Intelligent 3D printing system for oral medicine teaching

Abstract

The invention relates to the technical field of oral cavity teaching models, in particular to an intelligent 3D printing system for oral medicine teaching, which comprises an oral cavity disease model retrieval module, a model priority evaluation module, a model adjustment module and a 3D printing adjustment module. According to the invention, through matching of the oral disease data, the oral disease model meeting teaching requirements can be accurately positioned, accurate correspondence of teaching contents is ensured, so that the learning efficiency of students is improved, the model is adjusted, the size and proportion of the lesion model can be adjusted according to specific teaching requirements, and the teaching efficiency is improved. According to the technical scheme, the model is designed, the applicability and flexibility of the model are improved, the quality of the model is improved by controlling parameters of 3D printing, the material cost is effectively controlled, and the color of the model is optimized by adjusting the mixing proportion of different printing materials, so that teaching is more accurate and visual, and understanding and mastering of students on anatomical forms and disease diagnosis and treatment skills of all parts of the oral cavity are deepened.

Description

Technical Field

[0001] The present invention relates to the technical field of oral teaching models, and in particular to an intelligent 3D printing system for oral medicine teaching. Background Art

[0002] The field of oral teaching model technology focuses on the development of simulated oral anatomical structures and disease morphology used in oral medicine education. Oral teaching model technology provides accurate replication of tooth and periodontal structures through physical models or digital methods, which is used to assist teachers in demonstrating disease diagnosis and treatment plans and students in practicing. The integration of 3D printing technology makes it possible to produce personalized and accurate oral teaching models, improving the usability and functionality of the models. It has achieved the application of real cases from clinical practice to oral medicine teaching, assisting teachers in teaching and students in learning.

[0003] Among them, the intelligent 3D printing system for oral education focuses on using 3D printing technology to make models for teaching, aiming to provide more efficient and intuitive teaching tools for oral education. The system can match cases in the clinical imaging database according to teaching needs, including common cases such as caries, pulpitis, periodontal disease, and edentulous teeth. The 3D printed tooth models can be used for teachers' teaching demonstrations and students' practical operation training, which can improve teaching effectiveness. At the same time, students can also deepen their understanding of various oral diseases and treatment techniques through practical operations.

[0004] Traditional printing systems have limitations in teaching applications and lack deep adaptation to teaching content and student needs. For example, traditional models cannot reproduce a variety of actual clinical situations, which limits the application effect of teaching models, resulting in waste of teaching resources and unsatisfactory teaching results. Traditional systems are relatively fixed in terms of model size adjustment and printing accuracy, and are difficult to adjust according to specific teaching needs, which limits the teaching applicability and economy of the model, resulting in the teaching model not being able to fully meet the needs of teaching, affecting the quality and efficiency of teaching. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose an intelligent 3D printing system for oral medicine teaching.

[0006] In order to achieve the above-mentioned purpose, the present invention adopts the following technical solution: an intelligent 3D printing system for oral medicine teaching, wherein the system comprises:

[0007] The oral disease model retrieval module is based on the oral dental teaching objectives. According to the target lesion type, lesion location and lesion size, it extracts matching oral disease models from the oral clinical image database, including tooth models, gum models and corresponding oral and jaw bone models. According to teaching needs, it extracts single or overall tooth and periodontal tissue data to obtain matching model recognition results.

[0008] The model adjustment module extracts the model data of the oral disease model at the differentiated lesion stage based on the matching model recognition result and the selection result of the teaching staff, evaluates the deviation between the actual size and the target display size, scales and adjusts the oral disease model, adjusts the size of the oral disease model, and obtains the model size adjustment result;

[0009] The 3D printing adjustment module adjusts the filling density in the 3D printing process based on the model size adjustment result, according to the volume size of the model and the material cost, and adjusts the printing accuracy according to the volume size of the model to obtain the printing parameter adjustment result;

[0010] Based on the printing parameter adjustment results, the printing implementation module prints models of oral diseases in multiple lesion stages through a printing device. According to teaching needs, multiple parts of the oral disease model are printed separately, and the mixing ratio of differentiated color printing materials is intelligently controlled by AI to match the actual color in the oral cavity to obtain a 3D printing result of the teaching model.

