A smart toothbrush user identity recognition method and device, an electronic device, and a storage medium

Abstract

The application relates to the field of intelligent control, and particularly discloses an intelligent toothbrush user identity recognition method, which comprises the following steps: acquiring tooth brushing sequence data of a user according to a plurality of preset tooth regions; acquiring tooth brushing habit data of at least one tooth region according to the tooth brushing sequence data; and recognizing the user identity according to the tooth brushing sequence data and the tooth brushing habit data.The intelligent toothbrush user identity recognition method can effectively distinguish different users by collecting key features in the tooth brushing process of the user.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of intelligent devices, and more particularly, to an intelligent toothbrush user identity recognition method and device, an electronic device, and a storage medium. BACKGROUND

[0002] The application of intelligent toothbrushes is becoming more and more popular. They can help people brush their teeth scientifically and effectively, and keep their teeth healthy. Existing intelligent toothbrushes can help users count the brushing time. However, there is still little research on automatically distinguishing users (users) based on intelligent toothbrushes. SUMMARY

[0003] To solve the above technical problems, embodiments of the present application provide an intelligent toothbrush user identity recognition method, comprising:

[0004] According to the preset plurality of tooth regions, the brushing sequence data of the user is obtained;

[0005] According to the brushing sequence data, the brushing habit data of at least one tooth region is obtained;

[0006] According to the brushing sequence data and the brushing habit data, the user identity is identified.

[0007] Optionally, obtaining the brushing habit data of each tooth region comprises:

[0008] The average value of the rotation angular velocity of the toothbrush handle is calculated and compared with a set threshold value, and when the average value is greater than the threshold value, the brushing action type is identified as wiping;

[0009] When the average value is less than the threshold value, the average value and the variance of the three-axis acceleration of the toothbrush movement are calculated to form a feature vector;

[0010] The feature vector is compared with the pre-stored training samples using a k-nearest neighbor classification algorithm to identify the horizontal brushing, vertical brushing, or vertical brushing action.

[0011] Optionally, obtaining the brushing habit data of each tooth region further comprises obtaining the brushing force F i ;

[0012] The average brushing force of each tooth region is calculated according to the following formula:

[0013]

[0014] where h is the device sampling frequency, T i is the brushing time of the tooth region, ax j , ay j , and az jThis represents the triaxial acceleration value at the j-th sampling point.

[0015] Optionally, obtaining brushing habit data for each of the tooth regions also includes obtaining the average Euler angle of the toothbrush orientation;

[0016] For each of the tooth regions, the average Euler angles of that region are calculated using the following formula:

[0017]

[0018]

[0019]

[0020] in, The average pitch angle, The average yaw angle, β is the average roll angle. j θ j , This represents the pitch angle, yaw angle, and roll angle values ​​at the j-th sampling point.

[0021] Optionally, identifying the user's identity based on the brushing sequence data and the brushing habit data includes:

[0022] The action type, brushing force, and average Euler angle are combined to form a feature vector, that is, at least one of the tooth regions obtains a seven-dimensional feature vector containing the tooth region, brushing duration, action type, brushing force, toothbrush pitch angle, yaw angle, and roll angle.

[0023] User identity is identified based on the brushing sequence data and the seven-dimensional feature vector.

[0024] Identifying user identity based on the brushing sequence data and the seven-dimensional feature vector includes: using a dynamic time warping method to calculate the warped path distance between the test sample and each training sample, obtaining the category corresponding to the sample with the smallest warped path distance, and assigning it to the test sample to identify the identity of the smart toothbrush user.

[0025] Optionally, the normalized path distance between the test sample and each training sample is calculated, and the category corresponding to the sample with the smallest normalized path distance is obtained, including:

[0026] Let the sequence of samples to be tested be X = [x1, x2, ..., xn]. m The i-th eigenvector x in ] i =[s1, s2, s3, s4, s5, s6, s7] T , 1≤i≤m, symbol [] Tdenotes the transpose of a vector; a training sample sequence Y = [y1, y2,..., y q ] where the jth feature vector y j = [r1, r2, r3, r4, r5, r6, r7] T , 1≤j≤q, the "similarity distance" between them is Dist(i,j), then:

[0027] Dist(i,j) = g[s1, r1] + k[s2, r2] + g[s3, r3] + k[s4, r4] + k[s5, r5] + k[s6, r6] + k[s7, r7];

[0028] For the tooth area and action type in the seven-dimensional feature vector, if the features are the same, the "similarity distance" is set to 0, and if the features are different, the "similarity distance" is set to 1, that is:

[0029]

[0030]

[0031] Optionally, according to the brushing duration, brushing force, toothbrush pitch angle, yaw angle and roll angle in the seven-dimensional feature vector, the "similarity distance" is calculated, including:

[0032]

[0033]

[0034]

[0035]

[0036]

[0037] Wherein, the symbol |x| represents the absolute value of x.

