An AR-based pig disease diagnosis and treatment teaching training method, device and equipment

Abstract

The application discloses a pig disease diagnosis and treatment teaching training method, device and equipment based on AR, which comprises the following steps: loading a three-dimensional sick pig model corresponding to the current teaching scene through an AR device, and presenting the current symptom performance including visual elements and sound at the corresponding part of the three-dimensional sick pig model; receiving the diagnosis and treatment decision input by a user according to the current symptom performance; analyzing the diagnosis and treatment decision based on a preset pharmacology-pathology response model, updating the symptom state of the three-dimensional sick pig model according to the analysis result, and presenting the updated symptom state in real time as corresponding AR visual effects; when the user confirms the completion of the diagnosis and treatment operation based on the updated symptom state, comprehensively scoring the drug selection accuracy, dosage rationality, processing timeliness and diagnosis and treatment process integrity of the user in the diagnosis and treatment process, and generating a teaching evaluation report. The interactive training scheme can simulate a complete diagnosis and treatment process, support autonomous decision-making and dynamically feedback the disease outcome, and improves the teaching interactivity.

Description

Technical Field

[0001] This invention relates to the field of AR teaching technology, and in particular to an AR-based teaching and training method, device and equipment for the diagnosis and treatment of pig diseases. Background Technology

[0002] With the increasing scale of pig farming, effective disease prevention and control has become a core element in ensuring farming efficiency and industry security. Against this backdrop, training veterinarians and pig farmers with solid clinical diagnostic skills is crucial. However, the training of pig disease diagnostic skills faces many practical difficulties: traditional teaching models rely heavily on apprenticeship-style on-site experience transfer, requiring learners to interact with sick pigs in real pig farms to accumulate diagnostic experience. This not only has a long training period but also poses biosafety risks. Furthermore, pig diseases are numerous, with complex and variable symptoms, and mixed infections are common. Relying solely on theoretical teaching or static illustrations is insufficient to present the dynamic evolution and pathological characteristics of diseases. While some auxiliary teaching or intelligent diagnostic systems have emerged, such as AR-based animal physiological cycle observation systems or database-matching disease information query systems, these systems mostly focus on knowledge display or auxiliary diagnostic functions, lacking interactive training capabilities for the complete diagnostic process. Learners find it difficult to repeatedly practice the complete diagnosis and treatment process, from symptom identification and medication decision-making to disease outcome assessment, in a safe and controlled environment. As a result, they cannot effectively develop clinical decision-making abilities and thus cannot effectively train and develop the practical ability to make accurate clinical judgments and decisions in complex and dynamic situations. Summary of the Invention

[0003] In view of this, the purpose of this invention is to propose an AR-based teaching and training method, device and equipment for swine disease diagnosis and treatment, which aims to solve the problems in existing swine disease diagnosis and treatment teaching that lack interactive training programs that can simulate the complete diagnosis and treatment process, support autonomous decision-making and dynamically provide feedback on the outcome of the disease.

[0004] To achieve the above objectives, the present invention provides an AR-based teaching and training method for swine disease diagnosis and treatment, the method comprising: A three-dimensional sick pig model corresponding to the current teaching scenario is loaded using an AR device, and the current symptoms, including visual elements and sounds, are displayed in the corresponding parts of the three-dimensional sick pig model. The system receives treatment decisions input by the user based on the current symptoms, including the selected medication and dosage. The diagnosis and treatment decision is analyzed based on a preset pharmacology-pathology response model, and the symptom status of the three-dimensional diseased pig model is updated according to the analysis results. The updated symptom status is then converted into corresponding AR visual effects in real time for presentation. When a user confirms the completion of the diagnosis and treatment operation based on the updated symptom status, a comprehensive score is given based on the accuracy of the user's drug selection, the rationality of the dosage, the timeliness of the treatment, and the completeness of the diagnosis and treatment process, and a teaching evaluation report is generated.

[0005] To achieve the above objectives, the present invention also provides an AR-based teaching and training device for pig disease diagnosis and treatment, the device comprising: The model loading unit is used to load a three-dimensional sick pig model corresponding to the current teaching scenario through an AR device, and to display the current symptoms, including visual elements and sounds, in the corresponding parts of the three-dimensional sick pig model. A decision input unit is used to receive a diagnosis and treatment decision input by the user based on the current symptom presentation, the diagnosis and treatment decision including the selected drug and dosage; The status update unit is used to analyze the diagnosis and treatment decision based on the preset pharmacology-pathology response model, update the symptom status of the three-dimensional diseased pig model according to the analysis results, and convert the updated symptom status into the corresponding AR visual effect in real time for presentation. The comprehensive scoring unit is used to comprehensively score the user's medication selection accuracy, dosage rationality, treatment timeliness, and treatment process completeness when the user confirms the completion of the diagnosis and treatment operation based on the updated symptom status, and generates a teaching evaluation report.

[0006] To achieve the above objectives, the present invention also proposes an AR-based teaching and training device for pig disease diagnosis and treatment, comprising a processor, a memory, and a computer program stored in the memory. The computer program is executed by the processor to implement the steps of an AR-based teaching and training method for pig disease diagnosis and treatment as described in the above embodiments.

[0007] To achieve the above objectives, the present invention also proposes a computer-readable storage medium storing a computer program that is executed by a processor to implement the steps of an AR-based teaching and training method for swine disease diagnosis and treatment as described in the above embodiments.

[0008] Beneficial effects: The above solution uses AR devices to present the real-time symptoms of virtual sick pigs, receives user treatment decisions, infers disease changes based on pharmacological-pathological response models and converts them into AR visual effects in real time, and finally provides a comprehensive score for user operations and generates an evaluation report. This achieves a complete closed-loop simulation of diagnosis and treatment from "symptom observation → medication decision → disease outcome," enabling learners to repeatedly train their clinical decision-making abilities in an environment free from biosafety risks. It allows them to fully practice the entire process from symptom recognition to efficacy observation and obtain immediate quantitative feedback, thereby efficiently cultivating clinical decision-making abilities and standardized diagnosis and treatment, and improving teaching interactivity and learning effectiveness.

