Periodontal state analysis method and device, electronic equipment and storage medium

Abstract

The invention discloses a periodontal state analysis method and device, electronic equipment and a storage medium. The specific scheme is as follows: acquiring an original image including a to-be-detected tooth; receiving an infrared reflection signal corresponding to the to-be-detected tooth, and determining at least one piece of to-be-processed data corresponding to the infrared reflection signal according to the relative angle between the infrared device and the to-be-detected tooth; according to at least one preset feature calculation method, determining a feature value corresponding to each piece of to-be-processed data, and obtaining a plurality of to-be-processed features; regression processing is carried out on the multiple to-be-processed features of all the to-be-processed data to obtain regression feature values; performing joint calculation processing on the regression features of all the to-be-processed data to obtain a target value, and determining state information of the to-be-detected teeth based on the target value; and adjusting display information of the to-be-detected teeth in the original image based on the state information. According to the invention, the accuracy of periodontal state analysis is improved through quantitative processing of the to-be-detected tooth state.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular, to a method, device, electronic device and storage medium for periodontal status analysis. Background Art

[0002] At present, the examination of periodontal-related diseases has gradually entered ordinary households, and the examination of periodontal status has become more and more popular.

[0003] Currently, there are two processing methods for periodontal status analysis. One is to rely on the knowledge accumulation and experience of relevant personnel for observation and judgment. In this case, there may be a problem of subjectivity in the judgment of relevant personnel, thus affecting the accuracy of the analysis results of periodontal status. The other is that relevant personnel compare the image corresponding to the current periodontal status with the image of the normal periodontal status for judgment, so as to realize the analysis of periodontal status. Therefore, both of the above two processing methods lack objectivity and corresponding accuracy of the processing results. Summary of the Invention

[0004] The present invention provides a method, device, electronic device and storage medium for periodontal status analysis, which improves the accuracy of periodontal status analysis through quantitative processing of the teeth status to be detected.

[0005] According to one aspect of the present invention, a method for periodontal status analysis is provided. The method includes:

[0006] Obtain an original image including the teeth to be detected;

[0007] Receive an infrared reflection signal corresponding to the teeth to be detected, and determine at least one data to be processed corresponding to the infrared reflection signal according to the relative angle between the infrared device and the teeth to be detected; wherein, the infrared device is a device for emitting and receiving infrared signals;

[0008] Determine the feature value corresponding to each data to be processed respectively according to at least one preset feature calculation method, and obtain a plurality of features to be processed;

[0009] Obtain a regression feature value through regression processing of the multiple features to be processed of all the data to be processed;

[0010] Obtain a target value through joint calculation processing of the regression features of all the data to be processed, so as to determine the status information of the teeth to be detected based on the target value;

[0011] Adjust the display information of the teeth to be detected in the original image based on the status information.

[0012] According to another aspect of the present invention, a device for periodontal status analysis is provided. The device includes:

[0013] An original image acquisition module, configured to acquire an original image including the tooth to be detected;

[0014] A data-to-be-processed determination module, configured to receive an infrared reflection signal corresponding to the tooth to be detected, and determine at least one data to be processed corresponding to the infrared reflection signal according to the relative angle between the infrared device and the tooth to be detected; wherein, the infrared device is a device for emitting and receiving infrared signals;

[0015] A feature-to-be-processed determination module, configured to respectively determine the feature values corresponding to each data to be processed according to at least one preset feature calculation method, and obtain a plurality of features to be processed;

[0016] A regression feature value determination module, configured to obtain a regression feature value through regression processing of the plurality of features to be processed of all the data to be processed;

[0017] A status information determination module, configured to obtain a target value through joint calculation and processing of the regression features of all the data to be processed, and determine the status information of the tooth to be detected based on the target value;

[0018] A display information determination module, configured to adjust the display information of the tooth to be detected in the original image based on the status information.

[0019] According to another aspect of the present invention, there is provided an electronic device, which includes:

[0020] At least one processor; and

[0021] A memory communicatively connected to the at least one processor; wherein,

[0022] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the periodontal status analysis method of any embodiment of the present invention.

[0023] According to another aspect of the present invention, there is provided a computer-readable storage medium, which stores computer instructions for causing a processor to implement the periodontal status analysis method of any embodiment of the present invention when executed.

[0024] In the technical solution of the embodiment of the present invention, by acquiring the original image including the tooth to be detected, receiving the infrared reflection signal corresponding to the tooth to be detected, and determining at least one data to be processed corresponding to the infrared reflection signal according to the relative angle between the infrared device and the tooth to be detected; wherein, the infrared device is a device that emits and receives infrared signals, respectively determining the feature values corresponding to each data to be processed according to at least one preset feature calculation method, and obtaining a plurality of features to be processed; further, by performing regression processing on the plurality of features to be processed of all the data to be processed, a regression feature value is obtained; by performing joint calculation processing on the regression features of all the data to be processed, a target value is obtained, so as to determine the status information of the tooth to be detected based on the target value; adjusting the display information of the tooth to be detected in the original image based on the status information, which solves the problem of lack of objectivity and accuracy in the analysis of the periodontal status in the prior art. By performing quantitative processing on the status of the tooth to be detected, the accuracy of the analysis of the periodontal status is improved. At the same time, according to the display information, relevant personnel can intuitively determine the periodontal status.

