Disclosure of Invention
Aiming at the problems in the related art, the invention provides an equivalent core body temperature acquisition method and system suitable for wearing equipment, wherein the wearing equipment is used for carrying out continuous and non-intrusive equivalent core body temperature detection on a tested person, abnormal body temperature conditions can be quickly and simply screened during a pandemic period, medical bases can also be provided for conditions of quick body temperature loss (cold risk), physiological period or pregnancy period, long-term body temperature abnormality and the like, the precision of an equivalent core body temperature algorithm can reach the typical precision of +/-0.2 ℃ in actual verification, and is superior to a non-contact type forehead temperature and ear temperature measurement method, and meanwhile, the heat balance time (generally 5-10 minutes) of a contact type measurement method is not required, so that the technical problems in the prior related art are solved.
Therefore, the invention adopts the following specific technical scheme:
according to one aspect of the present invention, there is provided an equivalent core body temperature acquisition method suitable for use with a wearable device, the method comprising the steps of:
s1, acquiring the environment temperature, the wrist temperature and the armpit temperature of the user by using preset data acquisition equipment;
s2, analyzing and summarizing the correlation among the environment temperature, the wrist temperature and the armpit temperature based on sufficient user data, and establishing an equivalent core body temperature algorithm model;
s3, calculating to obtain the equivalent core body temperature of the corresponding user by using the equivalent core body temperature algorithm model;
wherein, in S2, the establishing of the equivalent core body temperature algorithm model based on the sufficient user data analysis and the induction of the correlation between the environmental temperature, the wrist temperature and the axillary temperature includes the following steps:
s21, constructing a plurality of groups of temperature data point clouds of the user about the environment temperature, the wrist temperature and the armpit temperature based on sufficient user data;
s22, carrying out weight proportion analysis on the temperature data point cloud, inducing the correlation among the environment temperature, the wrist temperature and the axillary temperature, and establishing an equivalent core body temperature algorithm model as follows:
furthermore, the data acquisition equipment comprises wearing equipment and core body temperature measuring equipment;
the wearable device is a bracelet with an environment temperature sensor and a skin temperature sensor, the environment temperature sensor measures the environment temperature through an opening on the bracelet, and the skin temperature sensor measures the skin temperature of the wrist of a user through contact type heat conduction;
the core body temperature measurement device is a compact device with an underarm temperature sensor that measures the temperature of the armpit of the user through contact heat conduction.
Further, the step of S1 acquiring the ambient temperature and the wrist temperature and the armpit temperature of the user by using a preset data acquisition device includes the following steps:
s11, starting the wearable device and the core body temperature measuring device;
s12, carrying out Bluetooth communication self-checking on the wearable device and the core body temperature measuring device;
s13, respectively acquiring an ambient temperature and a wrist temperature of a user through an ambient temperature sensor and a skin temperature sensor in the wearable device, and acquiring an armpit temperature of the user through an armpit temperature sensor in the core body temperature measuring device;
s14, verifying the data of the environment temperature, the wrist temperature and the axillary temperature by using a preset data verification method;
s15, the wearing equipment stores the checked temperature data, and meanwhile, the core body temperature measuring equipment synchronizes the temperature of the armpit to the wearing equipment through Bluetooth;
and S16, performing data cleaning and algorithm smoothing on the data of the environmental temperature, the wrist temperature and the armpit temperature stored in the wearable device.
Further, before the step of starting the wearable device and the core body temperature measurement device in S11, the method further includes: and the user wears the wearing equipment and the core body temperature measuring equipment which are prepared in advance.
Furthermore, in S13, the skin temperature sensor is in contact with the skin of the wrist by any one of a PCB flexible board and a heat conductive contact pin, a contact spring and a heat conductive contact pin, or a heat conductive pad and a contact pin.
Further, the data verification method in S14 is performed through a mean value regression algorithm, and the data verification method includes verifying the data of the environment temperature, the wrist temperature, and the axillary temperature through the mean value regression algorithm, respectively.
Further, the verifying the wrist temperature by using the mean regression algorithm comprises the following steps:
firstly, the change of the temperature field is set to be smooth and continuous in a second-order time domain, and then a first temperature point T is calculated
1And a third temperature point T
3Has an average value of
Then the product is mixed withAverage value T
2' with a second temperature point T
2Carrying out difference operation to obtain T
2’-T
2Finally, according to the difference and the ratio
Checking, if the ratio is greater than 0.1, determining that the wrist temperature data is influenced by various interference factors such as wearing state, shower and hand washing, and using a third temperature point T
3Instead of the second temperature point T
2。
Further, the process of data cleansing in S16 mainly depends on the timestamp, the auxiliary information of the wear release record and the charging record, and the weight of the abnormal data is configured to be 0, so as to obtain a highly reliable data set.
