Identity identification method and device, intelligent toilet and computer storage medium

Abstract

The present disclosure provides an identity recognition method and device, a smart toilet and a computer storage medium. The method is used to improve the accuracy of user identity recognition and thus improve the user experience. The method comprises: after determining that a user sits on a smart toilet, acquiring a human body parameter of the user, wherein the human body parameter comprises body fat and body weight; correcting the body fat of the user by using the body weight of the user to obtain corrected body fat; matching the corrected body fat and each registered human body parameter corresponding to the smart toilet respectively to obtain each matching value; based on the matching values, obtaining a target registered human body parameter corresponding to the corrected body fat of the user, and determining registered identity information corresponding to the target registered human body parameter as the identity information of the user.

Description

Technical Field

[0001] This invention relates to the field of information processing technology, and in particular to an identity recognition method, device, smart toilet, and computer storage medium. Background Technology

[0002] Currently, users can use smart toilets for health checks, especially when it comes to identifying the user's identity. Existing identification methods typically involve scanning or fingerprinting to log in, but these methods are inefficient and negatively impact the user experience.

[0003] To improve the efficiency of user identification and enhance user experience, some smart toilets can currently use body weight for identification. For example, the disclosed solution with patent number ZL201910395817.6 mentions a method for identification based on weight. However, due to the influence of the usage environment and the human body itself, not only are there differences in the weight measured under different body positions, but body weight may also fluctuate greatly in the short term, thus affecting the effectiveness of user identification and resulting in a low accuracy rate, thereby reducing the user experience. Summary of the Invention

[0004] This disclosure provides an identity recognition method, apparatus, smart toilet, and computer storage medium in exemplary embodiments. These are used to improve the accuracy of user identity recognition, thereby enhancing the user experience.

[0005] The first aspect of this disclosure provides an identity recognition method applied to a smart toilet, the method comprising:

[0006] The user's body fat percentage is adjusted using the user's weight to obtain the adjusted body fat percentage;

[0007] The corrected body fat percentage is matched with each registered human parameter corresponding to the smart toilet to obtain each matching value;

[0008] Based on the matching values, target registered human body parameters corresponding to the user's corrected body fat are obtained, and the registered identity information corresponding to the target registered human body parameters is determined as the user's identity information.

[0009] This embodiment uses the user's weight to correct for body fat percentage, and then uses the corrected body fat percentage to identify the user's identity. Since changes in posture can alter the measured body fat percentage, this embodiment uses the user's weight to correct for body fat percentage, and then uses the corrected body fat percentage to identify the user's identity. This improves the accuracy of user identification and thus enhances the user experience.

[0010] Furthermore, when users sit on the smart toilet, they naturally remove their outer pants, allowing their lower limbs to directly contact the toilet seat. Since the sensors for body fat and weight detection on typical smart toilets are usually located on the seat, this not only improves the accuracy of body fat detection and further enhances the accuracy of user identification, but also automatically identifies user information during toilet use without requiring the user to actively log in, thus improving user identification efficiency and further enhancing the user experience.

[0011] In one embodiment, the weight includes at least two pressure values, wherein each pressure value is obtained by measuring the user's weight at different locations on the smart toilet.

[0012] The step of correcting the user's body fat percentage using the user's weight to obtain the corrected body fat percentage includes:

[0013] If the weight includes two pressure values, a proportionality coefficient is obtained based on these two pressure values. A target correction coefficient is then obtained based on the proportionality coefficient and a pre-set fitting coefficient. This target correction coefficient is then used to correct the user's body fat percentage, resulting in the corrected body fat percentage; or...

[0014] If the user's weight includes more than two stress values, then the stress values ​​included in the weight and the body fat are input into a pre-trained body fat correction model to obtain the corrected body fat.

[0015] In this embodiment, different pressure values ​​corresponding to body weight are used to correct body fat percentages, resulting in a more accurate body fat percentage.

[0016] In one embodiment, the fitting coefficients include a first fitting coefficient and a second fitting coefficient;

[0017] The process of obtaining the target correction coefficient based on the proportional coefficient and the pre-set fitting coefficient includes:

[0018] Multiply the proportional coefficient by the first fitting coefficient to obtain the intermediate fitting coefficient, and add the intermediate fitting coefficient to the second fitting coefficient to obtain the target correction coefficient;

[0019] The process of obtaining the proportionality coefficient based on the two pressure values ​​included in the body weight includes:

[0020] Divide the two pressure values ​​to obtain the proportionality coefficient;

[0021] The step of correcting the user's body fat percentage using the target correction coefficient to obtain the corrected body fat percentage includes:

[0022] The corrected body fat percentage is obtained by multiplying the target correction factor by the body fat percentage.

[0023] This embodiment effectively establishes the fluctuation in body fat detection between different sitting postures by using the ratio of two pressure values ​​corresponding to body weight, effectively calibrating the user's body fat value and improving the accuracy of body fat detection.

[0024] In one embodiment, the corrected body fat percentage is obtained using the following formula:

[0025]

[0026] Wherein, F0 is the user's body fat percentage, F1 is the corrected body fat percentage, P1 is one of the two pressure values, P2 is the other of the two pressure values, N1 is the first fitting coefficient, and N2 is the second fitting coefficient.

[0027] In one embodiment, the step of matching the corrected body fat percentage with each registered human parameter corresponding to the smart toilet to obtain matching values ​​includes:

[0028] For any registered human parameter, the corrected body fat percentage is divided by the registered body fat percentage in the registered human parameter to obtain a first similarity value; the absolute value of the difference between the first similarity value and a specified value is determined as the matching value between the corrected body fat percentage and the registered human parameter; or,

[0029] For any registered human body parameter, the registered pressure values ​​in the registered weight are summed to obtain a first total pressure value, and the pressure values ​​in the user's weight are summed to obtain a second total pressure value. The second total pressure value is subtracted from the first total pressure value to obtain a pressure difference. The pressure difference is then divided by the first total pressure value to obtain a second similarity value. The absolute value of the second similarity value and the absolute value of the difference between the first similarity value and a specified value are determined as the corrected body fat and the matching value of the registered human body parameter, wherein the number of pressure values ​​included in the registered weight is the same as the number of pressure values ​​included in the user's weight.

[0030] In this embodiment, the matching value between the corrected body fat and the registered body fat is obtained by using the similarity value between the corrected body fat and the registered body fat, or the matching value is determined by using the corrected body fat and weight. This makes the determination of the matching value more accurate and improves the accuracy rate of the matching value.

[0031] In one embodiment, obtaining the target registered human parameters corresponding to the user-corrected body fat percentage based on the matching values ​​includes:

[0032] When the matching value includes a body fat matching value, then for any registered human parameter, if the body fat matching value in the matching value corresponding to the registered human parameter is less than a preset body fat threshold, then the registered human parameter is determined as the target registered human parameter corresponding to the user's corrected body fat, wherein the body fat matching value is a matching value determined based on the corrected body fat; or,

[0033] When the matching value includes body fat matching value and weight matching value, for any registered human parameter, if the body fat matching value is less than a preset body fat threshold and the weight matching value is less than a preset weight threshold, then the corresponding registered human parameter is determined as the target registered human parameter corresponding to the user's corrected body fat, wherein the weight matching value is a matching value determined based on the user's weight.

[0034] This embodiment determines the target registered human parameters by matching the body fat percentage or by combining it with the weight percentage from the registered human parameters. This makes the determined target registered human parameters more accurate.

[0035] In one embodiment, after obtaining the target registered human parameters corresponding to the user-corrected body fat percentage based on the matching values, the method further includes:

[0036] If the number of target registered human body parameters is a specified number, then the step of determining the registered identity information corresponding to the target registered human body parameters as the user's identity information is executed;

[0037] If the number of target registered human parameters is not equal to the specified number, then the user's ECG data from at least two leads are acquired, wherein the leads include limb leads and / or chest leads; contour recognition is performed on each ECG data to obtain the contours of each wave of a specified type in each ECG data, wherein the specified wave of each type includes at least one of P wave, T wave and QRS wave; the contours of each wave corresponding to each ECG data are projected onto a specified plane to obtain the user's ECG vector loop; the user's ECG vector loop is matched with each preset template ECG vector loop to obtain each matching value, wherein each preset template ECG vector loop corresponds to different user identity information; the user's identity information is determined based on each matching value.

[0038] This embodiment uses the user's electrocardiogram data to determine the user's identity information if the number of registered human parameters is not equal to the specified number, thereby ensuring that the user's identity information can be automatically identified and improving the efficiency of user identity information identification.

