A method and device for restoring parameter model during denture processing

Abstract

The present invention relates to the field of denture model restoration, and in particular to a method and device for restoring a parameter model during denture processing, comprising: obtaining initial parameters of a denture when denture processing begins; obtaining behavior data of a denture processing device in real time, the behavior data including a processing trajectory and tool parameters of the denture processing device on the denture; judging whether a parameter change occurs in the denture according to the behavior data; when a parameter change occurs in the denture, adding part of the behavior data of the denture processing device when the parameter change occurs in the denture to a time series, and inputting the part of the behavior data and the initial parameters added to the time series into a preset model, analyzing and saving the denture change data at each time point through the preset model; when a restoration instruction from a user end is received, parsing the time point corresponding to the restoration instruction, and obtaining the corresponding denture change data according to the time point; and controlling a 3D printing device to generate a denture restoration model based on the denture change data and the initial parameters corresponding to the time point.

Description

Technical Field

[0001] The present application relates to the technical field of denture model restoration, and in particular to a method and device for restoring a parameter model during denture processing. Background Art

[0002] A denture processing device is a mechanical device specially used for making dentures. It usually includes multiple parts to complete the various processing steps of dentures. These steps may include scanning, designing, cutting, grinding, coloring and assembling the denture model. The design and operation of the denture processing device usually rely on computer-aided design and manufacturing (CAD / CAM) technology, which makes the denture processing process more precise and efficient. Dentures usually need to accurately match the patient's mouth, and the size requirements are very high. At the same time, the shape of the denture is usually irregular and contains multiple curved surfaces, which increases the difficulty of processing. Due to the small size and complex shape of the denture, it is easily affected by various factors during the processing, such as the stability of the processing device, the technical level of the operator, etc. The oral condition and needs of each patient are different, so the design and processing of the denture need to be customized.

[0003] In the existing technology, denture processing usually relies on the operator's experience and skills, and lacks an automated and intelligent monitoring system. Once a denture is over-processed during the processing, it is usually impossible to effectively restore it through existing technology. However, many times, the previous step is almost completed, but over-processing occurs due to errors in the processing equipment. The existing technology is unable to record the parameters of the previous step, and re-processing a denture is too much work and it is difficult to guarantee the desired effect.

[0004] Therefore, the prior art has defects and needs to be improved. Summary of the invention

[0005] In order to solve one or several problems in the prior art, the main purpose of the present application is to provide a method and device for restoring a parameter model during denture processing.

[0006] In order to achieve the above-mentioned invention object, the present application proposes a method for restoring a parameter model during denture processing, the method comprising:

[0007] When the denture begins to be processed, obtaining initial parameters of the denture;

[0008] Acquiring behavior data of the denture processing device in real time, wherein the behavior data includes a processing track and tool parameters of the denture processing device on the denture;

[0009] determining whether a parameter change occurs to the denture according to the behavior data;

[0010] When the denture parameter changes, part of the behavior data of the denture processing device when the denture parameter changes are added to the time series, and the part of the behavior data added to the time series and the initial parameters are input into a preset model, and the denture change data at each time point is analyzed and saved through the preset model;

[0011] When receiving a restoration instruction from the user terminal, parsing the time point corresponding to the restoration instruction, and acquiring corresponding denture change data according to the time point;

[0012] Based on the denture change data and initial parameters corresponding to the time point, the 3D printing device is controlled to generate a denture restoration model.

[0013] Furthermore, the adding of part of the behavior data of the denture processing device when the parameters of the denture change into the time series includes:

[0014] When the processing track of the denture processing device on the denture moves, obtaining the start time point and the end time point when the denture processing device contacts the denture;

[0015] Based on the start time point and the end time point, acquiring tool parameters and processing trajectory of the denture processing device according to a preset acquisition frequency, wherein the tool parameters include tool type, working parameters and position parameters;

[0016] The tool parameters and processing trajectory are added into a time series.

[0017] Furthermore, the preset model includes model training, the steps include:

[0018] Collect historical denture processing behavior data and denture initial parameters;

[0019] Extracting features from the behavior data using a frequency domain feature extraction method;

[0020] Collect historical denture change data, and annotate the historical denture change data according to the preset change time points;

[0021] The features extracted from the behavior data and the labeled denture change data are used to train a linear regression model to obtain a trained model.

[0022] Furthermore, the step of acquiring the tool parameters and processing trajectory of the denture processing device according to a preset acquisition frequency includes acquiring the acquisition frequency, and the steps include:

[0023] When the denture processing device is in contact with the denture, obtaining a rotation speed and a feed speed of the denture processing device;

[0024] Analyzing the parameter change rate of the denture processing device according to the rotation speed and feed speed;

[0025] Inputting the parameter change rate of the denture processing device into a preset frequency analysis model, outputting the acquisition frequency through the frequency analysis model, and acquiring the tool parameters and processing trajectory of the denture processing device based on the acquisition frequency;

[0026] When the rotation speed and feed speed of the gear machining device undergo parameter changes, the acquisition frequency is reanalyzed.