[0009] By pre-setting various teaching scenarios for swine diseases and corresponding initial symptom state vectors and medication regimen libraries, and by specifying symptom parameters (body temperature, respiratory rate, mental level, appetite, nasal foam value, posture) and drug information (identity, matching degree, dosage range, efficacy vector), complex clinical symptoms and pharmacological knowledge are transformed into data structures that can be recognized and processed by computers. This provides the system with quantifiable disease models and drug knowledge bases, supports flexible configuration and expansion of different disease scenarios, and enhances the diversity of teaching content and the adaptability of the system.

[0010] By calculating the comprehensive efficacy coefficient using matching degree coefficient and dosage coefficient, and combining it with preset path selection priority strategies (such as death threshold, contraindicated drugs, toxic dosage, matching degree and dosage combination, and time-effect), the target path is determined from multiple disease outcome paths (such as relief, aggravation, death, complications, relapse after temporary relief, and cure). The efficacy vector and natural disease course vector are used to calculate the changes in symptom parameters, which realizes the accurate quantitative assessment of diagnosis and treatment decisions and the dynamic simulation of disease evolution. This enables learners to intuitively understand the differentiated outcomes caused by different medication strategies, cultivate scientific medication and clinical judgment abilities, and enhance the realism, logic and teaching value of the training.

[0011] By using a predefined parameter-performance mapping table, quantitative parameters such as body temperature, respiratory rate, mental status, and nasal foam levels are driven in real time to generate AR visual effects such as changes in the color of thermal imaging pseudo-color textures, changes in the scaling cycle of rib bones, pose switching of animation state machines, and changes in particle emitter rate. This achieves intuitive visualization and dynamic representation of symptom states, enhances learners' immersion and perception of changes in the condition, and enables learners to intuitively perceive the symptoms of sick pigs as if they were observing real sick pigs, thereby training their ability to observe and judge symptoms based on multimodal information.

[0012] The evaluation system comprehensively assesses learners' performance across multiple dimensions, including accuracy of drug selection, rationality of dosage, timeliness of treatment, and completeness of the diagnostic and treatment process. It also clarifies the operational steps of the diagnostic and treatment process (multi-site observation, drug selection confirmation, dosage input, decision submission, and observation outcome confirmation), thus constructing a comprehensive quantitative evaluation system. This allows learners to clearly understand their strengths and weaknesses in each stage, enabling them to make targeted improvements. At the same time, it standardizes the diagnostic and treatment procedures, provides precise learning feedback, guides learners towards standardized and regulated clinical diagnostic and treatment behaviors, and cultivates rigorous clinical work habits.

[0013] By recording the user's complete operation trajectory in a single diagnosis and treatment training session and comparing it with the preset standard diagnosis and treatment process and marking the differences, the system realizes the functions of operation review and comparative teaching. This helps learners intuitively discover the deviations between their own operation and the standard process, facilitating self-reflection and targeted improvement, and further enhancing teaching effectiveness and skill mastery efficiency. Attached Figure Description

[0014] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0015] Figure 1 This is a flowchart illustrating an AR-based teaching and training method for diagnosing and treating pig diseases, provided as an embodiment of the present invention.

[0016] Figure 2 This is a schematic diagram of an AR-based teaching and training device for swine disease diagnosis and treatment, provided as an embodiment of the present invention.

[0017] The realization of the invention's objective, its functional characteristics, and advantages will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention. Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to represent selected embodiments of the invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] The present invention will be described in detail below with reference to the embodiments.

[0020] Reference Figure 1 The diagram shows a flowchart of an AR-based teaching and training method for swine disease diagnosis and treatment according to an embodiment of the present invention. Specifically, the method includes: S10, preset multiple teaching scenarios for pig diseases, and configure corresponding initial symptom state vectors and medication regimen libraries for each pig disease teaching scenario; wherein, the initial symptom state vectors include body temperature, respiratory rate, mental level, appetite, nasal foam value, and posture state, and the medication regimen library includes drug identity, disease matching degree, dosage range, and efficacy vector; the efficacy vector defines the influence coefficient of the corresponding drug on body temperature, respiratory rate, mental level, and appetite per unit simulation time.

[0021] In this embodiment, the system presets various teaching scenarios for swine diseases in the data processing platform. These scenarios include, for example, porcine reproductive and respiratory syndrome (PRRS), swine pasteurellosis, swine dysentery (Treponema pallidum infection), porcine circovirus disease, classical swine fever, foot-and-mouth disease, contagious pleuropneumonia, and yellow-white scours in piglets. For each disease teaching scenario, a corresponding initial symptom state vector and a medication regimen library are configured. The initial symptom state vector consists of multiple quantifiable clinical parameters, including body temperature, respiratory rate, mental status, appetite, nasal foam levels, and postural status. Continuous variables, such as body temperature, are stored directly as floating-point numbers (e.g., 41.8℃) for easy incremental calculations. Discrete variables, such as mental level, are defined as enumerated values ​​(0=normal, 1=mild depression, 2=moderate, 3=severe), with each level corresponding to a different skeletal animation posture (standing, lying down, side-lying, etc.). Appetite is expressed as a percentage (0%~100%). Nasal foam values ​​can be quantified as levels or floating-point numbers. Posture states are managed through a state machine (e.g., dog sitting, lying down, side-lying, standing, etc.). Taking swine contagious pleuropneumonia as an example, its initial symptom characteristics can be set as: high fever (above 41℃), depression (mental level ≥2), complete loss of appetite (0% appetite), difficulty breathing, dog sitting posture, and frothy bloody discharge from the mouth and nose (nasal foam value >1).

