Crop leaf disease diagnosis method and system driven by large language model

Abstract

The invention discloses a crop leaf disease diagnosis method and system driven by a large language model. Comprising the following steps: firstly, extracting a leaf disease image of a target crop and corresponding text semantic information from a basic crop management file so as to obtain an initial crop disease knowledge database; then, the initial crop disease knowledge database is optimized and updated in combination with visual understanding of a large language model; and then, constructing a crop disease classification agent model, inputting a to-be-diagnosed leaf disease image into the crop disease classification agent model, performing crop disease diagnosis by the crop disease classification agent model according to the crop disease knowledge database, and outputting a disease identification result. Under the condition that large-scale image training is not carried out, disease diagnosis can be accurately carried out on the crop disease images, disease image diagnosis requirements of different crops can be met, and the problem that existing work is insufficient in potential in the aspects of zero sample application and expandability is solved.

Description

Technical Field

[0001] The invention relates to a crop leaf disease diagnosis method and system, and in particular to a crop leaf disease diagnosis method and system driven by a large language model. Background Art

[0002] Accurate and timely disease identification is essential for effective disease management to reduce yield losses. However, crop disease identification is challenging due to the complexity and increasing number of crop species and the existence of plant pathology issues. Establishing an accurate and universal crop disease identification model is of great significance to ensure food security.

[0003] Deep learning has shown high classification accuracy in image-based disease recognition. As a typical multi-layer feature extraction model in the image domain, convolutional neural networks have achieved remarkable success in various visual classification tasks in crop disease detection. However, these deep learning models usually require a large amount of data for training to achieve satisfactory performance in specific situations. There is still a lot of uncertainty in the performance of trained models in new scenarios, especially in identifying various crop diseases.

[0004] The development of artificial intelligence technology has made it possible to train large language models (LLM) with hundreds of billions of parameters, such as the Generative Pre-trained Transformer Model 4 (GPT-4). These models have demonstrated their strong generation and text understanding capabilities and have achieved success in various natural language processing tasks, such as reasoning, summarization, and translation. Advanced LLMs have been rapidly studied and evaluated in many fields, such as medical diagnosis, financial reporting, manuscript review, etc. In the agricultural field, recent studies have also evaluated their performance in crop disease classification. However, existing studies generally focus on pre-training visual-language models without considering the potential of LLMs in zero-shot applications and scalability. Summary of the invention

[0005] In order to solve the problems and needs in the background technology, the present invention proposes a large language model driven crop leaf disease diagnosis method and system. The present invention can accurately diagnose crop disease images without large-scale image training, and can adapt to the disease image diagnosis needs of different crops, improving the potential problem of insufficient zero-sample application and scalability of existing work.

[0006] The technical solution adopted by the present invention to solve the technical problem is as follows: 1. A large language model driven crop leaf disease diagnosis method Step 1: Extract the leaf disease images and corresponding text semantic information of the target crop from the basic crop management files to obtain the initial crop disease knowledge database; Step 2: Optimize the initial crop disease knowledge database by combining the visual understanding of the large language model to obtain an updated crop disease knowledge database; Step 3: Construct a large language model under the framework of logical thinking chain guidance and record it as the crop disease classification agent model, input the leaf disease image to be diagnosed into the crop disease classification agent model, and the crop disease classification agent model diagnoses crop diseases according to the crop disease knowledge database and outputs the disease identification results.

[0007] The step 2 is specifically as follows: A plurality of leaf disease images corresponding to each crop disease type in the initial crop disease knowledge database are randomly selected as example images of the crop disease type, and the image semantic information of the crop disease type is generated using a large language model. Then, combined with the image semantic information of the current crop disease type, all text semantic information of the crop disease type is data simplified so that each text semantic information is aligned with the image semantic information to obtain optimized text semantic information, and then corresponding prompt information is generated according to all optimized text semantic information of the current crop disease type; after traversing and processing the text semantic information corresponding to other crop disease types in the initial crop disease knowledge database, the optimized text semantic information and prompt information corresponding to all crop disease types are obtained, thereby obtaining an updated crop disease knowledge database.

