Artificial intelligence oral abutment selection method and equipment

Abstract

The invention provides an artificial intelligence oral abutment selection method and equipment, and the method comprises the steps: obtaining the oral feature information of a patient according to an imported digital order model; the oral cavity feature information of the patient is input into a pre-trained AI model selection model, the AI model selection model is trained through multiple sets of training data, and each set of training data in the multiple sets of training data comprises the oral cavity feature information and identification information used for identifying spatial data required for restoration; obtaining an abutment model screened out by the AI model selection model, wherein restoration demand space data matched with the abutment model meets restoration space requirements; and matching the base station model to the digital order model, and reflecting the base station model on the missing position of the digital order model in a three-dimensional manner. The problems that in the prior art, an oral abutment selection method is high in subjectivity, large in error and low in efficiency are solved.

Description

Technical Field

[0001] The present application relates to the field of cavity digital medical technology, and more specifically, to an artificial intelligence oral base selection method and device. Background Art

[0002] As an important branch of medicine, stomatology is also facing the transformation of digitalization and intelligence. In the medical process of dental implants, it is usually necessary to select the oral abutment according to the tooth shape of the missing teeth on the patient. The traditional method of selecting an oral abutment is usually to measure the patient's mouth manually and visually, and then select the abutment based on the measurement and judgment data.

[0003] As people pay more and more attention to oral health, they also put forward higher requirements for the quality and efficiency of oral medical services. And with the rapid development of artificial intelligence technology, its application in the medical field has attracted more and more attention. However, the traditional oral abutment selection method has problems such as strong subjectivity, large errors, and low efficiency. It is expected to be optimized by applying digital technology and intelligent technology.

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

[0005] The purpose of the present application is to provide an artificial intelligence oral abutment selection method and device, which solves the problems of strong subjectivity, large errors and low efficiency in the oral abutment selection method in the prior art.

[0006] To achieve the above purpose, the technical solution adopted in this application is:

[0007] On the one hand, the present application provides an artificial intelligence oral abutment selection method, the method comprising the steps of:

[0008] Obtain the patient's oral characteristics information based on the imported digital order model;

[0009] Input the patient's oral feature information into a pre-trained AI selection model, wherein the AI ​​selection model is trained by multiple sets of training data, and each set of training data in the multiple sets of training data includes: oral feature information and identification information for identifying the spatial data of the restoration requirement;

[0010] Obtain the base model selected by the AI ​​selection model, wherein the restoration requirement space data matched by the base model meets the restoration space requirements;

[0011] The base model is matched to the digital order model and reflected in the missing positions of the digital order model in three dimensions.

[0012] Optionally, in the step of obtaining the base model selected by the AI ​​selection model, the step of selecting the base model by the AI ​​selection model specifically includes:

[0013] Obtain the repair demand space data output by the AI ​​selection model;

[0014] Searching the database for a preset base model that matches the spatial data required for restoration;

[0015] The found preset abutment model is output as the abutment model.

[0016] Optionally, in the step of searching a database for a preset base model that matches the required spatial data for restoration:

[0017] Generate a reference oral model based on the spatial data of the restoration requirements;

[0018] Detecting the similarity matching degree between a plurality of preset abutment models in a database within a predetermined range of values ​​and the reference oral cavity model;

[0019] According to the similarity matching degree, the base platform model is determined from a plurality of preset base platform models within a predetermined range of values.

[0020] Optionally, in the step of obtaining the patient's oral characteristic information according to the imported digital order model:

[0021] Importing a first oral cavity model and a second oral cavity model respectively, wherein the first oral cavity model has a gingival contour, and the second oral cavity model has a scanning rod and a substitute body;

[0022] fusing the first oral cavity model and the second oral cavity model to obtain a fused oral cavity model;

[0023] By fusing the oral model, the patient's oral feature information is obtained.

[0024] Optionally, before fusing the first oral cavity model and the second oral cavity model to obtain the fused oral cavity model, the method includes the following steps:

[0025] The site area to be implanted of the fused oral model is segmented, and the site area to be implanted is extracted as the effective position of the oral model.

[0026] Optionally, in the steps of respectively importing the first oral cavity model and the second oral cavity model:

[0027] Model information of the first oral cavity model and the second oral cavity model is collected through the three-dimensional grid.