[0022] Simultaneously, a pre-defined medication regimen library is provided for each disease scenario. This library contains relevant information for various drugs: drug identity (name, dosage form, route of administration), matching degree to the current disease (categorized as first-line drugs, second-line drugs, ineffective drugs, contraindicated drugs, etc.), dosage range (including effective dose interval, lower limit of safe dose, toxicity threshold, etc.), and an efficacy vector. The efficacy vector defines the influence coefficient of the corresponding drug on several symptom parameters such as body temperature, respiratory rate, mental status, and appetite within a unit of simulation time (usually based on 24 hours). For example, for porcine infectious pleuropneumonia, the efficacy vector of florfenicol can be set as body temperature -0.8℃, respiratory rate -15 breaths / min, mental status -1 level, and appetite +30%.

[0023] In addition, the system pre-defines the natural disease progression vector for each disease under no-intervention conditions to describe the natural progression of the disease (e.g., body temperature increases by 0.1℃ per hour, mental state decreases by one level every 2 hours), and the mortality threshold (body temperature > 42.5℃, respiratory rate > 100 breaths / min, or mental state level = 3 and appetite = 0 for one calculation cycle). All the above rules, parameters, and vectors are stored in a configuration file and dynamically loaded by the system to form an extensible rule base. When a user selects a teaching scenario for a specific disease, the system can load the corresponding initial symptom state vector and medication regimen library, providing a foundation for subsequent symptom presentation and diagnostic decision analysis.

[0024] S11, load a three-dimensional sick pig model corresponding to the current teaching scenario through an AR device, and present the current symptoms, including visual elements and sounds, in the corresponding parts of the three-dimensional sick pig model.

[0025] In this embodiment, after the user initiates the teaching training through an AR device (such as AR glasses or a tablet), the system first uses the device's camera to identify a landmark plane in the real space (such as a desktop or the ground) as the placement anchor point for the virtual sick pig. When the user moves the device, the 3D sick pig model will be stably anchored at this plane position, maintaining spatial consistency with the real environment. Based on the disease teaching scenario previously selected by the user, the system loads the corresponding 3D sick pig model from the database. This model has a multi-layered structure including bones, muscles, and skin, supporting the local dynamic display of different symptoms. Next, the system reads the initial symptom state vector of the current disease scenario. This vector contains quantifiable parameters such as body temperature, respiratory rate, mental status, appetite, nasal foam levels, and posture. To convert these values ​​into visible and audible symptom manifestations for the user, the system uses a predefined parameter-manifestation mapping table to drive each symptom parameter into corresponding AR visual elements and sounds in real time.

[0026] Specifically: body temperature parameters are mapped to color changes in the pseudo-color texture of the thermal imaging on the surface of the 3D sick pig model; for example, it appears red when there is a high fever, gradually fading to orange-yellow until it reaches normal skin color as the body temperature decreases. Respiratory rate parameters are mapped to the periodic changes controlling the scaling of the ribcage; the higher the frequency, the shorter the scaling period, manifesting as rapid breathing, and the period lengthens as the frequency decreases. Mental state parameters are mapped to an animation state machine, controlling the 3D sick pig model to switch between various postures such as standing, lying down, sitting, and side-lying. For example, when the mental state level is 3 (severe depression), the model is in a side-lying posture; as the level decreases, it transitions to lying down or standing. Nasal foam parameters are mapped to changes in the emitter rate of the particle system; when the respiratory rate is greater than 60 breaths / min and the nasal foam value is greater than 1, the particle emitter rate is set to high, continuously spraying foam-like particles from the mouth and nose; the particle rate returns to zero after the symptoms lessen. Furthermore, posture is also directly reflected through skeletal animation, such as a "sitting posture" or a "falling posture." Meanwhile, the system plays corresponding sound effects based on the current symptom parameter values, such as coughing, wheezing, and painful cries, further enhancing the immersive experience. Through the above mapping, the corresponding parts of the 3D sick pig model (such as the mouth, nose, chest, and body surface) present dynamic symptom manifestations in real time that perfectly match the current disease scenario, including visual thermal imaging colors, foam particles, and abnormal postures, as well as auditory pathological sounds, enabling users to intuitively and comprehensively observe and judge the condition of the virtual sick pig.

[0027] S12, receive the treatment decision input by the user based on the current symptom presentation, the treatment decision including the selected drug and dosage.

[0028] In this embodiment, the user inputs diagnostic and treatment decisions through the interactive interface of the AR device. The user first observes the symptoms (including visual elements and sounds) presented by the 3D model of the sick pig, and then interacts with the system based on their own judgment via touchscreen, gesture recognition, or voice input. Specifically: the user clicks the virtual medicine box icon in the AR interface to open the drug list and view basic information such as the name, dosage form, and route of administration for each drug; based on the observed symptoms, the user selects one or more drugs from the list (e.g., for porcine infectious pleuropneumonia, florfenicol or tilmicosin can be selected). After selecting a drug, the system displays a dosage setting interface. The user sets the dosage of the drug (e.g., 8ml) by dragging a slider or directly entering numbers, and confirms that the unit matches the drug dosage form (ml for injections, g for powders). The user can repeat the above operation to set the dosage for each selected drug. After all drugs and dosages are set, the user clicks the "Administer Medication" or "Confirm Submission" button in the AR interface to complete the input of the diagnostic and treatment decision. The system receives and records the treatment decision, including the user's selected medication and corresponding dosage, as the basis for analysis in the subsequent disease progression module. If the user needs to modify the selection during the process, they can return to reselect the medication or adjust the dosage; if the user submits without selecting a medication, the system will prompt that the operation is incomplete and guide the user to complete the decision input. In this way, the system ensures that the user's input treatment decision is complete and standardized, providing accurate input data for subsequent efficacy analysis and disease outcome simulation.

[0029] S13, the diagnosis and treatment decision is analyzed based on the preset pharmacology-pathology response model, and the symptom status of the three-dimensional diseased pig model is updated according to the analysis results, and the updated symptom status is converted into the corresponding AR visual effect in real time for presentation.

