A remote management system based on oral scan data

Abstract

The application relates to the technical field of oral cavity medical treatment, in particular to a remote management system based on oral cavity scanning data, which comprises the following: a data acquisition module is used for acquiring three-dimensional scanning data of teeth, gums and jaw bones in an oral cavity; an intelligent chip processing unit is used for real-time processing of the scanning data, three-dimensional reconstruction, pathological feature recognition and generation of a preliminary diagnosis prompt; an AI diagnosis platform is used for deep analysis of the data through an AI diagnosis model according to the preliminary diagnosis prompt, generation of a detailed diagnosis report and treatment scheme suggestion; a doctor-patient interaction module is used for doctor's checking of the diagnosis report, adjustment of the treatment scheme, patient's inquiry of the diagnosis and treatment progress and submission of questions; a dynamic follow-up unit is used for automatic generation of follow-up reminders based on the scanning data change trend, feedback of the follow-up data to a cloud platform to update a patient diagnosis and treatment archive, and periodical encryption of the scanning data and diagnosis and treatment records. Therefore, the problems of low remote cooperation precision and patient management fragmentation in the prior art are solved.

Description

Technical Field

[0001] This invention relates to the field of oral medical technology, specifically to a remote management system based on oral scanning data. Background Technology

[0002] The remote oral scanning data management system is a core facility supporting the digital transformation of oral healthcare and enabling cross-regional collaborative diagnosis and treatment. It relies on high-precision three-dimensional dental and jaw data generated by technologies such as intraoral laser scanning and CBCT to provide crucial decision-making support for caries diagnosis, orthodontic treatment planning, implant planning, and postoperative follow-up. However, in long-term clinical application, factors such as the massive volume of scanned data (500-1000MB for a single case of three-dimensional dental and jaw data), inconsistent data standards across institutions, and the geographically dispersed nature of doctors and patients have led to problems such as data transmission delays, diagnostic information asymmetry, and inconsistent follow-up tracking. These issues result in low efficiency of remote diagnosis and treatment, and even errors in treatment plans due to data deviations, affecting patient treatment outcomes and medical safety. As oral healthcare develops towards intelligence, remoteness, and personalization, higher demands are placed on the management of scan data in terms of real-time performance (rapid processing and transmission), accuracy (remote diagnostic matching), continuity (full-cycle follow-up), and security (data privacy protection). There is an urgent need for a remote management system that can realize real-time collaboration of scan data, accurate remote diagnosis, and dynamic management throughout the entire cycle, so as to ensure the efficient and orderly conduct of oral healthcare services in diverse scenarios (such as collaboration with primary healthcare institutions and follow-up of patients in different locations).

[0003] However, traditional oral scanning data management models have inherent flaws: Data processing mechanisms are lagging; raw scan data must be completely transmitted to the cloud or local server before noise reduction and reconstruction can be performed, and the massive data volume causes transmission times exceeding 5 minutes, delaying the diagnostic cycle. Remote collaboration faces significant barriers; doctors mostly share data via email and USB drives, making it impossible to annotate pathological features (such as caries location and occlusal interference points) on 3D dental models in real time. Information transmission deviation rates exceed 15% during cross-institutional consultations, making it difficult to ensure consistency in diagnosis and treatment. Patient management is rudimentary; follow-up plans rely on manual records and telephone reminders, failing to dynamically adjust follow-up frequency based on changes in multi-time-point scan data (such as orthodontic tooth movement and caries progression), resulting in a missed diagnosis rate exceeding 20%. Furthermore, there is a conflict between medical data security and processing efficiency; while traditional encryption methods (such as AES-256) can protect privacy, they further reduce data transmission and analysis speed. Moreover, scanning terminals only have data acquisition functions and lack real-time preprocessing capabilities, failing to immediately identify blind spots (such as missing gingival sulcus details), requiring repeated scanning more than 30%. The overall technology faces multiple challenges, including low data processing efficiency, low accuracy of remote collaboration, fragmented patient management, and an imbalance between safety and efficiency, making it difficult to meet the current needs of digital transformation in oral healthcare. Summary of the Invention

[0004] This application provides a remote management system based on oral scan data to solve problems such as low accuracy of remote collaboration and fragmented patient management in existing technologies.

[0005] The first aspect of this application provides a remote management system based on oral scan data, comprising: a data acquisition module, an intelligent chip processing unit, an AI diagnostic platform, a doctor-patient interaction module, and a dynamic follow-up unit; wherein, the data acquisition module is used to acquire three-dimensional scan data of teeth, gums, and jawbone in the oral cavity; the intelligent chip processing unit is used to process the scan data in real time, perform three-dimensional reconstruction and pathological feature recognition, and generate preliminary diagnostic prompts; the AI ​​diagnostic platform is used to perform in-depth analysis of the data through an AI diagnostic model based on the preliminary diagnostic prompts, and generate detailed diagnostic reports and treatment plan suggestions; the doctor-patient interaction module is used for doctors to view diagnostic reports and adjust treatment plans, and for patients to check treatment progress and submit questions; the dynamic follow-up unit is used to automatically generate follow-up reminders based on the trend of scan data changes, and feed the follow-up data back to the cloud platform to update the patient's medical records, while periodically encrypting the scan data and medical records.

[0006] Preferably, the data acquisition module includes a three-dimensional scanning unit and a data transmission unit. The three-dimensional scanning unit is used to acquire three-dimensional scanning data of tooth morphology, gingival contour and jawbone structure in the oral cavity. The data transmission unit is used to transmit the acquired three-dimensional scanning data to the intelligent chip processing unit in real time to ensure the stability of data transmission.

[0007] Preferably, the intelligent chip processing unit includes a three-dimensional reconstruction unit and a pathological feature recognition unit. The three-dimensional reconstruction unit is used to process the scanned data in real time to construct a three-dimensional model of the teeth, gums and jawbone in the oral cavity. The pathological feature recognition unit is used to identify pathological features such as dental caries and gingival inflammation in the three-dimensional model and generate a preliminary diagnostic prompt with suspected lesion annotations.

[0008] Preferably, the AI ​​diagnostic platform includes a data receiving unit and a diagnostic analysis and generation unit. The data receiving unit is used to receive preliminary diagnostic prompts and associated scan data generated by the intelligent chip processing unit. The diagnostic analysis and generation unit is used to call the AI ​​diagnostic model to perform in-depth analysis of the data and generate a detailed diagnostic report including lesion type and severity, as well as treatment plan suggestions adapted to the patient's condition.

[0009] Preferably, the doctor-patient interaction module includes a doctor-side interaction unit and a patient-side interaction unit. The doctor-side interaction unit is used by doctors to log in to the system to view detailed diagnostic reports, adjust treatment plans according to clinical needs, and save modification records. The patient-side interaction unit is used by patients to query their personal treatment progress and diagnostic reports, and submit treatment-related questions to doctors.