[0027] Furthermore, after the step of analyzing and saving the denture change data at each time point through the preset model, the method further includes:

[0028] Analyzing the denture change data at each time point, performing a quality check on the denture change data, inputting the denture change data at each time point into an error detection model, and analyzing whether an abnormal value appears in the denture change data at each time point through the error detection model;

[0029] When an abnormal value appears in the denture change data, determining a compensation value required for the abnormal value based on the normal denture change data and the abnormal value;

[0030] adjusting the denture change data at the time point corresponding to the abnormal value based on the compensation value;

[0031] Analyze the data source that causes the abnormal value, and analyze the cause of the abnormal value based on the data source.

[0032] Furthermore, after the step of analyzing the cause of the abnormal value according to the data source, the method further includes:

[0033] Analyze the cause of the abnormal value, when the cause of the abnormal value is that the denture change data at the preset model analysis time point is inaccurate;

[0034] The abnormal values ​​and the compensation values ​​are used to generate a training set for optimizing the preset model.

[0035] Furthermore, the step of determining the compensation value required for the abnormal value based on the normal denture change data and the abnormal value includes:

[0036] constructing a three-dimensional virtual model of the denture according to the initial parameters of the denture;

[0037] Reconstructing the three-dimensional virtual model based on the normal denture change data and the denture change data corresponding to the abnormal value to obtain a reconstructed three-dimensional virtual model;

[0038] Annotating outlier positions in the reconstructed three-dimensional virtual model, and extracting parameters of adjacent positions of the outlier positions;

[0039] The compensation value required for the abnormal value is calculated according to the adjacent position point parameters to obtain the compensation value required for the abnormal value.

[0040] The present application also provides a device for restoring a parameter model during denture processing, comprising:

[0041] A first acquisition module, used for acquiring initial parameters of the denture when the denture begins to be processed;

[0042] A second acquisition module is used to acquire the behavior data of the denture processing device in real time, wherein the behavior data includes the processing track and tool parameters of the denture processing device on the denture;

[0043] A judgment module, used for judging whether a parameter change occurs to the denture according to the behavior data;

[0044] An input module, used for adding part of the behavior data of the denture processing device when the parameters of the denture change to the time series when the parameters of the denture change, and inputting the part of the behavior data added to the time series and the initial parameters into a preset model, and analyzing and saving the denture change data at each time point through the preset model;

[0045] The parsing module is used to parse the time point corresponding to the restoration instruction when receiving the restoration instruction from the user end, and obtain the corresponding denture change data according to the time point;

[0046] The control module is used to control the 3D printing device to generate a denture restoration model based on the denture change data and initial parameters corresponding to the time point.

[0047] The present application also provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any one of the above methods when executing the computer program.

[0048] The present application also provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of any of the above-mentioned methods are implemented.

[0049] The method and device for restoring the parameter model during denture processing of the embodiment of the present application monitors in real time whether the denture processing device starts processing the material, immediately starts the processing program, and adjusts the processing strategy according to the real-time feedback to ensure the timeliness and accuracy of the processing process. When the parameters of the denture change, the method can add the behavioral data at the time of change to the time series, and input it into the preset model together with the initial parameters. In this way, even if the denture is over-processed during the processing, the original state of the denture can be restored by restoring the model, avoiding the trouble and uncertainty of reprocessing. Through automated and intelligent monitoring, the method can reduce the intervention and adjustment of the operator, thereby reducing workload and cost. At the same time, the recording and restoration function of parameter changes also helps to solve the problem that it is difficult to achieve the desired effect when reprocessing is required due to over-processing, thereby further reducing costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 A schematic flow chart of a method for restoring a parameter model during denture processing according to an embodiment of the present application;

[0051] Figure 2 A schematic flow chart of a method for restoring a parameter model during denture processing according to an embodiment of the present application;

[0052] Figure 3 A schematic block diagram of the structure of a device for restoring a parameter model during denture processing according to an embodiment of the present application;

[0053] Figure 4 A schematic block diagram of the structure of a computer device according to an embodiment of the present application.