[0030] Furthermore, in step S13, the analysis of the diagnosis and treatment decision based on the preset pharmacological-pathological response model, and the updating of the symptom status of the three-dimensional diseased pig model according to the analysis results, includes: S13-1, Based on the drug selected in the treatment decision, query the disease matching degree in the medication regimen database and determine the matching degree coefficient; S13-2, Based on the dosage in the treatment decision, query the dosage range of the corresponding drug in the medication regimen library to determine the dosage coefficient; S13-3, Calculate the comprehensive therapeutic effect coefficient based on the matching degree coefficient and the dosage coefficient; S13-4, Based on the diagnosis and treatment decision and the updated symptom status, determine the target outcome path from multiple disease outcome paths according to a preset path selection priority strategy; S13-5, input the comprehensive efficacy coefficient, the efficacy vector of the corresponding drug in the medication regimen library and the preset disease natural course vector into the pharmacology-pathology response model to obtain the change of each symptom parameter in the symptom state of the three-dimensional diseased pig model under the target outcome path; S13-6, The changes are superimposed on the symptom state of the three-dimensional diseased pig model to obtain the updated symptom state.

[0031] Furthermore, the disease progression pathways include symptom relief pathways, symptom aggravation pathways, death pathways, complication occurrence pathways, symptom relapse pathways after temporary symptom relief, and cure pathways; the pathway selection priority strategy includes executing pathway selection in the priority order of death threshold triggering, contraindicated drug use, toxic dose triggering, drug compatibility and dosage combination determination, and time-sensitivity correction; wherein, When the death threshold is met, the death path is triggered first. When a contraindicated drug is used or the dosage reaches a toxic level, the symptom exacerbation pathway is triggered. When the medication is matched and the dosage is effective, the symptom relief pathway is triggered. When medication is matched but the dosage is low, it triggers a relapse pathway after symptom relief. If medication is not adjusted in time during the relapse pathway after symptom relief, the complication pathway will be triggered. If an effective dose is maintained for several consecutive cycles in the symptom relief pathway, the patient enters the recovery pathway.

[0032] The mortality threshold includes at least one of the following: the body temperature of the three-dimensional diseased pig model exceeds a first preset threshold, the respiratory rate of the three-dimensional diseased pig model exceeds a second preset threshold, and the mental level of the three-dimensional diseased pig model reaches the highest level and the appetite parameter value is zero.

[0033] Furthermore, in step S13, the real-time conversion of the updated symptom status into corresponding AR visual effects for presentation includes: S13-7, Based on a predefined parameter-performance mapping table, the parameter values ​​of each symptom parameter in the symptom state are used to drive changes in the corresponding visual performance elements in the three-dimensional diseased pig model, wherein the parameter-performance mapping table includes: The body temperature parameter values ​​are mapped to the color changes of the thermal imaging pseudo-color texture on the surface of the three-dimensional diseased pig model; The respiratory rate parameter value is mapped to the periodic changes that control the scaling cycle of the rib skeleton of the three-dimensional diseased pig model. The mental level parameter value is mapped to an animation state machine that controls the switching of the three-dimensional sick pig model between various postures; The numerical parameters of the nasal foam are mapped to the emitter rate changes of the particle system.

[0034] In this embodiment, the system analyzes the user-input diagnosis and treatment decisions based on a preset pharmacology-pathology response model, dynamically updates the symptom status of the three-dimensional diseased pig model according to the analysis results, and then presents the updated status to the user in real time as an AR visual effect. Specifically, the system first determines the matching degree coefficient based on the disease matching degree in the drug treatment plan library selected in the diagnosis and treatment decision: if the drug is a first-line drug for the current disease, the matching degree coefficient is set to 1.0; for second-line drugs, it is set to 0.6 to 0.8; for ineffective drugs, it is set to 0; and for contraindicated drugs, it is set to -1.0 to -2.0. Simultaneously, based on the dosage in the treatment decision, the dosage range of the corresponding drug in the medication regimen database is consulted to determine the dosage coefficient: if the dosage is within the effective dosage range, the dosage coefficient is 1.0; if it is slightly lower than the effective dosage (effective lower limit × 0.7 to 1.0), the coefficient is 0.3 to 0.7; if it is severely insufficient (below 70% of the effective dosage), the coefficient is 0 to 0.2; if it exceeds the safe range but does not cause poisoning, the coefficient is 0 to 0.5; and if it reaches the toxic dosage, the coefficient is -1.2 to -1.5. Then, the system calculates the comprehensive efficacy coefficient: Comprehensive efficacy coefficient = matching degree coefficient × dosage coefficient.

[0035] Next, based on treatment decisions (including whether the drug is contraindicated and whether the dosage reaches a toxic dose) and the current symptom status of the 3D diseased pig model (whether the mortality threshold is met), a target outcome path is determined from multiple disease outcome paths according to a preset path selection priority strategy. This priority strategy is: mortality threshold trigger > contraindicated drug use > toxic dose trigger > drug matching degree and dosage combination judgment > time-based correction. The mortality threshold includes: body temperature exceeding 42.5℃, respiratory rate exceeding 100 breaths / min, or mental status reaching 3 (highest) and appetite being 0, lasting for one calculation cycle (e.g., 2 hours of actual time corresponds to one discrete time step). If the mortality threshold is met, the mortality path is directly selected; if a contraindicated drug is used or the dosage reaches a toxic dose, the symptom aggravation path is selected; if the drug is matched (first-line or second-line) and the dosage is effective, the symptom relief path is selected; if the drug is matched but the dosage is low (slightly below the effective dose), the relapse path after temporary symptom relief is selected. In the relapse pathway after symptom relief, if medication is not adjusted in time, the complication pathway is triggered; in the symptom relief pathway, if an effective dose is maintained for several consecutive cycles (e.g., 3 cycles), the patient enters the cure pathway.

