Intelligent drinking monitoring method based on multi-sensor fusion

Abstract

The invention relates to an intelligent drinking monitoring method based on multi-sensor fusion, which comprises the following steps: S1, reading basic information of equipment of a cup collision opposite side through NFC (Near Field Communication) on a wine cup, and judging effective cup collision based on the information of the equipment of the opposite side and an acceleration value of a gyroscope; s2, obtaining a weight difference value of the wine glass through a pressure sensor on the wine glass, and calculating a compensation coefficient in combination with data of a temperature sensor so as to obtain an actual wine drinking amount; and S3, acquiring basic data information of the cup holder, calculating the real-time blood alcohol concentration of the cup holder, comparing the real-time blood alcohol concentration with a standard value, and performing early warning after a detection result shows that the real-time blood alcohol concentration exceeds a threshold value.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of safety monitoring, more particularly, to an intelligent drinking monitoring method based on multi-sensor fusion. BACKGROUND

[0002] Alcohol can have an excitatory or inhibitory effect on the central nervous system of the human body, and the process of drinking alcohol can cause the judgment and cognitive abilities of a person to gradually decline, thereby reducing tactile ability, causing visual impairment, and causing fatigue. The impact of the amount of alcohol consumed on the central nervous system of the human body is not only related to the amount of alcohol in the blood, but also related to factors such as gender, age, body weight, drinking habits, drinking time, and mood. Some people's judgment and cognitive abilities are severely affected when the blood alcohol concentration reaches 50mg / 100mL, while others do not experience severe damage to the normal functioning of the central nervous system even when the blood alcohol concentration reaches 400mg / 100mL, which is more than 8 times the difference in blood alcohol concentration.

[0003] According to statistics, the overall alcohol consumption rate of adults has exceeded 50%, and the consumption of alcohol is still on the rise every year. Every year, about 3 million people worldwide die due to alcohol-related problems. Therefore, it is necessary to prevent the risks associated with excessive drinking.

[0004] Currently, the method for testing the alcohol content in the human body after drinking alcohol generally involves breath testing, infrared testing, and saliva testing. The above common testing methods basically require specific detection devices or instruments to achieve testing, are only suitable for specific use scenarios, and have a certain lag.

[0005] Therefore, it is necessary to propose an intelligent drinking monitoring method based on multi-sensor fusion. SUMMARY

[0006] The present application provides an intelligent drinking monitoring method based on multi-sensor fusion to solve the technical problems of poor alcohol monitoring precision and lag in existing drinking.

[0007] According to one aspect of the present application, an intelligent drinking monitoring method based on multi-sensor fusion is provided, comprising the following steps:

[0008] Step S1, reading the basic information of the opposite device through the NFC on the wine glass, and determining an effective clinking based on the information of the opposite device and the acceleration value of the gyroscope;

[0009] Step S2, obtaining the weight difference of the clinking wine glass through the pressure sensor on the wine glass, and calculating the compensation coefficient in combination with the temperature sensor data to obtain the actual amount of drinking;

[0010] Step S3, obtaining the basic data information of the cup holder, calculating the real-time blood alcohol concentration of the cup holder, and comparing with the standard value to detect the threshold value and give a warning.

[0011] On the basis of the above scheme, the step S1 further comprises:

[0012] Step S11, the acceleration sensor acquires three-axis data of the wine glass, and the NFC periodically sends an instruction to detect the adjacent device to acquire electromagnetic energy change data of the adjacent device;

[0013] Step S12, the three-axis acceleration data acquired in step S11 is vectorized, and the time differential algorithm is used to acquire the acceleration change rate;

[0014] Step S13, the electromagnetic energy change data detected by the NFC in step S11 is converted into a quantifiable electrical signal, the electromagnetic energy change data is used to confirm the physical shielding characteristics and communication reliability, and the event duration is calculated by comparing with the time axis, the device time synchronization is acquired by combining the acceleration change rate data in step S12 with the NFC electromagnetic energy change data corresponding to the time axis;

[0015] Step S14, based on the acceleration change rate, event duration, device time synchronization, physical shielding characteristics and communication reliability judgment, the current behavior is taken as the clinking time, and the NFC on the wine glass is started to read the basic information of the clinking opponent device.