[0054] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0055] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0056] Reference Figure 1 In an embodiment of the present application, a method for restoring a parameter model during denture processing is provided, comprising a heat exchanger, and the method comprises:

[0057] S1. When the denture begins to be processed, obtaining initial parameters of the denture;

[0058] S2, acquiring the behavior data of the denture processing device in real time, wherein the behavior data includes the processing track and tool parameters of the denture processing device on the denture;

[0059] S3, judging whether the denture has parameter changes according to the behavior data;

[0060] S4. When the denture parameter changes, part of the behavior data of the denture processing device when the denture parameter changes is added to the time series, and the part of the behavior data added to the time series and the initial parameters are input into a preset model, and the denture change data at each time point is analyzed and saved through the preset model;

[0061] S5. When receiving a restoration instruction from the user terminal, analyzing the time point corresponding to the restoration instruction, and acquiring corresponding denture change data according to the time point;

[0062] S6. Based on the denture change data and initial parameters corresponding to the time point, control the 3D printing device to generate a denture restoration model.

[0063] As described in the above steps S1-S2, when the denture begins to be processed, the initial parameters of the denture need to be obtained first. This includes information such as the design specifications of the denture and the patient's oral condition, which can be obtained by scanning, measuring, etc. During the denture processing, it is necessary to obtain the behavior data of the denture processing device in real time, including the processing trajectory and tool parameters. These data can be collected in real time by sensors, scanners and other equipment, and transmitted to the system for processing. With the help of sensors and other equipment, the working status of the denture processing device is monitored, and the behavior data may include parameters such as the position, processing speed, and processing pressure of the processing tool. The initial parameters obtained by digital scanning technology are highly accurate, ensuring the accuracy and consistency of subsequent processing and restoration. Sensors and cameras and other equipment can monitor the working status of the denture processing device in real time, ensuring the timeliness and accuracy of the data. Real-time acquisition of behavior data helps to promptly discover abnormal conditions in the processing process, such as tool wear, processing errors, etc., and improves the efficiency of problem diagnosis and resolution.

[0064] As described in the above steps S3-S4, by analyzing the behavior data obtained in real time, it can be determined whether the denture has a parameter change. Parameter changes may be caused by material wear, processing errors, etc., and parameter changes indicate that the denture has begun to be processed, indicating that the material of the denture has begun to be consumed. When it is found that the denture has a parameter change, part of the behavior data at the time of the change is added to the time series. These data may include information such as changes in processing trajectories and adjustments to tool parameters. The real-time behavior data is stored in the form of a time series to establish a data model of changes. Machine learning algorithms or statistical analysis methods can be used to identify and analyze the patterns and trends of parameter changes. The law of denture parameter changes is analyzed using machine learning models or statistical models. The changed data and model results are stored for subsequent restoration and processing. By monitoring parameter changes, the system can determine in real time whether the device has started to process the denture material to ensure the timeliness of the start of the processing process. Monitoring parameter changes can also be used for production supervision, recording the start time and processing status of the processing process, providing data support for production management, and ensuring the traceability and compliance of the production process.

[0065] As described in the above steps S5-S6, when the restoration instruction from the user end is received, the time point corresponding to the instruction is parsed, and the corresponding denture change data is obtained according to the time point. According to the parsed denture change data and initial parameters corresponding to the time point, the 3D printing device is controlled to generate a restoration model of the denture at that time point to restore the state of the denture before over-processing. By establishing a time series data model and a machine learning model, a large amount of complex behavioral data can be effectively processed to identify and predict denture parameter changes; sensor technology can monitor parameter changes in real time during the processing process, so that the system can respond and adjust the processing strategy in a timely manner. Using the results of time series data and model analysis, the design parameters of the denture can be accurately restored to ensure that the final processed denture meets the patient's needs and design requirements. Through model analysis and preservation, a large amount of denture processing data and experience can be accumulated to provide a reference for future optimization and improvement. The saved model results can ensure the accuracy and consistency of the denture restoration process and improve the accuracy and efficiency of denture restoration.

[0066] It is worth mentioning that existing methods also include using cameras to record changes during each processing process and directly analyzing these video data to determine the denture parameters. Video data usually contains a large amount of visual information, which needs to be converted into actionable data when analyzed. Extracting the parameter change data of the denture directly from the video may require processing a large amount of image data, which is not only inefficient, but may also fail to accurately capture small parameter changes. Denture processing requires extremely high precision, and video data may not provide sufficient accuracy to accurately reflect the small changes of the denture during the processing. In addition, the processing of video data may be affected by environmental factors (such as lighting conditions, camera angles, etc.), resulting in unstable data quality. By adding time series data to the parameter changes, it can be ensured that the data of each processing process is repeatable, which helps to improve the prediction accuracy of the model and the stability of the system. Combining behavioral data with initial parameters and using preset models for analysis can more comprehensively consider various factors in the denture processing process, thereby more accurately predicting and restoring denture changes.