[0036] After determining the target outcome path, the comprehensive efficacy coefficient, the efficacy vector of the corresponding drug in the medication regimen library (e.g., the influence coefficient on body temperature, respiratory rate, mental status, and appetite), and the preset natural disease course vector (describing the rate of natural disease progression without intervention, such as a body temperature increase of 0.1°C per hour) are input into the pharmacology-pathology response model. The model calculates the changes in each symptom parameter according to the rules corresponding to the target outcome path. For example, under the symptom relief path, the new value = current value + (efficacy vector × time coefficient) - (natural disease course vector × time coefficient); under the symptom aggravation path, the new value = current value + (toxicity vector × time coefficient) + (natural disease course vector × time coefficient); where the time coefficient depends on the simulation step size (e.g., each calculation cycle represents 2 hours). For body temperature, if the current temperature is 41.8℃, and the efficacy vector under the action of an effective drug for 24 hours (12 cycles) is -0.8℃, then the change is -0.8℃, and the updated body temperature is 41.0℃. If a contraindicated drug is used, the efficacy vector is negative, and the body temperature rises by 0.5℃ to 42.3℃. After calculating the changes in all symptom parameters (body temperature, respiratory rate, mental status, appetite, nasal foam count, postural status, etc.), the system adds these changes to the current symptom status to obtain the updated symptom status.

[0037] Finally, the system updates the symptom status and translates it into corresponding AR visual effects in real time. Based on a predefined parameter-performance mapping table, the system uses the values ​​of each symptom parameter to drive changes in the corresponding visual elements in the 3D sick pig model: the body temperature parameter value is mapped to the color change of the thermal imaging pseudo-color texture on the model surface; for example, when the body temperature drops from 41.8℃ to 41.0℃, the texture fades from red to orange-yellow; the respiratory rate parameter value is mapped to the periodic change of the rib skeleton scaling cycle, with the cycle shortening when breathing is rapid and lengthening when breathing is calm; the mental level parameter value is mapped to an animation state machine, controlling the model to switch between postures such as standing, lying down, sitting, and side-lying; the nasal foam parameter value is mapped to the change of the emitter rate of the particle system, with the emitter rate increasing and foam increasing when symptoms are severe, and returning to zero when symptoms lessen. Simultaneously, the system plays corresponding sounds (such as breathing sounds, coughing sounds, etc.) according to the updated symptom status. Through this process, users can intuitively see the symptom outcome (improvement, worsening, death, etc.) of their virtual sick pig after medication and receive immediate AR visual and auditory feedback.

[0038] S14. When the user confirms the completion of the diagnosis and treatment operation based on the updated symptom status, a comprehensive score is given based on the accuracy of the user's drug selection, the rationality of the dosage, the timeliness of the treatment, and the completeness of the diagnosis and treatment process, and a teaching evaluation report is generated.

[0039] Furthermore, in step S14, the comprehensive scoring based on the user's accuracy in drug selection, appropriate dosage, timeliness of treatment, and completeness of the treatment process includes: S14-1, score the disease matching degree of the selected drug in the medication regimen library for the current teaching scenario to obtain the first score of the accuracy of the drug selection; S14-2, score the dosage range of the corresponding drug in the medication regimen library according to the dosage to obtain a second score for the rationality of the dosage. S14-3, A third score is obtained based on the time elapsed from the time the current symptoms appeared to the time the user submitted the diagnosis and treatment decision, which corresponds to the timeliness of the processing. S14-4, score the user based on whether they have fully executed the steps of the diagnosis and treatment process, and obtain the fourth score for the completeness of the corresponding diagnosis and treatment process; S14-5, add the first score, the second score, the third score and the fourth score together to obtain the comprehensive score.

[0040] Furthermore, the operational steps of the aforementioned diagnosis and treatment process include, in sequence: Users can observe multiple key symptom areas of the three-dimensional diseased pig model using the AR device, and the observation time is not less than the preset minimum observation time. The user opens the virtual medicine box through the AR device and selects at least one medicine before confirming the selection; The user enters the corresponding dosage for each selected drug and confirms. The user confirms and submits the treatment decision, including the selected drug and dosage, through the AR device; After the user submits the diagnosis and treatment decision, the changes in the updated symptom status of the three-dimensional diseased pig model are observed until the outcome is indicated and the diagnosis and treatment operation is confirmed to be completed.

[0041] In this embodiment, when the user confirms the completion of the diagnosis and treatment operation based on the updated symptom status, the system enters the comprehensive scoring and teaching evaluation report generation stage. The user must first observe the changes in the symptom status of the updated 3D sick pig model until the system indicates the outcome (such as "treatment successful," "treatment failed," "complication occurred," or the virtual sick pig shows a recovered / dead posture). The user then clicks the "End Observation" or "Confirm Completion" button to confirm the completion of this diagnosis and treatment operation. A comprehensive score is then calculated based on the user's performance throughout the entire diagnosis and treatment training process. The scoring dimensions include the accuracy of drug selection, the rationality of dosage, the timeliness of treatment, and the completeness of the diagnosis and treatment process. Each dimension is scored independently, and the scores are added together to obtain the total score.

[0042] Specifically, regarding the accuracy of drug selection, the system scores the selected drug based on its disease matching level in the current teaching scenario within the medication regimen library: if the user selects a first-line drug, the user receives the highest score (e.g., 40 points); if it is a second-line drug, the user receives the second highest score (e.g., 30 points); if it is an ineffective or contraindicated drug, the user receives the lowest score (e.g., 0 points). Regarding the rationality of dosage, the system scores the dosage entered by the user within the corresponding dosage range in the medication regimen library: if the dosage is within the effective dosage range, the user receives the highest score (e.g., 30 points); if it is within the safe dosage range but below the effective dosage range, the user receives the second highest score (e.g., 20 points); if it exceeds the safe dosage range but does not reach the toxic dosage, the user receives the third highest score (e.g., 5 points); if it reaches the toxic dosage or is below the lower limit of the safe dosage, the user receives the lowest score (e.g., 0 points).