[0010] Preferably, the dynamic follow-up unit includes a follow-up reminder generation unit and a data feedback update unit. The follow-up reminder generation unit is used to automatically generate follow-up time reminders and push them to both the doctor and the patient based on the changing trends of scan data at different treatment stages. The data feedback update unit is used to receive new scan data and medical records collected during follow-up, feed them back to the cloud platform to update the patient's medical records, and periodically encrypt the scan data and medical records.

[0011] The second aspect of this application provides a remote management method based on oral cavity scan data, comprising: acquiring three-dimensional scan data of teeth, gingiva, and jawbone within the oral cavity; performing real-time analysis and processing of the three-dimensional scan data of teeth, gingiva, and jawbone within the oral cavity, performing three-dimensional reconstruction and pathological feature identification, and generating preliminary diagnostic prompts; based on the preliminary diagnostic prompts, performing in-depth analysis of the data through an AI diagnostic model to generate detailed diagnostic reports and treatment plan suggestions, enabling doctors to view diagnostic reports and adjust treatment plans, while patients can check treatment progress and submit questions; based on the detailed diagnostic reports and treatment plan suggestions, combined with the trend of scan data changes, automatically generating follow-up reminders, and feeding follow-up data back to the cloud platform to update patient medical records, while periodically encrypting the scan data and medical records.

[0012] A third aspect of this application provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor. The processor executes the program to implement a remote management method based on oral scan data as described in the above embodiments.

[0013] A fourth aspect of this application provides a computer-readable storage medium having a computer program stored thereon, which is executed by a processor to implement a remote management method based on oral scan data as described in the above embodiments.

[0014] A fifth aspect of this application provides a computer program product, including a computer program or instructions, for implementing a remote management method based on oral scan data as described in the above embodiments.

[0015] Therefore, this application has the following beneficial effects: This application's embodiments accurately acquire three-dimensional oral cavity data through a data acquisition module. Combined with real-time reconstruction and pathological identification by an intelligent chip processing unit, preliminary diagnostic prompts are quickly generated, significantly shortening the pre-diagnosis time. The AI ​​diagnostic platform's deep analysis outputs precise lesion information and suitable treatment plans, reducing human diagnostic bias and improving the professionalism of diagnosis and treatment. The doctor-patient interaction module breaks down communication barriers, allowing doctors to efficiently adjust treatment plans and patients to monitor treatment progress in real time, optimizing the collaborative experience for both parties. The dynamic follow-up unit ensures the continuity of treatment tracking through automatic reminders, while relying on a periodic encryption mechanism to protect the security of scan data and treatment records, comprehensively improving the efficiency, accuracy, interactivity, and data security of oral diagnosis and treatment. Thus, it solves the problems of low accuracy in remote collaboration and fragmented patient management in existing technologies.

[0016] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0017] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein: Figure 1 This is a schematic diagram of the structure of a remote management system based on oral scanning data according to an embodiment of this application; Figure 2 This is a schematic diagram of a remote management system based on oral scan data provided according to an embodiment of this application; Figure 3 This is a flowchart illustrating a remote management method based on oral scan data according to an embodiment of this application; Figure 4 This is a schematic diagram of a remote management method based on oral scan data according to an embodiment of this application; Figure 5 This is a schematic diagram of the structure of an electronic device provided according to an embodiment of this application. Detailed Implementation

[0018] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0019] The following description, with reference to the accompanying drawings, illustrates a remote management system based on oral scan data, according to an embodiment of this application. Addressing the issue of low response speed mentioned in the background section, this application provides a remote management system based on oral scan data. In this system, a data acquisition module accurately acquires three-dimensional oral data, and combined with real-time reconstruction and pathological identification by an intelligent chip processing unit, quickly generates preliminary diagnostic prompts, significantly shortening the pre-diagnosis time. The deep analysis of the AI ​​diagnostic platform outputs accurate lesion information and suitable treatment plans, reducing human diagnostic bias and improving the professionalism of diagnosis and treatment. The doctor-patient interaction module breaks down communication barriers, allowing doctors to efficiently adjust treatment plans and patients to monitor treatment progress in real time, optimizing the collaborative experience for both parties. The dynamic follow-up unit ensures the continuity of treatment tracking through automatic reminders, while relying on a periodic encryption mechanism to protect the security of scan data and treatment records, comprehensively improving the efficiency, accuracy, interactivity, and data security of oral diagnosis and treatment. Thus, it solves the problems of low accuracy in remote collaboration and fragmented patient management in existing technologies.

[0020] Figure 1 This is a schematic diagram of the structure of a remote management system based on oral scan data, provided in an embodiment of this application.

[0021] This application provides a remote management system based on oral scan data. The system 10 includes: Data acquisition module 100, intelligent chip processing unit 200, AI diagnostic platform 300, doctor-patient interaction module 400, dynamic follow-up unit 500.

[0022] The system includes a data acquisition module 100 for collecting three-dimensional scan data of teeth, gums, and jawbone within the oral cavity; an intelligent chip processing unit 200 for processing the scan data in real time, performing three-dimensional reconstruction and pathological feature recognition, and generating preliminary diagnostic prompts; an AI diagnostic platform 300 for conducting in-depth analysis of the data based on the preliminary diagnostic prompts using an AI diagnostic model, generating detailed diagnostic reports and treatment plan suggestions; a doctor-patient interaction module 400 for doctors to view diagnostic reports and adjust treatment plans, and for patients to check treatment progress and submit questions; and a dynamic follow-up unit 500 for automatically generating follow-up reminders based on the changing trends of scan data, feeding follow-up data back to the cloud platform to update patient medical records, and periodically encrypting scan data and medical records.

[0023] Understandably, in this embodiment, the data acquisition module accurately acquires three-dimensional oral cavity data, and combined with the real-time reconstruction and pathological identification of the intelligent chip processing unit, it quickly generates preliminary diagnostic prompts, significantly shortening the pre-diagnosis time. The deep analysis of the AI ​​diagnostic platform can output accurate lesion information and suitable treatment plans, reducing human diagnostic bias and improving the professionalism of diagnosis and treatment. The doctor-patient interaction module breaks down communication barriers, allowing doctors to efficiently adjust treatment plans and patients to keep track of treatment progress in real time, optimizing the collaborative experience for both parties. The dynamic follow-up unit ensures the continuity of treatment tracking through automatic reminders, while relying on a periodic encryption mechanism to protect the security of scan data and treatment records, comprehensively improving the efficiency, accuracy, interactivity, and data security of oral diagnosis and treatment. Thus, it solves the problems of low accuracy in remote collaboration and fragmented patient management in existing technologies.