[0038] According to another aspect of the present application, there is also provided an intelligent toothbrush user identity recognition device, comprising:

[0039] A brushing sequence data acquisition module configured to acquire brushing sequence data of a user according to a plurality of preset tooth areas;

[0040] A brushing habit data acquisition module configured to acquire brushing habit data of at least one tooth area according to the brushing sequence data;

[0041] An identification module configured to identify the user identity according to the brushing sequence data and the brushing habit data.

[0042] According to still another aspect of the present application, an electronic device is provided, comprising: a processor; and a memory having stored therein computer program instructions, which, when executed by the processor, cause the processor to perform the above-mentioned intelligent toothbrush user identity recognition method.

[0043] According to still another aspect of the present application, a computer readable medium is provided, having stored thereon computer program instructions, which, when executed by a processor, cause the processor to perform the above-mentioned intelligent toothbrush user identity recognition method.

[0044] Compared with the prior art, the intelligent toothbrush user identity recognition method provided by the present application has the following beneficial effects:

[0045] The present application automatically identifies the identity of a user based on different tooth brushing data of the user for the intelligent toothbrush, rather than the common biological characteristics such as fingerprints and faces for user identity recognition.

[0046] In the process of identifying the identity of a user using tooth brushing data, the present application extracts a series of feature vectors arranged in sequence according to the sequence of brushing areas in the entire tooth brushing process of the user as the input of a machine learning model, rather than a single feature vector as the input in the traditional way.

[0047] For each feature vector arranged in sequence, the present application adopts key features such as brushing area, brushing duration, brushing force, action type and Euler angle, which can comprehensively and thoroughly reflect the differences in the tooth brushing process of the user.

[0048] The present application also adopts an improved dynamic time warping algorithm (using "similarity distance" for calculation) to process and analyze the series of feature vectors arranged in sequence, which can effectively identify the identity of the user of the intelligent toothbrush. BRIEF DESCRIPTION OF DRAWINGS

[0049] The accompanying drawings, which form a part of this application, are intended to provide further understanding of the application and are incorporated herein for a purpose of explanations and are in no way limiting on the present application. The schematic embodiment drawings of the present application and their descriptions are used to explain the present application, and do not constitute an improper limitation on the present application. In the drawings:

[0050] Figure 1 is a flow chart of the intelligent toothbrush user identity recognition method according to the embodiment of the present application;

[0051] Figure 2 is a block diagram of the electronic device according to the embodiment of the present application. DETAILED DESCRIPTION

[0052] Hereinafter, example embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only a part but not all of the embodiments of the present application, and the present application can be implemented in many different forms. Therefore, the attached drawings should be regarded in a descriptive rather than restrictive sense.

[0053] Please refer to Figure 1 , Figure 1 The flow chart of the intelligent toothbrush user identity recognition method according to the embodiment of the present application.

[0054] In this embodiment, the intelligent toothbrush user identity recognition method comprises:

[0055] S2: According to the preset plurality of tooth regions, the tooth brushing sequence data of the user is obtained;

[0056] The present application collects acceleration and angular velocity data of the user during tooth brushing based on the intelligent toothbrush base, and distinguishes different users through feature extraction, model establishment, sequence matching and recognition analysis. The specific implementation steps include:

[0057] The intelligent toothbrush base with an accelerometer and a gyroscope is used to collect data during the user's tooth brushing. During the user's tooth brushing, the following features of the user are extracted: tooth brushing area of the user and tooth brushing time of each area. The calculation method of these two features can refer to the literature "A tooth brushing evaluation method and system" (application number 2017103715419), which will not be described here. In this way, the user's tooth brushing area can be identified, which is a total of 16 (left lower inner side, left lower outer side, middle lower inner side, middle lower outer side, right lower inner side, right lower outer side, left upper inner side, left upper outer side, middle upper inner side, middle upper outer side, right upper inner side, right upper outer side, left lower occlusal surface, right lower occlusal surface, left upper occlusal surface, right upper occlusal surface).