[0043] Regarding timeliness, the system records the time elapsed from the first appearance of current symptoms to the time the user submits a treatment decision, and compares this time with the preset optimal intervention time. If the time is less than the optimal intervention time, a first-tier score (e.g., 20 points) is obtained; if it is greater than or equal to the optimal intervention time but less than 1.5 times the optimal intervention time, a second-tier score (e.g., 10 points) is obtained; if it is greater than or equal to 1.5 times the optimal intervention time, the lowest-tier score (e.g., 0 points) is obtained. Regarding the completeness of the diagnosis and treatment process, the system checks whether the user has fully executed multiple preset operation steps. Each step must meet specific judgment conditions: First, the user observes multiple key symptom areas (at least three areas related to the current disease, such as mouth, nose, chest, and body posture) of the 3D sick pig model using an AR device, and the observation time is not less than the minimum observation time preset by the system (such as 30 seconds or adjusted according to the complexity of the disease). The system will record the number of interactions between the user and the virtual sick pig and the observation time. If the user does not perform any observation operations or the observation time is insufficient and multiple parts are not interacted with, this step is judged as incomplete. Second, the user opens the virtual medicine box through the AR device and selects at least one drug and confirms the selection. The system records the explicit drug selection operation. If the user does not select a drug, the system will skip directly. If the user fails to complete the first five steps, the process is considered incomplete. The third step involves the user inputting the corresponding dosage for each selected drug and confirming it. The system checks that each drug has a valid input value (non-negative, non-zero, and conforming to dosage unit requirements). If any value is missing or invalid, the process is considered incomplete. The fourth step involves the user confirming and submitting a treatment decision, including the selected drugs and dosages, via an AR device. The system records the submission, and the first two steps must be completed at the time of submission; otherwise, the process is considered incomplete. The fifth step involves the user observing the changes in the updated symptoms of the 3D sick pig model after submitting the treatment decision, until the system indicates the outcome and the user confirms the completion of the treatment. The observation time must cover at least one system calculation cycle (e.g., 24 hours of simulation time corresponds to 10-20 seconds in reality). If the user terminates the observation prematurely or fails to confirm the outcome, the process is considered incomplete. If the user completes all five steps, they receive a full score (e.g., 10 points); missing any one step results in zero points.

[0044] Finally, by adding the first, second, third, and fourth scores, a comprehensive score is obtained, generating a teaching evaluation report that includes the scores for each item, explanations of deductions, and suggestions for improvement. This report can be displayed in text form on the AR interface or saved to the user's learning record for review and self-assessment. Through this scoring mechanism, the system can comprehensively and quantitatively evaluate the user's clinical decision-making ability and operational standardization in diagnostic and treatment training, helping learners identify their shortcomings and make targeted improvements.

[0045] In another embodiment, the method further includes: S15, record the user's operation trajectory in a single diagnosis and treatment training session, compare and display the operation trajectory with the preset standard diagnosis and treatment process, and mark the operation differences. The operation trajectory includes the user's observation site and observation duration on the three-dimensional sick pig model, the record of drug selection, the record of inputting drug dosage, the record of submitting diagnosis and treatment decisions, and the record of observation outcome.

[0046] In this embodiment, the system also includes operation playback and comparative teaching functions. The system automatically records the user's complete operation trajectory in a single diagnosis and treatment training session, including: the parts and duration of observation of the 3D sick pig model by the user through the AR device (e.g., whether key symptom areas such as the mouth, nose, chest, and body posture were clicked, and whether the dwell time on each part reached the preset minimum observation time), the record of the user opening the virtual medicine box and selecting drugs (including the selected drug name and selection time), the record of the user entering the corresponding dosage for each drug, the record of the user confirming and submitting the diagnosis and treatment decision, and the operation record of the user observing the outcome after submitting the decision until confirmation of completion. The system stores these operation trajectory data locally or on a server.

[0047] When users complete the diagnostic training and review the replay, the system compares their operational trajectory with a pre-defined standard diagnostic procedure. This standard procedure is a pre-defined sequence of standardized operations for the current disease teaching scenario, including: key symptom sites to be observed and minimum observation time, recommended medications and effective dosage ranges to be selected, decision submission within the optimal intervention time, and the sequence of the five steps to be fully executed. The system simultaneously displays the user's operation replay and the standard procedure in a split-screen or picture-in-picture format, highlighting differences in operation with bold colors (such as red borders or flashing markers) during the comparison. Examples include key sites not observed, insufficient observation time, medication selection inconsistent with standard recommendations, dosage deviating from the effective range, decision submission timeout, or omission of a necessary step (such as ending without confirmation). Users can interactively control the replay progress using AR devices, repeatedly viewing differences to intuitively understand deviations between their own operations and the standard procedure, facilitating self-reflection and improvement. Teachers can also use this function to provide targeted guidance to students, enhancing teaching effectiveness. In this way, the system not only provides training and assessment functions, but also strengthens the ability to review and correct mistakes after learning, forming a complete teaching loop.

[0048] Reference Figure 2 The diagram shown is a schematic representation of an AR-based teaching and training device for swine disease diagnosis and treatment, provided in an embodiment of the present invention.

[0049] In this embodiment, the device 20 includes: The model loading unit 21 is used to load a three-dimensional sick pig model corresponding to the current teaching scenario through an AR device, and to display the current symptoms, including visual elements and sounds, in the corresponding parts of the three-dimensional sick pig model. The decision input unit 22 is used to receive a diagnosis and treatment decision input by the user based on the current symptom presentation, the diagnosis and treatment decision including the selected drug and dosage; The status update unit 23 is used to analyze the diagnosis and treatment decision based on the preset pharmacology-pathology response model, update the symptom status of the three-dimensional diseased pig model according to the analysis results, and convert the updated symptom status into the corresponding AR visual effect in real time for presentation. The comprehensive scoring unit 24 is used to comprehensively score the user's medication selection accuracy, dosage rationality, processing timeliness, and treatment process completeness when the user confirms the completion of the diagnosis and treatment operation based on the updated symptom status, and to generate a teaching evaluation report.