[0025] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present invention, nor is it used to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0027] Figure 1 is a flowchart of a method for analyzing periodontal status provided by an embodiment of the present invention;

[0028] Figure 2 is a flow example diagram of the method for analyzing periodontal status provided by an embodiment of the present invention;

[0029] Figure 3 is a flowchart of a method for analyzing periodontal status provided by an embodiment of the present invention;

[0030] Figure 4 is a schematic structural diagram of a device for analyzing periodontal status provided by an embodiment of the present invention;

[0031] Figure 5 is a schematic structural diagram of an electronic device for implementing the method for analyzing periodontal status according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0032] To enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative work shall fall within the protection scope of the present invention.

[0033] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily have to be used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0034] Embodiment 1

[0035] Figure 1 is a flowchart of a periodontal status analysis method provided by an embodiment of the present invention. This embodiment is applicable to the situation of processing the infrared reflection signal of a tooth to be detected to determine the status information of the tooth to be detected. This method can be executed by a periodontal status analysis device, which can be implemented in the form of hardware and / or software, and the periodontal status analysis device can be configured in an electronic device such as a mobile phone, a computer, or a server. As Figure 1 shown, the method includes:

[0036] S110. Obtain an original image including the tooth to be detected.

[0037] When analyzing the periodontal status of the current user, each tooth of the current user can be detected. Then, the currently detected and analyzed tooth can be used as the tooth to be detected. To facilitate the analysis of the status of the tooth to be detected, an image of the tooth to be detected can be collected by a corresponding imaging device and stored in a corresponding database, and it can be obtained from the corresponding database when in use. Among them, the image of the tooth to be detected collected by the imaging device is the original image.

[0038] Specifically, the tooth that needs to be detected currently can be selected from multiple teeth of the current user, which is the tooth to be detected. Then, an imaging device can be used to collect an image of the tooth to be detected to obtain an original image including the tooth to be detected.

[0039] Among them, when obtaining the original image of the tooth to be detected, the devices used, in addition to the imaging device, also include an illumination device, a signal transmission device, an image display device, and a storage device. Among the above devices, the illumination device is used to provide an illumination light source when obtaining the original image to ensure the brightness of the original image. The signal transmission device is used to transmit the obtained original image to the corresponding image display device and storage device. The image display device is the device for displaying the original image. The storage device is the device for storing the original image. The storage device can include two types: local storage and remote storage. Local storage means storing the original image in a local server or corresponding electronic device. Among them, the electronic device can be devices such as a hard disk or a USB flash drive. Remote storage is a method of transmitting the original image to a remote server or cloud server for storage using a network. In addition, the connection between the local server and the cloud server can be realized using a Bluetooth or WiFi module to achieve remote storage of the original image.

[0040] S120. Receive the infrared reflection signal corresponding to the tooth to be detected, and determine at least one data to be processed corresponding to the infrared reflection signal according to the relative angle between the infrared device and the tooth to be detected.

[0041] Among them, the infrared device is a device for emitting and receiving infrared signals.

[0042] In the imaging device, there is a device for emitting and receiving infrared signals, that is, the infrared device. Correspondingly, the infrared reflection signal can be understood as the infrared signal that is not absorbed by the tooth to be detected when the infrared device emits an infrared signal to the tooth to be detected. In addition, when emitting the infrared signal, there is a certain angle between the infrared device and the plane corresponding to the tooth to be detected, and this angle is the relative angle. The data to be processed can be the data obtained after corresponding compensation processing according to the received infrared reflection signal. Among them, the compensation processing can be a method of calculating and processing according to the relative angle between the infrared device and the tooth to be detected using a corresponding compensation calculation formula. By using the compensation processing, the integrity and accuracy of the obtained infrared reflection signal can be ensured.

[0043] Specifically, after the infrared device emits an infrared signal, due to the different periodontal states of the teeth to be detected, the reflected infrared reflection signals are also different. It can be understood that if the periodontal state of the teeth to be detected is relatively severe, the degree of absorption of the infrared signal is weaker. Correspondingly, the unabsorbed infrared signal is stronger, that is, the infrared reflection signal received by the infrared device is stronger. Based on this, the infrared signal can be analyzed to realize the analysis of the periodontal state. In addition, when the infrared device emits an infrared signal to the teeth to be detected, there is a certain inclination angle, that is, a relative angle, between the infrared signal and the surface of the teeth to be detected. To ensure the integrity and accuracy of the subsequent processed infrared reflection signal, the compensation processing method can be used to perform compensation calculation on the infrared reflection signal, so as to determine at least one data to be processed corresponding to the infrared reflection signal.

[0044] Exemplarily, as Figure 2 shown, after the infrared light source is emitted, the teeth to be detected absorb and reflect the infrared signal irradiated on their surfaces. Further, the infrared device can receive the infrared signal that is not absorbed by the teeth to be detected, that is, Figure 2 the signal acquisition in. After the acquisition is completed, the received infrared reflection signal can be subjected to signal conversion processing to convert the received continuous infrared reflection signal into discrete data corresponding to the infrared reflection signal for subsequent processing. Based on the data corresponding to the above-obtained infrared signal, data analysis and calculation are performed, that is, compensation processing is performed on the infrared reflection signal to obtain the data to be processed.

[0045] Optionally, before compensating the infrared reflection signal according to the relative angle to determine at least one data to be processed corresponding to the infrared reflection signal, it further includes: filtering the infrared reflection signal by using a hybrid filtering method to update the infrared reflection signal.