[0039] In one embodiment, the profile of any wave is composed of the potential difference of the heart at various points in time;

[0040] The step of projecting the contours of each wave corresponding to each ECG data onto a specified plane to obtain the user's ECG vector loop includes:

[0041] For any given wave of any specified type in any electrocardiogram (ECG) data, based on the wave's contour, the potential difference value corresponding to the wave at each time point is obtained; and...

[0042] Based on the potential difference value corresponding to the wave at each time point, the position coordinates of each projection point of the wave at each time point on the target coordinate axis are obtained, wherein the target coordinate axis is determined based on the lead corresponding to the electrocardiogram data;

[0043] The target position coordinates of the projection point are obtained by using the position coordinates of the projection point on the target coordinate axis at the same time point in each electrocardiogram data.

[0044] By using the target position coordinates of each projection point, the ECG vector loop corresponding to each wave of the specified type can be obtained;

[0045] The user's ECG vector loop is obtained by using the ECG vector loops corresponding to each wave of the specified type, wherein the number of the user's ECG vector loops is the same as the number of wave types.

[0046] This embodiment determines the user's ECG vector loop by projecting the contours of each wave corresponding to each ECG data onto a specified plane, making the determined ECG vector loop more accurate.

[0047] In one embodiment, determining the user's identity information based on the matching values ​​includes:

[0048] If any of the matching values ​​exceeds a specified threshold, the template ECG vector ring corresponding to the largest value among those exceeding the specified threshold is determined as the target template ECG vector ring. Then, using a preset correspondence between the template ECG vector ring and identity information, the identity information corresponding to the target template ECG vector ring is determined, and this determined identity information is then used as the user's identity information; or,

[0049] If none of the matching values ​​is greater than a specified threshold, the ECG vector rings are rotated in specified directions by specified angles to obtain multiple intermediate ECG vector rings. For any intermediate ECG vector ring, multiple different shrinkage ratios are used to shrink the intermediate ECG vector rings to obtain multiple target ECG vector rings. For any one of the preset template ECG vector rings, a preset matching algorithm is used to match the multiple target ECG vector rings with the template ECG vector rings to obtain matching values. The maximum value among the matching values ​​is determined as the target matching value between the user's ECG vector ring and the template ECG vector ring. The template ECG vector rings with target matching values ​​greater than a specified threshold are determined as the target template ECG vector rings. Using the preset correspondence between template ECG vector rings and identity information, the identity information corresponding to the target template ECG vector rings is determined, and the determined identity information is then used as the user's identity information.

[0050] In this embodiment, it is first determined whether there is a matching value greater than a specified threshold among the matching values. If a matching value greater than the specified threshold is found, the template ECG vector ring corresponding to the matching value with the largest value among the matching values ​​greater than the specified threshold is determined as the target template ECG vector ring, and the user's identity information is determined based on the target template ECG vector ring. If no matching value greater than the specified threshold is found, the ECG vector ring is rotated and shrunk. Then, the ECG vector ring after shrinkage is matched with each template ECG vector ring to obtain the target template ECG vector ring, and the user's identity information is determined based on the target template ECG vector ring. This improves the accuracy of user identity information.

[0051] In one embodiment, before performing contour recognition on each electrocardiogram (ECG) data to obtain the contours of each wave of a specified type in each ECG data, the method further includes:

[0052] The electrocardiogram data is then filtered and denoised.

[0053] In this embodiment, the ECG data needs to be filtered and denoised before contour recognition is performed, so as to make the contour recognition results more accurate.

[0054] A second aspect of this disclosure provides an identity verification device, the device comprising:

[0055] The first acquisition module is used to acquire the user's human body parameters after determining that the user is sitting on the smart toilet, wherein the human body parameters include body fat and weight.

[0056] The correction module is used to correct the user's body fat percentage based on the user's weight, thereby obtaining the corrected body fat percentage.

[0057] The first matching module is used to match the corrected body fat percentage with each registered human parameter corresponding to the smart toilet to obtain each matching value.

[0058] The first identity information determination module is used to obtain target registered human body parameters corresponding to the user's corrected body fat based on the matching values, and to determine the registered identity information corresponding to the target registered human body parameters as the user's identity information.

[0059] In one embodiment, the weight includes at least two pressure values, wherein each pressure value is obtained by measuring the user's weight at different locations on the smart toilet.

[0060] The correction module is specifically used for:

[0061] If the weight includes two pressure values, a proportionality coefficient is obtained based on these two pressure values. A target correction coefficient is then obtained based on the proportionality coefficient and a pre-set fitting coefficient. This target correction coefficient is then used to correct the user's body fat percentage, resulting in the corrected body fat percentage; or...

[0062] If the user's weight includes more than two stress values, then the stress values ​​included in the weight and the body fat are input into a pre-trained body fat correction model to obtain the corrected body fat.

[0063] In one embodiment, the fitting coefficients include a first fitting coefficient and a second fitting coefficient;

[0064] The correction module performs the process of obtaining the target correction coefficient based on the proportional coefficient and the pre-set fitting coefficient, specifically for:

[0065] Multiply the proportional coefficient by the first fitting coefficient to obtain the intermediate fitting coefficient, and add the intermediate fitting coefficient to the second fitting coefficient to obtain the target correction coefficient;

[0066] The correction module performs the calculation based on the two pressure values ​​included in the weight to obtain a proportionality coefficient, specifically used for:

[0067] Divide the two pressure values ​​to obtain the proportionality coefficient;

[0068] The correction module performs the correction of the user's body fat using the target correction coefficient to obtain the corrected body fat percentage, specifically for:

[0069] The corrected body fat percentage is obtained by multiplying the target correction factor by the body fat percentage.

[0070] In one embodiment, the correction module is specifically used for:

[0071] The corrected body fat percentage is obtained using the following formula:

[0072]

[0073] Wherein, F0 is the user's body fat percentage, F1 is the corrected body fat percentage, P1 is one of the two pressure values, P2 is the other of the two pressure values, N1 is the first fitting coefficient, and N2 is the second fitting coefficient.

[0074] In one embodiment, the first matching module is specifically used for:

[0075] For any registered human parameter, the corrected body fat percentage is divided by the registered body fat percentage in the registered human parameter to obtain a first similarity value; the absolute value of the difference between the first similarity value and a specified value is determined as the matching value between the corrected body fat percentage and the registered human parameter; or,

[0076] For any registered human body parameter, the registered pressure values ​​in the registered weight are summed to obtain a first total pressure value, and the pressure values ​​in the user's weight are summed to obtain a second total pressure value. The second total pressure value is subtracted from the first total pressure value to obtain a pressure difference. The pressure difference is then divided by the first total pressure value to obtain a second similarity value. The absolute value of the second similarity value and the absolute value of the difference between the first similarity value and a specified value are determined as the corrected body fat and the matching value of the registered human body parameter, wherein the number of pressure values ​​included in the registered weight is the same as the number of pressure values ​​included in the user's weight.

[0077] In one embodiment, the first identity information determination module is specifically used for:

[0078] When the matching value includes a body fat matching value, then for any registered human parameter, if the body fat matching value in the matching value corresponding to the registered human parameter is less than a preset body fat threshold, then the registered human parameter is determined as the target registered human parameter corresponding to the user's corrected body fat, wherein the body fat matching value is a matching value determined based on the corrected body fat; or,

[0079] When the matching value includes body fat matching value and weight matching value, for any registered human parameter, if the body fat matching value is less than a preset body fat threshold and the weight matching value is less than a preset weight threshold, then the corresponding registered human parameter is determined as the target registered human parameter corresponding to the user's corrected body fat, wherein the weight matching value is a matching value determined based on the user's weight.

[0080] In one embodiment, the apparatus further includes:

[0081] The second acquisition module is used to obtain target registered human parameters corresponding to the user's corrected body fat based on the matching values, and then acquire ECG data of the user in at least two leads, wherein the leads include limb leads and / or chest leads.

[0082] The contour recognition module is used to perform contour recognition on each electrocardiogram (ECG) data to obtain the contours of each wave of a specified type in each ECG data, wherein the specified wave of each type includes at least one of P wave, T wave and QRS wave.

[0083] The ECG vector loop determination module is used to project the contours of each wave corresponding to each ECG data onto a specified plane to obtain the user's ECG vector loop.

[0084] The second matching module is used to match the user's ECG vector ring with each preset template ECG vector ring to obtain each matching value, wherein each preset template ECG vector ring corresponds to different user identity information.

