PATH_IMAGE047
(ii) a If the accessory of the needleless injector is detached from the needleless injector, the signal for closing the accessory of the needleless injector is sent through the Bluetooth module A before the normally open switch is switched from the closed state to the open state
Figure 727141DEST_PATH_IMAGE048
Sending the information to the medication reminding terminal;
step seven: if the Bluetooth module B of the medication reminding terminal receives the signal
Figure 377565DEST_PATH_IMAGE049
Jumping to the second step, otherwise, jumping to the eighth step;
step eight: if the injection event detection module does not detect the injection event, skipping to the step six, otherwise, taking the system time stamp at the moment as the medication time of the user at the timet1And recording the information to a data storage module B to inject the injectionAnd the event detection module is switched from the activated state to the closed state and jumps to the step two.
10. A needle-free injection system, comprising:
a memory for storing a program;
a processor for loading the program to perform the method of any one of claims 1 to 9.
CN202210981481.3A 2022-08-16 2022-08-16 Method and system for reminding medicine taking for needleless injection based on voice recognition Pending CN115064244A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210981481.3A CN115064244A (en) 2022-08-16 2022-08-16 Method and system for reminding medicine taking for needleless injection based on voice recognition

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210981481.3A CN115064244A (en) 2022-08-16 2022-08-16 Method and system for reminding medicine taking for needleless injection based on voice recognition

Publications (1)

Publication Number Publication Date
CN115064244A true CN115064244A (en) 2022-09-16

Family

ID=83207274

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210981481.3A Pending CN115064244A (en) 2022-08-16 2022-08-16 Method and system for reminding medicine taking for needleless injection based on voice recognition

Country Status (1)

Country Link
CN (1) CN115064244A (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105597197A (en) * 2016-01-26 2016-05-25 宁波睿诺电子科技有限公司 Additional electronic monitoring and recording device of injection pen
US20180147362A1 (en) * 2015-05-29 2018-05-31 Insulcloud, S.L. Monitoring device for drug application with a drug pen, with logging, communication and alarms
CN109074822A (en) * 2017-10-24 2018-12-21 深圳和而泰智能控制股份有限公司 Specific sound recognition methods, equipment and storage medium
CN113350629A (en) * 2021-02-24 2021-09-07 吉林大学第一医院 Chronic disease medication reminding and recording device

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20180147362A1 (en) * 2015-05-29 2018-05-31 Insulcloud, S.L. Monitoring device for drug application with a drug pen, with logging, communication and alarms
CN105597197A (en) * 2016-01-26 2016-05-25 宁波睿诺电子科技有限公司 Additional electronic monitoring and recording device of injection pen
CN109074822A (en) * 2017-10-24 2018-12-21 深圳和而泰智能控制股份有限公司 Specific sound recognition methods, equipment and storage medium
CN113350629A (en) * 2021-02-24 2021-09-07 吉林大学第一医院 Chronic disease medication reminding and recording device

Similar Documents

Publication Publication Date Title
CN110251105B (en) Noninvasive blood pressure measuring method, device, equipment and system
Choi et al. Preverbal infants discover statistical word patterns at similar rates as adults: Evidence from neural entrainment
CN101785702B (en) Health information system, method, corresponding device, equipment and reagent carrier
AU2016291569B2 (en) System, device and method of dynamic glucose profile response to physiological parameters
CN104470430A (en) Method and system to indicate hyperglycemia or hypoglycemia for people with diabetes
CN107260187A (en) A kind of method and its system that habituation drug craving is induced in reality environment
EP2124736A1 (en) Electrophysiological analysis system
CN110141249B (en) Non-invasive blood glucose monitoring method, system, equipment and medium based on PPG signal
JP6508938B2 (en) INFORMATION PROCESSING DEVICE, ACTION SUPPORT METHOD, AND PROGRAM
EP3305186A1 (en) Method and system for monitoring stress in a user
Xie et al. Stability and plasticity in neural encoding of linguistically relevant pitch patterns
Ferretti et al. How discourse constraints influence neurolinguistic mechanisms during the comprehension of proverbs
Dickson et al. When 2× 4 is meaningful: The N400 and P300 reveal operand format effects in multiplication verification
CN115064244A (en) Method and system for reminding medicine taking for needleless injection based on voice recognition
KR102383512B1 (en) Glucose measuring apparatus and measuring system using the same
KR20110077317A (en) Emotion reasoning apparatus of mobile terminal using physiological signal
CN204318765U (en) A kind of infrared spectrum technology non-invasive blood-sugar detecting instrument
Hagiwara et al. Validity of the mind monitoring system as a mental health indicator
CN105662433A (en) Blood sugar information acquiring and processing system convenient and rapid to use
Rohaut et al. What are the boundaries of unconscious semantic cognition?
CN115458121A (en) Needleless injection oriented medicine taking reminding method and system based on data fusion
KR101901388B1 (en) Apparatus and method of guiding activity of taking medicine for compliance improvement of activity of taking medicine
RU2661724C1 (en) Device for automatic identification and correction of patients with diabetes mellitus
FR2473874A1 (en) METHOD AND APPARATUS FOR MONITORING AND STORING CARDIAC ACTIVITY SIGNALS WITH A DATA PROCESSOR
CN108294765A (en) Diabetic population assisting in diagnosis and treatment device and its control method

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
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20220916