[0046] In the embodiment of the present invention, the hybrid filtering method can be understood as a filtering method that combines multiple filtering techniques. Processing the infrared reflection signal based on the hybrid filtering method can remove the unnecessary infrared reflection signal and obtain an accurate infrared reflection signal. Optionally, the hybrid filtering method can be a hybrid filtering automatic compensation optimization method or other filtering processing methods, and this embodiment does not limit this. Among them, the hybrid filtering automatic compensation optimization method can automatically select appropriate filters and compensation parameters according to the characteristics of the infrared reflection signal to achieve the purposes of removing noise, eliminating signal distortion, reducing errors, and improving accuracy.

[0047] Specifically, after receiving the infrared reflection signal, a hybrid filtering method can be used to filter the clutter of the infrared reflection signal to ensure that while removing the data corresponding to the unwanted infrared reflection signal, the effective infrared reflection signal can be retained to the greatest extent. Among them, a preset infrared reflection signal threshold can be set, and the infrared reflection signal is processed by the hybrid filtering method according to the preset infrared reflection signal threshold to remove the data corresponding to the infrared reflection signal below the preset infrared reflection signal threshold and retain the data corresponding to the infrared reflection signal above the preset infrared reflection signal threshold. For example, the preset infrared signal threshold can be 50 Hz. After the above filtering process, the obtained infrared reflection signal is the updated infrared reflection signal.

[0048] Exemplarily, in combination with the above example Figure 2 as shown, that is Figure 2 for the signal noise reduction and filtering process in, that is, after receiving the infrared reflection signal, a hybrid filtering method can be used to perform signal noise reduction and filtering on the infrared reflection signal to obtain the data to be processed based on the updated infrared reflection signal.

[0049] S130. Respectively determine the feature values corresponding to each data to be processed according to at least one preset feature calculation method, and obtain a plurality of features to be processed.

[0050] In the embodiment of the present invention, the feature calculation method can be a method for calculating features of the data to be processed. Optionally, the feature calculation method can include at least one of feature calculation methods such as Lyapunov exponent, time complexity, space complexity, and C0 complexity. Correspondingly, after processing the data to be processed by the feature calculation method, the obtained data is the feature value. The feature to be processed can be a feature corresponding to the feature value.

[0051] Specifically, the feature values can be calculated for each data to be processed according to at least one preset feature calculation method respectively to obtain the feature values corresponding to each feature calculation method and the corresponding features to be processed. For example, if the feature values are calculated for each data to be processed by using two feature calculation methods respectively, two feature values and the corresponding features to be processed can be obtained correspondingly.

[0052] Exemplarily, as Figure 2 shown, after obtaining at least one data to be processed corresponding to the infrared reflection signal, the data to be processed can be subjected to feature calculation to obtain the corresponding feature values.

[0053] S140. Through regression processing of the multiple features to be processed of all the data to be processed, a regression feature value is obtained.

[0054] In an embodiment of the present invention, the regression process can utilize a corresponding linear regression processing method to predict the value of the output target variable, i.e., the regression feature value, based on the input features to be processed. In other words, the regression feature value is the output value obtained after performing a regression process on the data to be processed.

[0055] Specifically, after obtaining multiple features to be processed corresponding to all the data to be processed, perform a regression process on the feature values corresponding to the multiple features to be processed. Among them, one regression feature value can be obtained corresponding to each regression processing method. Optionally, to ensure the accuracy of subsequent analysis results, the multiple features to be processed can be respectively subjected to regression processing based on multiple regression processing methods to obtain multiple regression feature values.

[0056] S150. Through joint calculation and processing of the regression features of all the data to be processed, obtain a target value, and determine the status information of the tooth to be detected based on the target value.

[0057] In an embodiment of the present invention, the joint calculation and processing of regression features can be understood as a processing method of inputting all the regression feature values into a preset joint calculation function to obtain the final output result, i.e., the target value. That is, the target value is the output result of the preset joint calculation function. Among them, the preset joint calculation function is obtained through independent research according to actual needs.

[0058] Specifically, perform joint calculation and processing on the regression feature values corresponding to all the data to be processed by using the preset joint calculation function to obtain the output result, i.e., the target value. Further, the status of the tooth to be detected can be analyzed according to the target value to obtain the status information of the tooth to be detected.

[0059] S160. Adjust the display information of the tooth to be detected in the original image based on the status information.

[0060] In an embodiment of the present invention, the display information can be information used to characterize the severity of the tooth to be detected. For example, the display information can include one of the status information such as the status of the tooth to be detected is very severe, relatively severe, less severe, and least severe.

[0061] Specifically, after analyzing the status of the tooth to be detected according to the target value to obtain the status information of the tooth to be detected, the obtained status information can be updated to the corresponding position of the tooth to be detected in the original image and displayed. Thus, relevant personnel can intuitively obtain the status of the tooth to be detected according to the display information.