[0011] The present invention is improved in that the steps of obtaining the matching model recognition result are:

[0012] Based on the teaching objectives of each sub-specialty of stomatology, the lesion type, lesion location and lesion size data of each model are extracted from the oral clinical image database to obtain the disease model data;

[0013] Based on the disease model data, according to the target lesion type, lesion location and lesion size, the formula:

[0014]

[0015] Calculate the matching degree D of the oral disease model, where w Di represents the weight of the i-th feature, v Di represents the ith eigenvalue of the oral disease model, m Di represents the i-th eigenvalue of the matching target, s Di represents the standard deviation of the i-th feature, p D is the power parameter, and D is the matching degree;

[0016] Based on the matching degree D, a comparison is made with a preset matching degree threshold, and the oral disease model whose matching degree D exceeds the matching degree threshold is marked as a matching model to obtain a matching model recognition result.

[0017] The present invention is improved in that, based on the matching model recognition result, the teaching staff selects the oral disease model and extracts the model data of the oral disease model at the differentiated lesion stage to obtain the model selection result;

[0018] Based on the model selection result, the size data of the lesion area is compared with the target display size, the size deviation ratio is calculated, and the size deviation information is obtained.

[0019] The present invention is improved in that the steps of obtaining the model size adjustment result are:

[0020] Based on the size deviation information, by the formula:

[0021]

[0022] Calculate the scaling ratio R, where δ is the size deviation ratio, k R is the reinforcement coefficient, λ R is the attenuation coefficient, R is the scaling factor, and e is the base of the natural logarithm;

[0023] Based on the scaling ratio R, the oral disease model is scaled and adjusted to adjust the size of the oral disease model and obtain a model size adjustment result.

[0024] The present invention is improved in that the method for adjusting the filling density during 3D printing is:

[0025] Based on the model size adjustment result, a preset reference filling density of the 3D printing device is obtained, and volume data of the oral disease model and printing material cost data are extracted to obtain printing-related data;

[0026] Based on the print association data, by the formula:

[0027]

[0028] Calculate the adjusted packing density E fill , get the filling density adjustment information, where k E is the volume adjustment factor, m E is the cost adjustment factor, E base is the base packing density, V model is the model volume, V base is the base volume, B is the material cost, E is fill is the adjusted packing density, and e is the base of the natural logarithm.

[0029] The present invention is improved in that the steps of obtaining the printing parameter adjustment result are:

[0030] Based on the model size adjustment result, a preset benchmark printing accuracy of the 3D printing device is obtained, and volume data of the oral disease model is extracted to obtain accuracy correlation data;

[0031] Based on the accuracy correlation data, through the formula:

[0032]

[0033] Calculate the adjusted printing precision P adjust , integrating the adjusted packing density E fill , get the printing parameter adjustment result, where P base is the benchmark printing accuracy, V model is the model volume, V standard is the standard volume, h P is the precision adjustment coefficient, P adjust This is the printing accuracy after adjustment.

[0034] The present invention is improved in that the steps of obtaining the 3D printing result of the teaching model are as follows:

[0035] Based on the printing parameter adjustment result and according to the teaching objectives, the oral disease model is divided into a plurality of regions, including teeth, gums, jaws and lesion regions, and a region division instruction is obtained;

[0036] Based on the area division instruction, the nozzle path of the printing device is adjusted to avoid mutual influence during the printing process, and the partition printing is performed to obtain the printing path adjustment result;

[0037] Based on the adjustment result of the printing path, a printing material with a corresponding hardness is selected according to the hardness of the differentiated area, and according to the target teaching display effect, a printing material with a transparent material is selected in the target area, and according to the color of the printing material provided by the current printing device, the actual color of the target area is extracted by using the oral image data, and the material mixing ratio required for the target color is analyzed by AI to obtain the material mixing ratio information;

[0038] Based on the material mixing ratio information, the printing path adjustment result and the area division instruction, the oral disease model is printed in different areas to obtain a 3D printing result of the teaching model.