[0058] S4: According to the tooth brushing sequence data, the tooth brushing habit data of at least one tooth region is obtained;

[0059] S6: According to the tooth brushing sequence data and the tooth brushing habit data, the user identity is recognized.

[0060] Each tooth region corresponds to a seven-dimensional feature vector. When the user brushes a tooth region, the training sample only contains a training sample containing a seven-dimensional feature vector. When the user brushes multiple tooth regions, the training sample contains a training sample containing multiple seven-dimensional feature vectors.

[0061] In this embodiment, obtaining the tooth brushing habit data of each tooth region comprises:

[0062] The mean value of the rotation angular velocity of the toothbrush handle is calculated and compared with the set threshold value. When the mean value is greater than the threshold value, the tooth brushing action type is identified as wiping;

[0063] When the mean value is less than the threshold value, the mean value and variance of the three-axis acceleration of the toothbrush motion are calculated to form a feature vector;

[0064] The feature vector is compared with pre-stored training samples using a k-nearest neighbor classification algorithm to identify horizontal brushing, vertical brushing, or vertical brushing action.

[0065] During the user's brushing process with the intelligent toothbrush, the following features of the user are extracted: the action type of each region, including horizontal brushing (toothbrush bristles facing the oral cavity, toothbrush moving left and right in the horizontal plane), vertical brushing (toothbrush bristles facing the oral cavity, toothbrush moving up and down), vertical brushing (toothbrush bristles facing the occlusal surface, toothbrush moving left and right in the horizontal plane), and wiping brushing (toothbrush bristles facing the oral cavity, toothbrush rotating).

[0066] They are identified in the following way:

[0067] The mean value of the angular velocity of the toothbrush handle rotation in the region is calculated and compared with a set threshold value. If it is greater than the threshold value, the brushing action type is identified as wiping brushing. If it is less than the threshold value, the following steps are performed.

[0068] The mean value and variance of the three-axis acceleration of the toothbrush motion in the region are calculated to form a feature vector.

[0069] Pre-stored are multiple training samples (feature vectors) of horizontal brushing, vertical brushing, and vertical brushing actions.

[0070] The calculated feature vector is compared with the training samples using a k-nearest neighbor classification algorithm (such as a 4-neighbor algorithm) to identify horizontal brushing, vertical brushing, or vertical brushing action.

[0071] Obtaining brushing habit data for each tooth region also includes obtaining brushing force F i ;

[0072] The average brushing force for each tooth region is calculated according to the following formula:

[0073]

[0074] where h is the device sampling frequency, T i is the brushing duration of the tooth region, ax j , ay j , and az j represent the three-axis acceleration values at the jth sampling point.

[0075] During the user's brushing process with the intelligent toothbrush, the following features of the user are extracted: the brushing force of each region, and for each brushing region P i (1≤i≤16), the average brushing force of the region is calculated, and the toothbrush base device sampling frequency is h, and the brushing duration of the region is Ti (1≤i≤16), the average brushing force F of the region i The following formula is used:

[0076]

[0077] wherein ax j , ay j , az j represents the three-axis acceleration value at the jth sampling point.

[0078] Obtaining the brushing habit data of each tooth region also includes obtaining the average Euler angle of the toothbrush orientation;

[0079] The average Euler angle of each tooth region is calculated according to the following formula:

[0080]

[0081]

[0082]

[0083] wherein, is the average pitch angle, is the average yaw angle, is the average roll angle, β j , θ j , represents the pitch angle value, the yaw angle value and the roll angle value at the jth sampling point.

[0084] In the process of the user brushing teeth with the intelligent toothbrush, the following features of the user are extracted: the average Euler angle of the toothbrush orientation of each region (including the pitch angle, the yaw angle and the roll angle), wherein the calculation of the real-time Euler angle can be solved according to the quaternion, and for a region, the average pitch angle of the toothbrush orientation of the region is the yaw angle the roll angle is:

[0085]

[0086]

[0087]

[0088] wherein β j , θ j , represents the pitch angle value, the yaw angle value and the roll angle value at the jth sampling point.