[0024] In this embodiment, the data acquisition module 100 includes a three-dimensional scanning unit and a data transmission unit.

[0025] The three-dimensional scanning unit is used to collect three-dimensional scanning data of tooth morphology, gingival contour and jaw structure in the oral cavity; the data transmission unit is used to transmit the collected three-dimensional scanning data to the intelligent chip processing unit in real time to ensure the stability of data transmission.

[0026] It is understood that the three-dimensional scanning unit in this application embodiment accurately collects three-dimensional scanning data of tooth morphology, gingival contour and jaw structure in the oral cavity, providing comprehensive and detailed original information support for subsequent three-dimensional reconstruction, pathological identification and diagnostic analysis, ensuring the integrity and accuracy of the diagnostic basis; the data transmission unit transmits the scanned data to the intelligent chip processing unit in real time and stably, ensuring the timeliness and continuity of data flow, avoiding the impact of transmission delay or interruption on subsequent processing, and laying a solid foundation for data acquisition and transmission for the efficient operation of the system.

[0027] In this embodiment, the smart chip processing unit 200 includes: a three-dimensional reconstruction unit and a pathological feature recognition unit.

[0028] The three-dimensional reconstruction unit is used to process the scanned data in real time and construct a three-dimensional model of the teeth, gums and jawbone in the oral cavity; the pathological feature recognition unit is used to identify pathological features such as dental caries and gingival inflammation in the three-dimensional model and generate preliminary diagnostic suggestions with suspected lesion annotations.

[0029] It is understood that the three-dimensional reconstruction unit in this application constructs a three-dimensional model of teeth, gums, and jawbone in the oral cavity through real-time processing of scan data, transforming the original scan data into an intuitive and recognizable three-dimensional structure, providing a concrete basis for subsequent pathological analysis, and the real-time processing characteristics ensure the efficiency of the process; the pathological feature recognition unit accurately identifies pathological features such as dental caries and gingival inflammation in the three-dimensional model and generates preliminary diagnostic prompts with suspected lesion annotations, which not only realizes the rapid location of pathological features and reduces the omissions and delays of manual recognition, but also provides targeted references for the in-depth analysis of the AI ​​diagnostic platform and the clinical judgment of doctors, effectively improving the accuracy and efficiency of the pre-diagnosis stage.

[0030] For example, taking a patient's oral examination scenario as an example, after receiving discrete scanning data such as tooth fissure texture, gingival margin undulation, and jawbone bone distribution transmitted by the data acquisition module, the 3D reconstruction unit first removes interference points caused by saliva reflection and scanning blind spots through noise reduction processing. Then, it uses algorithms to fill in data gaps such as interproximal caries gaps and gingival redness and swelling tomography, and finally integrates them to generate a high-fidelity 3D oral model. This model can clearly present the height of tooth cusps, the attachment relationship between the gingiva and the tooth surface, and even the location of impacted teeth in the jawbone and their distance from nerves. It not only provides a precise "carrier" for the subsequent pathological feature recognition unit to locate early caries and gingival inflammation, but also makes it convenient for doctors to intuitively explain the condition to patients by rotating and sectioning the model. At the same time, it provides millimeter-level precision support for treatment design such as veneer restoration morphology simulation and orthodontic bracket positioning planning.

[0031] In this embodiment, the AI ​​diagnostic platform 300 includes: a data receiving unit and a diagnostic analysis generation unit.

[0032] The data receiving unit receives preliminary diagnostic prompts and associated scan data generated by the intelligent chip processing unit; the diagnostic analysis generation unit calls the AI ​​diagnostic model to perform in-depth analysis of the data, generating a detailed diagnostic report including lesion type and severity, as well as treatment plan suggestions adapted to the patient's condition.

[0033] It is understood that the data receiving unit in this embodiment of the application receives preliminary diagnostic prompts and associated scan data from the intelligent chip processing unit, providing a complete and coherent information foundation for in-depth analysis and ensuring the comprehensiveness of the diagnostic basis. The diagnostic analysis generation unit calls the AI ​​diagnostic model to perform in-depth analysis of the data, which can accurately determine the type of lesion (such as the degree of dental caries and the grade of gingivitis) and its severity, generate a detailed diagnostic report, and output personalized treatment plan suggestions that are suitable based on the patient's oral structure characteristics and pathological manifestations. This not only makes up for the subjectivity and limitations of manual analysis by leveraging the deep learning capabilities of AI, improving the accuracy and standardization of diagnosis, but also provides professional reference for doctors, shortens the diagnosis cycle, and allows patients to receive more targeted diagnosis and treatment guidance.

[0034] For example, taking a patient with symptoms of tooth sensitivity and gingival bleeding as an example, when the smart chip processing unit transmits a preliminary prompt containing the annotation "suspected pit and fissure caries of the lower left second molar, redness and swelling of the lower anterior gingiva" and corresponding 3D model data, the diagnostic analysis generation unit immediately calls the well-trained AI diagnostic model. The model first compares the density changes and margin irregularities of the pits and fissures in the 3D model, and combines them with the historical case database to determine that the caries is superficial caries (only affecting the enamel surface); then it analyzes the extent of redness and swelling of the lower anterior gingiva, simulated bleeding on probing data, and, combined with the patient's age (35 years old) and previous cleaning records, classifies the gingivitis as moderate (with mild subgingival calculus). The final detailed report not only clearly marks the location, pathological type, and severity of the lesions, but also recommends topical fluoride application and regular follow-up for superficial caries, and ultrasonic scaling and daily Bass brushing guidance for moderate gingivitis. It also includes a personalized note such as "Because the patient's enamel is thin, avoid using high-concentration whitening products." This provides doctors with data-driven treatment directions and allows patients to clearly understand their condition and coping strategies.

[0035] In this embodiment, the doctor-patient interaction module 400 includes: a doctor-side interaction unit and a patient-side interaction unit.

[0036] The doctor-side interaction unit is used by doctors to log in to the system to view detailed diagnostic reports, adjust treatment plans according to clinical needs, and save modification records; the patient-side interaction unit is used by patients to check their personal treatment progress and diagnostic reports, and submit treatment-related questions to doctors.

[0037] Understandably, this embodiment allows doctors to directly view detailed diagnostic reports generated by AI after logging in via a doctor-side interaction unit. Doctors can then adjust treatment plans based on their clinical experience (e.g., changing the AI-suggested "follow-up in two weeks" to "three weeks later" depending on the patient's travel schedule). Modification records are saved in real time, ensuring both personalization and traceability of the plan while reducing the cumbersome nature of paper records. The patient-side interaction unit allows patients to check their treatment progress at any time (e.g., "AI diagnosis completed, awaiting doctor's confirmation"), view diagnostic reports (including lesion locations marked in a 3D model), and submit questions online (e.g., "How long after treatment can I eat normally?"), eliminating the need for repeated offline visits. This module provides doctors with flexibility in adjusting treatment plans while empowering patients with control over their treatment, effectively breaking down information barriers and improving doctor-patient communication efficiency and treatment cooperation.