Further, in the step S3, the deviation between the equivalent core body temperature of the corresponding user and the actual axillary temperature of the user is calculated and obtained by using the equivalent core body temperature algorithm model, and is kept within a preset reasonable range.
According to another aspect of the invention, an equivalent core body temperature acquisition system suitable for a wearing device is provided, and the system comprises a data acquisition device for temperature acquisition and a model construction module for equivalent core body temperature algorithm model construction;
the data acquisition equipment comprises wearing equipment and core body temperature measuring equipment;
the wearable device comprises but is not limited to any one of a smart bracelet worn on the wrist of a user or smart equipment of a smart watch, an environment temperature sensor and a skin temperature sensor are respectively arranged on the wearable device, the environment temperature sensor measures the environment temperature through an opening on the wearable device, and the skin temperature sensor measures the skin temperature of the wrist of the user through contact type heat conduction;
the core body temperature measurement device is a compact device with an underarm temperature sensor that measures the temperature of the armpit of the user through contact thermal conduction,
wearing equipment and core body temperature measuring equipment's inside all is provided with main chip and power management unit, just wearing equipment's inside still is provided with the demonstration communication module.
The invention has the beneficial effects that:
1) compared with two types of body temperature detection modes which are mainstream at present, the invention can support wearing equipment with higher popularization rate to continuously and non-invasively detect the body temperature through the established equivalent core body temperature algorithm, not only solves the problem of precision deviation of a non-contact infrared thermopile mode, but also solves the problem of overlong measurement preparation time of a contact mercury or electronic thermometer, provides an economic choice for realizing quick, efficient and non-sensitive body temperature abnormity screening in a pandemic period, and simultaneously can provide early warning for cold fever, and provides continuous and accurate medical reference for a physiological cycle, a pregnancy basic body temperature and the like.
2) Compared with non-contact forehead temperature or ear temperature measurement, the invention can realize typical precision of +/-0.2 ℃ and the highest precision of +/-0.1 ℃; compared with contact type tongue temperature, axillary temperature or rectal temperature measurement, the method is almost completely 'non-sensitive', does not need high cooperation willingness of a measured person, and does not need preparation time as long as 5-10 minutes.
3) Compared with the single-point data of the two traditional body temperature measurement modes, the continuous body temperature measurement method can also be used for portraying a user through big data, carrying out early warning such as cold and fever on abnormal body temperature change in a short period, and carrying out further medical analysis on the abnormal body temperature change in a long period.
Detailed Description
For further explanation of the various embodiments, the drawings which form a part of the disclosure and which are incorporated in and constitute a part of this specification, illustrate embodiments and, together with the description, serve to explain the principles of operation of the embodiments, and to enable others of ordinary skill in the art to understand the various embodiments and advantages of the invention, and, by reference to these figures, reference is made to the accompanying drawings, which are not to scale and wherein like reference numerals generally refer to like elements.
According to an embodiment of the present invention, there is provided an equivalent core body temperature acquiring method and system for a wearable device, which is an operation method of a heat conduction type digital temperature sensor in continuous, non-invasive human body core body temperature monitoring, acquires user data within a sufficient range (gender, region, season, day and night, body state) through a set of initial devices (including a wrist device and an underarm device), analyzes and summarizes an environmental temperature (T) based on the relatively sufficient user dataa) Wrist temperature (T)s) The temperature of the axillacAlso called core body temperature), a set of equivalent core body temperature algorithm T is established through a mathematical methodc′=f(Ts,Ta) That is, an equivalent core body temperature (T) is derived from the ambient temperature and the axillary temperature onlyc') to be maintained within a reasonable range, such as + -0.2 deg.C, from the actual core or axillary temperature.
Based on such a set of equivalent core body temperature algorithm Tc′=f(Ts,Ta) After two high-precision temperature sensors are integrated in the wearable device, the body temperature data of a wearer can be conveniently and continuously obtained in a non-intervention mode, and a high-precision basis is provided for further medicine or large health.