[0016] On the basis of the above scheme, the step S12 in detail comprises:

[0017] Step S121, the instantaneous synthetic acceleration scalar acquired by the three-axis acceleration sensor of the device is calculated, and the calculation formula is: ;

[0018] And ;

[0019] x-axis vector coordinate is represented by x; y-axis vector coordinate is represented by y; z-axis vector coordinate is represented by z;

[0020] Step S122, the jerk feature of the acceleration change rate is calculated by time differential: .

[0021] On the basis of the above scheme, the calculation formula of the actual drinking amount in step S2 is: ;

[0022] Wherein, V represents the actual drinking amount (ml);

[0023] W_pre represents the total weight of the cup before clinking;

[0024] W_post represents the total weight of the cup after clinking;

[0025] ρ represents the density coefficient of the liquor;

[0026] k_temp represents the temperature compensation coefficient, ranging from 0.98 to 1.02.

[0027] On the basis of the above scheme, the step S3 acquires the basic data information of the cup holder, including user weight M, gender coefficient G (male = 0.68, female = 0.55), and drinking speed Δt;

[0028] And the formula for calculating the real-time blood alcohol concentration of the cup holder is: ;

[0029] Wherein:

[0030] BAC t represents the real-time blood alcohol concentration;

[0031] V i represents the volume of the i th drink;

[0032] M represents the user's weight;

[0033] G represents the gender coefficient (male = 0.68, female = 0.55).

[0034] Δt represents the total time from starting drinking to the current time;

[0035] n represents the number of drinks up to the current time.

[0036] On the basis of the above scheme, the step S3 further includes calculating the cumulative contribution of alcohol intake to BAC based on the total amount of alcohol already drunk by the user, weight and gender, and correcting it in combination with the amount of alcohol metabolized over time to obtain the real-time blood alcohol concentration correction number.

[0037] On the basis of the above scheme, the real-time blood alcohol concentration correction number is compared with the standard value, and a warning is given after the threshold value is detected.

[0038] On the basis of the above scheme, the cumulative contribution of alcohol intake to BAC is calculated by the formula: ;

[0039] Wherein, V iThe volume of the alcoholic beverage consumed in the i-th instance is represented by ; M represents the user's weight; G represents the gender coefficient, where G=0.68 for males and G=0.55 for females.

[0040] The formula for calculating the reduction in alcohol metabolism over time is -0.015×Δt, where Δt is the total time from the start of drinking to the current moment.

[0041] The present invention also provides a method for social interaction through toasting, comprising the following steps:

[0042] Step A1: Read the basic information of the other party's device by NFC on the wine glass. Based on the information of the other party's device and the gyroscope acceleration value, determine that the toasting is valid.

[0043] Step A2: Obtain the weight difference between the glasses when clinking by using a pressure sensor on the glass, and calculate the compensation coefficient by combining it with the temperature sensor data to obtain the actual amount of alcohol consumed each time.

[0044] Step A3: Based on the toasting records generated in A1 and the drinking volume data generated in A2, construct a social graph and calculate the drinking intimacy index of the glass holders who effectively toasted.

[0045] Step A4: Collect the data uploaded by each person holding the glass and generate a drinking ranking list and a table showing the drinking volume and speed of both parties when clinking glasses.

[0046] Based on the above scheme, the preferred embodiment of the social graph is: G = (V, E);

[0047] Where V represents an individual entity in a social network, and E represents a relationship line connecting two individual entities;

[0048] The formula for calculating the drinking intimacy index is as follows: ;

[0049] Among them, I AB Indicates the intimacy index of drinking; V ABi This indicates the total amount of alcohol consumed by both parties in a single drinking session.

[0050] n represents the total number of times A and B drank together; T AB N represents the cumulative interaction time between A and B in a drinking scenario; AB This indicates the number of times A and B clink glasses;

[0051] log represents the natural logarithm.

[0052] The application discloses an intelligent drinking monitoring method based on multi-sensor fusion, which is characterized in that: an NFC is arranged on a wine glass to obtain the equipment information of a cupping opponent, a gyro acceleration value is combined to determine whether it is a cup spouting behavior, and a temperature sensor data is combined to calculate a compensation coefficient, so that the actual blood alcohol concentration of a person holding the wine glass can be quickly and accurately obtained, and a warning can be given, and the detection is more accurate and fast. BRIEF DESCRIPTION OF DRAWINGS

[0053] In order to more clearly illustrate the technical solutions of the embodiments of the application, the following will briefly introduce the drawings needed to be used in the embodiment description. Obviously, the drawings in the following description only some of the embodiments of the application, and for those skilled in the art, other drawings can also be obtained without creative labor. In the drawings:

[0054] Figure 1 The flow chart of the intelligent drinking monitoring method based on multi-sensor fusion of the application;

[0055] Figure 2 The flow chart of step S1 of the application; DETAILED DESCRIPTION

[0056] The specific embodiments of the application will be further described in detail below in combination with the drawings and embodiments. The following embodiments are used to illustrate the application, but not to limit the scope of the application.