[0062] The technical solution of this embodiment obtains the original image including the tooth to be detected, receives the infrared reflection signal corresponding to the tooth to be detected, and determines at least one data to be processed corresponding to the infrared reflection signal according to the relative angle between the infrared device and the tooth to be detected. The infrared device is a device that emits and receives infrared signals. According to at least one preset feature calculation method, the feature value corresponding to each data to be processed is determined respectively, and a plurality of features to be processed are obtained. Further, through regression processing of the plurality of features to be processed of all the data to be processed, a regression feature value is obtained. Through joint calculation processing of the regression features of all the data to be processed, a target value is obtained to determine the status information of the tooth to be detected based on the target value. Based on the status information, the display information of the tooth to be detected in the original image is adjusted, which solves the problem of lack of objectivity and accuracy in the analysis of periodontal status in the prior art. Through the quantitative processing of the status of the tooth to be detected, the accuracy of the analysis of periodontal status is improved. At the same time, according to the display information, relevant personnel can intuitively determine the periodontal status.

[0063] Embodiment 2

[0064] Figure 3 It is a flowchart of a method for analyzing periodontal status provided by an embodiment of the present invention. This embodiment is a preferred embodiment of the above embodiment. The specific implementation manner can refer to the technical solution of this embodiment. Among them, the same or corresponding technical terms as those in the above embodiment will not be described in detail here. As Figure 3 shown, the method includes:

[0065] S210. Obtain the original image including the tooth to be detected.

[0066] S220. Receive the infrared reflection signal corresponding to the tooth to be detected, and determine at least one data to be processed corresponding to the infrared reflection signal according to the relative angle between the infrared device and the tooth to be detected.

[0067] Among them, the infrared device is a device that emits and receives infrared signals.

[0068] Optionally, receiving the infrared reflection signal corresponding to the tooth to be detected, and determining at least one data to be processed corresponding to the infrared reflection signal according to the relative angle between the infrared device and the tooth to be detected includes: when collecting the tooth to be detected based on the imaging device, the infrared device deployed in the imaging device emits an infrared signal to the tooth to be detected; receiving the infrared reflection signal fed back by the tooth to be detected based on the infrared device, and determining the relative angle between the infrared device and the plane where the tooth to be detected is located; compensating the infrared reflection signal according to the relative angle, and determining at least one data to be processed corresponding to the infrared reflection signal.

[0069] In an embodiment of the present invention, the imaging device may be a device for collecting an original image corresponding to a tooth to be detected. An infrared device for transmitting and receiving infrared signals is deployed in the imaging device.

[0070] Specifically, when using the imaging device to collect the original image of the tooth to be detected, the infrared device deployed in the imaging device may transmit an infrared signal to the tooth to be detected, and the tooth to be detected will absorb a part of the infrared signal and reflect the unabsorbed infrared signal back. Among them, the reflected infrared signal, that is, the infrared reflection signal, can be received by the infrared device. In addition, since there is a relative angle between the infrared signal and the surface of the tooth to be detected, in order to ensure the integrity of the obtained infrared reflection signal, a compensation calculation formula can be used for compensation processing to determine at least one data to be processed corresponding to the infrared reflection signal.

[0071] Among them, the compensation calculation formula may first obtain corresponding data values according to the relative angle and the corresponding trigonometric functions, and multiply the data values by the data corresponding to the infrared reflection signal to obtain the data value of the data to be processed corresponding to the infrared reflection signal. The compensation calculation formula can be expressed as follows:

[0072]

[0073] Among them, represents the data value of the data to be processed, m represents the value corresponding to the received infrared reflection signal, and α represents the relative angle.

[0074] S230. Respectively determine the feature values corresponding to each data to be processed according to at least one preset feature calculation method, and obtain a plurality of features to be processed.

[0075] Optionally, at least one feature calculation method includes at least one of Lyapunov exponent, time complexity, space complexity, and C0 complexity. Respectively determining the feature values corresponding to each data to be processed according to at least one preset feature calculation method and obtaining a plurality of features to be processed includes: for each data to be processed, respectively processing the current data to be processed according to each feature calculation method to obtain the feature values to be processed corresponding to the current data to be processed under each feature calculation method.

[0076] In an embodiment of the present invention, the Lyapunov exponent may be a characteristic index used to characterize the degree of difference between data to be processed. The time complexity may be used to characterize the growth relationship of the corresponding execution time when the input data to be processed increases. The space complexity may be a metric used to characterize the relationship between the data to be processed and the additional storage space required for processing the data to be processed. The C0 complexity may be used to characterize the efficiency in processing the data to be processed. The eigenvalue to be processed may be a numerical value output after a feature calculation method performs feature calculation on the input data to be processed.

[0077] Specifically, each data to be processed can be processed according to each feature calculation method respectively. For example, the Lyapunov exponent can be used to process the current data to be processed to obtain the eigenvalue to be processed under this feature calculation method. Optionally, if the Lyapunov exponent, time complexity, space complexity, and C0 complexity are respectively used to process the data to be processed, four eigenvalues to be processed can be correspondingly obtained.

[0078] Among them, taking the processing of the data to be processed by the Lyapunov exponent as an example. The Lyapunov exponent can be used to present the change trend of the spatial difference of the data to be processed.

[0079] First, classify the obtained data to be processed in chronological order, and calculate the exponential change rate of the data to be processed. Then, integrate the exponential change rates of all the data to be processed into a quantization index, that is, the Lyapunov exponent eigenvalue, which is the eigenvalue to be processed mentioned above.