[0089] According to the tooth brushing sequence data and the tooth brushing habit data, the user identity is identified, which comprises:

[0090] The action type, the tooth brushing force, and the average Euler angle are composed into a feature vector, i.e., at least one of the tooth region is obtained as a seven-dimensional feature vector comprising a tooth region, a tooth brushing duration, an action type, a tooth brushing force, a toothbrush pitch angle, a yaw angle, and a roll angle;

[0091] According to the tooth brushing sequence data and the seven-dimensional feature vector, the user identity is identified;

[0092] According to the tooth brushing sequence data and the seven-dimensional feature vector, the user identity is identified, which comprises: using a dynamic time warping method to respectively calculate a warping path distance between a to-be-tested sample and each training sample, obtaining a class corresponding to a sample with the smallest warping path distance, and assigning the class to the to-be-tested sample, so as to identify the identity of the smart toothbrush user.

[0093] According to the tooth brushing sequence of the user, a series of seven-dimensional feature vectors arranged in sequence (for example, a user brushes 8 regions, and there are 8 seven-dimensional feature vectors) are obtained, and training samples and to-be-tested samples are constructed.

[0094] Using a dynamic time warping method, a warping path distance between a to-be-tested sample (a plurality of seven-dimensional feature vectors) and each training sample (a plurality of seven-dimensional feature vectors) is respectively calculated, a class corresponding to a sample with the smallest warping path distance is obtained, and the class is assigned to the to-be-tested sample, so as to identify the identity of the smart toothbrush user.

[0095] The features extracted in the above steps are composed into a feature vector, so that corresponding to a region in the tooth brushing process of the smart toothbrush user, the following seven-dimensional feature vector is obtained, i.e., [tooth brushing region, tooth brushing duration, action type, tooth brushing force, toothbrush pitch angle, yaw angle, and roll angle];

[0096] The region sequence in the tooth brushing process of the user is arranged in sequence (it needs to be noted that not every user brushes all 16 regions), and a series of seven-dimensional feature vectors arranged in sequence are obtained, for example: [left lower inner side, duration 7 seconds, wiping action, force value 13, toothbrush pitch angle 25 degrees, yaw angle 61 degrees, and roll angle 42 degrees], [right lower outer side, duration 5 seconds, horizontal brushing action, force value 16, toothbrush pitch angle 38 degrees, yaw angle 52 degrees, and roll angle 30 degrees], [middle lower outer side, duration 8 seconds, vertical brushing action, force value 12, toothbrush pitch angle 44 degrees, yaw angle 29 degrees, and roll angle 37 degrees], and the like;

[0097] These sequentially arranged seven-dimensional feature vectors are the key features that describe the identity of a smart toothbrush user. This is because different users have different brushing habits. For example, the order in which users brush their teeth may be different, the type of brushing action may be different for each area, the brushing force and duration may be different for each area, and the toothbrush position may be different for each area, etc.

[0098] It is worth noting that the path distance calculated using the dynamic time warping method in this invention is not Euclidean distance, but rather a "similarity distance" defined based on a seven-dimensional feature vector (containing both discrete and continuous variables). Therefore, in one embodiment of this application, calculating the warped path distance between the test sample and each training sample to obtain the category corresponding to the sample with the smallest warped path distance includes:

[0099] Let a sample to be tested be:

[0100] X = [x1, x2, ..., x] m ], 1≤m≤16

[0101] The sample length is m, indicating that the sample contains m regions; it is important to note that x i (1≤i≤m) is a vector, that is, a seven-dimensional eigenvector;

[0102] Let a certain training sample be:

[0103] Y = [y1, y2, ..., y] q ], 1≤q≤16

[0104] A sample length of q indicates that the sample contains a total of q regions; similarly, y j (1≤j≤q) is also a vector, that is, a seven-dimensional eigenvector;

[0105] Using the dynamic time warping method, the formula for calculating the warped path distance D(i,j) is as follows:

[0106] D(i,j)=Dist(i,j)+min{D(i-1,j),D(ij-1),D(i-1.j-1)}

[0107] Where Dist(i,j) represents the distance between the i-th feature vector in the X sequence and the j-th feature vector in the Y sequence. In this invention, since the seven-dimensional feature vectors contain both discrete and continuous variables, the distance between two feature vectors is calculated using "similarity distance". Let i = m, j = q, then D(m,q) is the regularized path distance between the test sample and the training sample.