[0039] Compared with the prior art, the advantages and positive effects of the present invention are:

[0040] In the present invention, by matching oral disease data, the oral disease model required for teaching can be accurately located, ensuring the accurate correspondence of teaching content, thereby improving students' learning efficiency, and adjusting the model so that the lesion model can be adjusted in size and proportion according to specific teaching needs, and by printing the model parts separately, it is convenient to split and display for actual dental teaching, thereby increasing the applicability and flexibility of the model, and by controlling the parameters of 3D printing, the quality of the model is improved, and the material cost is effectively controlled, and by adjusting the mixing ratio of different printing materials and optimizing the model color, teaching is made more accurate and intuitive, which deepens students' understanding and mastery of the anatomical morphology of various parts of the oral cavity and disease diagnosis and treatment skills. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 is a system flow chart of the present invention;

[0042] Figure 2 A flow chart for obtaining matching model recognition results of the present invention;

[0043] Figure 3 A flow chart for evaluating the deviation of the actual size from the target display size for the present invention;

[0044] Figure 4 A flow chart for obtaining the model size adjustment result of the present invention;

[0045] Figure 5 A flow chart of adjusting the filling density during 3D printing according to the present invention;

[0046] Figure 6 A flow chart of obtaining the printing parameter adjustment result of the present invention;

[0047] Figure 7 The flowchart of the present invention for obtaining the 3D printing results of the teaching model. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention 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 invention and are not intended to limit the present invention.

[0049] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating positions or positional relationships, are based on the positions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0050] See also Figure 1 The present invention provides a technical solution: an intelligent 3D printing system for oral medicine teaching, the system comprising:

[0051] The oral disease model retrieval module is based on the oral dental teaching objectives. According to the target lesion type, lesion location and lesion size, it extracts matching oral disease models from the oral clinical image database, including tooth models, gum models and corresponding oral and jaw bone models. According to teaching needs, it extracts single or overall tooth and periodontal tissue data to obtain matching model recognition results.

[0052] The model adjustment module extracts the model data of the oral disease model at the differentiated lesion stage based on the matching model recognition results and the selection results of the teaching staff, evaluates the deviation between the actual size and the target display size, scales and adjusts the oral disease model, adjusts the size of the oral disease model, and obtains the model size adjustment result;

[0053] The 3D printing adjustment module adjusts the filling density in the 3D printing process based on the model size adjustment result, according to the model volume and material cost, and adjusts the printing accuracy according to the model volume to obtain the printing parameter adjustment result;

[0054] The printing implementation module adjusts the printing parameters based on the results and uses a printing device to print models of oral diseases in multiple lesion stages. According to teaching needs, the multiple parts of the oral disease model are printed separately. The mixing ratio of differentiated color printing materials is intelligently controlled by AI to match the actual color in the oral cavity to obtain the 3D printing result of the teaching model.

[0055] The matching model identification results include the matching score, the matching model ID and the matching model attribute information. The model size adjustment results include the adjusted size parameters, lesion stage and three-dimensional data of the model. The printing parameter adjustment results include the printing accuracy parameters and filling density parameters. The teaching model 3D printing results include the type of material used and the size specifications of the model.

[0056] See also Figure 2, the steps to obtain the matching model recognition results are:

[0057] Based on the teaching objectives of each sub-specialty of stomatology, the lesion type, lesion location and lesion size data of each model are extracted from the oral clinical image database to obtain the disease model data;

[0058] Based on the disease model data, according to the target lesion type, lesion location and lesion size, the formula is:

[0059]

[0060] Calculate the matching degree D of the oral disease model, where w Di represents the weight of the i-th feature, v Di represents the ith eigenvalue of the oral disease model, m Di represents the i-th eigenvalue of the matching target, s Di represents the standard deviation of the i-th feature, p D is the power parameter, and D is the matching degree;

[0061] Based on the matching degree D, it is compared with the preset matching degree threshold, and the oral disease model whose matching degree D exceeds the matching degree threshold is marked as a matching model to obtain a matching model recognition result.