[0080] Specifically, the data to be processed can be classified according to its dimension first. Since the Lyapunov exponent is used to describe the spatial difference, the data to be processed can be divided into three dimensions, calculate the corresponding numerical values of the spatial dispersion characteristics of each dimension, and perform operations on the spatial dispersion eigenvalues of the three dimensions to obtain the final Lyapunov exponent eigenvalue. Taking the spatial dispersion eigenvalue of one dimension as an example, the data to be processed at the current k-th step can be obtained as where can represent multiple data to be processed sorted in chronological order. When i = I k at this time, j = J k , J k represents the maximum value of j. Then, the coefficient value obtained by calculating the current data to be processed can be After that, the average calculation of all steps can be performed as the average calculation of the spatial dispersion of this dimension, that is, the spatial dispersion eigenvalue of this dimension, which is represented as where φ tThe coefficient value used to represent the spatial dispersion, where t = 1, 2,..., T represents the time period, that is, the time sequence, which can be understood as the time length for obtaining the data to be processed. Further, the final Lyapunov exponent eigenvalue, that is, the eigenvalue to be processed, can be obtained by synthesizing the spatial dispersion eigenvalue characteristics of the three dimensions, and it is expressed as:

[0081] S240. For each eigenvalue to be processed, perform eigenvalue decomposition on the current eigenvalue to be processed in at least one dimension to obtain the eigenvalue decomposition value.

[0082] In the embodiment of the present invention, eigenvalue decomposition can be understood as decomposing the current eigenvalue to be processed into eigenvalues containing more useful information. Correspondingly, the eigenvalue containing more useful information of the eigenvalue to be processed obtained is denoted as the eigenvalue decomposition value. Additionally, at least one dimension can be determined according to actual needs and is used as different angles for eigenvalue decomposition of the eigenvalue to be processed.

[0083] Specifically, for the eigenvalues to be processed obtained according to different eigenvalue calculation methods, each eigenvalue to be processed can be subjected to eigenvalue decomposition in at least one dimension set in advance to obtain the eigenvalue decomposition value corresponding to each dimension. For example, if there are four eigenvalue calculation methods and the at least one dimension set in advance is three dimensions, then four eigenvalues to be processed are obtained according to the four eigenvalue calculation methods, and each eigenvalue to be processed can be subjected to eigenvalue decomposition in three dimensions, and twelve eigenvalue decomposition values can be correspondingly obtained.

[0084] S250. Perform linear regression processing on the eigenvalue decomposition values corresponding to all eigenvalues to be processed to obtain the regression eigenvalue corresponding to each eigenvalue decomposition value.

[0085] In the embodiment of the present invention, linear regression can be a processing method for studying the influence relationship between eigenvalue decomposition values.

[0086] Specifically, after performing eigenvalue decomposition on the eigenvalue to be processed in at least one dimension to obtain the corresponding eigenvalue decomposition value, linear regression processing can be performed on the eigenvalue decomposition value. Among them, at least two linear regression processing methods can be used to perform regression processing on the eigenvalue decomposition value to obtain the regression eigenvalue corresponding to this eigenvalue decomposition value. Optionally, the regression eigenvalue can be in the form of a constant.

[0087] Optionally, the linear regression processing methods include at least two of logistic regression, Fourier regression, and Bayesian regression.

[0088] In an embodiment of the present invention, logistic regression may be a machine learning method for solving binary classification problems and may be used to estimate the likelihood of the corresponding state of the tooth to be detected. Fourier regression may be a processing method that converts the eigen-decomposition values into Fourier coefficients and then uses these coefficients for regression analysis. Bayesian regression may be a processing method that uses prior probabilities and likelihood functions to estimate the posterior probability distribution of unknown parameters.

[0089] Exemplarily, linear regression processing may be performed on the eigen-decomposition values corresponding to all the feature values to be processed by using at least two linear regression processing methods to obtain corresponding regression feature values. For example, logistic regression and Fourier regression may be used to perform linear regression processing on the eigen-decomposition values respectively to obtain corresponding regression feature values.

[0090] Among them, taking the linear regression processing of the eigen-decomposition values by logistic regression as an example, as Figure 2 shown, historical data to be processed may be obtained from the corresponding database first, and then the corresponding eigen-decomposition values may be obtained through the above processing of the historical data to be processed. A logistic regression model may be established and trained based on the eigen-decomposition values corresponding to the historical data to be processed, that is, Figure 2 the analysis model in, so as to perform regression processing on the eigen-decomposition values corresponding to the data to be processed by using the trained logistic regression model.

[0091] When establishing the logistic regression model, the probability P may be first converted into the odds Ω:

[0092] Ω = P / (1 - P)

[0093] Among them, Ω is used to represent the ratio of the probability that the state of the tooth to be detected is severe to the probability that the state of the tooth to be detected is not severe. This conversion is non-linear, which can ensure that Ω is a monotonic function of P and their increase and decrease are consistent. From the value range of P being [0, 1], it can be known that the value range of Ω is [0, +∞].

[0094] Furthermore, Ω may be converted into ln(Ω):

[0095] lnΩ = ln[P / (1 - P)]

[0096] In the above formula, ln(Ω) is set as LogitP, where LogitP and Ω have the same increase and decrease, and the value range of LogitP is [-∞, +∞]. Among them, LogitP is the probability value calculated through the above function in logistic regression.