[0038] For example, three days after completing his oral scan, Mr. Wang logged into the patient-facing interactive unit of the system via his mobile phone. He first saw a clear notification in the "Treatment Progress" section: "The AI ​​diagnostic report has been generated. Attending physician Dr. Li is expected to confirm the treatment plan before 3:00 PM today." Clicking on the "Diagnostic Report," he could visually view the highlighted "superficial caries of the upper right first molar" on the 3D model, along with text descriptions to understand the extent of the lesion. Remembering his question about whether anesthesia was needed during treatment, he entered his question in the "Online Consultation" section and uploaded a screenshot of the model. Half an hour later, he received a reply from Dr. Li: "Superficial caries treatment does not require anesthesia. The process takes approximately 10 minutes. We have attached a treatment video of a similar case for your reference." This process allowed Mr. Wang to stay informed about his treatment progress without repeated phone calls, and his questions were quickly and professionally answered, significantly reducing the anxiety caused by information asymmetry.

[0039] In this embodiment, the dynamic follow-up unit 500 includes: a follow-up reminder generation unit and a data feedback update unit.

[0040] The follow-up reminder generation unit is used to automatically generate follow-up time reminders based on the changing trends of scan data at different treatment stages and push them to both doctors and patients; the data feedback update unit is used to receive new scan data and medical records collected during follow-up visits, feed them back to the cloud platform to update the patient's medical records, and periodically encrypt the scan data and medical records.

[0041] Understandably, the follow-up reminder generation unit in this application embodiment automatically generates appropriate follow-up time reminders (such as "review of filling integrity 3 months post-surgery") based on the changing trends of the patient's scan data at different treatment stages (e.g., restoration margin fit data 1 month after caries filling, and gingival recession improvement data 2 months after periodontal treatment). These reminders are simultaneously pushed to both the doctor and patient, avoiding missed reviews due to manual recording and ensuring the continuity and timeliness of treatment tracking. The data feedback update unit receives newly collected scan data (e.g., a 3D model of the teeth during the follow-up) and treatment records (e.g., adjusted medication regimens) during follow-ups, and updates the patient's file in real time on the cloud platform. This allows doctors to directly compare changes in the patient's condition before and after treatment (e.g., checking if the area of ​​gingival redness and swelling has decreased). Simultaneously, a periodic encryption mechanism protects the scan data and treatment records, preventing privacy leaks. This ensures both the dynamism and accuracy of treatment management and provides reliable protection for patient data security, improving the quality of remote medical care.

[0042] For example, taking Ms. Zhang, a patient who had undergone dental filling, as an example, during her 3-month follow-up, when medical staff collected new 3D scan data of her oral cavity through the system (focusing on recording the fit of the filling margin and the density of surrounding tooth tissue), and entered the treatment record stating "no loosening of the filling, no secondary caries on the proximal surfaces, and no bleeding on gingival probing," the data feedback update unit immediately started working. It first integrated this new data with the treatment record, uploaded it to the cloud platform in real time, and automatically overwrote the old data in Ms. Zhang's original file for "1-month follow-up examination." This allowed doctors to directly compare the 3D models of the three stages—"preoperative caries—immediate postoperative filling—3-month postoperative recovery"—through the system, clearly assessing the treatment effect. Simultaneously, the unit encrypted the newly collected scan data and treatment records according to a preset cycle to prevent the leakage of patient privacy information. The entire process not only achieved dynamic updates to the patient's treatment record, providing a basis for subsequent follow-up planning, but also ensured data security, allowing both doctors and patients to confidently trace the entire treatment process.

[0043] This application proposes a remote management system based on oral scan data. Through a data acquisition module, it accurately acquires three-dimensional oral data. Combined with real-time reconstruction and pathological identification by an intelligent chip processing unit, it quickly generates preliminary diagnostic prompts, significantly shortening the pre-diagnosis time. The AI ​​diagnostic platform's deep analysis outputs accurate lesion information and suitable treatment plans, reducing human diagnostic bias and improving the professionalism of diagnosis and treatment. The doctor-patient interaction module breaks down communication barriers, allowing doctors to efficiently adjust treatment plans and patients to monitor treatment progress in real time, optimizing the collaborative experience for both parties. The dynamic follow-up unit ensures continuous treatment tracking through automatic reminders, while relying on a periodic encryption mechanism to protect the security of scan data and treatment records, comprehensively improving the efficiency, accuracy, interactivity, and data security of oral diagnosis and treatment. Thus, it solves the problems of low accuracy in remote collaboration and fragmented patient management in existing technologies.

[0044] The following will illustrate a remote management system based on oral cavity scan data through a specific embodiment, such as... Figure 2 As shown, it includes: Using the remote diagnosis and treatment service system of a chain dental clinic as an application scenario, a remote management system based on oral scanning data was built to realize a closed-loop service from data collection to follow-up management. The system has completed clinical pilot verification and can be stably adapted to medical institutions at all levels and home diagnosis and treatment scenarios. The core architecture of the system adopts a layered design of "terminal acquisition - edge processing - cloud analysis - interactive follow-up". The modules achieve data interconnection through industrial-grade Ethernet and 5G private network, and the overall response latency is controlled within 500ms to meet the needs of real-time diagnosis and treatment. The data acquisition module uses an FDA-certified portable oral 3D scanner. This device is equipped with 16 high-resolution industrial cameras and near-infrared imaging components. The scanning range can cover the entire area of ​​the oral cavity from incisors to molars, with a scanning accuracy of 0.01mm. It can clearly capture detailed data such as tooth fissures, gingival margin morphology, and jawbone occlusal surface texture. The device's built-in data transmission unit adopts a "5G+WiFi6" dual-mode transmission solution. In medical institutions, it connects directly to the local server via WiFi6, while in home medical scenarios, it accesses the cloud via a 5G network. During transmission, the UDP protocol is used to ensure real-time performance, and a data fragmentation verification mechanism is used to ensure the integrity of the 3D scan data and avoid model distortion caused by packet loss during transmission.