[0057] It should be understood that when used in the specification and the appended claims, the term "comprising" indicates the presence of the described features, integers, steps, operations, elements, and / or components, but does not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0058] In order to make the drawing simple, only the parts related to the application are shown in the drawings, which do not represent the actual structure of the product. In addition, in order to make the drawing simple and easy to understand, in some drawings, only one of the components with the same structure or function is shown, or only one of them is marked. In this paper, "one" not only means "only one", but also means "more than one".

[0059] It should be further understood that the term "and / or" used in the present application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes these combinations.

[0060] In the embodiments shown in the drawings, the indications of directions, such as up, down, left, right, front and back, are used to explain the structure and movement of various components of the present application, which are not absolute but relative. These descriptions are appropriate when these components are in the positions shown in the drawings. If the positions of these components change, the indications of these directions also change accordingly.

[0061] In addition, in the description of the present application, the terms "first", "second", and the like are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0062] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the specific embodiments of the present application will be described below with reference to the drawings. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained from these drawings without creative labor, and other embodiments can also be obtained.

[0063] Please refer to Figure 1 , and in combination with Figure 2 , a kind of intelligent drinking monitoring method based on multi-sensor fusion of the present application, comprising the following steps:

[0064] Step S1, the basic information of the opposite device is read through NFC on the wine glass, and based on the information of the opposite device and the gyroscope acceleration value, it is determined as effective clinking;

[0065] Specifically, step S11, the three-axis data of the wine glass is obtained by the acceleration sensor =(ax,ay,az), NFC periodically sends command SENS_REQ to detect adjacent devices to obtain the electromagnetic energy change data of adjacent devices;

[0066] Step S12, the three-axis acceleration data obtained in step S11 is vectorized, and the acceleration change rate is obtained by time differential algorithm;

[0067] That is, first, step S121, the instantaneous resultant acceleration scalar collected by the three-axis acceleration sensor of the device is calculated, and the calculation formula is: ;

[0068] And ;

[0069] x-axis vector coordinate is represented as y-axis vector coordinate is represented as z-axis vector coordinate is represented as

[0070] Then, step S122, the jerk feature of acceleration change rate is calculated by time differential: .

[0071] Step S13, the electromagnetic energy change data detected by NFC in step S11 is converted into quantifiable electrical signals, the electromagnetic energy change data is used to confirm the physical shielding characteristics and communication reliability, and the event duration is calculated by comparing the time axis, the device time synchronization is obtained by combining the acceleration change rate data in S12 with the NFC electromagnetic energy change data corresponding to the time axis;

[0072] Step S14, based on the acceleration change rate, event duration, device time synchronization, physical shielding characteristics and communication reliability judgment, the current behavior is taken as the clinking time, and the NFC on the wine glass is started to read the basic information of the clinking opponent device.

[0073] Step S2, the weight difference of the clinking wine glass is obtained by the pressure sensor on the wine glass, and the compensation coefficient is calculated by combining the temperature sensor data to obtain the actual drinking amount;

[0074] Among them, the actual drinking amount calculation formula of step S2 is: ;

[0075] Among them, V represents the actual drinking amount (ml);

[0076] W_pre represents the total weight of the cup before clinking;

[0077] W_post represents the total weight of the cup after clinking;

[0078] ρ represents the density coefficient of the wine;

[0079] k_temp represents the temperature compensation coefficient, ranging from 0.98 to 1.02.

[0080] Step S3, the basic data information of the person holding the cup is obtained, the real-time blood alcohol concentration of the person holding the cup is calculated, and compared with the standard value, and the warning is given after the detection is found to exceed the threshold value.