[0097] Furthermore, after the above transformation, the following logistic regression equation may be established:

[0098]

[0099] Among them, β0 represents the intercept, that is, the constant obtained after performing logistic regression on the eigenvalue decomposition values. p represents the number of eigenvalue decomposition values. β i represents the coefficient of the i-th feature, and x i represents the i-th eigenvalue decomposition value.

[0100] Correspondingly, the logistic regression equation can be transformed into:

[0101] LogitP = -C + a * eigenvalue decomposition value 1 + b * eigenvalue decomposition value 2

[0102] Among them, -C is β0, that is, the constant term obtained after logistic regression processing, and a and b represent the weight coefficients corresponding to the eigenvalue decomposition values.

[0103] S260. By performing joint calculation and processing on the regression features of all data to be processed, a target value is obtained to determine the status information of the teeth to be detected based on the target value.

[0104] Optionally, by performing joint calculation and processing on the regression features of all data to be processed, a target value is obtained to determine the status information of the teeth to be detected, including: calculating all regression features according to a preset joint calculation function to determine the target value; determining the target level of the teeth to be detected according to the target value and a preset level threshold range; and determining the status information of the teeth to be detected according to the target level.

[0105] In the embodiments of the present invention, the preset joint calculation function can be a function determined in advance according to actual requirements and regression feature values. The preset level threshold range can be a target value range corresponding to the severity level of the status of the teeth to be detected defined according to actual requirements. For example, the severity of the status of the teeth to be detected can be divided into four levels, namely the first level to the fourth level. Among them, the higher the level, the more severe the severity. The first level indicates that the severity of the status of the teeth to be detected is relatively light, and the fourth level indicates that the severity of the status of the teeth to be detected is the most severe. For each level, its corresponding numerical range can be set, that is, if the target value is within this numerical range, it corresponds to this level. Based on this, the level threshold range can be set. Correspondingly, the target level can be the level corresponding to the level threshold range to which the target value of the teeth to be detected belongs. The status information can be information used to characterize the severity of the teeth to be detected.

[0106] Specifically, all regression feature values can be calculated according to the preset joint calculation function to determine the target value. Then, according to the preset level threshold range, the numerical range corresponding to the target value and the corresponding level, that is, the target level of the teeth to be detected, can be determined. The status information of the teeth to be detected can be obtained correspondingly according to the determined target level.

[0107] Exemplarily, in Figure 2 , the analysis result is the status information of the tooth to be detected. Additionally, if the regression eigenvalue obtained through logistic regression is x1 and the regression eigenvalue obtained through Fourier regression is x2, then the combined calculation function can be expressed as where c is a variable, which is a coefficient used to ensure the correctness of the final result of the combined calculation function, and m, n are constants, which are used to represent the weight coefficients corresponding to each regression eigenvalue. The above letters are all obtained from specific calculation formulas.

[0108] S270. Adjust the display information of the tooth to be detected in the original image based on the status information.

[0109] Optionally, adjusting the display information of the tooth to be detected in the original image based on the status information includes: updating the status information to a preset position of the tooth to be detected in the original image and displaying it.

[0110] In the embodiments of the present invention, the preset position may be the position where the infrared signal irradiates on the surface of the tooth to be detected.

[0111] Specifically, the obtained status information can be corresponded to the preset position of the tooth to be detected in the original image, and the original image can be updated based on the status information. Among them, corresponding identifiers can be set at the preset position to identify the status information of the tooth to be detected. Then, the updated original image can be displayed. Further, all the teeth of the current user can be detected, and the status information can be updated to the original image, so that relevant personnel can intuitively determine the periodontal status of the current user.

[0112] Exemplarily, updating the status information to the preset position of the tooth to be detected in the original image and displaying it, that is Figure 2 visualizing the result in

[0113] The technical solution of this embodiment is to obtain the original image including the tooth to be detected; receive the infrared reflection signal corresponding to the tooth to be detected, and determine at least one data to be processed corresponding to the infrared reflection signal according to the relative angle between the infrared device and the tooth to be detected; determine the eigenvalue corresponding to each data to be processed respectively according to at least one preset feature calculation method, and obtain a plurality of features to be processed; further, for each eigenvalue to be processed, perform eigen - decomposition on the current eigenvalue to be processed in at least one dimension to obtain the eigen - decomposition value; perform linear regression processing on the eigen - decomposition values corresponding to all eigenvalues to be processed to obtain the regression eigenvalue corresponding to each eigen - decomposition value. Then, through the joint calculation and processing of the regression features of all data to be processed, a target value is obtained to determine the status information of the tooth to be detected based on the target value. This solves the problem of lack of objectivity and accuracy in the analysis of periodontal status in the prior art. By quantifying the status of the tooth to be detected, the accuracy of periodontal status analysis is improved. At the same time, by displaying the status information, relevant personnel can intuitively determine the periodontal status.

[0114] Embodiment III

[0115] Figure 4 It is a schematic structural diagram of a periodontal status analysis device provided by an embodiment of the present invention. As Figure 4 shown, the device includes: an original image acquisition module 310, a data - to - be - processed determination module 320, a feature - to - be - processed determination module 330, a regression eigenvalue determination module 340, a status information determination module 350, and a display information determination module 360.