[0062] formula:

[0063]

[0064] The meaning and acquisition method of parameters:

[0065] n D : The total number of features. Determined based on the number of available features for each oral disease model in the actual dataset, such as common features in a database such as lesion size, location, and type.

[0066] w Di : The weight of the ith feature. The weight is determined through expert consultation or previous statistical analysis and reflects the importance of different features in the matching process.

[0067] v Di : The eigenvalue of the ith oral disease model. The value is directly extracted from the oral clinical image database.

[0068] m Di : The i-th feature value of the matching target. Determined based on user input or preset conditions.

[0069] s Di : The standard deviation of the ith feature. Obtained through statistical analysis of historical data sets, it is used for normalization to balance the comparison between features.

[0070] p D : Power parameter. Choose a suitable p D The value is used to increase the sensitivity to the difference in feature values ​​and is usually set by experts according to the matching requirements.

[0071] Calculation example:

[0072] Set the following parameters and feature values:

[0073] n D =3: Indicates that the model takes three features into consideration.

[0074] w D1 =0.5, w D2 =0.3, w D3 =0.2: weights of different features.

[0075] v D1 =10. D2 =20. D3 =30: tooth model feature value extracted from the database.

[0076] m D1 =10,m D2 =22, m D3 =28: The set matching target feature value.

[0077] s D1 =2,s D2 =3,s D3 =4: Standard deviation of each feature.

[0078] p D =2: The power parameter is set to 2.

[0079] Calculation process:

[0080]

[0081] Calculate D:

[0082]

[0083] The calculated matching score D≈5.41 indicates that the matching degree between the given matching target and the model is high.

[0084] See also Figure 3 , the method to evaluate the deviation between the actual size and the target display size is:

[0085] Based on the lesion model display information, the teaching staff selects the oral disease model and extracts the model data of the oral disease model at the differentiated lesion stage to obtain the model selection result;

[0086] Based on the model selection results, the size data of the lesion area is compared with the target display size, using the formula:

[0087]

[0088] Calculate the size deviation ratio δ to obtain the size deviation information, where δ represents the deviation ratio, S actual is the lesion area size, S target is the target display size, and δ is the size deviation ratio.

[0089] formula:

[0090]

[0091] Parameter details and how to obtain them:

[0092] S actual : The size of the lesion area is directly measured from the 3D data of the oral disease model.

[0093] S target : Target display size, which is pre-set according to teaching needs or the specifications of the display equipment. This size is to ensure that the model can be displayed to learners in the most suitable proportion when it is actually used, and is usually determined by the designer of the educational program or the teaching staff.

[0094] Calculation example:

[0095] Set the following values:

[0096] S actual =15mm: Assume that the lesion area size is 15 mm. target =10mm: Assume that the target display size set for teaching purposes is 10 mm.

[0097] Substitute into the formula to calculate:

[0098]

[0099] The calculated size deviation ratio δ = 0.5 means that the actual lesion area is 50% larger than the target size. This ratio deviation provides a clear indicator that the model needs to be scaled down to reach the target size, ensuring that the model is accurate and appropriate for teaching.

[0100] See also Figure 4 , the steps to obtain the model size adjustment results are:

[0101] Based on the size deviation information, the formula:

[0102]

[0103] Calculate the scaling ratio R, where δ is the size deviation ratio, k R is the reinforcement coefficient, λ R is the attenuation coefficient, R is the scaling factor, and e is the base of the natural logarithm;

[0104] Based on the scaling ratio R, the oral disease model is scaled and adjusted, and the size of the oral disease model is adjusted to obtain a model size adjustment result.

[0105] formula:

[0106]

[0107] Parameter details and how to obtain them:

[0108] δ: Dimensional deviation ratio, calculated by the previous method.