[0045] The intelligent chip processing unit adopts an embedded hardware design, integrating the NVIDIA Jetson AGX Orin intelligent chip. This chip has a computing power of 200 TOPS, which can meet the computing power requirements for real-time 3D reconstruction and pathological feature recognition. The 3D reconstruction unit is equipped with an optimized engine based on the MarchingCubes algorithm, performing real-time surface rendering processing on the scanned data. It can generate a complete 3D oral cavity model within 30 seconds of data acquisition, including the spatial relationships and surface texture information of teeth, gums, and jawbone, supporting 10x zoom for distortion-free viewing. The pathological feature recognition unit uses a lightweight CNN model, trained and optimized through transfer learning on a dataset of 500,000 oral pathology cases, and can automatically identify eight common oral problems such as dental caries, gingivitis, and alveolar bone resorption. In dental caries identification, the system can distinguish between normal tooth tissue (grayscale value 180-220) and decayed tissue (grayscale value 80-150) through grayscale value analysis, and mark the extent and depth of decay. In gingival inflammation identification, the system uses color feature extraction (RGB values ​​of inflamed gingiva are 220-240, 100-130, 100-130) combined with edge detection algorithms to identify red and swollen areas and generate an inflammation severity score (1-5 levels). Finally, this information is integrated into a preliminary diagnostic prompt, including the coordinates, type, and confidence level of suspected lesions (accurate to over 95%).

[0046] The AI ​​diagnostic platform is deployed on an Alibaba Cloud Elastic Compute Service (ECS) cluster, employing an "edge-cloud" collaborative computing model. Preliminary diagnostic prompts processed by the edge's intelligent chip, along with compressed scan data (compression ratio 10:1, retaining key pathological information), are synchronized to the cloud. The data receiving unit utilizes a load-balanced design, supporting data transmission from over 1000 scanning devices simultaneously. Abnormal data (such as blurred scan data caused by oral saliva interference) is removed through a data verification interface, and a rescan command is automatically triggered. The diagnostic analysis and generation unit is equipped with an AI diagnostic model based on the Transformer architecture. This model integrates an oral anatomy knowledge base and clinical treatment guidelines, generating detailed diagnostic reports through multimodal data fusion analysis (3D model data + pathological feature data + patient's historical medical records). The report includes core information such as the specific location of the lesion (accurate to the tooth position number and surface area), pathological type (e.g., superficial caries, moderate caries, chronic gingivitis, etc.), severity classification, and differential diagnosis basis. Treatment recommendations are tailored to the patient's age, oral condition, and treatment expectations, providing personalized options. For example, for patients with proximal caries, both composite resin fillings and inlay restorations are offered, along with the treatment cycle, cost range, and prognostic data for each option.

[0047] The doctor-patient interaction module adopts a multi-terminal adaptation design of "Web + Mobile APP" to achieve efficient two-way communication between doctors and patients. The doctor's web interface integrates three core functions: viewing diagnostic reports, model annotation, and treatment plan editing. After logging into the system, doctors can observe lesions from multiple angles through operations such as rotating and cutting sections of the 3D model, mark key areas using built-in annotation tools (such as circle selection and arrow indicators), and directly adjust treatment plans within the system. Adjustment records are automatically generated into version logs, supporting retrospective viewing. For complex cases, the system supports online consultations by multiple doctors, sharing 3D models and diagnostic data in real time, and forming consensus solutions through collaborative annotation functions. The patient's APP adopts a minimalist design, with the homepage intuitively displaying the treatment progress (such as "Data collection completed - Preliminary diagnosis in progress - Treatment plan completed" status). Patients can view anonymized diagnostic reports (annotated version with professional terminology removed) and treatment plan summaries, and upload text, images, or short videos for consultation through the "Question Submission" function. Doctors respond within 24 hours. The system also has a built-in intelligent Q&A robot that can automatically answer common questions such as "Post-treatment precautions" and "Follow-up schedule," improving communication efficiency.

[0048] The dynamic follow-up unit constructs a full-cycle treatment management system to ensure continuous tracking and assurance of treatment effectiveness. The follow-up reminder generation unit automatically sets follow-up nodes based on the treatment plan, such as 1 week, 1 month, and 3 months after a cavity filling as routine follow-up times. The system sends reminders to both the doctor and patient via APP push, SMS, and telephone. The reminders include the purpose of the follow-up (e.g., checking the integrity of the filling and the recovery of the gums) and the required materials (e.g., recent oral photos and dietary information). Follow-up data collection can be performed in two modes: during follow-ups at medical institutions, new data is collected using the same scanning device; during home follow-ups, patients can use a simple oral scanner (compatible with the system) to collect data from key areas themselves. The data feedback and update unit compares and analyzes newly collected scan data with historical data, generating a trend report (e.g., whether the decay area has expanded or whether gingival inflammation has subsided), and automatically updates the patient's cloud-based treatment record. The record uses hierarchical access control, with only authorized doctors able to view the complete data. In terms of data security, the system uses the AES-256 encryption algorithm to encrypt and store scan data and medical records, automatically updating the encryption key every 7 days. It also records all data access and modification activities through operation logs, meeting medical data security compliance requirements. In pilot applications, the system improved remote diagnosis and treatment efficiency by 40% and patient follow-up compliance by 65%.

[0049] In summary, this application's embodiments ensure complete and real-time data acquisition through high-precision portable scanning combined with dual-mode transmission. The efficient processing of the intelligent chip and AI model enables 3D modeling to be completed within 30 seconds with a pathological identification confidence level exceeding 95%, generating personalized diagnostic reports and treatment plans that better meet patient needs. The "Web + Mobile" interaction mode, coupled with multi-doctor consultations and intelligent Q&A functions, significantly improves the efficiency of doctor-patient communication and the accuracy of treatment plans. Full-cycle dynamic follow-up and AES-256 encryption mechanisms not only track treatment effects and improve patient compliance through follow-up data comparison but also ensure data security and compliance. Pilot applications show that the system increases remote diagnosis and treatment efficiency by 40% and patient follow-up compliance by 65%, making it suitable for medical institutions at all levels and home settings, possessing broad clinical application value.

[0050] Next, referring to the accompanying drawings, a remote management method based on oral scanning data is described according to an embodiment of this application.

[0051] like Figure 3 As shown, this remote management method based on oral cavity scan data includes the following steps: In step S101, three-dimensional scan data of teeth, gums and jawbone in the oral cavity are acquired.

[0052] It is understood that the embodiments of this application can clearly capture details such as tooth fissures, gingival margin morphology, and jawbone structure relationships through high-precision scanning equipment, providing data basis for accurate identification of pathological features; the full-area coverage design avoids missing key areas and ensures comprehensive diagnosis and treatment; the acquired three-dimensional scanning data can support real-time three-dimensional reconstruction to generate accurate models, laying the foundation for AI deep analysis and doctors' multi-dimensional observation of lesions; at the same time, it is compatible with multiple scenarios such as institutions and homes for data collection and stable transmission, improving the accessibility of diagnosis and treatment, and the data integrity is ensured through a data verification mechanism to avoid distortion in subsequent modeling or diagnosis.