[0028] Optionally, in the step of inputting the patient's oral feature information into a pre-trained AI selection model:

[0029] During the training of the AI ​​selection model:

[0030] Batch collect the finished abutment design data after the patient's oral scan;

[0031] Export oral surface data STL file through dental design software;

[0032] The oral feature information of the oral surface data STL file and the corresponding restoration requirement space data form a set of training data, wherein the restoration requirement space data is used as identification information;

[0033] The AI ​​selection model is trained using multiple sets of training data.

[0034] Optionally, the training step of the AI ​​selection model further includes:

[0035] The model of the finished base is standardized and fitted with the data of the required spatial data for restoration to form a preset base model and build a database.

[0036] Optionally, the patient's oral characteristic information includes: the patient's oral shape, size, dentition and occlusion information; the restoration required spatial data includes: gingival penetration size, cuff diameter and gingival-jaw distance;

[0037] In the step where the restoration demand space data matched by the base model meets the restoration space requirements:

[0038] For full zirconium abutments, the abutment height should not be less than 5.0mm, the abutment should ensure 4mm of restoration space, and the zirconium surface needs 1mm;

[0039] For all-ceramic abutments or porcelain-fused-to-metal abutments, the abutment height should not be less than 5.5mm. The abutment should ensure 4mm of restoration space and the porcelain surface requires 1.5mm.

[0040] On the other hand, the present application also proposes an artificial intelligence oral abutment selection device, which includes: a processor, a memory, and a communication bus;

[0041] The memory stores a computer-readable program executable by the processor;

[0042] The communication bus realizes the connection and communication between the processor and the memory;

[0043] When the processor executes the computer-readable program, the steps in the artificial intelligence oral abutment selection method as described above are implemented.

[0044] The beneficial effects of an artificial intelligence oral abutment selection method and device provided by the present application are at least as follows: after obtaining the patient's oral feature information and processing it with a pre-trained AI selection model, the abutment model selected by the AI ​​selection model is obtained, so that the restoration demand space data matched by the obtained abutment model meets the restoration space requirements, and the selected abutment model is matched to the digital order model, which is reflected in the missing position of the digital order model in a three-dimensional manner. Thus, the selection process of the oral abutment is optimized by using artificial intelligence technology, which can provide patients with more personalized and higher-quality oral medical services. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0046] Figure 1 A flowchart of the main steps of an artificial intelligence oral abutment selection method provided in an embodiment of the present application;

[0047] Figure 2 A flowchart of the detailed steps of step S100 of an artificial intelligence oral abutment selection method provided in an embodiment of the present application;

[0048] Figure 3 A schematic diagram of the principles of the steps of an artificial intelligence oral abutment selection method provided in an embodiment of the present application;

[0049] Figure 4 A flowchart of the training process of an AI selection model in an artificial intelligence oral abutment selection method provided in an embodiment of the present application;

[0050] Figure 5 A flowchart of the detailed steps of step S300 of an artificial intelligence oral abutment selection method provided in an embodiment of the present application;

[0051] Figure 6 A schematic diagram of the principle of an artificial intelligence oral base selection device provided in an embodiment of the present application.

[0052] Among them, the reference numerals in the figure are:

[0053] 10. Fusion oral model; 11. First oral model; 12. Second oral model; 13. AI selection model; 14. Base model; 20. Processor; 21. Display screen; 22. Memory; 23. Communication interface; 24. Bus. DETAILED DESCRIPTION

[0054] In order to make the technical problems, technical solutions and beneficial effects to be solved by 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.

[0055] It should be noted that when a component is referred to as being "fixed on" or "disposed on" another component, it may be directly or indirectly located on the other component. When a component is referred to as being "connected to" another component, it may be directly or indirectly connected to the other component. The directions or positions indicated by the terms "upper", "lower", "left", "right", "front", "back", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc. are based on the directions or positions shown in the accompanying drawings and are only for the convenience of description and cannot be understood as limitations on the present technical solution. The terms "first" and "second" are only used for the convenience of description and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features. "Multiple" means two or more, unless otherwise clearly and specifically defined.

[0056] Embodiment 1

[0057] like Figure 1 As shown, this embodiment proposes an artificial intelligence oral abutment selection method, which is mainly used to automatically select an oral abutment that matches the missing position (the position of the missing teeth) of the patient during the medical process of dental implantation. The artificial intelligence oral abutment selection method of this embodiment mainly includes the following steps:

[0058] Step S100: Obtain the patient's oral feature information based on the imported digital order model.

[0059] In the specific process, the digital order model is obtained by scanning the patient's mouth or the mouth cavity, and the digital order model contains the jaw model and the scanning rod data. The digital order model is imported into the software, and the patient's oral characteristic information is obtained according to the imported digital order model. The patient's oral characteristic information includes: the patient's oral shape, size, dentition and occlusion information.