[0008] The step 3 is specifically as follows: The process of crop disease classification by the large language model includes the visual understanding stage and the image classification reasoning stage; for the visual understanding stage, the prompt engineering based on chain thinking (CoT) is used to drive the large language model to capture the key visual features of the leaf status in the leaf disease image; for the image classification reasoning stage, the prompt engineering based on chain thinking (CoT) is used to remind the large language model to pay attention to the common characteristics of the disease when calculating the degree of match between image semantic information and text semantic information, and to use the inconsistency and conflict between the image semantic information and the text semantic information as important deviations of negative samples, so that the large language model can classify the leaf disease image into the correct disease type from the perspective of reasoning, thereby obtaining a crop disease classification proxy model; then the leaf disease image to be diagnosed is input into the crop disease classification proxy model, and the crop disease classification proxy model performs crop disease diagnosis according to the crop disease knowledge database, and takes the disease type with the highest degree of match between the image semantic information and the text semantic information as the disease recognition result.

[0009] The key visual features of leaf condition include leaf color and shape and the distribution pattern of lesions.

[0010] Common characteristics of the disease include spot size, color and leaf condition.

[0011] In the image classification reasoning stage, the chain of thought (CoT)-based prompt engineering generates reference reasoning examples based on the crop disease knowledge database, and uses the reference reasoning examples to generate recommended scoring tendencies when there is a semantic conflict in the image semantic information or the text semantic information is lost in the large language model.

[0012] 2. A large language model driven crop leaf disease diagnosis system A crop disease knowledge database construction unit is used to extract leaf disease images and corresponding text semantic information of target crops from crop management files, thereby obtaining an initial crop disease knowledge database; A database updating unit, used to optimize the initial crop disease knowledge database in combination with the visual understanding of the large language model to obtain an updated crop disease knowledge database; The disease diagnosis unit is used to combine the latest crop disease knowledge database and the crop disease classification agent model to diagnose crop diseases according to the leaf disease images to be diagnosed, thereby outputting the disease identification results.

[0013] The crop disease classification agent model is specifically a large language model under the framework of logical thinking chain guidance.

[0014] 3. A computer device The device includes a memory and a processor, the memory stores a computer program, and the processor implements the steps of the crop leaf disease diagnosis method driven by a large language model when executing the computer program.

[0015] 4. A computer-readable storage medium The storage medium stores a computer program, which, when executed by a processor, implements the steps of the crop leaf disease diagnosis method driven by a large language model.

[0016] V. A computer program product The product includes a computer program / instruction, which, when executed by a processor, implements the steps of the crop leaf disease diagnosis method driven by a large language model.

[0017] The present invention has the following beneficial effects: The present invention constructs a crop disease knowledge database and a crop disease classification agent model in a large language model through logical thinking chain guidance strategy, prompt engineering and other technologies. It can accurately diagnose diseases on crop disease images without large-scale image training, and can adapt to the disease image diagnosis needs of different crops, improving the potential of existing work in zero-sample application and scalability.

[0018] Compared with traditional disease recognition methods that rely on large-scale image data training, the present invention only requires disease description text to identify crop diseases by inputting unlabeled images, which significantly simplifies the operational process of disease recognition, reduces the demand for data and computing resources, and improves the accuracy of large language models in diagnosing crop disease images.

[0019] Due to the scalability of pathological text, the present invention can be directly applied to the diagnosis of different disease images of different crops, and does not require an additional training process, which improves the generalization of the workflow and can complete zero-sample diagnosis.

[0020] In addition, the method and system proposed in the present invention are highly adaptable and scalable, and can be easily transferred to new disease classification scenarios. This crop disease diagnosis framework based on a large language model is particularly suitable for the identification of variable diseases in agricultural production environments, greatly improving the response efficiency of farmers and managers to different crop diseases. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 Flowchart for the construction and updating of crop disease knowledge database.

[0022] Figure 2 Schematic diagram of the text semantic information of tomato early blight image before and after simplification, where (a) is the original pathological description text of tomato early blight image, and (b) is the simplified pathological description text of tomato early blight image.

[0023] Figure 3 Flowchart of a large language model-driven crop leaf disease diagnosis method.

[0024] Figure 4 This is the accuracy diagram of tomato disease classification in this embodiment.