[0053] In step S102, the three-dimensional scan data of teeth, gums and jawbone in the oral cavity are analyzed and processed in real time, and three-dimensional reconstruction and pathological feature identification are performed to generate preliminary diagnostic suggestions.

[0054] It is understood that the embodiments of this application transform raw scan data into structured information with diagnostic and treatment reference value, and rely on high-performance computing chips to quickly reconstruct high-precision three-dimensional oral models, clearly presenting the spatial relationships and texture details of teeth, gums, and jawbones, providing an intuitive and visual foundation for subsequent diagnosis and treatment; through trained and optimized CNN models, common oral problems are accurately identified, and the extent, degree, and confidence of lesions are marked by quantitative analysis of grayscale values, color features, etc., reducing the risk of missed diagnosis and misdiagnosis; the generated preliminary diagnostic prompts provide targeted data support for in-depth analysis by the AI ​​diagnostic platform, reducing cloud computing power consumption, while providing doctors with preliminary references for subsequent diagnosis and treatment, shortening the treatment plan development cycle, ensuring timely doctor-patient interaction, and improving the diagnosis and treatment experience and efficiency.

[0055] In step S103, based on the preliminary diagnostic prompts, the AI ​​diagnostic model performs in-depth analysis of the data to generate a detailed diagnostic report and treatment plan suggestions, allowing doctors to view the diagnostic report and adjust the treatment plan. At the same time, patients can check the treatment progress and submit questions.

[0056] Among them, AI diagnostic models refer to artificial intelligence models that use machine learning or deep learning algorithms to perform in-depth analysis of oral three-dimensional scan data and preliminary diagnostic prompts, identify pathological features, and generate detailed diagnostic reports and personalized treatment plan suggestions.

[0057] It is understood that the embodiments of this application utilize AI diagnostic models to transform preliminary diagnostic prompts and associated oral 3D scan data into structured diagnostic and treatment information with clinical guidance significance. Relying on the deep mining capabilities of deep learning algorithms, pathological features can be accurately identified and detailed diagnostic reports containing core content such as lesion type, severity, and differential diagnosis criteria can be generated. At the same time, personalized treatment plan suggestions are output based on the individual patient's situation, providing doctors with accurate references for reviewing reports and making targeted adjustments to treatment plans, effectively shortening the plan development cycle. The standardized diagnostic and treatment information generated also provides patients with a reliable basis for clearly checking treatment progress and clarifying the direction of questions, significantly improving the efficiency of doctor-patient collaboration and reducing diagnostic and treatment deviations caused by information asymmetry.

[0058] For example, in the common clinical scenario of treating proximal caries, after a patient completes data collection using a 0.01mm precision scanner, the AI ​​diagnostic model can identify 0.1mm-level occult caries on the proximal surface within 5 seconds, marking the extent of the caries and the number of dentin layers involved, and generating a report with options for "composite resin filling" and "inlay restoration," along with the cost, treatment time, and prognosis data for each option. After the dentist verifies the data using the 3D model, they can adjust the filling material type. The patient can then view the treatment details on the app, submit questions about "material durability," and receive immediate answers from an intelligent robot, saving 40% of the time compared to the traditional method. For instance, in a common clinical scenario of treating proximal caries, after a patient completes oral data collection using a portable scanner, the AI ​​diagnostic model can quickly identify 0.1mm-level caries lesions on the proximal surface, marking the extent, depth, and number of dentin layers involved, and generating a report with options for "composite resin filling" and "inlay restoration." After the dentist adjusts the filling material type based on the 3D visualization analysis of the model, the patient can view the treatment details and estimated treatment time through the app, and can also directly submit questions about "material durability" for immediate feedback.

[0059] In step S104, based on the detailed diagnostic report and treatment plan recommendations, and combined with the trend of changes in the scan data, a follow-up reminder is automatically generated, and the follow-up data is fed back to the cloud platform to update the patient's medical records. At the same time, the scan data and medical records are periodically encrypted.

[0060] Among them, the trend of changes in scanning data refers to the evolution of pathological states, morphological structures, etc., presented by comparing and analyzing three-dimensional scanning data of teeth, gums, and jawbone collected at different time points.

[0061] It is understood that this application's embodiments, by comparing oral 3D scan data at different time points, accurately capture the evolution patterns of teeth, gums, and jawbones in pathological states (such as increases or decreases in the extent of caries and changes in the severity of gingival inflammation) and morphological structures (such as adjustments in jawbone occlusion), providing data support for follow-up management. Its advantages include the ability to accurately assess treatment effectiveness by combining diagnostic reports and treatment plans, making automatically generated follow-up reminders more targeted (such as triggering follow-ups earlier for patients with slow caries regression), and improving doctor-patient cooperation during follow-ups; simultaneously, it feeds back change data to the cloud to update records, allowing treatment records to present a dynamic trajectory throughout the entire cycle, providing doctors with intuitive evidence to review the effectiveness of treatment plans and adjust subsequent treatment strategies; and in conjunction with a periodic encryption mechanism, it manages the entire treatment process while ensuring the security of scan data and treatment records, strengthening the continuity and accuracy of treatment.

[0062] According to the embodiments of this application, a remote management method based on oral scanning data accurately acquires three-dimensional oral data through a data acquisition module. Combined with real-time reconstruction and pathological identification by an intelligent chip processing unit, it quickly generates preliminary diagnostic prompts, significantly shortening the pre-diagnosis time. The deep analysis of the AI ​​diagnostic platform outputs accurate lesion information and suitable treatment plans, reducing human diagnostic bias and improving the professionalism of diagnosis and treatment. The doctor-patient interaction module breaks down communication barriers, allowing doctors to efficiently adjust treatment plans and patients to monitor treatment progress in real time, optimizing the collaborative experience for both parties. The dynamic follow-up unit ensures the continuity of treatment tracking through automatic reminders, while relying on a periodic encryption mechanism to protect the security of scanning data and treatment records, comprehensively improving the efficiency, accuracy, interactivity, and data security of oral diagnosis and treatment. This solves the problems of low accuracy in remote collaboration and fragmented patient management in existing technologies.