[0085] The second identity information determination module is used to determine the user's identity information based on the matching values.

[0086] In one embodiment, the profile of any wave is composed of the potential difference of the heart at various points in time;

[0087] The ECG vector loop determination module is specifically used for:

[0088] For any given wave of any specified type in any electrocardiogram (ECG) data, based on the wave's contour, the potential difference value corresponding to the wave at each time point is obtained; and...

[0089] Based on the potential difference value corresponding to the wave at each time point, the position coordinates of each projection point of the wave at each time point on the target coordinate axis are obtained, wherein the target coordinate axis is determined based on the lead corresponding to the electrocardiogram data;

[0090] The target position coordinates of the projection point are obtained by using the position coordinates of the projection point on the target coordinate axis at the same time point in each electrocardiogram data.

[0091] By using the target position coordinates of each projection point, the ECG vector loop corresponding to each wave of the specified type can be obtained;

[0092] The user's ECG vector loop is obtained by using the ECG vector loops corresponding to each wave of the specified type, wherein the number of the user's ECG vector loops is the same as the number of wave types.

[0093] In one embodiment, the second identity information determination module is specifically used for:

[0094] If any of the matching values ​​exceeds a specified threshold, the template ECG vector ring corresponding to the largest value among those exceeding the specified threshold is determined as the target template ECG vector ring. Then, using a preset correspondence between the template ECG vector ring and identity information, the identity information corresponding to the target template ECG vector ring is determined, and this determined identity information is then used as the user's identity information; or,

[0095] If none of the matching values ​​is greater than a specified threshold, the ECG vector rings are rotated in specified directions by specified angles to obtain multiple intermediate ECG vector rings. For any intermediate ECG vector ring, multiple different shrinkage ratios are used to shrink the intermediate ECG vector rings to obtain multiple target ECG vector rings. For any one of the preset template ECG vector rings, a preset matching algorithm is used to match the multiple target ECG vector rings with the template ECG vector rings to obtain matching values. The maximum value among the matching values ​​is determined as the target matching value between the user's ECG vector ring and the template ECG vector ring. The template ECG vector rings with target matching values ​​greater than a specified threshold are determined as the target template ECG vector rings. Using the preset correspondence between template ECG vector rings and identity information, the identity information corresponding to the target template ECG vector rings is determined, and the determined identity information is then used as the user's identity information.

[0096] In one embodiment, the apparatus further includes:

[0097] The preprocessing module is used to perform contour recognition on each ECG data. Before obtaining the contours of each wave of a specified type in each ECG data, the ECG data is filtered and denoised.

[0098] According to a third aspect of the present disclosure, a smart toilet is provided, comprising:

[0099] At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor; the instructions being executed by the at least one processor to enable the at least one processor to perform the method as described in the first aspect.

[0100] According to a fourth aspect provided in the embodiments of this disclosure, a computer storage medium is provided, the computer storage medium storing a computer program for performing the method as described in the first aspect. Attached Figure Description

[0101] To more clearly illustrate the technical solutions in the embodiments of this disclosure, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0102] Figure 1 This is a schematic diagram illustrating an applicable scenario according to one embodiment of the present disclosure;

[0103] Figure 2 This is one of the flowcharts illustrating an identity recognition method according to an embodiment of the present disclosure;

[0104] Figure 3 A schematic diagram of a process for correcting body fat according to an embodiment of the present disclosure;

[0105] Figure 4 This is a flowchart illustrating an identity recognition method based on electrocardiogram signals according to an embodiment of the present disclosure;

[0106] Figure 5 This is a schematic diagram of an electrocardiogram according to an embodiment of the present disclosure;

[0107] Figure 6 This is a schematic diagram of waves in electrocardiogram data according to an embodiment of the present disclosure;

[0108] Figure 7 This is a schematic diagram of a process for determining a user's electrocardiogram vector loop according to an embodiment of the present disclosure;

[0109] Figure 8 A schematic diagram of an electrocardiogram vector loop according to an embodiment of the present disclosure;

[0110] Figure 9This is a second schematic flowchart of an identity recognition method according to an embodiment of the present disclosure;

[0111] Figure 10 This is an identity recognition device according to one embodiment of the present disclosure;

[0112] Figure 11 This is a schematic diagram of the structure of a smart toilet according to an embodiment of the present disclosure. Detailed Implementation

[0113] To make the objectives, technical solutions, and advantages of the embodiments of this disclosure clearer, the technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this disclosure, and not all embodiments. Based on the embodiments of this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.

[0114] In this disclosure, the term "and / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent three cases: A alone, A and B simultaneously, and B alone. The character " / " generally indicates that the preceding and following related objects have an "or" relationship.

[0115] The application scenarios described in this disclosure are for the purpose of more clearly illustrating the technical solutions of this disclosure and do not constitute a limitation on the technical solutions provided in this disclosure. Those skilled in the art will understand that with the emergence of new application scenarios, the technical solutions provided in this disclosure are also applicable to similar technical problems. In the description of this disclosure, unless otherwise stated, "multiple" means two or more.

[0116] The ideas behind the embodiments of this disclosure are summarized below.

[0117] Existing methods for identity recognition based on weight are affected by the usage environment and the human body itself. Not only do weights measured in different body positions vary, but human weight may also fluctuate significantly in the short term, thus affecting the effectiveness of user identity recognition, resulting in low accuracy and reduced user experience.

[0118] Therefore, this disclosure provides an identity recognition method that corrects a user's body fat percentage using their weight, and then uses the corrected body fat percentage to identify the user's identity information. Since changes in a person's sitting posture can cause changes in the measured body fat percentage, this embodiment uses the user's weight to correct the body fat percentage, and then uses the corrected body fat percentage to identify the user's identity information. This improves the accuracy of user identity recognition, thereby enhancing the user experience. The solution of this disclosure will now be described in detail with reference to the accompanying drawings.

[0119] like Figure 1 As shown, an application scenario of an identity recognition method is presented, which includes a terminal device 110 and a smart toilet 120.

[0120] In one possible application scenario, once a user sits on the smart toilet 120, the smart toilet 120 acquires the user's body parameters, including body fat and weight. The smart toilet 120 uses the user's weight to correct the body fat percentage, obtaining a corrected body fat percentage. The corrected body fat percentage is then matched with each registered body parameter corresponding to the smart toilet, obtaining matching values. Based on these matching values, a target registered body parameter corresponding to the user's corrected body fat percentage is obtained, and the registered identity information corresponding to the target registered body parameter is identified as the user's identity information. The smart toilet 120 then sends the user's identity information to the terminal device 110 for display.

[0121] in, Figure 1 The smart toilet 120 and the terminal device 110 can interact through a communication network. The communication network can be either wireless or wired.

[0122] For example, the smart toilet 120 can access the network via cellular mobile communication technology and communicate with the terminal device 110, wherein the cellular mobile communication technology includes, for example, 5th Generation Mobile Networks (5G) technology.

[0123] Optionally, the smart toilet 120 can access the network and communicate with the terminal device 110 via short-range wireless communication, such as Wireless Fidelity (Wi-Fi) technology.

[0124] Furthermore, the description in this application focuses only on a single terminal device 110 and smart toilet 120. However, those skilled in the art should understand that the illustrated terminal device 110 and smart toilet 120 are intended to illustrate the operation of the terminal device 110 and smart toilet 120 involved in the technical solution of this application, and do not imply any limitation on the number, type, or location of the terminal device 110 and smart toilet 120. It should be noted that adding additional modules to or removing individual modules from the illustrated environment will not change the underlying concept of the exemplary embodiments of this disclosure.

[0125] For example, terminal device 110 includes, but is not limited to: large visual screens, tablet computers, laptops, handheld computers, mobile internet devices (MID), wearable devices, virtual reality (VR) devices, augmented reality (AR) devices, wireless terminal devices in industrial control, wireless terminal devices in autonomous driving, wireless terminal devices in smart grids, wireless terminal devices in transportation safety, wireless terminal devices in smart cities, or wireless terminal devices in smart homes, etc.; the terminal device may have a related client installed, which may be software (e.g., browsers, short video software, etc.), or web pages, mini-programs, etc.

[0126] It should be noted that the identity verification method proposed in this application is not only applicable to... Figure 1 The application scenarios shown can also be applied to any device with identity recognition capabilities.

[0127] The following describes an exemplary embodiment of the identity recognition method of this application in conjunction with the application scenarios described above and with reference to the accompanying drawings. It should be noted that the above application scenarios are only shown to facilitate understanding of the methods and principles of this application, and the implementation of this application is not limited in any way in this respect.