[0025] Figure 5 This is a comparison chart of the classification accuracy and scalability of the newly added diseases in this embodiment. DETAILED DESCRIPTION

[0026] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0027] The present invention proposes a crop leaf disease diagnosis method driven by a large language model, such as Figure 1 and Figure 3 As shown, the specific steps include: Step 1: Extract the text semantic information corresponding to the leaf disease images of the target crop from the basic crop management files to obtain the initial crop disease knowledge database; Step 1 is as follows: The purpose of the crop disease knowledge database is to provide knowledge of crop pathology. Crop disease description text is the basis for disease classification. This information includes the visual features of leaves under the corresponding disease, such as color, shape, and leaf state. For example, leaves infected with bacterial leaf spot usually have small, round spots with a dark brown to black appearance. Especially for the first infection, the spots have a water-soaked appearance. As the disease progresses, the number of spots increases, making more spots visible on the leaves, and the infected leaves will also turn yellow. The disease description text data was collected from crop management manuals available on university portals, such as the University of Minnesota Extension. These manuals mainly provide text-based descriptions of disease information and related management strategies. In order to improve the quality of disease description texts, ChatGPT was used to process these manuals, collect clear and concise text information related to the visual features of infected leaves, and record them as text semantic information corresponding to each leaf disease image. The selected information was then stored in JSON files. These JSON files store all the key information of the disease in the form of key-value pairs, which facilitates the call and analysis of subsequent methods and systems.

[0028] Step 2: Optimize the initial crop disease knowledge database by combining the visual understanding of the large language model to obtain an updated crop disease knowledge database; Step 2 is as follows: Considering the possible gap between the disease descriptions in the crop management manual and the visual understanding of the GPT-4o model, such as "mosaic patterns", "burn spots", and "root and fruit features". However, in the visual feature extraction stage, only relatively simple attributes such as shape and color can be accurately captured. Therefore, five leaf disease images corresponding to each crop disease type in the initial crop disease knowledge database are randomly selected and used as example images of the crop disease type, and the GPT-4o model is used to generate the image semantic information of the crop disease type. Combined with the image semantic information of the current crop disease type, all text semantic information of the crop disease type is streamlined so that each piece of text semantic information is aligned with the image semantic information to obtain optimized text semantic information, thereby deleting information that is not related to the visual features of the infected leaves, such as information on the roots, stems, and fruits of infected plants. Taking the text semantic information of tomato early blight images as an example, Figure 2 (a) and Figure 2As shown in (b), the score after text semantic optimization has been improved, and the GPT-4o model is better able to understand the image. Then, the corresponding prompt information is generated based on all the optimized text semantic information of the current crop disease type, so that the GPT-4o model can identify the disease of the crop leaves; after traversing and processing the text semantic information corresponding to other crop disease types in the initial crop disease knowledge database, the optimized text semantic information and prompt information corresponding to all crop disease types are obtained, thereby obtaining an updated crop disease knowledge database. Due to the scalability of text, text descriptions of different diseases can be easily obtained and stored, and stored uniformly in the database of the same crop disease description.

[0029] Step 3: Construct a large language model under the framework of logical thinking chain guidance and record it as the crop disease classification agent model, input the leaf disease image to be diagnosed into the crop disease classification agent model, and the crop disease classification agent model diagnoses crop diseases according to the crop disease knowledge database and outputs the disease identification results.

[0030] Step 3 is as follows: The process of large language model in crop disease classification includes task definition, visual understanding stage and image classification reasoning stage.

[0031] In the task definition phase, the task content that GPT-4o needs to perform is clarified, including the definition of GPT-4o's general framework identity, as well as the input, output, and detailed task content of the workflow. In this example, GPT-4o is defined as an experienced botanist, and the task is to evaluate whether the leaf disease in the image meets the semantic meaning of the text prompt according to the scoring criteria.

[0032] For the visual understanding stage, the GPT-4o model is driven by the chain of thought (CoT)-based prompt engineering to capture the key visual features of the leaf state in the leaf disease image, so that the GPT-4o model can capture these key features related to crop diseases; the key visual features of the leaf state include the color and shape of the leaf and the distribution pattern of the lesions. For example, infected leaves usually have some lesions and vary in color and shape. The visual understanding process enables the GPT-4o model to capture these key features related to crop diseases.

[0033] For the image classification reasoning stage, the prompt engineering based on chain thinking (CoT) is used to remind the GPT-4o model to pay attention to the common features of diseases when calculating the degree of match between image semantic information and text semantic information, and to use the inconsistency and conflict between image semantic information and text semantic information as important deviations of negative samples, so that the GPT-4o model can classify leaf disease images into the correct disease type from the perspective of reasoning, thereby obtaining a crop disease classification agent model. Common features of diseases include spot size, color, and leaf state. The guidance of the present invention in two stages enhances the reasoning ability of the GPT-4o model in crop disease classification. Among them, the inconsistency and conflict between the image semantic information and the text semantic information are important deviations of negative samples. Specifically, when there is inconsistency and / or conflict between the image semantic features and the text semantic features, it is suggested that the text semantic information tends to be a negative sample, otherwise it is suggested that the text semantic information tends to be a positive sample; in this stage, the prompt engineering based on chain thinking (CoT) generates reference reasoning examples based on the crop disease knowledge database, and when the GPT-4o model has semantic conflicts in image semantic information or loss of text semantic information, it uses reference reasoning examples to generate recommended scoring tendencies. Compared with traditional prompts, the developed CoT prompts enable the disease classification agent to follow the logical reasoning chain and gradually classify the disease.