[0108] Let x be the i-th feature vector in the sequence of the sample X to be tested. i= [s1, s2, s3, s4, s5, s6, s7] T , the jth feature vector in the training sample Y sequence is y j = [r1, r2, r3, r4, r5, r6, r7] T , the "similarity distance" between the two is Dist(i,j), then:

[0109] Dist(i,j) = g[s1, r1] + k[s2, r2] + g[s3, r3] + k[s4, r4] + k[s5, r5] + k[s6, r6] + k[s7, r7];

[0110] For the two discrete variables of the tooth area and the action type in the seven-dimensional feature vector, if the features are the same, the "similarity distance" is set to 0, and if the features are different, the "similarity distance" is set to 1, that is:

[0111]

[0112]

[0113] In an embodiment of the present application, according to the brushing duration, brushing force, toothbrush pitch angle, yaw angle and roll angle in the seven-dimensional feature vector, the "similarity distance" is calculated, including:

[0114]

[0115]

[0116]

[0117]

[0118]

[0119] Wherein, the symbol |x| represents the absolute value of x.

[0120] For example, the ith feature vector x i in the test sample X sequence is: [left lower inner side, duration 7 seconds, wiping action, force value 13, toothbrush pitch angle 25 degrees, yaw angle 61 degrees, roll angle 42 degrees];

[0121] The jth feature vector y j in the training sample Y sequence is: [right lower outer side, duration 5 seconds, horizontal brushing action, force value 16, toothbrush pitch angle 38 degrees, yaw angle 52 degrees,

[0122] roll angle 30 degrees],

[0123] Then: Dist(i,j)=g[s1,r1]+k[s2,r2]+g[s3,r3]+k[s4,r4]+k[s5,r5]+k[s6,r6]+k[s7,r7]=3.25;

[0124] Where: g[s1,r1]=1; k[s2,r2]=2 / 7; g[s3,r3]=1; k[s4,r4]=3 / 16; k[s5,r5]=13 / 38; k[s6,r6]=9 / 61; k[s7,r7]=12 / 42

[0125] One embodiment of this application also provides a smart toothbrush user identification device, including:

[0126] The brushing sequence data acquisition module is configured to acquire the user's brushing sequence data based on multiple preset tooth areas;

[0127] The brushing habit data acquisition module is configured to acquire brushing habit data for at least one tooth area based on brushing sequence data.

[0128] The recognition module is configured to identify the user's identity based on brushing sequence data and brushing habit data.

[0129] In some embodiments of this application, the electronic device for obtaining various data is disposed in the toothbrush base, but this is not a limitation. Those skilled in the art can place the electronic device in any part of the toothbrush according to actual needs, and all such placements fall within the scope of protection claimed in this application.

[0130] Exemplary electronic devices

[0131] Below, for reference Figure 2 This describes an electronic device according to embodiments of the present application.

[0132] Figure 2 A block diagram of an electronic device according to an embodiment of this application is illustrated.

[0133] like Figure 2 As shown, the electronic device 10 includes one or more processors 11 and memory 12.

[0134] The processor 11 may be a central processing unit (CPU) or other form of processing unit with data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 10 to perform desired functions.

[0135] The memory 12 can include one or more computer program products, which can include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory, for example, can include random access memory (RAM), cache memory, and / or the like. The non-volatile memory, for example, can include read only memory (ROM), hard disk, flash memory, and / or the like. One or more computer program instructions can be stored on the computer-readable storage media, and the processor 11 can execute the program instructions to implement the functions in the intelligent toothbrush user identity recognition method of the embodiments of the present application described above and / or other desired functions. Various contents, such as the target position feature vector, etc., can also be stored in the computer-readable storage media.

[0136] In one example, the electronic device 10 can further include an input device 13 and an output device 14, which are interconnected through a bus system and / or other forms of connection mechanism (not shown).

[0137] The input device 13 can include, for example, a keyboard, a mouse, and / or the like.

[0138] The output device 14 can output various information, including the decoded value, etc., to the outside. The output device 14 can include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto, and / or the like.