[0128] Figure 2 The flowchart of the identity recognition method disclosed herein may include the following steps:

[0129] Step 201: After confirming that the user is sitting on the smart toilet, obtain the user's human body parameters, including body fat and weight;

[0130] It should be noted that body fat is obtained through electrodes on the smart toilet, and the weight is measured by a pressure sensor on the smart toilet. The pressure sensor can also be used to determine whether the user is sitting on the smart toilet. That is, when the pressure sensor value is greater than a specified threshold, it is determined that the user is sitting on the smart toilet. The specific determination method can be set according to the actual situation. This embodiment is only used for illustration and does not limit the specific determination method.

[0131] Step 202: Correct the user's body fat percentage using the user's weight to obtain the corrected body fat percentage;

[0132] In one embodiment, body fat is corrected in the following two ways:

[0133] Method 1: For example Figure 3 The diagram shown illustrates the process of correcting body fat percentage, which includes the following steps:

[0134] Step 301: If the user's weight includes two pressure values, then obtain a proportionality coefficient based on the two pressure values ​​included in the weight;

[0135] In one embodiment, step 301 may be specifically implemented as: dividing the two pressure values ​​to obtain the proportionality coefficient.

[0136] Step 302: Based on the aforementioned proportional coefficient and the pre-set fitting coefficient, obtain the target correction coefficient;

[0137] The fitting coefficient can be linear or nonlinear, and can be set according to the actual situation. For example, when pressure sensors are installed at the front and back of the smart toilet seat, the fitting coefficient can be linear when the user sits on the seat and leans forward or backward; when the user's sitting posture is in other states, the fitting coefficient can be nonlinear. This embodiment does not limit this. The fitting coefficient in this embodiment includes a first fitting coefficient and a second fitting coefficient.

[0138] In one embodiment, step 302 may be specifically implemented as follows: multiplying the proportional coefficient by the first fitting coefficient to obtain an intermediate fitting coefficient, and adding the intermediate fitting coefficient to the second fitting coefficient to obtain the target correction coefficient.

[0139] Step 303: Correct the user's body fat using the target correction coefficient to obtain the corrected body fat.

[0140] In one embodiment, step 303 may be implemented by multiplying the target correction coefficient by the body fat percentage to obtain the corrected body fat percentage. The corrected body fat percentage can be determined using formula (1):

[0141]

[0142] Wherein, F0 is the user's body fat percentage, F1 is the corrected body fat percentage, P1 is one of the two pressure values, P2 is the other of the two pressure values, N1 is the first fitting coefficient, and N2 is the second fitting coefficient.

[0143] Method 2: If the user's weight includes more than two stress values, then input each stress value included in the weight and the body fat into a pre-trained body fat correction model to obtain the corrected body fat.

[0144] It should be noted that the training method of the body fat correction model in this embodiment can be adjusted according to the actual situation. This embodiment does not limit the training method of the body fat correction model.

[0145] Step 203: Match the corrected body fat percentage with each registered human parameter corresponding to the smart toilet to obtain the matching values;

[0146] In one embodiment, each matching value is determined in the following two ways:

[0147] Method 1: For any registered human parameter, divide the corrected body fat percentage by the registered body fat percentage in the registered human parameter to obtain a first similarity value; and determine the absolute value of the difference between the first similarity value and a specified value as the matching value between the corrected body fat percentage and the registered human parameter. The matching value can be obtained using formula (2):

[0148]

[0149] Among them, S n The matching value is F1, and the corrected body fat percentage is F. n For registered body fat, A is the specified value.

[0150] It should be noted that: In this embodiment, the specified value A is 1, but the specified value is not limited. The specific value of the specified value can be set according to the actual situation.

[0151] Method 2: For any registered human body parameter, sum the registered pressure values ​​in the registered weight to obtain a first total pressure value, and sum the pressure values ​​in the user's weight to obtain a second total pressure value; subtract the second total pressure value from the first total pressure value to obtain a pressure difference, then divide the pressure difference by the first total pressure value to obtain a second similarity value, and determine the absolute value of the second similarity value and the absolute value of the difference between the first similarity value and a specified value as the corrected body fat and the matching value of the registered human body parameter, wherein the number of pressure values ​​included in the registered weight is the same as the number of pressure values ​​included in the user's weight. The second similarity value is obtained through formula (3):

[0152]

[0153] Where H is the second similarity value, P1~P n For each pressure value in the user's weight, P 10 ~P n0 These are the registered stress values ​​for each registered weight.

[0154] Step 204: Based on the matching values, obtain the target registered human body parameters corresponding to the user's corrected body fat, and determine the registered identity information corresponding to the target registered human body parameters as the user's identity information.

[0155] In one embodiment, the target registered human parameters can be determined in two ways:

[0156] Method 1: When the matching value includes a body fat matching value, for any registered human parameter, if the body fat matching value in the matching value corresponding to the registered human parameter is less than a preset body fat threshold, then the registered human parameter is determined as the target registered human parameter corresponding to the user's corrected body fat, wherein the body fat matching value is the matching value determined based on the corrected body fat.

[0157] For example, the user-corrected body fat percentage matches registered body fat percentage 1 in registered human parameters 1 with a value of A; the user-corrected body fat percentage matches registered body fat percentage 2 in registered human parameters 1 with a value of B; and the user-corrected body fat percentage matches registered body fat percentage 3 in registered human parameters 3 with a value of C. If C is determined to be less than a preset body fat percentage threshold, then registered human parameter 3 corresponding to the matching value C is determined as the target registered human parameter that matches the user-corrected body fat percentage.

[0158] Method 2: When the matching value includes body fat matching value and weight matching value, for any registered human parameter, if the body fat matching value is less than a preset body fat threshold and the weight matching value is less than a preset weight threshold, then the registered human parameter is determined as the target registered human parameter corresponding to the user's corrected body fat, wherein the weight matching value is a matching value determined based on the user's weight.

[0159] For example, the user-corrected body fat percentage matches the registered body fat percentage 1 in registered anatomy parameter 1 with a value of A, and matches the registered weight percentage 1 in registered anatomy parameter 1 with a value of M. The user-corrected body fat percentage matches the registered body fat percentage 2 in registered anatomy parameter 2 with a value of B, and the user-corrected weight matches the registered weight percentage 2 in registered anatomy parameter 2 with a value of N. The user-corrected body fat percentage matches the registered body fat percentage 3 in registered anatomy parameter 3 with a value of C, and the user-corrected weight matches the registered weight percentage 3 in registered anatomy parameter 3 with a value of Q. If it is determined that the matching value C is less than a preset body fat percentage threshold and the matching value Q is less than a preset weight percentage threshold, then the registered anatomy parameter 3 corresponding to the registered body fat percentage 3 and registered weight percentage 3 is determined to be the target registered anatomy parameter.

[0160] It should be noted that the preset body fat threshold and preset weight threshold in this embodiment can be set according to the actual situation, and this embodiment does not limit them.

[0161] After identifying the user, in one embodiment, the registered body fat percentage in the user's registered anatomy parameters is updated in the following way:

[0162] The user's corrected body fat percentage and the user's registered body fat percentage are weighted and summed to obtain the updated registered body fat percentage, which is then determined as the user's registered body fat percentage. The updated registered body fat percentage is obtained using formula (4):

[0163] F n ′ =m×F n +n×F1……(4);

[0164] Among them, F n ′ For the updated registered body fat, F n The registered body fat percentage is F1, the user-corrected body fat percentage is m, the preset weight of the registered body fat percentage is n, and the preset weight of the corrected body fat percentage is n.

[0165] It should be noted that in this embodiment, m is 0.9 and n is 0.1, but the specific values ​​of m and n are not limited. The specific values ​​of m and n can be set according to the actual situation.

[0166] To ensure automatic identification of user identity information, after obtaining the target registered human parameters based on the matching values, the following two scenarios may be included:

[0167] Scenario 1: If the number of target registered human body parameters is a specified number, then the step of determining the registration identity information corresponding to the target registered human body parameters as the user's identity information is executed. For example, Table 1 shows the correspondence between target registered human body parameters and registration identity information:

[0168] Target registered anthropometric parameters (body fat and / or weight) Register identity information Target registration human parameters 1 Registration Identity Information A Target registered human parameters 2 Registered identity information B Target registration human parameters 3 Registered identity information C ... ...