[0060] like Figure 1 , Figure 2 The step S100 specifically includes steps S110 to S130. The details are as follows:

[0061] Step S110, importing a first oral cavity model and a second oral cavity model respectively, wherein the first oral cavity model has a gingival contour, and the second oral cavity model has a scanning rod and a substitute.

[0062] like Figure 3As shown, in the specific process, the digital order model is collected through the three-dimensional grid, and the digital order model includes at least the first oral model 11 and the second oral model 12. The first oral model 11 is a transgingival contour oral model, which is mainly a three-dimensional contour of the transgingival contour in the oral dental model. The second oral model 12 is a scanning rod-substitute oral model, which is mainly a three-dimensional contour of the scanning rod and the substitute in the oral dental model.

[0063] The first oral cavity model and the second oral cavity model both use three-dimensional meshes to collect model information. In the specific process of this embodiment, in the process of exporting all three-dimensional information of the order, the first oral cavity model and the second oral cavity model both use mesh information (.stl format) to collect model information. The three-dimensional mesh oral cavity model formed in this way has topological information, making the information retained by the digital model more comprehensive. In addition, point cloud (Point Cloud) can also be used to collect information of the first oral cavity model and the second oral cavity model. Although it is easier, the point cloud data does not retain topological information.

[0064] Step S120: Fuse the first oral cavity model and the second oral cavity model to obtain a fused oral cavity model.

[0065] like Figure 3 As shown, in the specific process, the first oral cavity model 11 and the second oral cavity model 12 can be fused into a fused oral cavity model 10 through a fusion algorithm, so that the fused oral cavity model 10 includes the patient's oral and dental jaw model (three-dimensional contour of the dentition), the three-dimensional contour of the transgingival contour, and the three-dimensional contour of the scanning rod and the substitute. The information contained in the fused oral cavity model is relatively comprehensive.

[0066] Step S125: segment the site area to be implanted in the fused oral model, and extract the site area to be implanted as the effective position of the oral model.

[0067] In the specific process, the three-dimensional contour of the predetermined area where the scanning rod and the replacement body are located at the edentulous position in the fused oral model is the effective position of the oral model, and the effective position includes the site to be implanted, that is, the place that matches the abutment position.

[0068] A segmentation algorithm (such as a point cloud segmentation algorithm) is used to segment the fused oral model, segment the effective position, and extract the effective position. This allows the fused oral model to retain the effective position to improve the accuracy of the algorithm, and avoids interference of other contours in the fused oral model on the effective position, thereby improving the accuracy and quality of the data.

[0069] Step S130: Obtain the patient's oral cavity feature information by fusing the oral cavity model.

[0070] In the specific process, since the fused oral model is processed through the above process, the three-dimensional oral model is optimized, so that the fused oral model matches the patient's real oral cavity. Therefore, according to the three-dimensional information of the fused oral model, the patient's oral characteristic information is read, such as the patient's oral shape, size, dentition and occlusion information.

[0071] Step S200: input the patient's oral feature information into a pre-trained AI selection model, wherein the AI ​​selection model is trained using multiple sets of training data, and each set of training data includes: oral feature information and identification information used to identify the restoration requirement spatial data.

[0072] like Figure 3 As shown, in the specific process, the input digital order model is first effectively preprocessed and feature extracted to ensure that the AI ​​selection model 13 can accurately understand and analyze. Since the AI ​​selection model 13 used is pre-trained, the trained AI selection model 13 can directly output the restoration requirement space data based on the input patient oral feature information. The restoration requirement space data is associated with the oral abutment adapted in the patient's mouth. Therefore, the appropriate oral abutment can be automatically selected based on the restoration requirement space data.

[0073] The spatial data required for restoration are usually: gingival penetration size (referring to the height of the implant and the gums), cuff diameter (the diameter of the epithelial cuff formed by the gingival part of the implant and the gingival part), and gingival-mandibular distance (gingival-mandibular distance is an important oral anatomical parameter, which describes the distance between the maxillary bone and the gingival tissue covering it). The spatial data required for restoration are all spatial requirements to meet the needs of restoration.

[0074] like Figure 4 As shown, before this method, the AI ​​selection model needs to be trained in advance. The specific training process of the AI ​​selection model includes:

[0075] Step S210: Batch collect the finished base design completion data after the patient's oral cavity scan.

