阅读说明：本技术 一种用于真空保温杯的饮水监测方法 (Drinking water monitoring method for vacuum heat-preservation cup ) 是由 赵坤 余艳玮 于 2020-12-31 设计创作，主要内容包括：一种用于真空保温杯的饮水监测方法,包括以下步骤：(一)当所述杯盖状态感应器感知水杯被开启、且所述水接触感应器感知有水流过的时候,开始饮水量监测；(二)然后将上述加速度传感器的数据集按时间序列作为输入数据,交给神经网络模型进行学习,得到本次饮水量数据；(三)循环上述步骤一和二,即可得到一段时间内的饮水数据,该饮水数据包括各天内的饮水次数、每次的饮水量、总饮水量、饮水时间点。本发明可以不破坏保温杯内真空保温层的结构,在实现饮水监测的同时,可以真正实现长时间的保温。(A drinking water monitoring method for a vacuum thermos cup comprises the following steps: when the cup cover state sensor senses that a water cup is opened and the water contact sensor senses that water flows through, the water intake monitoring is started; secondly, taking the data set of the acceleration sensor as input data according to a time sequence, and submitting the input data to a neural network model for learning to obtain the water intake data; and (III) circulating the first step and the second step to obtain drinking water data in a period of time, wherein the drinking water data comprises drinking times, drinking water amount each time, total drinking water amount and drinking water time points in each day. The vacuum heat-preservation cup can not damage the structure of the vacuum heat-preservation layer in the vacuum cup, and can really realize long-time heat preservation while realizing drinking water monitoring.)

1. A drinking water monitoring method for a vacuum thermos cup is characterized by comprising the following steps:

a cup cover state sensor for sensing whether the cup cover is opened or not is arranged at the cup cover of the vacuum cup, an acceleration sensor is arranged in the cup cover, and a water contact sensor for sensing whether water flows through is arranged at the cup mouth of the cup cover;

when the cup cover state sensor senses that a water cup is opened and the water contact sensor senses that water flows through, water intake monitoring is started, data of the acceleration sensor are acquired at intervals, and water intake detection is finished once when the cup cover state sensor senses that the water cup is closed or the water contact sensor senses that no water flows through;

secondly, taking the data set of the acceleration sensor as input data according to a time sequence, and submitting the input data to a neural network model for learning to obtain the water intake data; the method for calculating the water intake data by the neural network model comprises the following steps:

generating a characteristic vector through An encoder by using acceleration sensor data A1, A2 and A3.. An corresponding to t1, t2 and t3... tn time by using a time-series codec model, and then generating the residual water volume and the water intake volume at the beginning of the drinking water through a decoder;

and (III) circulating the first step and the second step to obtain drinking water data in a period of time, wherein the drinking water data comprises drinking times, drinking water amount each time, residual water amount after drinking water each time, total drinking water amount and drinking water time points in each day.

2. The drinking water monitoring method for a vacuum thermos cup according to claim 1, characterized in that: before the step (one), the following steps are carried out:

step one, setting identification information of each vacuum cup;

and step two, collecting the personal information of the user of the vacuum heat-preservation cup, and correspondingly binding the personal information with the identification information of the vacuum heat-preservation cup.

3. The drinking water monitoring method for a vacuum thermos cup according to claim 2, characterized in that: the personal information of the user includes name, sex, age, weight and physical health information.

4. The drinking water monitoring method for a vacuum thermos cup according to claim 1, characterized in that: in the step (I), when the cup cover state sensor senses that the cup is opened and the water contact sensor senses that water flows through, the water intake monitoring is started, and data of the acceleration sensor is acquired every 50ms at the moment.

5. The drinking water monitoring method for a vacuum thermos cup according to claim 1, characterized in that: and (d) adopting a codec model selected from RNN, LSTM or transform for the neural network model in the step (two).

6. The drinking water monitoring method for a vacuum thermos cup according to claim 1, characterized in that: the cup cover state sensor for sensing whether the cup cover is opened is a Hall sensor.

7. The drinking water monitoring method for a vacuum thermos cup according to claim 1, characterized in that: the water contact sensor for sensing whether water flows through is a water immersion sensor or a water flow switch.

8. A vacuum insulated cup using the drinking water monitoring method according to any one of claims 1 to 7.

9. The vacuum insulated cup of claim 8, wherein: a cup cover state sensor used for sensing whether the cup cover is opened or not is arranged at the cup cover of the vacuum cup, an acceleration sensor is arranged in the cup cover, and a water contact sensor used for sensing whether water flows through or not is arranged at the cup opening of the vacuum cup.

10. The vacuum insulated cup of claim 9, wherein: the cup cover state sensor for sensing whether the cup cover is opened is a Hall sensor; the water contact sensor for sensing whether water flows through is a water immersion sensor or a water flow switch.

Technical Field

The invention relates to the technical field of intelligent water cups, in particular to a drinking water monitoring method for a vacuum heat-preserving cup.