[0116] The original image acquisition module 310 is used to acquire the original image including the tooth to be detected; the data - to - be - processed determination module 320 is used to receive the infrared reflection signal corresponding to the tooth to be detected, and determine at least one data to be processed corresponding to the infrared reflection signal according to the relative angle between the infrared device and the tooth to be detected, where the infrared device is a device for emitting and receiving infrared signals; the feature - to - be - processed determination module 330 is used to determine the eigenvalue corresponding to each data to be processed respectively according to at least one preset feature calculation method, and obtain a plurality of features to be processed; the regression eigenvalue determination module 340 is used to obtain the regression eigenvalue through regression processing of the multiple features to be processed of all data to be processed; the status information determination module 350 is used to obtain a target value through joint calculation and processing of the regression features of all data to be processed, so as to determine the status information of the tooth to be detected based on the target value; the display information determination module 360 is used to adjust the display information of the tooth to be detected in the original image based on the status information.

[0117] The technical solution of this embodiment is to obtain the original image including the tooth to be detected, receive the infrared reflection signal corresponding to the tooth to be detected, and determine at least one data to be processed corresponding to the infrared reflection signal according to the relative angle between the infrared device and the tooth to be detected. The infrared device is a device that emits and receives infrared signals. According to at least one preset feature calculation method, the feature value corresponding to each data to be processed is determined respectively, and multiple features to be processed are obtained. Further, through regression processing of the multiple features to be processed of all data to be processed, a regression feature value is obtained. Through joint calculation processing of the regression features of all data to be processed, a target value is obtained to determine the status information of the tooth to be detected based on the target value. Based on the status information, the display information of the tooth to be detected in the original image is adjusted, which solves the problem of lack of objectivity and accuracy in the analysis of periodontal status in the prior art. Through the quantitative processing of the status of the tooth to be detected, the accuracy of the analysis of periodontal status is improved. At the same time, according to the display information, relevant personnel can intuitively determine the periodontal status.

[0118] Based on the above embodiment, optionally, the data to be processed determination module is configured to, when collecting the tooth to be detected based on the imaging device, emit an infrared signal to the tooth to be detected based on the infrared device deployed in the imaging device; receive the infrared reflection signal fed back by the tooth to be detected based on the infrared device, and determine the relative angle between the infrared device and the plane to which the tooth to be detected belongs; perform compensation processing on the infrared reflection signal according to the relative angle, and determine at least one data to be processed corresponding to the infrared reflection signal.

[0119] Optionally, at least one feature calculation method includes at least one of Lyapunov exponent, time complexity, space complexity, and C0 complexity. The to-be-processed feature determination module is configured to, for each data to be processed, process the current data to be processed according to each feature calculation method respectively, and obtain the to-be-processed feature value corresponding to the current data to be processed under each feature calculation method.

[0120] Optionally, the regression feature value determination module includes: a feature decomposition value determination unit configured to perform feature decomposition on the current to-be-processed feature value in at least one dimension for each to-be-processed feature value to obtain a feature decomposition value; a regression feature value determination unit configured to perform linear regression processing on the feature decomposition values corresponding to all to-be-processed feature values to obtain a regression feature value corresponding to each feature decomposition value.

[0121] Optionally, the status information determination module is configured to calculate all regression features according to a preset joint calculation function to determine a target value; determine the target level of the tooth to be detected according to the target value and a preset level threshold range; and determine the status information of the tooth to be detected according to the target level.

[0122] Optionally, a display information determination module is configured to update the status information to a preset position of the tooth to be detected in the original image and display it.

[0123] Optionally, in the regression eigenvalue determination unit, the linear regression processing methods include at least two of logistic regression, Fourier regression, and Bayesian regression.

[0124] The periodontal status analysis device provided by the embodiments of the present invention can execute the periodontal status analysis method provided by any embodiment of the present invention, and has corresponding functional modules and beneficial effects for executing the method.

[0125] Embodiment 4

[0126] Figure 5 FIG. is a schematic structural diagram of an electronic device provided by an embodiment of the present invention. The electronic device 10 is intended to represent various forms of digital computers, such as, for example, laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as, for example, personal digital processors, cellular telephones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely exemplary and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0127] As Figure 5 shown, the electronic device 10 includes at least one processor 11, and a memory communicatively connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc. The memory stores a computer program executable by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. The input / output (I / O) interface 15 is also connected to the bus 14.

[0128] Multiple components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0129] Processor 11 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 executes the various methods and processes described above, such as the periodontal status analysis method.

[0130] In some embodiments, the periodontal status analysis method can be implemented as a computer program, which is tangibly included in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed onto electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the periodontal status analysis method described above can be executed. Alternatively, in other embodiments, processor 11 can be configured to execute the periodontal status analysis method by any other suitable means (e.g., by means of firmware).

[0131] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a dedicated or general-purpose programmable processor, receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0132] The computer program for implementing the periodontal status analysis method of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer program is executed by the processor, the functions / operations specified in the flowchart and / or block diagram are implemented. The computer program can be executed entirely on the machine, partially on the machine, executed partially on the machine and partially on a remote machine as an independent software package, or executed entirely on a remote machine or server.

[0133] Embodiment Five

[0134] An embodiment of the present invention also provides a computer-readable storage medium. The computer-readable storage medium stores computer instructions, and the computer instructions are used to cause a processor to execute a periodontal status analysis method. The method includes:

[0135] Obtain an original image including a tooth to be detected; receive an infrared reflection signal corresponding to the tooth to be detected, and determine at least one data to be processed corresponding to the infrared reflection signal according to the relative angle between the infrared device and the tooth to be detected, where the infrared device is a device that emits and receives infrared signals; determine a feature value corresponding to each data to be processed respectively according to at least one preset feature calculation method to obtain a plurality of features to be processed; obtain a regression feature value through regression processing of the plurality of features to be processed of all the data to be processed; obtain a target value through joint calculation processing of the regression features of all the data to be processed, so as to determine the status information of the tooth to be detected based on the target value; and adjust the display information of the tooth to be detected in the original image based on the status information.