[0067] Specifically, it is possible to monitor in real time whether the denture processing device has started processing the material, immediately start the processing program, and adjust the processing strategy based on real-time feedback to ensure the timeliness and accuracy of the processing process. When the parameters of the denture change, the method can add the behavioral data at the time of change to the time series and input it into the preset model together with the initial parameters. In this way, even if the denture is over-processed during the processing, the original state of the denture can be restored by restoring the model, avoiding the trouble and uncertainty of reprocessing. Through automated and intelligent monitoring, this method can reduce the intervention and adjustment of the operator, thereby reducing workload and cost. At the same time, the recording and restoration function of parameter changes can also help solve the problem that it is difficult to achieve the desired effect when reprocessing is required due to over-processing, thereby further reducing costs.

[0068] In a feasible embodiment, when the patient arrives at the denture processing factory, the staff first obtains the patient's oral data through oral scanning and other technologies, including parameters such as the size and shape of the teeth, which will be used as initial parameters. When the patient's denture begins to be processed, the processing device begins to obtain the behavior data of the denture processing process in real time, such as processing trajectory, tool speed, processing pressure, etc. These data are uploaded to the system in real time through the sensor system for subsequent analysis and processing. The system continuously analyzes the real-time uploaded behavior data to determine whether the parameters of the denture have changed, such as changes in the hardness of the material, increases in cutting force, etc. When the system detects that the parameters of the denture have changed, these changed data will be added to the time series and saved in the database, and the initial parameters will also be stored in the database. When the staff receives the restoration instruction from the user end, the system parses the instruction, determines the corresponding time point, and then obtains the denture change data corresponding to the time point from the database. Based on the acquired denture change data and initial parameters corresponding to the time point, the system controls the 3D printing device to generate a restored denture model based on these data. The 3D printing device prints according to the restored model and generates a denture model before the processing error occurs, so that the user can reprocess the denture according to the parameters of this model, so that the best processing state can be clearly recorded.

[0069] Reference Figure 2 In one embodiment, the adding of partial behavior data of the denture processing device when the denture parameters change into the time series comprises:

[0070] S31, when the processing track of the denture processing device on the denture moves, obtaining the start time point and the end time point when the denture processing device contacts the denture;

[0071] S32, based on the start time point and the end time point, acquiring tool parameters and processing trajectory of the denture processing device according to a preset acquisition frequency, wherein the tool parameters include tool type, working parameters and position parameters;

[0072] S33, adding the tool parameters and processing trajectory into a time series.

[0073] As described in the above steps, by real-time monitoring of the contact state between the denture processing device and the denture, the start and end time points of each contact are recorded. These time points reflect the critical moments when the processing trajectory of the denture processing device on the denture changes. These time points can be used as reference points for changes in denture parameters, which helps to more accurately analyze and restore changes in dentures. Between the start and end time points of each contact, tool parameters and processing trajectories are collected at a preset collection frequency. This ensures that there is a complete set of tool parameter and processing trajectory data at each time point to reflect the details of the denture processing process. This method can provide a more comprehensive data set, which helps to more accurately analyze and predict changes in dentures. The collected tool parameters and processing trajectories are added to the time series in chronological order. This can form a data set that changes over time, reflecting the state of each time point in the denture processing process. Time series data helps to more accurately analyze and restore changes in dentures because it contains detailed information about the processing process.

[0074] In one embodiment, the preset model includes model training, the steps include:

[0075] Collect historical denture processing behavior data and denture initial parameters;

[0076] Extracting features from the behavior data using a frequency domain feature extraction method;

[0077] Collect historical denture change data, and annotate the historical denture change data according to the preset change time points;

[0078] The features extracted from the behavior data and the labeled denture change data are used to train a linear regression model to obtain a trained model.

[0079] As described above, by collecting behavioral data and initial parameters from past denture processing, a historical data set is established, which will be used to train and validate the model. Historical data helps the model learn various change patterns that may occur during denture processing, thereby improving the model's predictive ability. By analyzing the frequency domain features of behavioral data, key features related to denture processing, such as frequency, amplitude, etc., can be extracted. Frequency domain feature extraction helps the model recognize and understand complex patterns in the denture processing process, thereby improving the model's predictive accuracy. Collect historical denture change data and annotate the data according to the preset change time points so that they correspond to the behavioral data features. Data annotation helps the model learn the relationship between denture changes and behavioral data features, thereby improving the model's predictive ability. Use behavioral data features and denture change data to train a linear regression model, and establish a predictive model by learning the relationship between data. The linear regression model can be used to predict the state of the denture at a specific point in time, thereby helping the operator identify the denture parameters before over-processing.

[0080] In one embodiment, the step of acquiring the tool parameters and processing trajectory of the denture processing device according to a preset acquisition frequency includes acquiring the acquisition frequency, and the steps include:

[0081] When the denture processing device is in contact with the denture, obtaining a rotation speed and a feed speed of the denture processing device;

[0082] Analyzing the parameter change rate of the denture processing device according to the rotation speed and feed speed;

[0083] Inputting the parameter change rate of the denture processing device into a preset frequency analysis model, outputting the acquisition frequency through the frequency analysis model, and acquiring the tool parameters and processing trajectory of the denture processing device based on the acquisition frequency;

[0084] When the rotation speed and feed speed of the gear machining device undergo parameter changes, the acquisition frequency is reanalyzed.