[0169] Table 1

[0170] The registered identity information includes name, age, gender, etc., which can be set according to the actual situation. This embodiment does not limit this setting.

[0171] As shown in Table 1, if the target registered human body parameter is target registered human body parameter 1 and the specified quantity is 1, then the registered identity information A corresponding to target registered human body parameter 1 will be determined as the user's identity information.

[0172] Scenario 2: If the number of target registered human parameters is not equal to the specified number, then an electrocardiogram (ECG) signal is used to identify the user. It should be noted that the specified number in this embodiment is 1, but this embodiment does not limit the specified number; the specified number can be set according to the actual situation.

[0173] like Figure 4 The diagram shown illustrates a flowchart of an identity verification method based on electrocardiogram (ECG) signals, including the following steps:

[0174] Step 401: Obtain ECG data from at least two leads of the user, wherein the leads include limb leads and / or chest leads;

[0175] For example, such as Figure 5 The diagram shows a schematic of an electrocardiogram (ECG), which includes leads I, II, III, aVR, aVF, aVL, and leads V1 to V6. In this embodiment, the ECG data for each lead is at least two ECG data points from leads I, II, III, aVR, aVF, aVL, and leads V1 to V6.

[0176] In this embodiment, ECG data is acquired using a device capable of detecting ECG data. Taking a smart toilet as an example, the specific method for acquiring ECG data from at least two leads is for the user to sit on the smart toilet with both legs touching the electrodes on the toilet seat and holding the handle electrodes with both hands to acquire the user's ECG data. Different devices can use different methods to acquire ECG data, and the specific acquisition method can be set according to the actual situation. This embodiment will not limit it further.

[0177] To make the identification results more accurate, in one embodiment, the electrocardiogram data is filtered and denoised.

[0178] It should be noted that the filtering and denoising process in this embodiment can use time-frequency domain digital signal processing methods, wavelet transform processing methods, and adaptive filtering processing methods, etc. The specific filtering and denoising method can be set according to the actual situation. This embodiment does not limit the filtering and denoising method, and the filtering and denoising process needs to perform full-band processing on the ECG data.

[0179] Step 402: Perform contour recognition on each ECG data to obtain the contour of each wave of a specified type in each ECG data, wherein each wave of the specified type includes at least one of P wave, T wave and QRS wave;

[0180] For example, such as Figure 6 The image shows the waves in electrocardiogram (ECG) data. The dark gray solid line represents the P wave, the light gray solid line represents the Q wave, the dark gray dashed line represents the R wave, the black dashed line represents the S wave, and the black dashed line represents the T wave. In this embodiment, the wave colors and lines are only used to illustrate the corresponding wave segments and do not limit the specific waves.

[0181] In this embodiment, the contour recognition method can be a signal processing feature extraction method or a deep learning contour recognition method, etc. The specific contour recognition method can be set according to the actual situation, and this embodiment does not limit it.

[0182] Step 403: Project the contours of each wave corresponding to each ECG data onto a specified plane to obtain the user's ECG vector loop;

[0183] like Figure 7 The diagram shown illustrates the process for determining a user's ECG vector loop, including the following steps:

[0184] Step 701: For any wave of any specified type in any ECG data, based on the contour of the wave, obtain the potential difference value corresponding to the wave at each time point;

[0185] For example, such as Figure 5The electrocardiogram (ECG) shown has the following representation: the horizontal axis of the waveform corresponding to any lead represents the time point, and the vertical axis represents the potential difference. A standard ECG... Figure 1 Generally, it is a 1mm*1mm grid graph paper. And the standard paper speed for electrocardiograms is 25mm / s, so each small square on the horizontal axis of a standard electrocardiogram represents 0.04s, and each small square on the vertical axis represents 0.1mV.

[0186] Step 702: Based on the potential difference value corresponding to the wave at each time point, obtain the position coordinates of each projection point of the wave at each time point on the target coordinate axis, wherein the target coordinate axis is determined based on the lead corresponding to the ECG data;

[0187] The target coordinate axes include the X-axis, Y-axis, and Z-axis. The target coordinate axes for each lead's ECG data are pre-set.

[0188] In one embodiment, the target position coordinates of each projection point of the wave at each time point on the target coordinate axis X can be determined by formula (5):

[0189] X0 = cos A° × Y t (5);

[0190] Where X0 is the position coordinate of the wave at time t on the target coordinate axis X, and A is the pre-set projection angle. t Let be the potential difference of the wave at time point t.

[0191] If the ECG data includes ECG data from lead I, then in this embodiment, A equals 0. Furthermore, the value of A is obtained based on the current lead I and the target coordinate axis X.

[0192] In one embodiment, the target position coordinates of each projection point of the wave at each time point on the target coordinate axis Y can be determined by formula (6):

[0193] Y0=cos B°×Y t (6);

[0194] Where Y0 is the position coordinate of the wave at time t on the target coordinate axis Y, and B° is the pre-set projection angle. t Let be the potential difference of the wave at time point t.

[0195] If the ECG data includes ECG data from lead II, then in this embodiment, B is 30, and the value of B is obtained based on the current lead II and the target coordinate axis Y.

[0196] In one embodiment, the target position coordinates of each projection point of the wave at each time point on the target coordinate axis Z can be determined by formula (7):

[0197] Z0=cos C°×Y t (7);

[0198] Where Z0 is the position coordinate of the wave at time t on the target coordinate axis Z, and C° is the pre-set projection angle. t Let be the potential difference of the wave at time point t.

[0199] Step 703: Based on the position coordinates of the projection points corresponding to the same time point in each ECG data on the target coordinate axis, obtain the target position coordinates of the projection points;

[0200] For example, in this embodiment, the ECG data used are leads I and II, and the target coordinate axis corresponding to lead I is the X-axis, and the target coordinate axis corresponding to lead II is the Y-axis. Therefore, the target position coordinates of the projection point corresponding to time point t are (X... t Y t ).

[0201] Step 704: Obtain the ECG vector loop corresponding to each wave of the specified type by using the target position coordinates of each projection point;

[0202] For example, such as Figure 8 As shown, the P wave is in lead I data. Based on the position coordinates of the projection points corresponding to each time point in the P wave, the ECG vector loop corresponding to the P wave is obtained.

[0203] Step 705: Using the ECG vector loops corresponding to each wave of the specified type, obtain the user's ECG vector loop, wherein the number of the user's ECG vector loops is the same as the number of wave types.

[0204] Specifically, for any given type, a preset algorithm is used to correct the ECG vector loop of each wave of the given type to obtain the user's ECG vector loop.

[0205] The preset algorithm may include geometric mean and piecewise fitting, etc., and can be set according to the actual situation. This embodiment does not limit it.

[0206] Step 404: Match the user's ECG vector loop with each preset template ECG vector loop to obtain each matching value, wherein each preset template ECG vector loop corresponds to different user identity information;

[0207] The template ECG vector loop is created when a user first uses a device with ECG monitoring, by entering their personal information through a standard application. The device then measures the user's ECG data, and a template ECG vector loop is generated based on this data. A single user can create multiple ECG vector loop templates; for example, templates can be created based on different body postures (e.g., leaning forward, leaning back, and normal sitting posture). This improves matching efficiency.

[0208] It should be noted that the preset matching algorithm in this embodiment includes matching algorithms such as Hu moment, and the specific algorithm can be set according to the actual situation. This embodiment does not limit it here. The number of ECG vector loops of the user can be one or more, and the number of ECG vector loops of the user is the same as the number of ECG vector loops in the template.

[0209] In one embodiment, step 404 can be implemented in the following two ways:

[0210] If the user has multiple ECG vector rings, then for any template ECG vector ring, the user's ECG vector ring is matched with ECG vector rings of the same type in the template ECG vector ring to obtain intermediate matching values. The intermediate matching values ​​corresponding to each type are weighted and summed to obtain the matching value between the user's ECG vector ring and the template ECG vector ring.

[0211] If the user has only one ECG vector loop, then the user's ECG vector loop is matched with each of the preset template ECG vector loops to obtain each matching value.

[0212] Step 405: Determine the user's identity information based on the matching values.

[0213] In one embodiment, the user's identity information is determined in the following two ways:

[0214] Method 1: If there is a matching value greater than a specified threshold among the matching values, then the template ECG vector ring corresponding to the matching value with the largest value among the matching values ​​greater than the specified threshold is determined as the target template ECG vector ring. After determining the identity information corresponding to the target template ECG vector ring by using the preset correspondence between the template ECG vector ring and identity information, the determined identity information is determined as the user's identity information.