[0050] In another embodiment, the device 20 further includes: The recording unit is used to record the user's operation trajectory in a single diagnosis and treatment training session, compare and display the operation trajectory with the preset standard diagnosis and treatment process, and mark the operation differences. The operation trajectory includes the user's observation site and observation duration on the three-dimensional sick pig model, the record of drug selection, the record of inputting drug dosage, the record of submitting diagnosis and treatment decisions, and the record of observation outcome.

[0051] Each unit module of the device 20 can execute the corresponding steps in the above method embodiment, so the details of each unit module will not be elaborated here. Please refer to the description of the corresponding steps above for details.

[0052] This invention also provides an AR-based teaching and training device for pig disease diagnosis and treatment. This device includes the AR-based teaching and training apparatus for pig disease diagnosis and treatment described above. The AR-based teaching and training apparatus for pig disease diagnosis and treatment can employ... Figure 2 The structure of the embodiment, correspondingly, can be executed Figure 1 The technical solutions of the method embodiments shown are similar in implementation principle and technical effect. For details, please refer to the relevant records in the above embodiments, which will not be repeated here.

[0053] The device includes: a mobile phone, digital camera, or tablet computer, or other device with a camera function; or a device with an image processing function; or a device with an image display function. The device may include components such as a memory, processor, input unit, display unit, and power supply.

[0054] The memory can be used to store software programs and modules. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory. The memory can mainly include a program storage area and a data storage area. The program storage area can store the operating system, applications required for at least one function, etc.; the data storage area can store data created according to the use of the device, etc. In addition, the memory can include high-speed random access memory, and can also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory can also include a memory controller to provide access to the memory for the processor and input units.

[0055] The input unit can be used to receive input numerical, character, or image information, and to generate keyboard, mouse, joystick, optical, or trackball signal inputs related to user settings and function control. Specifically, in addition to a camera, the input unit of this embodiment may also include a touch-sensitive surface (e.g., a touch screen) and other input devices.

[0056] The display unit can be used to display information input by the user or information provided to the user, as well as various graphical user interfaces of the device. These graphical user interfaces can be composed of graphics, text, icons, video, and any combination thereof. The display unit may include a display panel, optionally configured as an LCD (Liquid Crystal Display), OLED (Organic Light-Emitting Diode), or other similar display panel. Furthermore, a touch-sensitive surface may cover the display panel. When the touch-sensitive surface detects a touch operation on or near it, it transmits the information to the processor to determine the type of touch event. Subsequently, the processor provides corresponding visual output on the display panel based on the type of touch event.

[0057] This invention also provides a computer-readable storage medium, which may be a computer-readable storage medium included in the memory described in the above embodiments; or it may be a standalone computer-readable storage medium not assembled into a device. The computer-readable storage medium stores at least one instruction, which is loaded and executed by a processor to implement... Figure 1 The illustrated method is an AR-based teaching and training method for diagnosing and treating pig diseases. The computer-readable storage medium can be a read-only memory, a hard disk, or an optical disk, etc.

[0058] This invention also provides a computer program product, including a computer program / instructions, which are loaded and executed by a processor to implement... Figure 1 This paper presents an AR-based teaching and training method for diagnosing and treating diseases in pigs.

[0059] It should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the device embodiments, equipment embodiments, and storage medium embodiments, since they are basically similar to the method embodiments, the descriptions are relatively simple, and relevant parts can be referred to the descriptions in the method embodiments.

[0060] Furthermore, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0061] The foregoing description illustrates and describes preferred embodiments of the present invention. It should be understood that the present invention is not limited to the forms disclosed herein and should not be construed as excluding other embodiments. It can be used in various other combinations, modifications, and environments, and can be altered within the scope of the inventive concept by means of the foregoing teachings or techniques or knowledge in related fields. Any modifications and variations made by those skilled in the art that do not depart from the spirit and scope of the present invention should be within the protection scope of the appended claims.

Claims

1. An AR-based teaching and training method for swine disease diagnosis and treatment, characterized in that, The method includes: A three-dimensional sick pig model corresponding to the current teaching scenario is loaded using an AR device, and the current symptoms, including visual elements and sounds, are displayed in the corresponding parts of the three-dimensional sick pig model. The system receives treatment decisions input by the user based on the current symptoms, including the selected medication and dosage. The diagnosis and treatment decision is analyzed based on a preset pharmacology-pathology response model, and the symptom status of the three-dimensional diseased pig model is updated according to the analysis results. The updated symptom status is then converted into corresponding AR visual effects in real time for presentation. When a user confirms the completion of the diagnosis and treatment operation based on the updated symptom status, a comprehensive score is given based on the accuracy of the user's drug selection, the rationality of the dosage, the timeliness of the treatment, and the completeness of the diagnosis and treatment process, and a teaching evaluation report is generated.

2. The AR-based teaching and training method for pig disease diagnosis and treatment according to claim 1, characterized in that, Before loading the 3D diseased pig model corresponding to the current teaching scenario via the AR device, the method further includes: Multiple teaching scenarios for pig diseases are preset, and a corresponding initial symptom state vector and medication regimen library are configured for each teaching scenario. The initial symptom state vector includes body temperature, respiratory rate, mental state, appetite, nasal foam value, and posture. The medication regimen library includes drug identity, disease matching degree, dosage range, and efficacy vector. The efficacy vector defines the influence coefficient of the corresponding drug on body temperature, respiratory rate, mental state, and appetite per unit simulation time.