[0085] As described in the above steps, the contact state between the denture processing device and the denture is monitored in real time by sensors, and the two key parameters of rotation speed and feed speed are obtained. These parameters reflect the working state of the processing device and are the basis for analyzing the denture processing process and predicting parameter changes. By analyzing the changes in rotation speed and feed speed, the parameter change rate of the denture processing device, that is, the speed of change during the processing, can be inferred. The parameter change rate helps to evaluate the stability of the processing process. Using the preset frequency analysis model, the optimal acquisition frequency is determined according to the parameter change rate to ensure that important changes in the processing process can be accurately captured. Dynamic adjustment of the acquisition frequency can improve the efficiency of data acquisition, avoid missing key information during the processing process, and reduce unnecessary data processing burden. When the rotation speed and feed speed of the processing device change, it is necessary to re-analyze the parameter change rate and re-determine the acquisition frequency according to the new changes. This adaptive adjustment mechanism can ensure that the optimal acquisition frequency is always maintained during the processing process, thereby improving data quality and model prediction accuracy.

[0086] In one embodiment, after the step of analyzing and saving the denture change data at each time point through the preset model, the method further includes:

[0087] Analyzing the denture change data at each time point, performing a quality check on the denture change data, inputting the denture change data at each time point into an error detection model, and analyzing whether an abnormal value appears in the denture change data at each time point through the error detection model;

[0088] When an abnormal value appears in the denture change data, determining a compensation value required for the abnormal value based on the normal denture change data and the abnormal value;

[0089] adjusting the denture change data at the time point corresponding to the abnormal value based on the compensation value;

[0090] Analyze the data source that causes the abnormal value, and analyze the cause of the abnormal value based on the data source.

[0091] As described in the above steps, the denture change data at each time point is checked to ensure the accuracy and completeness of the data to avoid analysis errors caused by data quality issues. High-quality data is the basis for accurate analysis of denture changes and ensures the accuracy of subsequent operations. An error detection model is used to identify outliers in the data, which may be caused by sensor errors, equipment failures, or other unpredictable factors. Outlier identification helps to promptly discover and deal with problems in the data and improve the accuracy of the analysis results. By analyzing normal data and outliers, the compensation value required for the outliers can be determined so that the outliers can be corrected. The determination of the compensation value helps to restore the data accuracy of the outliers, thereby improving the prediction accuracy of the model. The compensation value is used to adjust the denture change data at the time point corresponding to the outliers to make it closer to the normal value. The adjusted data can improve the prediction accuracy of the model, thereby improving the quality and efficiency of denture processing. By analyzing the data source of the outliers, the causes of the outliers, such as sensor errors, equipment failures, etc., can be determined. Analyzing the causes of the outliers helps to find out the problem and take appropriate measures to avoid similar problems from happening again.

[0092] In one embodiment, after the step of analyzing the cause of the abnormal value according to the data source, the method further includes:

[0093] Analyze the cause of the abnormal value, when the cause of the abnormal value is that the denture change data at the preset model analysis time point is inaccurate;

[0094] The abnormal values ​​and the compensation values ​​are used to generate a training set for optimizing the preset model.

[0095] As described in the above steps, by analyzing the data source of the outlier, the cause of the outlier can be determined, such as sensor error, equipment failure, etc. Determining the cause of the outlier helps to take appropriate measures to avoid the recurrence of similar problems and improve the stability and reliability of the system. If the outlier is caused by inaccurate denture change data at the preset model analysis time point, the model needs to be optimized. This optimization can improve the prediction accuracy of the model, thereby improving the quality and efficiency of denture processing. By generating a training set with outliers and compensation values, more learning samples can be provided to the model to help the model better understand the relationship between outliers and compensation values. The generation of a training set helps the model learn how to handle outliers more accurately, thereby improving the prediction accuracy of the model. Use the generated training set to optimize the preset model to improve the prediction accuracy and robustness of the model. Model optimization helps to improve the quality and efficiency of denture processing and reduce errors caused by inaccurate models.

[0096] In one embodiment, determining the compensation value required for the abnormal value based on the normal denture change data and the abnormal value includes:

[0097] constructing a three-dimensional virtual model of the denture according to the initial parameters of the denture;

[0098] Reconstructing the three-dimensional virtual model based on the normal denture change data and the denture change data corresponding to the abnormal value to obtain a reconstructed three-dimensional virtual model;

[0099] Annotating outlier positions in the reconstructed three-dimensional virtual model, and extracting parameters of adjacent positions of the outlier positions;

[0100] The compensation value required for the outlier is calculated according to the adjacent position point parameters to obtain the compensation value required for the outlier.