[0034] Scoring is used to evaluate the consistency between the visual content of the disease image and the text description of the disease. Specifically, GPT-4o is guided to autonomously assign a score from 0 to 100 based on the degree of match between the visual features of the diseased leaves and the semantic information in the disease description. The scoring criteria are as follows: Low score: When there is a conflict between the text description and the image features, the overall score should be biased towards a lower value (e.g., the lesion is described as round, but the image shows that the lesion has an irregular shape).

[0035] Medium score: When some features of the image are consistent with the description of the corresponding disease, the score should be a medium value.

[0036] High score: When the text description matches the image features closely, a high score should be given. The higher the match, the higher the score.

[0037] The leaf disease image to be diagnosed is then input into the crop disease classification agent model. The crop disease classification agent model performs crop disease diagnosis based on the crop disease knowledge database and takes the disease type with the highest matching degree between the image semantic information and the text semantic information as the disease recognition result.

[0038] Take the four common tomato diseases - bacterial spot, late blight, yellow leaf curl virus, mosaic virus and healthy leaves as examples.

[0039] Image diagnosis example: Input a tomato mosaic virus image and different tomato pathology text descriptions in the crop disease knowledge database "Typical symptoms of tomato mosaic virus (ToMV) include mottled or mosaic patterns on leaves, in which irregular light green and dark green areas form obvious uneven colors. Leaf mottled or mosaic patterns are an important distinction from yellow leaf curl virus; tomato bacterial spot disease manifests as multiple irregular yellow-brown areas, mainly concentrated at the edges of the leaves, with many small spots or perforations scattered on the surface; late blight manifests as large areas of brown or gray-green lesions with a waterlogged appearance and blurred edges; tomato yellow leaf curl virus (TYLCV) infection usually causes the leaves to turn yellow overall, Yellowing is most noticeable in the interveinal areas, making the green veins stand out more. Leaves infected with TYLCV often curl upward and may be deformed, with a stunted or twisted appearance. Yellow leaves with prominent green veins, accompanied by obvious curling and deformation, are important distinguishing features from mosaic virus; healthy tomato leaves are uniformly dark green, with no yellow or brown spots on the surface, pinnately compound leaves, with serrated or wavy edges, and the main veins extend clearly from the base to the tip of the leaf. The leaf surface is smooth, with no obvious wrinkles or depressions. "In the tomato image disease diagnosis task, the tomato mosaic virus is matched with all the above descriptions through the logical thinking chain reasoning matching rules and the corresponding matching degree is obtained.

[0040] The proxy model outputs the disease type that best matches the disease description. The output of the LLM has a specified format and detailed instructions for handling missing data, scoring, and other issues to ensure the standardization of the framework output. The consistency of the proxy model when matching images and text does not require that the image and text are exactly the same, but a higher score is obtained when the image display and text description are relatively consistent.

[0041] The present invention also proposes a large language model driven crop leaf disease diagnosis system, comprising: A crop disease knowledge database construction unit is used to extract leaf disease images and corresponding text semantic information of target crops from crop management files using ChatGPT, thereby obtaining an initial crop disease knowledge database, which is used to provide knowledge of crop diseases; A database updating unit, used to optimize the initial crop disease knowledge database in combination with the visual understanding of the large language model to obtain an updated crop disease knowledge database; The disease diagnosis unit is used to combine the latest crop disease knowledge database and the crop disease classification agent model to diagnose crop diseases based on the leaf disease images to be diagnosed, thereby outputting disease identification results. Among them, the crop disease classification agent model is used to understand the pattern of infected leaves and identify the disease type. The performance effectiveness of the method and system (ChatLeafDisease, ChatLD) proposed in the present invention is evaluated below.