[0063] The following will illustrate a remote management method based on oral cavity scan data through a specific embodiment, such as... Figure 4 As shown, it includes: Using a remote collaboration project between the Department of Stomatology of a county-level People's Hospital and a provincial-level Stomatological Hospital as an application scenario, this project adapts to the basic diagnostic and treatment needs of primary healthcare institutions and the precise guidance needs of higher-level hospitals. After three months of clinical trial operation, 120 patients were treated without any data transmission or diagnostic errors. The data acquisition module uses the domestically developed KS-300 portable 3D oral scanner. This device weighs only 580g, features a wireless handheld design suitable for complex intraoral procedures, and is equipped with eight 2-megapixel high-definition cameras and a 3D structured light module. With a scanning accuracy of 0.02mm, it can simultaneously acquire complete 3D data of teeth, gums, and jawbone, including areas difficult to reach with traditional instruments such as proximal surfaces and fissures. The device has a built-in 1200mAh lithium battery that supports 4 hours of continuous operation. Data transmission adopts a "wired + wireless" dual backup solution: in the clinic scenario, it connects directly to the local server via gigabit Ethernet, and in mobile scenarios such as rural medical outreach, it connects to the cloud via a 5G industrial module. Before transmission, the data is automatically compressed by LZ4 (compression ratio 8:1) and verified by CRC32 to ensure data integrity and avoid packet loss caused by signal fluctuations.

[0064] After data acquisition, the intelligent chip processing unit is automatically triggered for real-time analysis. This unit uses the Huawei Ascend 310B intelligent chip, which has a computing power of 16 TOPS and can meet the needs of multi-task parallel processing. The 3D reconstruction stage uses an optimized Poisson reconstruction algorithm, combined with prior knowledge of oral anatomy to simplify the model's topology. A high-precision 3D oral model can be generated within 25 seconds after scanning. The model supports rotation, scaling, and cross-sectional cutting operations, clearly showing the direction of tooth root canals, gingival attachment height, and jawbone bone density distribution. The pathological feature recognition unit is equipped with a lightweight YOLOv8-n model, trained and optimized through transfer learning on a dataset of 80,000 labeled oral samples. It can automatically identify six common conditions, including dental caries, periodontal pockets, and gingival recession. For example, in dental caries identification, the system uses grayscale thresholds (190-230 for normal teeth, 90-160 for decayed tissue) and morphological features to jointly determine the location, area, and depth of the caries. For gingival inflammation, the system uses RGB color features (R value 210-240 for inflamed gingiva, G value 90-120) to identify the red and swollen area, generate a preliminary diagnostic prompt, and attach the three-dimensional coordinates and confidence level (minimum 92%) of the suspected lesion, which is then pushed to the local doctor's workstation in real time.

[0065] After initial diagnosis and confirmation by primary care physicians, the data is synchronized to the AI ​​diagnostic platform of the Provincial Stomatological Hospital via a dedicated medical data line. This platform, deployed on Alibaba Cloud's dedicated medical cloud server, employs an "edge computing + cloud collaboration" architecture. Edge nodes handle data preprocessing, while the cloud handles in-depth analysis. The platform utilizes a Transformer-based multimodal diagnostic model, integrating 3D scan data, initial diagnostic suggestions, and the patient's electronic medical records (including past medical history and allergy history) for comprehensive analysis, generating a detailed diagnostic report within 5 minutes. The report is divided into primary care and expert versions: the primary care version focuses on core diagnostic conclusions, basic treatment steps, and precautions; the expert version includes differential diagnostic criteria for lesions, pathological mechanism analysis, and personalized treatment recommendations. For example, for patients with moderate proximal caries, it provides two options: "glass ionomer filling" and "composite resin filling," indicating the operational difficulty, material cost, and 5-year prognostic success rate (85% and 92%, respectively). Doctors can log in to the system via the web interface to modify treatment plans and add annotations, with modification records automatically generated into a version log. Patients can log in via a WeChat mini-program to view the anonymized diagnostic report summary and treatment progress. After submitting questions, the system will respond instantly through an intelligent Q&A robot, and unanswered questions will be transferred to the corresponding doctor for processing within 12 hours.

[0066] The doctor-patient interaction module adopts a "tiered access control + real-time collaboration" design to ensure treatment efficiency and data security. The primary care physician's end is equipped with a 27-inch 4K touchscreen display, supporting operations such as annotation and measurement of 3D models. When encountering complex cases, the "remote consultation" function can invite experts from the provincial hospital to intervene in real time. Both parties share the same model data and communicate via voice. Experts can directly annotate key diagnostic and treatment points on the model. The provincial hospital expert's end system has a built-in case database association function, which can automatically match treatment plans for similar cases for reference, shortening the plan development time. The patient's end mini-program simplifies the operation process. The homepage displays nodes such as "data collection - preliminary diagnosis - AI analysis - plan confirmation" in the form of a progress bar. Clicking on a node allows viewing the core information of the corresponding stage. The "question submission" function supports the upload of text, images, and short videos. For example, after a patient uploads a photo of their postoperative gum condition, the system automatically extracts image features and compares them with preoperative data to help doctors quickly assess the recovery status. The system also has a treatment reminder function, automatically pushing information such as treatment time and preoperative preparation to patients, and pushing tasks such as pending questions and consultation requests to doctors.

[0067] The dynamic follow-up and data security modules form a closed-loop management system for diagnosis and treatment. The follow-up reminder generation unit sets personalized nodes according to the treatment plan. For example, routine follow-up times are 1 week, 1 month, and 3 months after caries filling. For orthodontic treatment, a follow-up reminder is generated every 4 weeks and pushed to both doctors and patients via SMS and mini-program. The reminder content includes key follow-up points (such as the integrity of the filling and the condition of gingival redness and swelling). Follow-up data collection adopts a combined "institutional collection + home self-testing" model: routine follow-up is conducted at the primary care hospital using the original scanner, while patients in other locations can use a simple scanning wand provided by the hospital (compatible with the system, with an accuracy of 0.05mm) to collect data on key areas at home and upload it. The data feedback and update unit compares the follow-up data with historical data and generates a trend report. For example, by overlaying 3D models at different time points, it can intuitively show changes such as the reduction of caries area and the regression of gingival inflammation, and automatically update the patient's cloud file. In terms of data security, the system uses the national cryptographic algorithm SM4 to encrypt and store scan data and medical records. The encryption key is automatically updated every 15 days. Cloud-based archives are managed using a "role-based access control" system, allowing only authorized doctors to view the complete data. Operation logs are retained for 10 years for traceability. During the trial operation, the system improved the diagnostic accuracy of difficult cases in primary hospitals from 68% to 91%, and increased patient follow-up compliance from 52% to 83%.