3. The AR-based teaching and training method for pig disease diagnosis and treatment according to claim 2, characterized in that, The diagnostic and treatment decisions are analyzed based on a pre-set pharmacological-pathological response model, and the symptom status of the three-dimensional diseased pig model is updated according to the analysis results, including: Based on the drug selected in the treatment decision, query the disease matching degree in the medication regimen database to determine the matching degree coefficient; Based on the dosage in the treatment decision, the dosage range of the corresponding drug in the medication regimen library is queried to determine the dosage coefficient; The comprehensive therapeutic effect coefficient is calculated based on the matching degree coefficient and the dosage coefficient. Based on the aforementioned diagnosis and treatment decisions and the updated symptom status, a target outcome path is determined from multiple disease outcome paths according to a preset path selection priority strategy. The comprehensive efficacy coefficient, the efficacy vector of the corresponding drug in the medication regimen library, and the preset disease natural course vector are input into the pharmacology-pathology response model to obtain the change in each symptom parameter in the symptom state of the three-dimensional diseased pig model under the target outcome path. The changes are superimposed on the symptom state of the three-dimensional diseased pig model to obtain the updated symptom state.

4. The AR-based teaching and training method for pig disease diagnosis and treatment according to claim 3, characterized in that, The disease progression pathways include symptom relief pathways, symptom aggravation pathways, death pathways, complication occurrence pathways, symptom relapse pathways after temporary symptom relief, and recovery pathways; the pathway selection priority strategy includes prioritizing pathway selection according to the following order: triggering a death threshold, use of contraindicated drugs, triggering toxic dosage, determination of drug compatibility and dosage combination, and time-sensitivity correction; wherein... When the death threshold is met, the death path is triggered first. When a contraindicated drug is used or the dosage reaches a toxic level, the symptom exacerbation pathway is triggered. When the medication is matched and the dosage is effective, the symptom relief pathway is triggered. When medication is matched but the dosage is low, it triggers a relapse pathway after symptom relief. If medication is not adjusted in time during the relapse pathway after symptom relief, the complication pathway will be triggered. If an effective dose is maintained for several consecutive cycles in the symptom relief pathway, the patient enters the recovery pathway.

5. The AR-based teaching and training method for pig disease diagnosis and treatment according to claim 1, characterized in that, The process of converting updated symptom states into corresponding AR visual effects in real time includes: Based on a predefined parameter-performance mapping table, the parameter values ​​of each symptom parameter in the symptom state are used to drive changes in the corresponding visual performance elements in the three-dimensional diseased pig model. The parameter-performance mapping table includes: The body temperature parameter values ​​are mapped to the color changes of the thermal imaging pseudo-color texture on the surface of the three-dimensional diseased pig model; The respiratory rate parameter value is mapped to the periodic changes that control the scaling cycle of the rib skeleton of the three-dimensional diseased pig model. The mental level parameter value is mapped to an animation state machine that controls the switching of the three-dimensional sick pig model between various postures; The numerical parameters of the nasal foam are mapped to the emitter rate changes of the particle system.

6. The AR-based teaching and training method for pig disease diagnosis and treatment according to claim 1, characterized in that, The evaluation is based on a comprehensive assessment of the user's accuracy in drug selection, appropriate dosage, timeliness of treatment, and completeness of the treatment process, including: The first score for the accuracy of drug selection is obtained by scoring the degree of disease matching of the selected drug in the medication regimen library for the current teaching scenario. The dosage is scored according to the dosage range of the corresponding drug in the medication regimen library to obtain a second score for the rationality of the dosage. A third score is obtained based on the time elapsed from the time the current symptoms appeared to the time the user submitted the diagnosis and treatment decision, corresponding to the timeliness of the processing. A fourth score is given based on whether the user has fully executed the steps of the diagnosis and treatment process, resulting in a score indicating the completeness of the corresponding diagnosis and treatment process. The first score, the second score, the third score, and the fourth score are added together to obtain the comprehensive score.

7. The AR-based teaching and training method for pig disease diagnosis and treatment according to claim 6, characterized in that, The operational steps of the diagnosis and treatment process include, in sequence: Users can observe multiple key symptom areas of the three-dimensional diseased pig model using the AR device, and the observation time is not less than the preset minimum observation time. The user opens the virtual medicine box through the AR device and selects at least one medicine before confirming the selection; The user enters the corresponding dosage for each selected drug and confirms. The user confirms and submits the treatment decision, including the selected drug and dosage, through the AR device; After the user submits the diagnosis and treatment decision, the changes in the updated symptom status of the three-dimensional diseased pig model are observed until the outcome is indicated and the diagnosis and treatment operation is confirmed to be completed.

8. The AR-based teaching and training method for pig disease diagnosis and treatment according to claim 1, characterized in that, The method further includes: The user's operation trajectory during a single diagnosis and treatment training session is recorded, and the operation trajectory is compared and displayed with the preset standard diagnosis and treatment process, with the differences in operation marked. The operation trajectory includes the user's observation site and observation duration on the three-dimensional sick pig model, the record of drug selection, the record of inputting drug dosage, the record of submitting diagnosis and treatment decisions, and the record of observation outcome.

9. An AR-based teaching and training device for swine disease diagnosis and treatment, characterized in that, The device includes: The model loading unit is used to load a three-dimensional sick pig model corresponding to the current teaching scenario through an AR device, and to display the current symptoms, including visual elements and sounds, in the corresponding parts of the three-dimensional sick pig model. A decision input unit is used to receive a diagnosis and treatment decision input by the user based on the current symptom presentation, the diagnosis and treatment decision including the selected drug and dosage; The status update unit is used to analyze the diagnosis and treatment decision based on the preset pharmacology-pathology response model, update the symptom status of the three-dimensional diseased pig model according to the analysis results, and convert the updated symptom status into the corresponding AR visual effect in real time for presentation. The comprehensive scoring unit is used to comprehensively score the user's medication selection accuracy, dosage rationality, treatment timeliness, and treatment process completeness when the user confirms the completion of the diagnosis and treatment operation based on the updated symptom status, and generates a teaching evaluation report.

10. An AR-based teaching and training device for swine disease diagnosis and treatment, characterized in that, It includes a processor, a memory, and a computer program stored in the memory, wherein when the computer program is executed by the processor, it implements the steps of an AR-based teaching and training method for swine disease diagnosis and treatment as described in any one of claims 1 to 8.

Images