[0215] For example, taking the number of ECG vector rings for a user as one, the matching value between user 1's ECG vector ring and template ECG vector ring 1 is 65%, the matching value between user 1's ECG vector ring and template ECG vector ring 2 is 30%, and the matching value between user 1's ECG vector ring and template ECG vector ring 3 is 90%. If the specified threshold is 60%, then the target template ECG vector rings are determined to be template ECG vector ring 1 and template ECG vector ring 3. Since the matching value of template ECG vector ring 3 is greater than the matching value of template ECG vector ring 1, the identity information corresponding to template ECG vector ring 3 is determined to be user 1's identity information.

[0216] Method 2: If none of the matching values ​​is greater than a specified threshold, the ECG vector ring is rotated in each specified direction by a specified angle to obtain multiple intermediate ECG vector rings. For any intermediate ECG vector ring, multiple different shrinkage ratios are used to shrink the intermediate ECG vector ring to obtain multiple target ECG vector rings. For any one of the preset template ECG vector rings, a preset matching algorithm is used to match the multiple target ECG vector rings with the template ECG vector ring to obtain matching values. The maximum value among the matching values ​​is determined as the target matching value between the user's ECG vector ring and the template ECG vector ring. The template ECG vector ring with a target matching value greater than a specified threshold is determined as the target template ECG vector ring. Using the preset correspondence between template ECG vector rings and identity information, the identity information corresponding to the target template ECG vector ring is determined, and the determined identity information is then used as the user's identity information.

[0217] In this embodiment, due to the slight change in the heart axis angle caused by leaning forward or backward while sitting, and the change in contraction intensity caused by physiological factors such as before or after meals and exercise, the specified rotation angle can be set to ±20 degrees, and the contraction ratio range can be set to 0.67–1.5. However, this embodiment does not limit the specified rotation angle and contraction ratio, and can be set according to the actual situation. Table 1 shows the correspondence between the template ECG vector loop and the identity information:

[0218] Template ECG vector loop Identity information Template ECG Vector Loop 1 Identity Information A Template ECG Vector Loop 2 Identity Information B Template ECG Vector Loop 3 Identity Information C … …

[0219] Table 2

[0220] It should be noted that the identity information in this embodiment includes name, gender, age, etc., which can be set according to the actual situation, and this embodiment will not limit it here. Furthermore, after each match with the target template ECG vector loop, methods such as geometric averaging or piecewise fitting can be used to track the user's ECG vector loop to update the template ECG vector loop for better matching.

[0221] After identifying the user's identity information, the test data can be associated with that user's identity information so that the user can access their own test data, which includes data such as electrocardiogram data and urine test data.

[0222] In one embodiment, if the user's identity information cannot be determined, the user should be prompted that the identification has failed and reminded to log in through a regular means such as an app so that the user's detection data can be associated with the user's identity information. At the same time, the ECG vector loop of the user detected this time should be set as the user's template ECG vector loop so that the user's identity information can be automatically identified next time.

[0223] If the user is a new user, they can be prompted via voice to register and log in through conventional methods such as an app, so that the user's test data can be associated with their identity information. Simultaneously, the ECG vector loop detected for this user will be set as their template ECG vector loop.

[0224] To further understand the technical solution of this disclosure, the following is in conjunction with... Figure 9 Provide a detailed explanation. Figure 9 The following steps are used as an example to illustrate human body parameters including weight and body fat:

[0225] Step 901: After confirming that the user is sitting on the smart toilet, obtain the user's human body parameters, including body fat and weight;

[0226] Step 902: Correct the user's body fat percentage using the user's weight to obtain the corrected body fat percentage;

[0227] Step 903: Match the corrected body fat percentage with each registered human parameter corresponding to the smart toilet to obtain the matching values;

[0228] Step 904: Based on the matching values, obtain the target registered human body parameters corresponding to the user's corrected body fat, and determine the registered identity information corresponding to the target registered human body parameters as the user's identity information;

[0229] Step 905: Determine whether the number of the target registered human parameters is equal to the specified number. If yes, proceed to step 906; otherwise, proceed to step 907.

[0230] Step 906: Determine the identity information corresponding to the target registered human body parameters as the user's identity information;

[0231] Step 907: Obtain ECG data from at least two leads of the user, wherein the leads include limb leads and / or chest leads;

[0232] Step 908: Perform contour recognition on each ECG data to obtain the contour of each wave of a specified type in each ECG data, wherein each wave of the specified type includes at least one of P wave, T wave and QRS wave;

[0233] Step 909: Project the contours of each wave corresponding to each ECG data onto a specified plane to obtain the user's ECG vector loop;

[0234] Step 910: Match the user's ECG vector loop with each preset template ECG vector loop to obtain each matching value, wherein each preset template ECG vector loop corresponds to different user identity information;

[0235] Step 911: Determine the user's identity information based on the matching values.

[0236] Based on the same disclosed concept, the identity recognition method described above can also be implemented by an identity recognition device. The effect of this device is similar to that of the aforementioned method, and will not be described further here.

[0237] Figure 10 This is a schematic diagram of the structure of an identity recognition-based device according to an embodiment of the present disclosure.

[0238] like Figure 10 As shown, the identity recognition device 1000 disclosed herein may include a first acquisition module 1010, a correction module 1020, a first matching module 1030, and a first identity information determination module 1040.

[0239] The first acquisition module 1010 is used to acquire the user's human body parameters after determining that the user is sitting on the smart toilet, wherein the human body parameters include body fat and weight.

[0240] The correction module 1020 is used to correct the user's body fat percentage based on the user's weight to obtain the corrected body fat percentage.

[0241] The first matching module 1030 is used to match the corrected body fat percentage with each registered human body parameter corresponding to the smart toilet to obtain each matching value.

[0242] The first identity information determination module 1040 is used to obtain target registered human body parameters corresponding to the user's corrected body fat based on the matching values, and to determine the registered identity information corresponding to the target registered human body parameters as the user's identity information.

[0243] In one embodiment, the weight includes at least two pressure values, wherein each pressure value is obtained by measuring the user's weight at different locations on the smart toilet;

[0244] The correction module 1020 is specifically used for:

[0245] If the weight includes two pressure values, a proportionality coefficient is obtained based on these two pressure values. A target correction coefficient is then obtained based on the proportionality coefficient and a pre-set fitting coefficient. This target correction coefficient is then used to correct the user's body fat percentage, resulting in the corrected body fat percentage; or...

[0246] If the user's weight includes more than two stress values, then the stress values ​​included in the weight and the body fat are input into a pre-trained body fat correction model to obtain the corrected body fat.

[0247] In one embodiment, the fitting coefficients include a first fitting coefficient and a second fitting coefficient;

[0248] The correction module 1020 executes the process of obtaining the target correction coefficient based on the proportional coefficient and the preset fitting coefficient, specifically for:

[0249] Multiply the proportional coefficient by the first fitting coefficient to obtain the intermediate fitting coefficient, and add the intermediate fitting coefficient to the second fitting coefficient to obtain the target correction coefficient;

[0250] The correction module 1020 executes the process of obtaining a proportionality coefficient based on the two pressure values ​​included in the weight, specifically for:

[0251] Divide the two pressure values ​​to obtain the proportionality coefficient;

[0252] The correction module 1020 performs the correction of the user's body fat using the target correction coefficient to obtain the corrected body fat, specifically for:

[0253] The corrected body fat percentage is obtained by multiplying the target correction factor by the body fat percentage.

[0254] In one embodiment, the correction module 1020 is specifically used for:

[0255] The corrected body fat percentage is obtained using the following formula:

[0256]

[0257] Wherein, F0 is the user's body fat percentage, F1 is the corrected body fat percentage, P1 is one of the two pressure values, P2 is the other of the two pressure values, N1 is the first fitting coefficient, and N2 is the second fitting coefficient.

[0258] In one embodiment, the first matching module 1030 is specifically used for:

[0259] For any registered human parameter, the corrected body fat percentage is divided by the registered body fat percentage in the registered human parameter to obtain a first similarity value; the absolute value of the difference between the first similarity value and a specified value is determined as the matching value between the corrected body fat percentage and the registered human parameter; or,

[0260] For any registered human body parameter, the registered pressure values ​​in the registered weight are summed to obtain a first total pressure value, and the pressure values ​​in the user's weight are summed to obtain a second total pressure value. The second total pressure value is subtracted from the first total pressure value to obtain a pressure difference. The pressure difference is then divided by the first total pressure value to obtain a second similarity value. The absolute value of the second similarity value and the absolute value of the difference between the first similarity value and a specified value are determined as the corrected body fat and the matching value of the registered human body parameter, wherein the number of pressure values ​​included in the registered weight is the same as the number of pressure values ​​included in the user's weight.