[0109] k R : Strengthening factor, used to adjust the impact of size deviation δ. Determines the strengthening or suppression of the deviation value in the scaling calculation, based on previous testing or model evaluation experience.

[0110] λ R : Attenuation coefficient, used to adjust the speed of scaling adjustment when the deviation δ increases. The parameter is obtained through model analysis and experimental optimization to ensure that the scaling is not over-adjusted due to excessive deviation.

[0111] Calculation example:

[0112] Set the following parameter values:

[0113] δ=0.5:Calculated dimensional deviation ratio. k R =2: reinforcement coefficient. R =1: Attenuation coefficient. Substitute into the formula for calculation:

[0114]

[0115] The calculated scaling ratio R≈0.868 means that in order to make the model size meet the teaching requirements, the current model size needs to be reduced to about 86.8% of the original size to ensure that the model does not lose details due to excessive scaling.

[0116] See also Figure 5 , the method to adjust the filling density during 3D printing is:

[0117] Based on the model size adjustment result, the preset reference filling density of the 3D printing device is obtained, and the volume data of the oral disease model and the printing material cost data are extracted to obtain the printing related data;

[0118] Based on printing related data, through the formula:

[0119]

[0120] Calculate the adjusted packing density E fill , get the filling density adjustment information, where k E is the volume adjustment factor, m E is the cost adjustment factor, E base is the base packing density, V model is the model volume, V base is the base volume, B is the material cost, E is fill is the adjusted packing density, and e is the base of the natural logarithm.

[0121] formula:

[0122]

[0123] Parameter details and how to obtain them:

[0124] E base : Baseline filling density, determined based on material supplier recommendations or past printing experience, is intended to provide a starting point for efficient and cost-effective filling.

[0125] V model : Model volume, obtained directly from the 3D modeling software, represents the total volume of the resized model.

[0126] V base : Baseline volume, usually based on a typical model volume or a preset standard volume setting, used for comparison and calculation of volume change ratios.

[0127] k E : The volume adjustment coefficient is an empirical parameter obtained through the optimization process and is used to adjust the impact of volume increase or decrease on filling density.

[0128] B: Material cost, which is set according to the market price of the material and the extent to which it affects the printing cost. High-cost materials will prompt the use of lower filling density to reduce costs.

[0129] m E : Material cost adjustment coefficient, which is a parameter that measures the sensitivity of material cost to filling density adjustment and is determined through market research and cost analysis.

[0130] Calculation example:

[0131] The following parameter values ​​are set for calculation:

[0132] E base =20%: basic filling density.

[0133] V model =1500cm 3 : Model volume obtained from the 3D model.

[0134] V base =1000cm 3 : The set base volume.

[0135] k E =0.1: volume adjustment factor.

[0136] B = 0.05: Material cost, reflecting higher cost materials.

[0137] m E =1.5: Material cost adjustment factor, a higher value indicates a significant cost impact.

[0138] Calculated:

[0139]

[0140] E fill =20% e -0.1·(1.5-1)-0.05·1.5

[0141] =20% e -0.1·0.5-0.075

[0142] =20% e -0.125

[0143] =20% 0.8825

[0144] ≈17.65%

[0145] Calculated adjusted packing density E fill ≈17.65%, which means that in order to accommodate material costs and model volume, the filling density needs to be adjusted from the baseline 20% to approximately 17.65%. The adjustment reflects the impact of larger volume and higher material costs, and by reducing the filling density to reduce material usage, costs are controlled to ensure the economical 3D printing process while meeting structural requirements.

[0146] See also Figure 6 , the steps to obtain the printing parameter adjustment results are:

[0147] Based on the model size adjustment result, the preset benchmark printing accuracy of the 3D printing equipment is obtained, and the volume data of the oral disease model is extracted to obtain the accuracy correlation data;

[0148] Based on the accuracy correlation data, through the formula:

[0149]

[0150] Calculate the adjusted printing precision P adjust , integrating the adjusted packing density E fill , get the printing parameter adjustment result, where P base is the benchmark printing accuracy, V model is the model volume, V standard is the standard volume, h P is the precision adjustment coefficient, P adjust This is the printing accuracy after adjustment.