Background

With the rapid development of human society, people are more and more seriously neglected in health due to busy work and various affairs, people cannot drink 2 cups of water every day, sleep for 5 and 6 hours every night, and the exercise amount is extremely lack every day, so that the people become the normal state of most people. According to the survey report of the world health organization, the sub-health population accounts for 75 percent of the whole world. One of the simplest causes of sub-health is the lack of drinking water.

In view of the above problems, vacuum thermos cups with a function of reminding users of drinking water have appeared, however, most of the reminders will need to drink how much water a day, and the average calculation is based on the time from the user getting up to sleep, and obviously, the drinking mode of the reminders is extremely unscientific. As is well known, drinking water is very exquisite, and not only different seasons, weather, temperatures and humidity affect the amount and time of water supplement, but also the conditions of different individuals (people) are very different, for example, some people have some basic diseases and cannot drink too much water, and some people need more water intake and/or water drinking frequency, and if a drinking mode is specified, all people cannot be used obviously.

Therefore, if a more scientific and more suitable drinking scheme is to be obtained, the drinking habit of the individual is obtained. In addition, even if scientific opinions are known, the drinking condition of an individual needs to be further monitored so as to further track and remind, and therefore the goal can be met. Therefore, it is necessary to develop a drinking water monitoring method for vacuum thermos cups.

In view of the above needs, many methods for collecting drinking water data by using some sensors have appeared, for example, chinese utility model patent CN204133035U discloses a self-powered temperature display and intelligent water cup for recording the daily drinking water amount, the cup body comprises a shell and a cup liner arranged in the shell, a heat insulation layer is formed between the shell and the cup liner, and a temperature difference power generation module, a temperature sensor, an acceleration sensor, a gyroscope, a control circuit and a bluetooth module are arranged in the heat insulation layer; wherein the pressure sensor is capable of detecting the daily drinking volume of the user.

However, practical applications find that the above structure requires a plurality of modules and sensors to be arranged in the cup insulation layer, and therefore certain damage is certainly brought to the structure of the vacuum insulation layer, which leads to the reduction of the insulation performance: the actual test results are: the vacuum cup with the structure can only keep the temperature for about 2 hours. Therefore, developing a new drinking water monitoring method for vacuum thermos cups without damaging the structure of the vacuum insulation layer becomes a new subject.

Disclosure of Invention

Aiming at the defects of the prior art, the invention provides a novel drinking water monitoring method for a vacuum thermos cup.

In order to solve the technical problems, the invention provides the following technical scheme: a drinking water monitoring method for a vacuum thermos cup comprises the following steps:

a cup cover state sensor for sensing whether the cup cover is opened or not is arranged at the cup cover of the vacuum cup, an acceleration sensor is arranged in the cup cover, and a water contact sensor for sensing whether water flows through is arranged at the cup mouth of the cup cover;

when the cup cover state sensor senses that a water cup is opened and the water contact sensor senses that water flows through, water intake monitoring is started, data of the acceleration sensor are acquired at intervals, and water intake detection is finished once when the cup cover state sensor senses that the water cup is closed or the water contact sensor senses that no water flows through;

secondly, taking the data set of the acceleration sensor as input data according to a time sequence, and submitting the input data to a neural network model for learning to obtain the water intake data; the method for calculating the water intake data by the neural network model comprises the following steps:

generating a characteristic vector through An encoder by using acceleration sensor data A1, A2 and A3.. An corresponding to t1, t2 and t3... tn time by using a time-series codec model, and then generating the residual water volume and the water intake volume at the beginning of the drinking water through a decoder;

and (III) circulating the first step and the second step to obtain drinking water data in a period of time, wherein the drinking water data comprises drinking times, drinking water amount each time, residual water amount after drinking water each time, total drinking water amount and drinking water time points in each day.

Preferably, before the step (one), the following steps are performed:

step one, setting identification information of each vacuum cup;

and step two, collecting the personal information of the user of the vacuum heat-preservation cup, and correspondingly binding the personal information with the identification information of the vacuum heat-preservation cup.

After the steps are adopted, drinking water information (or called drinking water data) of different individuals (users) can be obtained, and the data can be uploaded to the cloud end for big data management and drinking water reminding.

Preferably, the personal information of the user includes name, sex, age, weight and physical health information.

Preferably, in the step (one), when the cup cover state sensor senses that the cup is opened and the water contact sensor senses that water flows through, the water intake monitoring is started, and data of the acceleration sensor is acquired every 50 ms. Of course, the interval time can be adjusted according to actual requirements, and besides acquiring data every 50ms, the interval time can also be 100ms or other values.

Preferably, the neural network model in step (two) adopts a codec model selected from RNN, LSTM or Transformer. Other existing models may also be employed.

Preferably, the cup cover state sensor for sensing whether the cup cover is opened is a hall sensor. The sensor belongs to the prior art and has the function of sensing whether the cup cover is opened or not and then transmitting a signal to the controller.