[0136] In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, the computer-readable storage medium may be a machine-readable signal medium. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0137] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which the user can provide input to the electronic device. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0138] The systems and techniques described herein can be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected with each other by digital data communication in any form or medium (e.g., a communication network). Examples of communication networks include: local area network (LAN), wide area network (WAN), blockchain network, and the Internet.

[0139] A computing system can include a client and a server. The client and the server are generally remote from each other and typically interact through a communication network. The client-server relationship is created by computer programs running on respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system, solving the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services.

[0140] It should be understood that various forms of the processes shown above can be used, with steps reordered, added, or deleted. For example, the steps recited in the present invention can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved, and no limitation is imposed herein.

[0141] The above specific embodiments do not constitute a limitation on the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A periodontal status analysis method, characterized in that, Including: Obtaining an original image including the tooth to be detected; Receiving an infrared reflection signal corresponding to the tooth to be detected, and determining at least one data to be processed corresponding to the infrared reflection signal according to the relative angle between the infrared device and the tooth to be detected; wherein, the infrared device is a device for emitting and receiving infrared signals; Respectively determining eigenvalue corresponding to each data to be processed according to at least one preset feature calculation method, and obtaining a plurality of features to be processed; Obtaining a regression eigenvalue through regression processing of the plurality of features to be processed of all data to be processed; Obtaining a target value through joint calculation processing of the regression features of all data to be processed, so as to determine the status information of the tooth to be detected based on the target value; Adjusting the display information of the tooth to be detected in the original image based on the status information.

2. The method according to claim 1, characterized in that, The receiving the infrared reflection signal corresponding to the tooth to be detected, and determining at least one data to be processed corresponding to the infrared reflection signal according to the relative angle between the infrared device and the tooth to be detected includes: When collecting the tooth to be detected based on the imaging device, emitting an infrared signal to the tooth to be detected based on the infrared device deployed in the imaging device; Receiving the infrared reflection signal reflected by the tooth to be detected based on the infrared device, and determining the relative angle between the infrared device and the plane to which the tooth to be detected belongs; Performing compensation processing on the infrared reflection signal according to the relative angle, and determining at least one data to be processed corresponding to the infrared reflection signal.

3. The method according to claim 1, wherein The at least one feature calculation method includes at least one of Lyapunov exponent, time complexity, space complexity, and C0 complexity. The respectively determining eigenvalue corresponding to each data to be processed according to at least one preset feature calculation method, and obtaining a plurality of features to be processed includes: For each data to be processed, respectively processing the current data to be processed according to each feature calculation method, and obtaining the eigenvalue to be processed corresponding to the current data to be processed under each feature calculation method.

4. The method according to claim 1, wherein The obtaining a regression eigenvalue through regression processing of the plurality of features to be processed of all data to be processed includes: For each eigenvalue to be processed, performing eigenvalue decomposition on the current eigenvalue to be processed in at least one dimension to obtain an eigenvalue decomposition value; Performing linear regression processing on the eigenvalue decomposition values corresponding to all eigenvalues to be processed, and obtaining a regression eigenvalue corresponding to each eigenvalue decomposition value.

5. The method according to claim 1, wherein The obtaining a target value through joint calculation processing of the regression features of all data to be processed, so as to determine the status information of the tooth to be detected based on the target value includes: Calculating all regression features according to a preset joint calculation function to determine a target value; Determining the target grade of the tooth to be detected according to the target value and a preset grade threshold range; Determining the status information of the tooth to be detected according to the target grade.

6. The method according to claim 1, characterized in that, The adjusting the display information of the tooth to be detected in the original image based on the status information includes: Update the state information to a preset position of the tooth to be detected in the original image and display it.

7. The method according to claim 4, wherein The ways of the linear regression processing include at least two of logistic regression, Fourier regression, and Bayesian regression.

8. A periodontal condition analysis device, characterized in that, Comprising: An original image acquisition module, configured to acquire an original image including a tooth to be detected; A data-to-be-processed determination module, configured to receive an infrared reflection signal corresponding to the tooth to be detected, and determine at least one data to be processed corresponding to the infrared reflection signal according to a relative angle between an infrared device and the tooth to be detected; wherein, the infrared device is a device for emitting and receiving infrared signals; A feature-to-be-processed determination module, configured to respectively determine a feature value corresponding to each data to be processed according to at least one preset feature calculation method, and obtain a plurality of features to be processed; A regression feature value determination module, configured to obtain a regression feature value through regression processing of the plurality of features to be processed of all the data to be processed; A state information determination module, configured to obtain a target value through joint calculation and processing of the regression features of all the data to be processed, and determine the state information of the tooth to be detected based on the target value; A display information determination module, configured to adjust the display information of the tooth to be detected in the original image based on the state information.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the periodontal state analysis method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions, and the computer instructions are used to implement the periodontal state analysis method according to any one of claims 1-7 when executed by a processor.

Images