[0068] In summary, this application's embodiments utilize a high-precision portable scanning device combined with a wired + wireless dual transmission scheme to ensure complete and real-time acquisition of oral 3D data, solving the scanning blind spot problem that traditional instruments cannot reach. The Huawei Ascend chip and optimized algorithms support 3D reconstruction and 92% confidence level pathological identification within 25 seconds, significantly improving the efficiency and accuracy of preliminary diagnosis. The AI ​​diagnostic platform generates tiered reports and personalized treatment plans, and, in conjunction with a dedicated line, enables data collaboration between primary care and higher-level hospitals, effectively improving the diagnostic accuracy of complex cases at the primary care level. The "remote consultation + multi-terminal interaction" design breaks down geographical limitations in diagnosis and treatment, while intelligent question-and-answer and progress tracking functions reduce information asymmetry between doctors and patients, improving collaborative efficiency. The system is adapted to collaborative scenarios between primary care and higher-level hospitals. During trial operation, the diagnostic accuracy at the primary care level and patient follow-up compliance significantly improved, and the full-process data control strengthens the standardization and accuracy of diagnosis and treatment.

[0069] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device may include: The memory 501, the processor 502, and the computer program stored on the memory 501 and capable of running on the processor 502.

[0070] When the processor 502 executes the program, it implements a remote management method based on oral scan data provided in the above embodiments.

[0071] Furthermore, electronic devices also include: Communication interface 503 is used for communication between memory 501 and processor 502.

[0072] The memory 501 is used to store computer programs that can run on the processor 502.

[0073] The memory 501 may include high-speed RAM (Random Access Memory) memory, and may also include non-volatile memory, such as at least one disk storage.

[0074] If the memory 501, processor 502, and communication interface 503 are implemented independently, then the communication interface 503, memory 501, and processor 502 can be interconnected via a bus to complete communication between them. The bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 5 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0075] Optionally, in a specific implementation, if the memory 501, processor 502, and communication interface 503 are integrated on a single chip, then the memory 501, processor 502, and communication interface 503 can communicate with each other through an internal interface.

[0076] The processor 502 may be a CPU (Central Processing Unit), an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of this application.

[0077] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described remote management method based on oral scan data.

[0078] Furthermore, this application also provides a computer program product, including a computer program or instructions, which, when executed, implement the aforementioned remote management method based on oral scan data.

[0079] In the description of this specification, the references to "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0080] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0081] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0082] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any of the following techniques known in the art, or a combination thereof: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0083] Those skilled in the art will understand that all or part of the steps of the methods described in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0084] Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of this application.

Claims

1. A remote management system based on oral cavity scan data, characterized in that, include: The system comprises a data acquisition module, an intelligent chip processing unit, an AI diagnostic platform, a doctor-patient interaction module, and a dynamic follow-up unit; among which, The data acquisition module is used to collect three-dimensional scan data of teeth, gums and jawbone in the oral cavity; The intelligent chip processing unit is used to process scan data in real time, perform three-dimensional reconstruction and pathological feature recognition, and generate preliminary diagnostic prompts. The AI ​​diagnostic platform is used to perform in-depth analysis of data based on preliminary diagnostic prompts using an AI diagnostic model, and generate detailed diagnostic reports and treatment plan suggestions. The doctor-patient interaction module is used by doctors to view diagnostic reports and adjust treatment plans, and by patients to check treatment progress and submit questions. The dynamic follow-up unit is used to automatically generate follow-up reminders based on the changing trends of scan data, and to feed the follow-up data back to the cloud platform to update the patient's medical records. At the same time, the scan data and medical records are periodically encrypted.

2. The remote management system based on oral cavity scan data according to claim 1, characterized in that, The data acquisition module includes a three-dimensional scanning unit and a data transmission unit. The three-dimensional scanning unit is used to acquire three-dimensional scanning data of tooth morphology, gingival contour and jawbone structure in the oral cavity. The data transmission unit is used to transmit the acquired three-dimensional scanning data to the intelligent chip processing unit in real time to ensure the stability of data transmission.

3. The remote management system based on oral cavity scan data according to claim 1, characterized in that, The intelligent chip processing unit includes a three-dimensional reconstruction unit and a pathological feature recognition unit. The three-dimensional reconstruction unit is used to process the scanned data in real time and construct a three-dimensional model of the teeth, gums and jawbone in the oral cavity. The pathological feature recognition unit is used to identify pathological features such as dental caries and gingival inflammation in the three-dimensional model and generate preliminary diagnostic prompts with suspected lesion annotations.

4. The remote management system based on oral cavity scan data according to claim 1, characterized in that, The AI ​​diagnostic platform includes a data receiving unit and a diagnostic analysis and generation unit. The data receiving unit is used to receive preliminary diagnostic prompts and associated scan data generated by the intelligent chip processing unit. The diagnostic analysis and generation unit is used to call the AI ​​diagnostic model to perform in-depth analysis of the data and generate a detailed diagnostic report including lesion type and severity, as well as treatment plan suggestions adapted to the patient's condition.

5. A remote management system based on oral cavity scan data according to claim 1, characterized in that, The doctor-patient interaction module includes a doctor-side interaction unit and a patient-side interaction unit. The doctor-side interaction unit is used by doctors to log in to the system to view detailed diagnostic reports, adjust treatment plans according to clinical needs, and save modification records. The patient-side interaction unit is used by patients to check their personal treatment progress and diagnostic reports, and submit treatment-related questions to doctors.

6. A remote management system based on oral cavity scan data according to claim 1, characterized in that, The dynamic follow-up unit includes a follow-up reminder generation unit and a data feedback update unit. The follow-up reminder generation unit is used to automatically generate follow-up time reminders based on the changing trends of scan data at different treatment stages and push them to both doctors and patients. The data feedback update unit is used to receive new scan data and medical records collected during follow-up, feed them back to the cloud platform to update the patient's medical records, and periodically encrypt the scan data and medical records.

7. A method for a remote management system based on oral scan data according to any one of claims 1-6, characterized in that, The method includes: Obtain three-dimensional scan data of teeth, gums, and jawbone within the oral cavity; The three-dimensional scan data of the teeth, gums and jawbone in the oral cavity are analyzed and processed in real time to perform three-dimensional reconstruction, pathological feature identification and generate preliminary diagnostic suggestions. Based on the preliminary diagnostic suggestions, the AI ​​diagnostic model performs in-depth analysis of the data to generate a detailed diagnostic report and treatment plan suggestions. This allows doctors to view the diagnostic report and adjust the treatment plan, while patients can check the treatment progress and submit questions. Based on the detailed diagnostic report and treatment recommendations, and combined with the trend of changes in scan data, follow-up reminders are automatically generated, and the follow-up data is fed back to the cloud platform to update the patient's medical records. At the same time, the scan data and medical records are periodically encrypted.

8. An electronic device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor. The processor executes the program to implement the remote management method based on oral scan data as described in claim 7.

9. A computer-readable storage medium having a computer program or instructions stored thereon, characterized in that, When a computer program or instruction is executed, it implements the remote management method based on oral scan data as described in claim 7.

10. A computer program product, comprising a computer program or instructions, characterized in that, When a computer program or instruction is executed, it implements the remote management method based on oral scan data as described in claim 7.

Images