[0076] Step S220: Export the oral surface data STL file through dental design software.

[0077] Step S230: The oral feature information of the oral surface data STL file and the corresponding restoration requirement space data are combined to form a set of training data, wherein the restoration requirement space data is used as identification information.

[0078] Step S240: training the AI ​​selection model using multiple sets of training data.

[0079] In the above process, the AI ​​selection model is trained through multiple sets of training data, each set of training data includes oral feature information and restoration requirement space data corresponding to the oral feature information. The restoration requirement space data is used as identification information, and is the final data required for the AI ​​selection model to identify.

[0080] During the training process, the relevant information of the implant is introduced as prior knowledge. Therefore, the identification information in each set of training data, that is, the spatial data of the restoration requirement, needs to be determined. The confirmation process of the standard information is as follows: the spatial data of the restoration requirement in each set of training data is usually measured by using a probe or a gingival perforator. One end of the probe or gingival perforator is against the outer edge of the interface between the substitute and the gingival glue, and the gingival height is observed to be at the scale position. The 3shape software can also be used to import the fusion oral mold (including upper and lower jaws, gingival glue, scanning rod), and cut the cross section to directly measure the gingival height. The cuff diameter is measured with a vernier caliper or other tools to measure the cuff diameter of the missing position and the fusion oral mold imported by the software, cut the cross section, and check the cuff diameter. The gingival-jaw distance is measured by a caliper to restore the space as a standard indicator for selecting the abutment. Through the above process, the spatial data of the restoration requirement is determined in the training data as identification information. Make the results output by the trained AI selection model more accurate and better meet actual needs.

[0081] After the AI ​​selection model is trained, in the subsequent use process, you can directly input oral feature information and use the AI ​​selection model to directly output the required corresponding restoration demand space data. During the data training process, the AI ​​selection model has been trained with about 1,500 training data pairs.

[0082] The currently trained AI selection model can automatically identify the spatial data of restoration requirements required for production after importing oral feature information during the data testing process. The current trained data extraction accuracy rate is 100%.

[0083] Step S250: Perform a standardized fitting process on the model of the finished base station and the data of the required spatial data for repair to form a preset base station model and construct a database.

[0084] In the specific process, the parameters of the repair demand space data and the model of the finished abutment are compared, and the repair demand space data is standardized and fitted to associate the repair demand space data with the parameters of the model of the finished abutment. According to the model of the finished abutment, a corresponding model can be generated, that is, a preset abutment model is formed. The preset abutment model is associated with the repair demand space data to form a database, so that the AI ​​selection model can directly select the preset abutment model that meets the requirements based on the screened repair demand space data. Therefore, through the above steps, a database containing multi-layer finished abutment parameter indicators is constructed, and STL acquisition information is extracted through mesh information for training and optimization, and finally a high-precision and high-feasibility AI selection model algorithm with relevant tissue measurements of the finished implant system is constructed.

[0085] After systematic training, a dictionary file is created in the database. The dictionary file contains all the brands of implant systems under the existing data. Each implant brand contains all its corresponding order numbers. Each order number contains the names of all its sub-files, the root directory of the order number, and the date. Among them, jaw_bool is a 0, 1 variable; 0 represents missing teeth in the mandibular oral cavity, and 1 represents missing teeth in the maxillary oral cavity. In this way, the preset abutment model that meets the needs can be selected more accurately.

[0086] Step S300, obtaining a base model selected by the AI ​​selection model, wherein the repair requirement space data matched by the base model meets the repair space requirements.

[0087] like Figure 3 As shown, in the specific process, after the AI ​​selection model 13 is trained based on the relevant information of the introduced implant as prior knowledge and used as training data, during subsequent use, the patient's oral feature information is directly input into the AI ​​selection model, and the abutment model 14 or abutment model of the implant system with suitable size, size and angle can be automatically screened out.

[0088] When the restoration space requirement data is used as a selection parameter and an oral abutment matching the restoration space requirement data is selected, the selected abutment model 14 meets the restoration space requirement. The standards for the oral abutment to meet the restoration space requirement are as follows:

[0089] For all-zirconium abutments, the abutment height should not be less than 5.0mm, the abutment should ensure 4mm of restoration space, and the zirconium surface needs 1mm. For all-ceramic abutments or porcelain abutments, the abutment height should not be less than 5.5mm, the abutment should ensure 4mm of restoration space, and the porcelain surface needs 1.5mm.