[0101] As described above, using the initial parameters of the denture (such as size, shape, material properties, etc.) as input, a three-dimensional virtual model of the denture is constructed using a three-dimensional modeling software. This model will serve as the basis for subsequent analysis to compare the normal change data and the denture change data corresponding to the outliers. The three-dimensional virtual model can provide a three-dimensional perspective of the denture during the processing process, which helps to more accurately analyze and understand the changes in the denture. By comparing the normal denture change data and the denture change data corresponding to the outliers, the impact of the outliers on the denture model can be determined, and the three-dimensional virtual model can be reconstructed accordingly. This involves adjusting the original three-dimensional model to reflect the changes in the shape and size of the denture caused by the outliers. The reconstructed three-dimensional virtual model can accurately reflect the impact of the outliers on the denture model and provide accurate data for the calculation of the compensation value. The position of the outlier is marked in the reconstructed three-dimensional virtual model, and the parameters of the adjacent position points of the position are extracted. These adjacent position point parameters will be compared with the outliers to determine the compensation value. The marking of the outlier position and the extraction of the adjacent position point parameters provide necessary information for the compensation value calculation, which helps to accurately determine the compensation value. Based on the extracted adjacent position point parameters, the compensation value required for the outlier is calculated. It involves calculating the difference between the outlier and the parameters of the adjacent points and determining the compensation value based on these differences. The calculation of the compensation value helps to restore the original state of the denture model.

[0102] In yet another embodiment, the step of calculating the compensation value required for the outlier according to the adjacent position point parameters to obtain the compensation value required for the outlier includes:

[0103] In the reconstructed three-dimensional virtual model, the locations of the outliers are marked;

[0104] Parameters of neighboring points: Parameters of multiple neighboring points are extracted from around the outlier location. These parameters will be used to calculate the compensation value.

[0105] Compensation value calculation formula: The compensation value calculation formula is based on the parameters of the adjacent location points and the location of the outlier.

[0106] Formula: Compensation value = (sum of Σ adjacent position point parameters - outlier position parameter) / number of adjacent position points

[0107] ΣSum of parameters of adjacent location points: This is the sum of the parameters of all adjacent location points, which is used to reflect the average parameter value around the outlier location.

[0108] Outlier location parameter: This is the parameter value of the outlier location, which represents the deviation of the outlier from the normal value.

[0109] Number of neighboring points: This is the number of neighboring points used to calculate the compensation value, usually a fixed value such as 5 or 10.

[0110] Compensation value: The compensation value calculated by the above formula is used to adjust the denture change data at the time point corresponding to the abnormal value.

[0111] Apply compensation value: Apply the calculated compensation value to the denture change data at the time point corresponding to the outlier to restore the original state of the denture.

[0112] In one feasible embodiment, suppose a dental intern makes a mistake during the denture processing, resulting in over-processing of the denture. Through this method, the intern can learn how to identify and select a suitable time point, and print out the denture model at that time point through a 3D printer. Then, the instructor can guide the intern on how to repair the over-processed part based on this model, thereby improving the intern's skills and experience. Specifically, the intern accidentally over-processed a denture during the denture processing. Since the method has recorded the denture parameters in the current processing state. The instructor can guide the intern to select a previously recorded denture parameter in the normal state that is closest to the desired time point. And use a 3D printer to print out a denture model based on the parameters at that time point. The intern uses the printed model as a reference to compare the over-processed denture, and adjusts the over-processed part according to the model until it returns to the normal state. Throughout the repair process, the instructor closely monitors the intern's operation and provides immediate feedback and guidance. The instructor can point out the intern's shortcomings in the operation and provide suggestions for improvement. Through this process, interns use 3D printing technology to assist in restoration, and can quickly understand where the over-polishing is, rather than re-processing a denture without knowing the cause of the problem. This helps interns improve their operating skills and problem-solving abilities. Through practical operations and the guidance of mentors, interns have accumulated experience in repairing over-processed dentures.

[0113] The method for restoring the parameter model during denture processing of the present application monitors in real time whether the denture processing device starts processing the material, immediately starts the processing program, and adjusts the processing strategy based on real-time feedback to ensure the timeliness and accuracy of the processing process. When the parameters of the denture change, the method can add the behavioral data at the time of change to the time series, and input it into the preset model together with the initial parameters. In this way, even if the denture is over-processed during the processing, the original state of the denture can be restored by restoring the model, avoiding the trouble and uncertainty of reprocessing. Through automated and intelligent monitoring, the method can reduce the intervention and adjustment of the operator, thereby reducing workload and cost. At the same time, the recording and restoration function of parameter changes also helps to reduce the need for reprocessing due to over-processing, further reducing costs.