[0081] Specifically, the step S3 of the present application obtains the basic data information of the person holding the cup, including user weight M, gender coefficient G (male=0.68, female=0.55), drinking speed Δt;

[0082] And the formula for calculating the real-time blood alcohol concentration of the person holding the cup is: ;

[0083] Among them:

[0084] BAC t represents the real-time blood alcohol concentration;

[0085] Vi V i represents the volume of the alcohol beverage drunk for the i th time;

[0086] M represents the weight of the user;

[0087] G represents a gender coefficient (male = 0.68, female = 0.55).

[0088] Δt represents the total time from starting drinking to the current time;

[0089] n represents the number of times of drinking until the current time.

[0090] In order to ensure the accuracy of the data and reduce the error of human metabolism on detection, the step S3 of the application further comprises calculating the cumulative contribution of alcohol intake to BAC based on the total amount of alcohol drunk by the user, the weight and the gender, and correcting in combination with the reduction amount of alcohol metabolism over time to obtain a real-time blood alcohol concentration correction number, comparing the real-time blood alcohol concentration correction number with a standard value, and warning after detecting that the threshold is exceeded.

[0091] wherein the cumulative contribution of alcohol intake to BAC is calculated by the formula: ;

[0092] wherein V i represents the volume of the alcohol beverage drunk for the i th time; M represents the weight of the user; G represents a gender coefficient, wherein G = 0.68 for male and G = 0.55 for female;

[0093] and the reduction amount of alcohol metabolism over time is calculated by the formula -0.015 x Δt, and Δt is the total time from starting drinking to the current time.

[0094] The application further provides a clinking cup social interaction method, comprising the following steps:

[0095] Step A1, reading the basic information of the clinking cup opposite device through the NFC on the wine cup, and determining as valid clinking cup based on the information of the opposite device and the gyroscope acceleration value;

[0096] Step A2, obtaining the clinking cup weight difference through the pressure sensor on the wine cup, and calculating the compensation coefficient in combination with the temperature sensor data to obtain the actual drinking amount each time;

[0097] Step A3, constructing a social graph based on the clinking cup record generated by A1 and the drinking amount data generated by A2, and calculating the drinking intimacy index of the person holding the cup in the valid clinking cup.

[0098] wherein the social graph expression is: G = (V, E);

[0099] Wherein, V represents an individual entity in a social network, E represents a relationship line connecting two individual entities;

[0100] The calculation formula of the drinking closeness index is: ;

[0101] Wherein, I AB represents the drinking closeness index; V ABi represents the total amount of alcohol consumed by both parties in a single joint drinking event;

[0102] n represents the total number of joint drinking events of A and B; T AB represents the cumulative interaction time of A and B in the drinking scene; N AB represents the number of cup clinking of A and B;

[0103] log represents a natural logarithm.

[0104] An intelligent drinking monitoring method based on multi-sensor fusion of the present application sets an NFC on a wine glass to obtain the equipment information of a cup clinking opposite party, combines a gyro acceleration value to determine whether it is a cup spraying behavior, combines temperature sensor data to calculate a compensation coefficient, so as to quickly and accurately obtain the actual blood alcohol concentration of a cup holder, and prewarning, which is more accurate and fast in detection.

[0105] Finally, the method of the present application is only a preferred embodiment, and is not used to limit the protection scope of the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A multi-sensor fusion based intelligent drinking monitoring method, characterized in that, The method comprises the following steps: Step S1, reading the basic information of the clinking device through the NFC on the wine glass, and determining the clinking as valid based on the information of the clinking device and the acceleration value of the gyroscope; Step S2, obtaining the clinking wine glass weight difference through the pressure sensor on the wine glass, and calculating the compensation coefficient combined with the temperature sensor data to obtain the actual drinking amount; Step S3, obtaining the basic data information of the person holding the glass, calculating the real-time blood alcohol concentration of the person holding the glass, and comparing it with the standard value to detect if it exceeds the threshold value and give a warning.

2. The intelligent drinking monitoring method based on multi-sensor fusion according to claim 1, characterized in that, The step S1 further comprises: Step S11, the acceleration sensor obtains three-axis data of the wine glass, and the NFC periodically sends instructions to detect the nearby device to obtain the electromagnetic energy change data of the nearby device; Step S12, the three-axis acceleration data obtained in step S11 is vectorized, and the time differential algorithm is used to obtain the acceleration change rate; Step S13, the electromagnetic energy change data detected by the NFC in step S11 is converted into a quantifiable electrical signal, the electromagnetic energy change data is used to confirm the physical shielding characteristics and communication reliability, and the event duration is calculated by comparing with the time axis, the device time synchronization is obtained by combining the acceleration change rate data in S12 with the NFC electromagnetic energy change data and the corresponding relationship of the time axis; Step S14, based on the acceleration change rate, the event duration, the device time synchronization, the physical shielding characteristics and the communication reliability, the current behavior is determined as the clinking time, and the NFC on the wine glass is started to read the basic information of the clinking device.