[0139] Of course, in order to simplify, Figure 2 Only some of the components in the electronic device 10 related to the present application are shown in the figure, and components such as buses, input / output interfaces, and / or the like are omitted. In addition, the electronic device 10 can include any other appropriate components according to specific application cases.

[0140] Exemplary computer program product and computer-readable storage medium

[0141] In addition to the above method and device, the embodiments of the present application can also be a computer program product, which includes computer program instructions that, when executed by a processor, cause the processor to perform the steps in the functions of the intelligent toothbrush user identity recognition method according to various embodiments of the present application described in the above "Exemplary Method" section of the specification.

[0142] The computer program product can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C++ or the like, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computing device, partly on the user's computing device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device or entirely on the remote computing device or server. The embodiments of the present application are not limited by the programming languages made use of, and the use of "code" herein is used generically to refer to the programming language(s) in which the embodiments of the application are implemented.

[0143] In addition, the embodiments of the present application can also be a computer readable storage medium, which stores computer program instructions, and the computer program instructions make the processor execute the steps in the functions of the intelligent toothbrush user identity recognition method according to various embodiments of the present application described in the "Exemplary Method" part of the specification when the processor runs.

[0144] The computer readable storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium may, for example, include but is not limited to an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or apparatus, or any combination of the above. More specific examples (non-exhaustive list) of readable storage medium include: electrical connection having one or more conductive wires, portable disk, hard disk, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disk read only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above.

[0145] The basic principles of the present application are described above in combination with specific embodiments, but it should be pointed out that the advantages, advantages, effects and the like mentioned in the present application are only examples and are not limited, and these advantages, advantages, effects and the like cannot be considered as the must-have of each embodiment of the present application. In addition, the above specific details are only for the purpose of example and understanding, and the above details do not limit the present application to the must-use specific details.

[0146] The block diagrams of the devices, apparatuses, equipment, systems involved in the present application are only illustrative examples and are not intended to require or imply the connection, arrangement, configuration as shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, equipment, systems can be connected, arranged, configured in any manner. Words such as "include", "contain", "have", and the like are open-ended words, mean "including but not limited to", and can be used interchangeably. The words "or" and "and" used herein mean the word "and / or", and can be used interchangeably unless the context clearly indicates otherwise. The word "such as" used herein means the phrase "such as but not limited to", and can be used interchangeably.

[0147] It should also be noted that in the devices, apparatuses and methods of the present application, each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be considered as equivalent solutions of the present application.

[0148] The above description of the disclosed aspects is provided so that any person skilled in the art can make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of the present application. Thus, the present application is not intended to be limited to the aspects shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0149] The above description has been given for the purpose of illustration and description. Furthermore, this description is not intended to limit the embodiments of the present application to the forms disclosed herein. Although a number of example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.

[0150] The present application proposes a smart toothbrush user identity recognition method, which effectively distinguishes different users by collecting key features in the user's tooth brushing process. The key features proposed by the present application are a series of feature vectors arranged in order, each feature vector including tooth brushing area, tooth brushing time, action type, brushing force and Euler angle feature. This series of feature vectors can effectively represent the entire tooth brushing process of the user, which is one of the innovations of the present application. In addition, the present application proposes a dynamic time warping method based on "similarity distance" for training samples of different dimensions, which not only solves the path distance calculation problem between two seven-dimensional feature vectors, but also meets the model training and classification problem of different dimensional samples, and can effectively identify the identity of the smart toothbrush user. In summary, this method has clear logic and simple implementation steps, and can distinguish different users based on the data and key features in the user's tooth brushing process, and has certain practical value and application prospect.

Claims

1. A smart toothbrush user identity recognition method, characterized in that, The method comprises the following steps: According to the preset plurality of tooth regions, the tooth brushing sequence data of the user is obtained; According to the tooth brushing sequence data, the tooth brushing habit data of at least one tooth region is obtained, and the tooth brushing habit data comprises: action type, brushing strength, and average Euler angle; According to the tooth brushing sequence data and the tooth brushing habit data, the identity of the user is identified; According to the tooth brushing sequence data and the tooth brushing habit data, the identity of the user is identified, which comprises: The action type, the brushing strength, and the average Euler angle are combined into a feature vector, that is, at least one tooth region obtains a seven-dimensional feature vector comprising tooth region, brushing duration, action type, brushing strength, toothbrush pitch angle, yaw angle, and roll angle; According to the tooth brushing sequence data and the seven-dimensional feature vector, the identity of the user is identified; According to the tooth brushing sequence data and the seven-dimensional feature vector, the identity of the user is identified, which comprises:

2. The intelligent toothbrush user identity recognition method of claim 1, wherein, A dynamic time warping method is adopted to respectively calculate the warping path distance between the to-be-tested sample and each training sample, obtain the category corresponding to the sample with the minimum warping path distance, and assign the category to the to-be-tested sample, so as to identify the identity of the smart toothbrush user. The tooth brushing habit data of each tooth region comprises: The average value of the toothbrush handle rotation angular velocity is calculated, and compared with a set threshold value; when the average value is greater than the threshold value, it is identified that the tooth brushing action type is wiping; The feature vector is compared with A nearest neighbor classification algorithm is used to compare the feature vector with pre-stored training samples to identify a horizontal, vertical or upright brush stroke. 3.The smart toothbrush user identity recognition method of claim 2, wherein, acquiring brushing habit data for each of the tooth regions further includes acquiring brushing force ; When the average value is less than the threshold value, the average value and the variance of the toothbrush motion three-axis acceleration are calculated to form a feature vector; wherein, is the device sampling frequency, is the tooth region brushing duration, , , denotes the three-axis acceleration values at the time of the th sampling point.

4. The intelligent toothbrush user identity recognition method of claim 3, wherein, For each tooth region, the average brushing strength of the region is calculated according to the following formula: The tooth brushing habit data of each tooth region further comprises obtaining the average Euler angle of the toothbrush orientation; wherein is the average pitch angle, is the average yaw angle, is the average roll angle, , , denote the pitch angle value, the yaw angle value and the roll angle value at the time of the th sampling point.

5. The intelligent toothbrush user identity recognition method of claim 4, wherein, For each tooth region, the average Euler angle of the region is calculated according to the following formula: Let the sequence of samples to be tested be The first feature vector of the sequence of training samples , the symbol denotes the transpose of a vector; the first feature vector of the sequence of training samples , , , the "similarity distance" between the two is then: ； The warping path distance between the to-be-tested sample and each training sample is calculated, and the category corresponding to the sample with the minimum warping path distance is obtained, which comprises: For the tooth region and the action type in the seven-dimensional feature vector, if the features are the same, the "similarity distance" is set to 0, and if the features are different, the "similarity distance" is set to 1, that is: wherein the symbol represents the absolute value.

6. A smart toothbrush user identity recognition device, characterized by, According to the brushing duration, the brushing strength, the toothbrush pitch angle, the yaw angle, and the roll angle in the seven-dimensional feature vector, the "similarity distance" is calculated, which comprises: The method comprises the following steps: The tooth brushing sequence data acquisition module is configured to obtain the tooth brushing sequence data of the user according to the preset plurality of tooth regions; The tooth brushing habit data acquisition module is configured to obtain the tooth brushing habit data of at least one tooth region according to the tooth brushing sequence data, and the tooth brushing habit data comprises: action type, brushing strength, and average Euler angle; The identification module is configured to identify the identity of the user according to the tooth brushing sequence data and the tooth brushing habit data; According to the tooth brushing sequence data and the tooth brushing habit data, the identity of the user is identified, which comprises: The action type, the brushing strength, and the average Euler angle are combined into a feature vector, that is, at least one tooth region obtains a seven-dimensional feature vector comprising tooth region, brushing duration, action type, brushing strength, toothbrush pitch angle, yaw angle, and roll angle; According to the tooth brushing sequence data and the seven-dimensional feature vector, a user identity is identified; According to the tooth brushing sequence data and the seven-dimensional feature vector, a user identity is identified, which includes: using a dynamic time warping method to respectively calculate a warping path distance between a to-be-tested sample and each training sample, obtaining a class corresponding to a sample with the minimum warping path distance, and assigning the class to the to-be-tested sample, so as to identify the identity of the smart toothbrush user.

7. An intelligent toothbrush user identification electronic device comprising an external memory card, characterized in that, The electronic device includes the smart toothbrush user identity identification device as claimed in claim 6.

8. A storage medium, characterized by The computer program is stored in the memory and, when executed by the processor, implements the method as claimed in any one of claims 1-5.

Images