[0114] Reference Figure 3 In an embodiment of the present application, a device for restoring a parameter model during denture processing is also provided, comprising:

[0115] A first acquisition module 1 is used to acquire initial parameters of the denture when the denture begins to be processed;

[0116] A second acquisition module 2 is used to acquire the behavior data of the denture processing device in real time, wherein the behavior data includes the processing track and tool parameters of the denture processing device on the denture;

[0117] A judgment module 3, used for judging whether a parameter change occurs to the denture according to the behavior data;

[0118] An input module 4 is used for adding part of the behavior data of the denture processing device when the parameters of the denture change into a time series when the parameters of the denture change, and inputting the part of the behavior data added into the time series and the initial parameters into a preset model, and analyzing and saving the denture change data at each time point through the preset model;

[0119] The parsing module 5 is used for parsing the time point corresponding to the restoration instruction when receiving the restoration instruction from the user end, and obtaining the corresponding denture change data according to the time point;

[0120] The control module 6 is used to control the 3D printing device to generate a denture restoration model based on the denture change data and initial parameters corresponding to the time point.

[0121] As described above, it can be understood that the various components of the restoration device for the parameter model during denture processing proposed in this application can realize the functions of any of the restoration methods for the parameter model during denture processing described above, and the specific structure will not be repeated.

[0122] Reference Figure 4In an embodiment of the present application, a computer device is also provided. The computer device may be a server, and its internal structure may be as follows: Figure 4 As shown. The computer device includes a processor, a memory, a network interface and a database connected via a system bus. Among them, the processor designed by the computer is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data such as monitoring data. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a method for restoring a parameter model during denture processing is implemented.

[0123] The processor executes the method for restoring the parameter model when the denture is processed, including: when the denture starts to be processed, the initial parameters of the denture are obtained; the behavior data of the denture processing device is obtained in real time, and the behavior data includes the processing trajectory and tool parameters of the denture processing device on the denture; judging whether the parameters of the denture change according to the behavior data; when the parameters of the denture change, adding part of the behavior data of the denture processing device when the parameters of the denture change to the time series, and inputting the part of the behavior data added to the time series and the initial parameters into the preset model, and analyzing and saving the denture change data at each time point through the preset model; when a restoration instruction is received from the user end, parsing the time point corresponding to the restoration instruction, and obtaining the corresponding denture change data according to the time point; based on the denture change data and initial parameters corresponding to the time point, controlling the 3D printing device to generate a denture restoration model.

[0124] The above-mentioned method for restoring the parameter model during denture processing monitors in real time whether the denture processing device has started processing the material, immediately starts the processing program, and adjusts the processing strategy based on real-time feedback to ensure the timeliness and accuracy of the processing process. When the parameters of the denture change, the method can add the behavioral data at the time of change to the time series and input it into the preset model together with the initial parameters. In this way, even if the denture is over-processed during the processing, the original state of the denture can be restored by restoring the model, avoiding the trouble and uncertainty of reprocessing. Through automated and intelligent monitoring, this method can reduce the intervention and adjustment of the operator, thereby reducing workload and cost. At the same time, the recording and restoration function of parameter changes can also help solve the problem that it is difficult to achieve the desired effect when reprocessing is required due to over-processing, thereby further reducing costs.

[0125] An embodiment of the present application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a method for restoring a parameter model during denture processing, comprising the following steps: when the denture begins to be processed, obtaining the initial parameters of the denture; obtaining the behavior data of the denture processing device in real time, the behavior data including the processing trajectory and tool parameters of the denture processing device on the denture; judging whether the parameters of the denture have changed according to the behavior data; when the parameters of the denture have changed, adding part of the behavior data of the denture processing device when the parameters of the denture have changed to a time series, and inputting the part of the behavior data added to the time series and the initial parameters into a preset model, analyzing and saving the denture change data at each time point through the preset model; when a restoration instruction from a user terminal is received, parsing the time point corresponding to the restoration instruction, and obtaining the corresponding denture change data according to the time point; and controlling the 3D printing device to generate a denture restoration model based on the denture change data and the initial parameters corresponding to the time point.

[0126] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media provided in this application and used in the embodiments may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0127] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, device, article or method. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the existence of other identical elements in the process, device, article or method including the element.