3. The intelligent drinking monitoring method based on multi-sensor fusion according to claim 2, characterized in that, The step S12 in detail comprises: Step S121, the instantaneous combined acceleration scalar collected by the three-axis acceleration sensor of the device is calculated, and the calculation formula is: ； and ; denotes the x-axis vector coordinate; denotes the y-axis vector coordinate; denotes the z-axis vector coordinate; Step S122, jerk feature of the acceleration change rate is calculated by time differentiation: .

4. The intelligent drinking monitoring method based on multi-sensor fusion according to claim 2, characterized in that, The formula for calculating the actual drinking amount in step S2 is: ； Wherein, V represents the actual drinking amount (ml); W_pre represents the total weight of the cup before clinking; W_post represents the total weight of the cup after clinking; ρ represents the density coefficient of wine; k_temp represents the temperature compensation coefficient, ranging from 0.98 to 1.

02.

5. The intelligent drinking monitoring method based on multi-sensor fusion according to claim 4, characterized in that, The step S3 of obtaining the basic data information of the person holding the glass includes user weight M, gender coefficient G (male = 0.68, female = 0.55), and drinking speed Δt; And the formula for calculating the real-time blood alcohol concentration of the person holding the glass is: ； Wherein: BAC t BAC represents real-time blood alcohol concentration; V i V represents the volume of the alcoholic beverage consumed at the i-th time; M represents the user weight; G represents the gender coefficient (male = 0.68, female = 0.55); Δt represents the total time from starting drinking to the current time; n represents the number of drinks up to the current time.

6. The intelligent drinking monitoring method based on multi-sensor fusion according to claim 5, characterized in that, The step S3 further comprises calculating the cumulative contribution of alcohol intake to BAC based on the total amount of alcohol consumed by the user, weight and gender, and correcting it by combining the amount of alcohol metabolized over time to obtain the real-time blood alcohol concentration correction number.

7. The intelligent drinking monitoring method based on multi-sensor fusion according to claim 6, characterized in that, Compare the real-time blood alcohol concentration correction number with the standard value, and give a warning if it is found to exceed the threshold value.

8. The intelligent drinking monitoring method based on multi-sensor fusion according to claim 6, characterized in that, The formula for calculating the cumulative contribution of alcohol intake to BAC is: ； where V i represents the volume of alcohol consumed on the i-th occasion; M represents the weight of the user; G represents a gender coefficient, where G = 0.68 for males and G = 0.55 for females; And the formula for calculating the amount of alcohol metabolized over time is -0.015×Δt, Δt being the total time from starting drinking to the current time.

9. A clinking cup social interaction method, characterized in that, The method comprises the following steps: Step A1, read the basic information of the cup-clinking device on the other side through the NFC on the cup, and determine that it is a valid cup clinking based on the information of the device on the other side and the gyroscope acceleration value; Step A2, obtain the cup clinking weight difference through the pressure sensor on the cup, and calculate the compensation coefficient combined with the temperature sensor data to obtain the actual drinking amount each time; Step A3, construct a social graph based on the cup clinking record generated in A1 and the drinking amount data generated in A2, and calculate the drinking intimacy index of the cup holder in the valid cup clinking; Step A4, collect the uploaded data of each cup holder to generate a drinking amount ranking list, a cup clinking pair drinking amount and drinking speed information table.

10. A clinking cup social interaction method as claimed in claim 9, wherein, The social graph expression is: G = (V, E); Wherein, V represents an individual entity in a social network, and E represents a relationship line connecting two individual entities; The calculation formula of the drinking intimacy index is: ； where I AB represents the drinking closeness index; V ABi represents the total amount of alcohol consumed by both parties in a single joint drinking event; n represents the total number of times A and B drink together; T AB represents the cumulative interaction time of A and B in the drinking scene; N AB represents the number of times A and B clink glasses log represents the natural logarithm.

Images