[0151] formula:

[0152]

[0153] Parameter details and how to obtain them:

[0154] P base :Benchmark printing accuracy, a value preset according to the maximum performance of the printer and the detailed requirements of the model. It can be directly obtained from the user manual or technical specifications of the printer, or determined by experience.

[0155] V model : Model volume. This value is obtained directly from the 3D modeling software and represents the actual volume of the model.

[0156] V standard : Standard volume, usually based on the volume setting of a typical or preset model, used for comparison with the actual model volume.

[0157] h P : Precision adjustment coefficient, which is an empirical value, usually adjusted through printing tests and quality feedback to control the actual impact of volume changes on printing accuracy.

[0158] Calculation example:

[0159] Set the following parameter values:

[0160] P base =0.1mm: Benchmark printing accuracy. The value used here is the allowable error range.

[0161] V model =1200cm 3 : The actual model volume obtained from the 3D model.

[0162] V standard =1000cm 3 : The set standard volume.

[0163] h P =0.05: precision adjustment coefficient.

[0164] Calculate the volume ratio:

[0165]

[0166] Calculate the adjusted printing precision:

[0167] P adjust =0.1·(1+0.05·(1.2-1))

[0168] =0.1·(1+0.05·0.2)

[0169] =0.1·1.01

[0170] =0.101mm

[0171] The calculated adjusted printing precision P adjust =0.101mm, indicating that in order to accommodate the increase in model volume, the printing accuracy is slightly reduced compared to the baseline accuracy. This fine-tuning helps maintain cost efficiency.

[0172] See also Figure 7 , the steps to obtain the 3D printing results of the teaching model are:

[0173] Based on the printing parameter adjustment results and the teaching objectives, the oral disease model is divided into multiple regions, including teeth, gums, jaws, and lesion regions, and the regional division instructions are obtained;

[0174] Based on the area division instruction, the nozzle path of the printing device is adjusted to avoid mutual influence during the printing process, and the partition printing is performed to obtain the printing path adjustment result;

[0175] Based on the adjustment result of the printing path, a printing material with a corresponding hardness is selected according to the hardness of the differentiated area, and according to the target teaching display effect, a printing material with a transparent material is selected in the target area, and according to the color of the printing material provided by the current printing device, the actual color of the target area is extracted by using the oral image data, and the material mixing ratio required for the target color is analyzed by AI to obtain the material mixing ratio information;

[0176] Based on the material mixing ratio information, printing path adjustment results and area division instructions, the oral disease model is printed in different areas to obtain the 3D printing results of the teaching model.

[0177] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. An intelligent 3D printing system for oral medicine teaching, characterized in that: The system comprises: The oral disease model retrieval module is based on the oral dental teaching objectives. According to the target lesion type, lesion location and lesion size, it extracts matching oral disease models from the oral clinical image database, including tooth models, gum models and corresponding oral and jaw bone models. According to teaching needs, it extracts single or overall tooth and periodontal tissue data to obtain matching model recognition results. The model adjustment module extracts the model data of the oral disease model at the differentiated lesion stage based on the matching model recognition result and the selection result of the teaching staff, evaluates the deviation between the actual size and the target display size, scales and adjusts the oral disease model, adjusts the size of the oral disease model, and obtains the model size adjustment result; The 3D printing adjustment module adjusts the filling density in the 3D printing process based on the model size adjustment result, according to the volume size of the model and the material cost, and adjusts the printing accuracy according to the volume size of the model to obtain the printing parameter adjustment result; Based on the printing parameter adjustment results, the printing implementation module prints models of oral diseases in multiple lesion stages through a printing device. According to teaching needs, multiple parts of the oral disease model are printed separately, and the mixing ratio of differentiated color printing materials is intelligently controlled by AI to match the actual color in the oral cavity to obtain a 3D printing result of the teaching model.