Referring now to the drawings and the detailed description, in accordance with one embodiment of the present invention, there is provided an equivalent core body temperature acquisition method for wearable devices, which is adapted to continuously detect the ambient and wrist skin temperatures via the wearable device and derive the core body temperature of the human body via an algorithm to a typical accuracy of ± 0.2 ℃, and specifically, the method comprises the following steps:
s1, acquiring the environment temperature, the wrist temperature and the armpit temperature of the user by using preset data acquisition equipment; specifically, the data acquisition equipment comprises wearing equipment and core body temperature measuring equipment; as shown in fig. 2, obtain the schematic diagram for wearable equipment's ambient temperature and wrist temperature, wearable equipment is for the bracelet that has two sets of digital temperature measurement units (ambient temperature sensor and skin temperature sensor), and a set of (ambient temperature sensor) measures air temperature through the trompil, and another set of (skin temperature sensor) measures wrist skin temperature through contact heat-conduction, and two sets of units all need reasonable spatial structure and PCB design to avoid the device that generates heat and influence each other. And carrying out data synchronization through the Bluetooth module. The circuit architecture of the wearable device is shown in fig. 3.
The core body temperature measuring equipment is compact equipment with a group of digital temperature measuring units (armpit temperature sensors), armpit temperature is measured through contact type heat conduction, measuring results are synchronized to the wearable equipment through the Bluetooth module, and a complete data set is provided for algorithm establishment. The circuit architecture of the core body temperature measurement device is shown in fig. 4.
The digital temperature sensor is selected from products with the precision reaching +/-0.1 ℃ in the body temperature range, the typical value of the starting time is 1 millisecond, the typical value of the conversion time is 104 milliseconds, and the high sampling frequency can be realized.
Like a mercury thermometer, the digital temperature sensor measures the temperature in a heat conduction mode, and considering the continuity of a temperature field, the conversion time of about 0.1 second can completely cover the requirement of equivalent core body temperature measurement. But the physical processes of ambient temperature, wrist temperature sensor acquisition data, and key points on system and PCB design are as follows.
The contact mode of the digital temperature sensor and the wrist skin is I, and the contact mode is as shown in figure 5 through a PCB soft board and a heat conduction contact pin;
the contact mode of the digital temperature sensor and the wrist skin is the second mode, and the contact mode is as shown in figure 6 through a contact spring and a heat conduction contact pin;
fig. 7 shows a third contact manner between the temperature sensor and the wrist skin via the heat conducting pad and the contact pins.
Due to the fact that the change of the temperature field has excellent continuity, data distortion acquired under the high sampling frequency can be mostly considered to be caused by wearing relaxation or other abnormal heat conduction modes, and the problem can be well solved by adjusting the weight of the distorted data through an algorithm. FIG. 8 is a flowchart of the whole data acquisition device;
specifically, the S1 includes the following steps:
s11, starting the wearable device and the core body temperature measuring device; specifically, the step S11 further includes: and the user wears the wearing equipment and the core body temperature measuring equipment which are prepared in advance.
S12, carrying out Bluetooth communication self-checking on the wearable device and the core body temperature measuring device;
s13, respectively acquiring an ambient temperature and a wrist temperature of a user through an ambient temperature sensor and a skin temperature sensor in the wearable device, and acquiring an armpit temperature of the user through an armpit temperature sensor in the core body temperature measuring device;
s14, verifying the data of the environment temperature, the wrist temperature and the axillary temperature by using a preset data verification method; specifically, the data verification method in S14 is performed by a mean value regression algorithm, and the data verification method includes verifying the data of the environment temperature, the wrist temperature, and the axillary temperature by the mean value regression algorithm, respectively.
The method for verifying the wrist temperature by adopting the mean regression algorithm comprises the following steps:
firstly, the change of the temperature field is set to be smooth and continuous in a second-order time domain, and then a first temperature point T is calculated
1And a third temperature point T
3Has an average value of
Then the average value T
2' with a second temperature point T
2Carrying out difference operation to obtain T
2’-T
2Finally, according to the difference and the ratio
To check if the ratio is greater than0.1, the wrist temperature data is considered to be influenced by various interference factors such as wearing state, shower and hand washing, and a third temperature point T is used
3Instead of the second temperature point T
2(ii) a Ambient temperature T
aThe check of (a) can be relaxed to 0.3.
S15, the wearing equipment stores the checked temperature data, and meanwhile, the core body temperature measuring equipment synchronizes the temperature of the armpit to the wearing equipment through Bluetooth;
and S16, performing data cleaning and algorithm smoothing on the data of the environmental temperature, the wrist temperature and the armpit temperature stored in the wearable device. Specifically, the process of data cleansing in S16 mainly depends on the timestamp, the auxiliary information of the wear release record and the charging record, and the weight of the abnormal data is configured to be 0, so as to obtain a highly reliable data set.