[0261] In one embodiment, the first identity information determination module 1040 is specifically used for:

[0262] When the matching value includes a body fat matching value, then for any registered human parameter, if the body fat matching value in the matching value corresponding to the registered human parameter is less than a preset body fat threshold, then the registered human parameter is determined as the target registered human parameter corresponding to the user's corrected body fat, wherein the body fat matching value is a matching value determined based on the corrected body fat; or,

[0263] When the matching value includes body fat matching value and weight matching value, for any registered human parameter, if the body fat matching value is less than a preset body fat threshold and the weight matching value is less than a preset weight threshold, then the corresponding registered human parameter is determined as the target registered human parameter corresponding to the user's corrected body fat, wherein the weight matching value is a matching value determined based on the user's weight.

[0264] In one embodiment, the apparatus further includes:

[0265] The second acquisition module 1050 is used to acquire at least two leads of the user's electrocardiogram data after obtaining the target registered human parameters corresponding to the user's corrected body fat based on the matching values, wherein the leads include limb leads and / or chest leads.

[0266] The contour recognition module 1060 is used to perform contour recognition on each electrocardiogram data to obtain the contour of each wave of a specified type in each electrocardiogram data, wherein the specified type of wave includes at least one of P wave, T wave and QRS wave.

[0267] The ECG vector loop determination module 1070 is used to project the contours of each wave corresponding to each ECG data onto a specified plane to obtain the user's ECG vector loop.

[0268] The second matching module 1080 is used to match the user's ECG vector ring with each preset template ECG vector ring to obtain each matching value, wherein each preset template ECG vector ring corresponds to different user identity information.

[0269] The second identity information determination module 1090 is used to determine the user's identity information based on the matching values.

[0270] In one embodiment, the profile of any wave is composed of the potential difference of the heart at various points in time;

[0271] The ECG vector loop determination module 1070 is specifically used for:

[0272] For any given wave of any specified type in any electrocardiogram (ECG) data, based on the wave's contour, the potential difference value corresponding to the wave at each time point is obtained; and...

[0273] Based on the potential difference value corresponding to the wave at each time point, the position coordinates of each projection point of the wave at each time point on the target coordinate axis are obtained, wherein the target coordinate axis is determined based on the lead corresponding to the electrocardiogram data;

[0274] The target position coordinates of the projection point are obtained by using the position coordinates of the projection point on the target coordinate axis at the same time point in each electrocardiogram data.

[0275] By using the target position coordinates of each projection point, the ECG vector loop corresponding to each wave of the specified type can be obtained;

[0276] The user's ECG vector loop is obtained by using the ECG vector loops corresponding to each wave of the specified type, wherein the number of the user's ECG vector loops is the same as the number of wave types.

[0277] In one embodiment, the second identity information determination module 1090 is specifically used for:

[0278] If any of the matching values ​​exceeds a specified threshold, the template ECG vector ring corresponding to the largest value among those exceeding the specified threshold is determined as the target template ECG vector ring. Then, using a preset correspondence between the template ECG vector ring and identity information, the identity information corresponding to the target template ECG vector ring is determined, and this determined identity information is then used as the user's identity information; or,

[0279] If none of the matching values ​​is greater than a specified threshold, the ECG vector rings are rotated in specified directions by specified angles to obtain multiple intermediate ECG vector rings. For any intermediate ECG vector ring, multiple different shrinkage ratios are used to shrink the intermediate ECG vector rings to obtain multiple target ECG vector rings. For any one of the preset template ECG vector rings, a preset matching algorithm is used to match the multiple target ECG vector rings with the template ECG vector rings to obtain matching values. The maximum value among the matching values ​​is determined as the target matching value between the user's ECG vector ring and the template ECG vector ring. The template ECG vector rings with target matching values ​​greater than a specified threshold are determined as the target template ECG vector rings. Using the preset correspondence between template ECG vector rings and identity information, the identity information corresponding to the target template ECG vector rings is determined, and the determined identity information is then used as the user's identity information.

[0280] In one embodiment, the apparatus further includes:

[0281] The preprocessing module 1091 is used to perform contour recognition on each electrocardiogram (ECG) data and to perform filtering and noise reduction processing on the ECG data before obtaining the contours of each wave of a specified type in each ECG data.

[0282] After introducing an identity recognition method and apparatus according to an exemplary embodiment of the present disclosure, another exemplary embodiment of a smart toilet according to the present disclosure will be introduced next.

[0283] Those skilled in the art will understand that various aspects of this disclosure can be implemented as a system, method, or program product. Therefore, various aspects of this disclosure can be specifically implemented in the following forms: a completely hardware implementation, a completely software implementation (including firmware, microcode, etc.), or a combination of hardware and software aspects, collectively referred to herein as a "circuit," "module," or "system."

[0284] In some possible implementations, the smart toilet according to this disclosure may include at least one processor and at least one computer storage medium. The computer storage medium stores program code that, when executed by the processor, causes the processor to perform the steps of the identification methods according to the various exemplary embodiments of this disclosure described above. For example, the processor may perform actions such as... Figure 2 Steps 201-204 are shown in the diagram.

[0285] The following reference Figure 11 To describe an intelligent toilet 1100 according to such an embodiment of the present disclosure. Figure 11 The smart toilet 1100 shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments disclosed herein.

[0286] like Figure 11 As shown, the smart toilet 1100 is presented in the form of a general smart toilet. The components of the smart toilet 1100 may include, but are not limited to: at least one processor 1101, at least one computer storage medium 1102, and a bus 1103 connecting different system components (including the computer storage medium 1102 and the processor 1101).

[0287] Bus 1103 represents one or more of several bus structures, including a computer storage media bus or computer storage media controller, peripheral bus, processor, or local bus using any of the various bus structures.

[0288] Computer storage medium 1102 may include readable media in the form of volatile computer storage media, such as random access computer storage medium (RAM) 1121 and / or cache storage medium 1122, and may further include read-only computer storage medium (ROM) 1123.

[0289] The computer storage medium 1102 may also include a program / utility 1125 having a set (at least one) of program modules 1124, including but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of these examples may include an implementation of a network environment.

[0290] The smart toilet 1100 can also communicate with one or more external devices 1104 (e.g., keyboard, pointing device, etc.), one or more devices that enable a user to interact with the smart toilet 1100, and / or any device that enables the smart toilet 1100 to communicate with one or more other smart toilets (e.g., router, modem, etc.). This communication can be performed via input / output (I / O) interface 1105. Furthermore, the smart toilet 1100 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 1106. As shown, network adapter 1106 communicates with other modules used in the smart toilet 1100 via bus 1103. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with the smart toilet 1100, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0291] In some possible implementations, aspects of an identity recognition method provided in this disclosure may also be implemented as a program product comprising program code that, when run on a computer device, causes the computer device to perform the steps of the identity recognition method according to the various exemplary embodiments of this disclosure described above.

[0292] The program product may take the form of any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: electrical connections having one or more wires, portable disks, hard disks, random access computer storage media (RAM), read-only computer storage media (ROM), erasable programmable read-only computer storage media (EPROM or flash memory), optical fibers, portable compact disk read-only computer storage media (CD-ROM), optical computer storage media, magnetic computer storage media, or any suitable combination thereof.

[0293] The identity verification program product of this disclosure can be a portable compact disc read-only computer storage medium (CD-ROM) and include program code, and can run on a smart toilet. However, the program product of this disclosure is not limited thereto. In this document, the readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0294] A readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying readable program code. This propagated data signal may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium, capable of sending, propagating, or transmitting a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0295] The program code contained on the readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0296] Program code for performing the operations of this disclosure can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's smart toilet, partially on the user's device, as a standalone software package, partially on the user's smart toilet and partially on a remote smart toilet, or entirely on a remote smart toilet or server. In cases involving remote smart toilets, the remote smart toilet can be connected to the user's smart toilet via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external smart toilet (e.g., via the Internet using an Internet service provider).

[0297] It should be noted that although several modules of the apparatus have been mentioned in the detailed description above, this division is merely exemplary and not mandatory. In fact, according to embodiments of this disclosure, the features and functions of two or more modules described above can be embodied in one module. Conversely, the features and functions of one module described above can be further divided and embodied by multiple modules.