2. The intelligent 3D printing system for oral medicine teaching according to claim 1, characterized in that: The steps for obtaining the matching model recognition result are: Based on the teaching objectives of each sub-specialty of stomatology, the lesion type, lesion location and lesion size data of each model are extracted from the oral clinical image database to obtain the disease model data; Based on the disease model data, according to the target lesion type, lesion location and lesion size, the formula: Calculate the matching degree D of the oral disease model, where w Di represents the weight of the i-th feature, v Di represents the ith eigenvalue of the oral disease model, m Di represents the i-th eigenvalue of the matching target, s Di represents the standard deviation of the i-th feature, p D is the power parameter, and D is the matching degree; Based on the matching degree D, a comparison is made with a preset matching degree threshold, and the oral disease model whose matching degree D exceeds the matching degree threshold is marked as a matching model to obtain a matching model recognition result.

3. The intelligent 3D printing system for oral medicine teaching according to claim 1, characterized in that: The method for evaluating the deviation between the actual size and the target display size is: Based on the matching model recognition result, the teaching staff selects an oral disease model and extracts model data of the oral disease model at a differentiated lesion stage to obtain a model selection result; Based on the model selection result, the size data of the lesion area is compared with the target display size, the size deviation ratio is calculated, and the size deviation information is obtained.

4. The intelligent 3D printing system for oral medicine teaching according to claim 3, characterized in that: The steps for obtaining the model size adjustment result are: Based on the size deviation information, by the formula: Calculate the scaling ratio R, where δ is the size deviation ratio, k R is the reinforcement coefficient, λ R is the attenuation coefficient, R is the scaling factor, and e is the base of the natural logarithm; Based on the scaling ratio R, the oral disease model is scaled and adjusted to adjust the size of the oral disease model and obtain a model size adjustment result.

5. The intelligent 3D printing system for oral medicine teaching according to claim 1, characterized in that: The method for adjusting the filling density during 3D printing is: Based on the model size adjustment result, a preset reference filling density of the 3D printing device is obtained, and volume data of the oral disease model and printing material cost data are extracted to obtain printing-related data; Based on the print association data, by the formula: Calculate the adjusted packing density E fill , get the filling density adjustment information, where k E is the volume adjustment factor, m E is the cost adjustment factor, E base is the base packing density, V model is the model volume, V base is the base volume, B is the material cost, E is fill is the adjusted packing density, and e is the base of the natural logarithm.

6. The intelligent 3D printing system for oral medicine teaching according to claim 5, characterized in that: The steps for obtaining the printing parameter adjustment result are: Based on the model size adjustment result, a preset benchmark printing accuracy of the 3D printing device is obtained, and volume data of the oral disease model is extracted to obtain accuracy correlation data; Based on the accuracy correlation data, through the formula: Calculate the adjusted printing precision P adjust , integrating the adjusted packing density E fill , get the printing parameter adjustment result, where P base is the benchmark printing accuracy, V model is the model volume, V standard is the standard volume, h P is the precision adjustment coefficient, P adjust This is the printing accuracy after adjustment.

7. The intelligent 3D printing system for oral medicine teaching according to claim 1, characterized in that: The steps for obtaining the 3D printing results of the teaching model are as follows: Based on the printing parameter adjustment result and according to the teaching objectives, the oral disease model is divided into a plurality of regions, including teeth, gums, jaws and lesion regions, and a region division instruction is obtained; Based on the area division instruction, the nozzle path of the printing device is adjusted to avoid mutual influence during the printing process, and the partition printing is performed to obtain the printing path adjustment result; Based on the adjustment result of the printing path, a printing material with a corresponding hardness is selected according to the hardness of the differentiated area, and according to the target teaching display effect, a printing material with a transparent material is selected in the target area, and according to the color of the printing material provided by the current printing device, the actual color of the target area is extracted by using the oral image data, and the material mixing ratio required for the target color is analyzed by AI to obtain the material mixing ratio information; Based on the material mixing ratio information, the printing path adjustment result and the area division instruction, the oral disease model is printed in different areas to obtain a 3D printing result of the teaching model.

Images