[0128] The above description is only a preferred embodiment of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A method for restoring a parameter model during denture processing, characterized in that: The method comprises: When the denture begins to be processed, obtaining initial parameters of the denture; Acquire behavior data of the denture processing device in real time, wherein the behavior data type includes a processing track and tool parameters of the denture processing device on the denture; determining whether a parameter change occurs to the denture according to the behavior data; When the denture parameter changes, part of the behavior data type of the denture processing device when the denture parameter changes is added to the time series, and the part of the behavior data added to the time series and the initial parameters are input into a preset model, and the denture change data at each time point is analyzed and saved through the preset model; When receiving a restoration instruction from the user terminal, parsing the time point corresponding to the restoration instruction, and acquiring corresponding denture change data according to the time point; Based on the denture change data and initial parameters corresponding to the time point, the 3D printing device is controlled to generate a denture restoration model.

2. The method for restoring the parameter model during denture processing according to claim 1, characterized in that: The adding of some behavior data types of the denture processing device into the time series when the parameters of the denture change, includes: When the processing track of the denture processing device on the denture moves, obtaining the start time point and the end time point when the denture processing device contacts the denture; Based on the start time point and the end time point, acquiring tool parameters and processing trajectory of the denture processing device according to a preset acquisition frequency, wherein the tool parameters include tool type, working parameters and position parameters; The tool parameters and processing trajectory are added into a time series.

3. The method for restoring the parameter model during denture processing according to claim 2, characterized in that: The preset model includes model training, and the steps include: Collect historical denture processing behavior data and denture initial parameters; Extracting features from the behavior data using a frequency domain feature extraction method; Collect historical denture change data, and annotate the historical denture change data according to the preset change time points; The features extracted from the behavior data and the labeled denture change data are used to train a linear regression model to obtain a trained model.

4. The method for restoring the parameter model during denture processing according to claim 2, characterized in that: The step of acquiring the tool parameters and processing trajectory of the denture processing device according to the preset acquisition frequency includes acquiring the acquisition frequency, and the steps include: When the denture processing device is in contact with the denture, obtaining a rotation speed and a feed speed of the denture processing device; Analyzing the parameter change rate of the denture processing device according to the rotation speed and feed speed; Inputting the parameter change rate of the denture processing device into a preset frequency analysis model, outputting the acquisition frequency through the frequency analysis model, and acquiring the tool parameters and processing trajectory of the denture processing device based on the acquisition frequency; When the rotation speed and feed speed of the gear machining device undergo parameter changes, the acquisition frequency is reanalyzed.

5. The method for restoring the parameter model during denture processing according to claim 1, characterized in that: After the step of analyzing and saving the denture change data at each time point through the preset model, the method further includes: Analyzing the denture change data at each time point, performing a quality check on the denture change data, inputting the denture change data at each time point into an error detection model, and analyzing whether an abnormal value appears in the denture change data at each time point through the error detection model; When an abnormal value appears in the denture change data, determining a compensation value required for the abnormal value based on the normal denture change data and the abnormal value; adjusting the denture change data at the time point corresponding to the abnormal value based on the compensation value; Analyze the data source that causes the abnormal value, and analyze the cause of the abnormal value based on the data source.

6. The method for restoring the parameter model during denture processing according to claim 5, characterized in that: After the step of analyzing the cause of the abnormal value according to the data source, the method further includes: Analyze the cause of the abnormal value, when the cause of the abnormal value is that the denture change data at the preset model analysis time point is inaccurate; The abnormal values ​​and the compensation values ​​are used to generate a training set for optimizing the preset model.

7. The method for restoring the parameter model during denture processing according to claim 5, characterized in that: The step of determining the compensation value required for the abnormal value based on the normal denture change data and the abnormal value comprises: constructing a three-dimensional virtual model of the denture according to the initial parameters of the denture; Reconstructing the three-dimensional virtual model based on the normal denture change data and the denture change data corresponding to the abnormal value to obtain a reconstructed three-dimensional virtual model; Annotating outlier positions in the reconstructed three-dimensional virtual model, and extracting parameters of adjacent positions of the outlier positions; The compensation value required for the outlier is calculated according to the adjacent position point parameters to obtain the compensation value required for the outlier.

8. A device for restoring parameter models during denture processing, characterized in that: include: A first acquisition module, used for acquiring initial parameters of the denture when the denture begins to be processed; A second acquisition module is used to acquire the behavior data of the denture processing device in real time, wherein the behavior data type includes the processing track and tool parameters of the denture processing device on the denture; A judgment module, used for judging whether a parameter change occurs to the denture according to the behavior data; An input module, used for adding part of the behavior data type of the denture processing device when the parameters of the denture change, to a time series when the parameters of the denture change, and inputting the part of the behavior data added to the time series and the initial parameters into a preset model, and analyzing and saving the denture change data at each time point through the preset model; The parsing module is used to parse the time point corresponding to the restoration instruction when receiving the restoration instruction from the user end, and obtain the corresponding denture change data according to the time point; The control module is used to control the 3D printing device to generate a denture restoration model based on the denture change data and initial parameters corresponding to the time point.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images