[0298] Furthermore, although the operations of the methods disclosed herein are described in a specific order in the accompanying drawings, this does not require or imply that these operations must be performed in that specific order, or that all of the operations shown must be performed to achieve the desired result. Additionally or alternatively, certain steps may be omitted, multiple steps may be combined into one step, and / or one step may be broken down into multiple steps.

[0299] Those skilled in the art will understand that embodiments of this disclosure can be provided as methods, systems, or computer program products. Therefore, this disclosure can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this disclosure can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk computer storage media, CD-ROMs, optical computer storage media, etc.) containing computer-usable program code.

[0300] This disclosure is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to this disclosure. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0301] These computer program instructions may also be stored in a computer-readable computer storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable computer storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0302] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0303] Obviously, those skilled in the art can make various modifications and variations to this disclosure without departing from its spirit and scope. Therefore, if such modifications and variations fall within the scope of the claims of this disclosure and their equivalents, this disclosure is also intended to include such modifications and variations.

Claims

1. An identity recognition method, characterized in that, The method, applied to smart toilets, includes: Once it is determined that a user is sitting on the smart toilet, the user's human body parameters are obtained, including body fat and weight. The user's body fat percentage is adjusted using the user's weight to obtain the adjusted body fat percentage; The corrected body fat percentage is matched with each registered human parameter corresponding to the smart toilet to obtain each matching value; Based on the matching values, the target registered human parameters corresponding to the user's corrected body fat are obtained; If the number of target registered human body parameters is a specified number, then the registered identity information corresponding to the target registered human body parameters will be determined as the user's identity information; If the number of target registered human parameters is not equal to the specified number, then acquire ECG data from at least two leads of the user; perform contour recognition on each ECG data to obtain the contour of each wave of a specified type in each ECG data; project the contour of each wave corresponding to each ECG data onto a specified plane to obtain the user's ECG vector loop; match the user's ECG vector loop with each preset template ECG vector loop to obtain each matching value; and determine the user's identity information based on each matching value. The step of determining the user's identity information based on the matching values ​​includes: If none of the matching values ​​is greater than a specified threshold, the ECG vector rings are rotated in specified directions by specified angles to obtain multiple intermediate ECG vector rings. For any intermediate ECG vector ring, multiple different shrinkage ratios are used to shrink the intermediate ECG vector rings to obtain multiple target ECG vector rings. For any one of the preset template ECG vector rings, a preset matching algorithm is used to match the multiple target ECG vector rings with the template ECG vector rings to obtain matching values. The maximum value among the matching values ​​is determined as the target matching value between the user's ECG vector ring and the template ECG vector ring. The template ECG vector rings with target matching values ​​greater than a specified threshold are determined as target template ECG vector rings. Using the preset correspondence between template ECG vector rings and identity information, the identity information corresponding to the target template ECG vector ring is determined, and the determined identity information is then used as the user's identity information.

2. The method according to claim 1, characterized in that, The weight includes at least two pressure values, wherein each pressure value is obtained by measuring the user's weight at different locations on the smart toilet. The step of correcting the user's body fat percentage using the user's weight to obtain the corrected body fat percentage includes: If the weight includes two pressure values, a proportionality coefficient is obtained based on these two pressure values. A target correction coefficient is then obtained based on the proportionality coefficient and a pre-set fitting coefficient. This target correction coefficient is then used to correct the user's body fat percentage, resulting in the corrected body fat percentage; or... If the user's weight includes more than two stress values, then the stress values ​​included in the weight and the body fat are input into a pre-trained body fat correction model to obtain the corrected body fat.

3. The method according to claim 2, characterized in that, The fitting coefficients include a first fitting coefficient and a second fitting coefficient; The process of obtaining the target correction coefficient based on the proportional coefficient and the pre-set fitting coefficient includes: Multiply the proportional coefficient by the first fitting coefficient to obtain the intermediate fitting coefficient, and add the intermediate fitting coefficient to the second fitting coefficient to obtain the target correction coefficient; The process of obtaining the proportionality coefficient based on the two pressure values ​​included in the body weight includes: Divide the two pressure values ​​to obtain the proportionality coefficient; The step of correcting the user's body fat percentage using the target correction coefficient to obtain the corrected body fat percentage includes: The corrected body fat percentage is obtained by multiplying the target correction factor by the body fat percentage.

4. The method according to any one of claims 1 to 3, characterized in that, The corrected body fat percentage is obtained using the following formula: ； in, For the user's body fat, The corrected body fat percentage is referred to here. It is one of two pressure values. The other pressure value among the two pressure values. The first fitting coefficient, The second fitting coefficient is .

5. The method according to claim 1, characterized in that, The process of matching the corrected body fat percentage with each registered human parameter corresponding to the smart toilet to obtain matching values ​​includes: For any registered human parameter, the corrected body fat percentage is divided by the registered body fat percentage in the registered human parameter to obtain a first similarity value; the absolute value of the difference between the first similarity value and a specified value is determined as the matching value between the corrected body fat percentage and the registered human parameter; or, For any registered human body parameter, the registered pressure values ​​in the registered weight are summed to obtain a first total pressure value, and the pressure values ​​in the user's weight are summed to obtain a second total pressure value. The second total pressure value is subtracted from the first total pressure value to obtain a pressure difference. The pressure difference is then divided by the first total pressure value to obtain a second similarity value. The absolute value of the second similarity value and the absolute value of the difference between the first similarity value and a specified value are determined as the corrected body fat and the matching value of the registered human body parameter, wherein the number of pressure values ​​included in the registered weight is the same as the number of pressure values ​​included in the user's weight.

6. The method according to claim 1, characterized in that, The step of obtaining target registered human parameters corresponding to the user's corrected body fat percentage based on the matching values ​​includes: When the matching value includes a body fat matching value, then for any registered human parameter, if the body fat matching value in the matching value corresponding to the registered human parameter is less than a preset body fat threshold, then the registered human parameter is determined as the target registered human parameter corresponding to the user's corrected body fat, wherein the body fat matching value is a matching value determined based on the corrected body fat; or, When the matching value includes body fat matching value and weight matching value, for any registered human parameter, if the body fat matching value is less than a preset body fat threshold and the weight matching value is less than a preset weight threshold, then the corresponding registered human parameter is determined as the target registered human parameter corresponding to the user's corrected body fat, wherein the weight matching value is a matching value determined based on the user's weight.

7. An identity recognition device, characterized in that, The device includes: The first acquisition module is used to acquire the user's human body parameters after determining that the user is sitting on the smart toilet, wherein the human body parameters include body fat and weight. The correction module is used to correct the user's body fat percentage based on the user's weight, thereby obtaining the corrected body fat percentage. The first matching module is used to match the corrected body fat percentage with each registered human parameter corresponding to the smart toilet to obtain each matching value. The first identity information determination module is used to obtain target registered human parameters corresponding to the user's corrected body fat based on the matching values. If the number of target registered human parameters is a specified number, the registered identity information corresponding to the target registered human parameters is determined as the user's identity information. If the number of target registered human parameters is not equal to the specified number, the module obtains ECG data from at least two leads of the user; performs contour recognition on each ECG data to obtain the contours of each wave of a specified type in each ECG data; projects the contours of each wave corresponding to each ECG data onto a specified plane to obtain the user's ECG vector loop; matches the user's ECG vector loop with each preset template ECG vector loop to obtain matching values; and determines the user's identity information based on the matching values. The step of determining the user's identity information based on the matching values ​​includes: If none of the matching values ​​is greater than a specified threshold, the ECG vector rings are rotated in specified directions by specified angles to obtain multiple intermediate ECG vector rings. For any intermediate ECG vector ring, multiple different shrinkage ratios are used to shrink the intermediate ECG vector rings to obtain multiple target ECG vector rings. For any one of the preset template ECG vector rings, a preset matching algorithm is used to match the multiple target ECG vector rings with the template ECG vector rings to obtain matching values. The maximum value among the matching values ​​is determined as the target matching value between the user's ECG vector ring and the template ECG vector ring. The template ECG vector rings with target matching values ​​greater than a specified threshold are determined as target template ECG vector rings. Using the preset correspondence between template ECG vector rings and identity information, the identity information corresponding to the target template ECG vector ring is determined, and the determined identity information is then used as the user's identity information.

8. A smart toilet, characterized in that, The method includes at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that are executed by the at least one processor; the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1-6.

9. A computer storage medium, characterized in that, The computer storage medium stores a computer program for performing the method according to any one of claims 1-6.

Images