Preferably, the water contact sensor for sensing whether water flows through is a water immersion sensor or a water flow switch. The sensor belongs to the prior art, and has the function of sensing whether water flows through the cup (namely whether water is actually drunk) and then transmitting a signal to the controller. This sensor is necessary because: in actual monitoring, it is often detected that people often open the cup cover, and abandon drinking water when people meet accidents (such as receiving a call, finding people, or other emergencies) when preparing to drink water, at the moment, the cup cover is opened, a signal is sent out, monitoring is started, a cup is very likely to be toppled over (the people are prepared to drink water but interrupted without actually drinking water), at the moment, the acceleration sensor also generates a signal, so that water drinking amount data is generated, and no water is actually drunk. Therefore, the provision of the water contact sensor can prevent such a practical problem.

The invention also discloses a vacuum thermos cup adopting the drinking water monitoring method.

By means of the technical scheme, the drinking water monitoring method for the vacuum heat-preservation cup at least has the following beneficial effects:

1. the invention develops a novel drinking water monitoring method for a vacuum heat-preserving cup, which can not destroy the structure of a vacuum heat-preserving layer in the heat-preserving cup, can really realize long-time heat preservation while realizing drinking water monitoring, and practical tests prove that: the vacuum cup can keep the temperature for about 6 hours, and has remarkable effect;

2. according to the invention, the water contact sensor is arranged at the cup opening and is matched with the cup cover state sensor for detecting whether the cup cover is opened or not, and when the cup cover state sensor senses that the cup is opened and the water contact sensor senses that water flows through, the water intake monitoring is started, so that a new practical problem is solved: people often open the cup cover and abandon drinking water when meeting unexpected conditions (such as answering a telephone, finding by someone or other emergencies) when preparing to drink water; the occurrence of the misdetection situation is avoided, so that the monitoring data is more real and accurate;

3. the method of the invention is simple and easy to implement, has low cost and starts to be popularized and applied.

Drawings

Fig. 1 is a model structure diagram according to a first embodiment of the present invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the 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 invention.

Example one

A drinking water monitoring method for a vacuum heat-preserving cup is characterized in that a cup cover state sensor for sensing whether a cup cover is opened or not is arranged at the cup cover of the vacuum heat-preserving cup, an acceleration sensor is arranged in the cup cover, and a water contact sensor for sensing whether water flows through is arranged at the cup mouth of the vacuum heat-preserving cup; the method comprises the following steps:

step one, setting identification information of each vacuum cup;

secondly, collecting personal information of a user of the vacuum heat-preservation cup, and correspondingly binding the personal information with the identification information of the vacuum heat-preservation cup;

step three, acquiring drinking water information of the vacuum cup:

when the cup cover state sensor senses that the water cup is opened and the water contact sensor senses that water flows through, the water intake monitoring is started, data of the acceleration sensor is acquired every 50ms at the moment, and the water intake detection is completed once when the cup cover state sensor senses that the water cup is closed or the water contact sensor senses that no water flows through;

secondly, taking the data set of the acceleration sensor as input data according to a time sequence, and submitting the input data to a neural network model for learning to obtain the water intake data; the method for calculating the water intake data by the neural network model comprises the following steps:

firstly, training data is constructed, a person drinks water by using a water cup of the device, the process of collecting the data is similar to the process of detecting the water drinking amount, and when the cup cover state sensor senses that the water cup is opened and the water contact sensor senses that water flows through, series acceleration sensor data A including three reverse acceleration data of x, y and z are recorded; meanwhile, measuring and recording the water amount L1 in the cup before drinking by using a weighing tool, and calculating the current water drinking amount L2-L1 by using the water amount L2 after drinking; each set of training data is input data A and output data L1, L;

repeatedly testing and collecting data by using different groups of people (men, women, children, old people and the like) to drink water with different water temperatures and different initial water amounts, and collecting 5 ten thousand groups of data according to the method; 4 ten thousand groups of data are used as a training set, and 1 ten thousand groups of data are used as a verification set;

the model structure is shown in the attached figure 1, and the operation process is as follows:

generating a characteristic vector by An encoder through acceleration sensor data A1, A2, A3 and a.an corresponding to t1, t2, t3 and tn time by adopting a time-series codec model, and then generating output data, namely the residual water volume and the water intake volume at the beginning of the drinking water at this time through a decoder;

taking the LSTM model as an example, the input data is a signal sequence of 3 directions acquired by an acceleration sensor, and the output data is the initial water volume corresponding to the drinking water at this time and the water drinking amount at this time; the encoder adopts a three-layer LSTM encoder, and the loss function adopts a smooth L1 loss function; an Adam optimizer can be adopted when the gradient is reduced; and the training efficiency is improved by using batch updating;

and (III) circulating the first step and the second step to obtain drinking water data in a period of time, wherein the drinking water data comprises drinking times, drinking water amount each time, total drinking water amount and drinking water time points in each day.

In this embodiment, the personal information of the user includes name, sex, age, weight, and physical health information. The neural network model in the step (two) is selected from an LSTM model.

In this embodiment, the cup cover state sensor for sensing whether the cup cover is opened is a hall sensor (for example, a hall sensor of AHKC-EKAA DC300A/4-20mA model of ancorum electrical corporation may be used). The water contact sensor for sensing whether water flows through is a water immersion sensor (for example, an NB-IoT water immersion probe manufactured by shenzhen marten technologies gmbh) can be adopted.

It is to be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.

Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.

It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.

Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.