[0042] GPT-4o and the contrastive language-image pre-training (CLIP) model were used as baseline methods. The original GPT-4o model was used to evaluate the contribution of the CoT cues developed in the present invention in crop disease classification. The parameters of GPT-4o were uniformly set with a temperature of 0.1 and a sampling strategy (Top-p) value of 0.9. The CLIP model is a typical neural network trained on various image-text pairs. The CLIP model is able to predict the most relevant text fragments from a given image under natural language instructions without directly optimizing for the task, similar to the zero-shot capabilities of GPT-2 and GPT-3. The CLIP model shows good performance in cross-modal retrieval, image classification, and text-to-image generation.

[0043] First, the classification performance of GPT-4o, CLIP and ChatLD models was independently evaluated on the tomato disease dataset. Each model was evaluated 5 times to ensure the reliability of the results. Taking into account the differences in the fields, five images of each tomato disease were randomly selected to fine-tune the CLIP model. The input sample batch size was 8, and 50 rounds of fine-tuning training were performed until the model reached a fitting state. The classification accuracy of tomato diseases by the present invention, GPT-4o and CLIP models is shown in the figure below. Figure 4 shown.

[0044] As can be seen from the figure, the ChatLD framework achieved the highest classification accuracy in tomato disease classification, with an average accuracy of 88.9% (see Table 1). When the original GPT-4o model was directly applied to classify tomato disease leaf images, the classification accuracy was lower, with an average accuracy of 45.9%. These results indicate that it is necessary to optimize and tune large language models (LLMs) in the corresponding domains. As a typical text-to-image connection method, the CLIP model outperformed the GPT-4o model with an average classification accuracy of 64.3%. However, it should be noted that the CLIP model was fine-tuned with a small number of samples (five samples per disease class) to achieve this performance, while the GPT-4o and ChatLD models did not require training. The poor performance of the CLIP model shows that crop disease classification faces difficulties when training data is scarce, which is a significant challenge for traditional data-driven models. The ChatLD model performed the most consistently across the five tests, with overall accuracy ranging from 85.6% to 91.6%. In contrast, the GPT-4o and CLIP models showed large fluctuations in accuracy in some categories, such as healthy leaves and yellow leaf curl virus. Notably, the Chain of Thoughts (CoT)-based prompt engineering significantly improved classification accuracy and stability compared to the two baseline models. This significant improvement can be attributed to the logical reasoning ability endowed by the CoT prompts.

[0045] Table 1 shows the experimental results of classification accuracy of tomato disease samples When faced with the need for new crop disease diagnosis, the knowledge database was updated according to the method flow, and the scalability of the framework was tested on new crop disease datasets such as grapes, strawberries, and peppers (100 images for each disease type). In order to emphasize the strong zero-shot capability of ChatLD, the amount of training data required for the CLIP model to achieve similar performance was also tested. The experimental results are shown in Figure 2. Figure 5 shown.

[0046] The results show that after updating the knowledge database according to the specific process, the ChatLD framework achieved high accuracy in zero-shot classification of new crop diseases, with an overall accuracy of 94.4%, showing its high stability on new datasets (see Figure 5). The ChatLD framework provided an average classification accuracy of 97.3%, 88.8%, and 100% for grape, strawberry, and pepper diseases, respectively. In traditional neural network diagnosis, the performance of the CLIP model improved significantly with the increase in the amount of fine-tuning data. When the amount of data per category increased from five to 50, the average disease classification accuracy increased from 74.3% to 92.1%. However, the performance of the CLIP model was limited when there were only five samples per category for fine-tuning. For some disease categories, such as black spot of grapes (21%) and angular spot of strawberries (37%), the classification accuracy was low. After increasing the number of samples per category to 50, the CLIP model provided a classification accuracy of more than 80% for most categories. The results show that the zero-shot performance of the ChatLD framework is better than that of the CLIP model even with fine-tuning data. The largest improvement of the ChatLD framework compared to the CLIP (50) model is in the classification of grape diseases, where the overall classification accuracy increased from 90.5% to 97.3%. It is worth noting that the proposed ChatLD framework is training-free and outperforms the retrained CLIP model in classification accuracy for three new crops. This result shows that the ChatLD framework has strong scalability and adaptability, which is crucial for crop disease classification in complex agricultural production scenarios.

[0047] It can be seen from the diagnosis accuracy results of strawberry, grape and pepper diseases using the traditional method and the method proposed in the present invention that the method proposed in the present invention allows the large language model to accurately diagnose different crop diseases without the need for training data, only by updating the knowledge database. Constructing a disease diagnosis method and system according to the present invention can reduce or even avoid the cost of training deep learning, and improve the recognition and generalization ability of new crop diseases.