[0090] Therefore, the selected abutment model matches the output restoration requirement space data, and the abutment model meets the restoration space requirements, thereby accurately selecting the abutment model that is compatible with the patient's mouth.

[0091] like Figure 5 As shown, in the above step S300, the process of selecting the base model by the AI ​​selection model specifically includes steps S310-S330, which are as follows:

[0092] Step S310: Obtain the repair requirement space data output by the AI ​​selection model.

[0093] Step S320: Search the database for a preset base model that matches the required spatial data for restoration.

[0094] In the specific process, a reference oral cavity model is generated based on the restoration demand spatial data. The similarity matching degree between multiple preset abutment models in the database within a predetermined range of values ​​and the reference oral cavity model is detected. According to the similarity matching degree, the abutment model is determined from the multiple preset abutment models within the predetermined range of values.

[0095] Step S330: output the found preset base model as the base model.

[0096] In the above steps, the network of the AI ​​selection model is optimized. After the restoration demand space data is selected, the parameters in the restoration demand space data include three parameters: gingival penetration size, cuff diameter, and gingival-jaw distance. The three parameters need to be comprehensively considered to select the corresponding preset abutment model. For example, there may be two parameters that match one preset abutment model, and the other parameter matches another preset abutment model. In this case, multiple preset abutment models may be selected. For the above situation, by generating an oral model, the oral model can directly call the digital order model in step S100 as a reference oral model to measure the similarity distance between the reference oral model and each abutment, that is, to determine the similarity matching degree of multiple preset abutment models within a predetermined range of values ​​with the reference oral model. According to the similarity matching degree, the abutment model is determined among the multiple preset abutment models within the predetermined range of values, so as to select the optimal abutment model in the corresponding implant system.

[0097] Therefore, through the above steps S200-S300, according to the imported digital order model, the AI ​​selection model automatically measures the required spatial data for restoration (gingival penetration size, cuff diameter and gingival-jaw distance), so that the selected oral abutment can meet the space required for restoration. Based on the pre-established database and AI selection model, the required spatial data for restoration is automatically measured, the oral abutment is automatically selected, and the abutment model is accurately selected.

[0098] Step S400: Match the base model to the digital order model, and reflect it in a three-dimensional manner at the missing position of the digital order model.

[0099] In the specific process, the abutment model of the oral abutment selected by the AI ​​selection model is automatically matched to the digital order model, and is reflected in the missing position in a three-dimensional way, making the diagnosis and treatment process more accurate, connected and automated.

[0100] In the above steps S100-S400, the patient's oral feature information is processed by a pre-trained AI selection model, and the abutment model selected by the AI ​​selection model is obtained, so that the restoration demand space data matched by the abutment model meets the restoration space requirements, and the selected abutment model is matched to the digital order model, which is reflected in the missing position of the digital order model in a three-dimensional manner. In this way, the selection process of the oral abutment is optimized by using artificial intelligence technology, which can provide patients with more personalized and higher-quality oral medical services.

[0101] Embodiment 2

[0102] like Figure 6 As shown, this embodiment proposes an artificial intelligence oral abutment selection device, which includes at least one processor (processor) 20, a display screen 21 and a memory (memory) 22, and may also include a communication bus, and the communication bus includes a communication interface (Communications Interface) 23 and a bus 24. The processor 20, the display screen 21, the memory 22 and the communication interface 23 can communicate with each other through the bus 24. The display screen 21 is configured to display a user operation interface and a related three-dimensional software interface. The communication interface 23 can transmit information. The processor 20 can call the logic instructions in the memory 22 to execute the artificial intelligence oral abutment selection method in the above embodiment.

[0103] In addition, the logic instructions in the above-mentioned memory 22 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. The memory 22, as a computer-readable storage medium, can be configured to store software programs, computer executable programs, such as program instructions or modules corresponding to the method in the embodiment of the present disclosure. The processor 20 executes functional applications and data processing by running the software programs, instructions or modules stored in the memory 22, that is, implementing the artificial intelligence oral abutment selection method in the above-mentioned embodiment.

[0104] The memory 22 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and at least one application required for a function; the data storage area may store data created according to the use of the terminal device, etc. In addition, the memory 22 may include a high-speed random access memory and may also include a non-volatile memory. For example, a variety of media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, may also be a transient storage medium.

[0105] In addition, the specific process of loading and executing the plurality of instructions in the storage medium and the processor in the mobile terminal has been described in detail in the method above, and will not be described here one by one.