The accuracy and flexibility of the equivalent core body temperature algorithm are determined by the completeness of data acquired by the acquisition equipment. To cover as much as possible the following long tail scenarios such as: gender, age, region, climate, circadian rhythm, physiological cycle, high fever and low fever, taking antipyretic drugs and the like, the volunteer users for data acquisition need to be distributed between different ages and sexualities in different regions, and the lowest power consumption is needed to meet the requirement of a longer acquisition period. Fig. 9 and 10 are schematic diagrams of two sets of temperature data acquired by the above-mentioned acquisition device.
S2, analyzing and summarizing the correlation among the environment temperature, the wrist temperature and the armpit temperature based on sufficient user data, and establishing an equivalent core body temperature algorithm model;
wherein the S2 includes the steps of:
s21, sampling for a long time and a region coverage range, and constructing a plurality of groups of temperature data point clouds of the user about the environment temperature, the wrist temperature and the armpit temperature based on sufficient user data;
s22, carrying out weight matching and other analyses on the temperature data point cloud, summarizing the correlation among the environment temperature, the wrist temperature and the axillary temperature, and establishing a set of equivalent core body temperature algorithm model with typical precision as high as +/-0.2 ℃ as follows:
an equivalent core body temperature algorithm model for wearable equipment refers to a public correlation formula between forehead temperature and core body temperature as follows:
wherein, TcIs the core body temperature, TsIs forehead temperature, TaIs ambient temperature.
S3, calculating to obtain the equivalent core body temperature of the corresponding user by using the equivalent core body temperature algorithm model;
in S3, the deviation between the equivalent core body temperature of the corresponding user and the actual axillary temperature of the user is calculated by using the equivalent core body temperature algorithm model and is kept within a preset reasonable range, such as ± 0.2 ℃.
Based on the set of equivalent core body temperature algorithm, the wearable device can continuously and non-invasively detect the core body temperature of the wearer, and the axillary temperature measured by the mercury thermometer is compared, so that the algorithm can realize the typical precision of +/-0.2 ℃, and even can reach the highest precision of +/-0.1 ℃ under the condition of stable body temperature.
According to another embodiment of the invention, an equivalent core body temperature acquisition system suitable for a wearing device is provided, and the system comprises a data acquisition device for temperature acquisition and a model construction module for equivalent core body temperature algorithm model construction;
the data acquisition equipment comprises wearing equipment and core body temperature measuring equipment;
the wearable device comprises but is not limited to any one of a smart bracelet worn on the wrist of a user or smart equipment of a smart watch, an environment temperature sensor and a skin temperature sensor are respectively arranged on the wearable device, the environment temperature sensor measures the environment temperature through an opening on the wearable device, and the skin temperature sensor measures the skin temperature of the wrist of the user through contact type heat conduction;
the core body temperature measurement device is a compact device with an underarm temperature sensor that measures the temperature of the armpit of the user through contact thermal conduction,
wearing equipment and core body temperature measuring equipment's inside all is provided with main chip and power management unit, just wearing equipment's inside still is provided with the demonstration communication module.
In summary, by means of the technical scheme, compared with the two most mainstream body temperature detection modes, the wearable device with high popularity can be supported to continuously and non-invasively detect the body temperature through the established equivalent core body temperature algorithm, the problem of precision deviation of a non-contact infrared thermopile mode is solved, the problem of overlong measurement preparation time of a contact mercury or electronic thermometer is solved, an economical choice is provided for quick, efficient and non-sensitive body temperature abnormity screening during a pandemic period, early warning is provided for cold fever, and continuous and accurate medical reference is provided for physiological cycles, basic body temperatures during pregnancy and the like.
In addition, compared with non-contact forehead temperature or ear temperature measurement, the invention can realize typical precision of +/-0.2 ℃ and the highest precision of +/-0.1 ℃; compared with contact type tongue temperature, axillary temperature or rectal temperature measurement, the method is almost completely 'non-sensitive', does not need high cooperation willingness of a measured person, and does not need preparation time as long as 5-10 minutes.
In addition, compared with single-point data of two traditional body temperature measurement modes, the continuous body temperature measurement method can also be used for portraying a user through big data, carrying out early warning such as cold and fever on abnormal body temperature change in a short period, and carrying out further medical analysis on the abnormal body temperature change in a long period.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.