[0048] Finally, it should be noted that the above embodiments and explanations are only used to illustrate the technical solution of the present invention rather than to limit it. Those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope disclosed in the technical solution of the present invention, which should be included in the scope of protection of the claims of the present invention.

Claims

1. A large language model driven crop leaf disease diagnosis method, characterized in that: The following steps are involved: Step 1: Extract the leaf disease images and corresponding text semantic information of the target crop from the basic crop management files to obtain the initial crop disease knowledge database; Step 2: Optimize the initial crop disease knowledge database by combining the visual understanding of the large language model to obtain an updated crop disease knowledge database; Step 3: Construct a large language model under the framework of logical thinking chain guidance and record it as the crop disease classification agent model, input the leaf disease image to be diagnosed into the crop disease classification agent model, and the crop disease classification agent model diagnoses crop diseases according to the crop disease knowledge database and outputs the disease identification results.

2. The method for diagnosing crop leaf diseases driven by a large language model according to claim 1, characterized in that: The step 2 is specifically as follows: A plurality of leaf disease images corresponding to each crop disease type in the initial crop disease knowledge database are randomly selected as example images of the crop disease type, and the image semantic information of the crop disease type is generated using a large language model; then, combined with the image semantic information of the current crop disease type, all text semantic information of the crop disease type is data simplified so that each text semantic information is aligned with the image semantic information to obtain optimized text semantic information; then, corresponding prompt information is generated according to all optimized text semantic information of the current crop disease type; After traversing and processing the text semantic information corresponding to other crop disease types in the initial crop disease knowledge database, the optimized text semantic information and prompt information corresponding to all crop disease types are obtained, thereby obtaining an updated crop disease knowledge database.

3. The method for diagnosing crop leaf diseases driven by a large language model according to claim 1, characterized in that: The step 3 is specifically as follows: The process of crop disease classification by the large language model includes the visual understanding stage and the image classification reasoning stage; for the visual understanding stage, the prompt engineering based on chain thinking is used to drive the large language model to capture the key visual features of the leaf status in the leaf disease image; for the image classification reasoning stage, the prompt engineering based on chain thinking is used to remind the large language model to pay attention to the common characteristics of the disease when calculating the matching degree between the image semantic information and the text semantic information, and to take the inconsistency and conflict between the image semantic information and the text semantic information as the important deviation of the negative sample, so that the large language model can classify the leaf disease image into the correct disease type from the perspective of reasoning, thereby obtaining the crop disease classification proxy model; then the leaf disease image to be diagnosed is input into the crop disease classification proxy model, and the crop disease classification proxy model performs crop disease diagnosis according to the crop disease knowledge database, and takes the disease type with the highest matching degree between the image semantic information and the text semantic information as the disease recognition result.

4. The method for diagnosing crop leaf diseases driven by a large language model according to claim 3, characterized in that: The key visual features of leaf condition include leaf color and shape and the distribution pattern of lesions.

5. The method for diagnosing crop leaf diseases driven by a large language model according to claim 3, characterized in that: Common characteristics of the disease include spot size, color and leaf condition.

6. The method for diagnosing crop leaf diseases driven by a large language model according to claim 3, characterized in that: In the image classification reasoning stage, the chain thinking-based prompt engineering generates reference reasoning examples based on the crop disease knowledge database, and uses the reference reasoning examples to generate recommended scoring tendencies when there is a semantic conflict in the image semantic information or the text semantic information is lost in the large language model.

7. A crop leaf disease diagnosis system driven by a large language model, characterized in that: include: A crop disease knowledge database construction unit is used to extract leaf disease images and corresponding text semantic information of target crops from crop management files, thereby obtaining an initial crop disease knowledge database; A database updating unit, used to optimize the initial crop disease knowledge database in combination with the visual understanding of the large language model to obtain an updated crop disease knowledge database; The disease diagnosis unit is used to combine the latest crop disease knowledge database and the crop disease classification agent model to diagnose crop diseases according to the leaf disease images to be diagnosed, thereby outputting the disease identification results.

8. The crop leaf disease diagnosis system driven by a large language model according to claim 7, characterized in that: The crop disease classification agent model is specifically a large language model under the framework of logical thinking chain guidance.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the crop leaf disease diagnosis method driven by a large language model as described in any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of a crop leaf disease diagnosis method driven by a large language model as described in any one of claims 1 to 6 are implemented.

Images