[0106] In summary, the present application provides an artificial intelligence oral abutment selection method and device, which is based on the data after intraoral scanning, obtains the image and digitizes the intraoral morphology, and artificial intelligence performs digitized measurement and analysis of the missing position to select the abutment method. Using artificial intelligence technology to optimize the oral selection process can provide patients with more personalized and higher-quality oral medical services.

[0107] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the protection scope of the present application.

Claims

1. An artificial intelligence oral abutment selection method, characterized in that: The method comprises the steps of: Obtain the patient's oral characteristics information based on the imported digital order model; Inputting the patient's oral characteristic information into a pre-trained AI selection model, wherein the AI ​​selection model is trained by multiple sets of training data, and each set of training data in the multiple sets of training data includes: oral characteristic information and identification information for identifying restoration requirement space data; Acquire a base model selected by the AI ​​selection model, wherein the repair demand space data matched by the base model meets the repair space requirements; The base model is matched to the digital order model and reflected in the missing position of the digital order model in a three-dimensional manner.

2. The artificial intelligence oral abutment selection method according to claim 1, characterized in that: In the step of obtaining the base model selected by the AI ​​selection model: The steps of selecting the base model by the AI ​​selection model specifically include: Based on the patient's oral characteristic information, output the restoration requirement spatial data; Searching a database for a preset base model that matches the required spatial data for restoration; The found preset base model is output as the base model.

3. The artificial intelligence oral abutment selection method according to claim 2, characterized in that: In the step of searching a database for a preset base model that matches the required spatial data for restoration: Generating a reference oral cavity model based on the restoration requirement spatial data; Detecting the similarity matching degree between a plurality of preset abutment models in a database within a predetermined range of values ​​and the reference oral cavity model; According to the similarity matching degree, a base platform model is determined from a plurality of preset base platform models within a predetermined range of values.

4. The artificial intelligence oral abutment selection method according to claim 3, characterized in that: In the step of obtaining the patient's oral characteristic information based on the imported digital order model: Importing a first oral cavity model and a second oral cavity model respectively, wherein the first oral cavity model has a gingival contour, and the second oral cavity model has a scanning rod and a substitute body; Fusing the first oral cavity model and the second oral cavity model to obtain a fused oral cavity model; The patient's oral cavity feature information is obtained through the fused oral cavity model.

5. The artificial intelligence oral abutment selection method according to claim 4, characterized in that: Before fusing the first oral cavity model and the second oral cavity model to obtain the fused oral cavity model, the steps include: The site area to be implanted of the fused oral model is segmented, and the site area to be implanted is extracted as the effective position of the oral model.

6. The artificial intelligence oral abutment selection method according to claim 4, characterized in that: In the steps of respectively importing the first oral cavity model and the second oral cavity model: Model information of the first oral cavity model and the second oral cavity model is collected through a three-dimensional grid.

7. The artificial intelligence oral abutment selection method according to claim 1, characterized in that: In the step of inputting the patient's oral feature information into the pre-trained AI selection model: During the training of the AI ​​selection model: Batch collect the finished abutment design data after the patient's oral scan; Export oral surface data STL file through dental design software; The oral cavity feature information of the oral cavity surface data STL file and the corresponding restoration requirement space data form a set of training data, wherein the restoration requirement space data is used as identification information; The AI ​​selection model is trained using multiple sets of the training data.

8. The artificial intelligence oral abutment selection method according to claim 7, characterized in that: The training step of the AI ​​selection model further includes: The model of the finished base is standardized and fitted with the data of the repair required spatial data to form a preset base model and build a database.

9. The artificial intelligence oral abutment selection method according to claim 1, characterized in that: The patient's oral characteristic information includes: the patient's oral shape, size, dentition and occlusion information; the restoration required spatial data includes: gingival penetration size, cuff diameter and gingival jaw distance; In the step where the repair demand space data matched by the base model meets the repair space requirement: For full zirconium abutments, the abutment height should not be less than 5.0mm, the abutment should ensure 4mm of restoration space, and the zirconium surface needs 1mm; For all-ceramic abutments or porcelain abutments, the abutment height should not be less than 5.5mm. The abutment should ensure 4mm of restoration space and the porcelain surface requires 1.5mm.

10. An artificial intelligence oral abutment selection device, characterized in that: include: Processor, memory and communication bus; The memory stores a computer-readable program executable by the processor; The communication bus realizes the connection and communication between the processor and the memory; When the processor executes the computer-readable program, the steps in the artificial intelligence oral abutment selection method as described in any one of claims 1-9 are implemented.

Images