Urology department traditional Chinese medicine inquiry result prediction method and system applying large language model

Abstract

The invention discloses a urology department traditional Chinese medicine inquiry result prediction method and system applying a large language model, and belongs to the technical field of large language models. The method comprises the following steps: preprocessing disease description data, and obtaining self-correlation parameters among the disease description data; constructing a prediction model according to the large language model; the core keyword data used for describing the focus is output, so that the specific cause of disease in the inquiry is predicted, and the accuracy is improved; the method comprises the following steps: recording feedback data related to core keyword data in real time; inputting the feedback data into the self-correction model, and outputting an adjustment value; and according to the adjustment value, parameters in the large language model are adjusted in real time, and through continuous use and adjustment based on feedback data, continuous refinement of the prediction model in the specific knowledge field of the urology department field is further realized, so that prediction of specific causes in inquiry is further realized, and the accuracy is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of large language models, and in particular to a method and system for predicting results of urology Chinese medicine consultation using a large language model. Background Art

[0002] Existing medical big language models, such as Bian Que and Ling Xin, often use the natural language understanding (NLP) and reasoning capabilities of the large language model (LLM), combined with private knowledge bases for data analysis and fine-tuning optimization, to accurately understand the text content related to urology Chinese medicine consultation reports, and develop a system for recommending prescriptions of medicinal and edible substances based on the large language model.

[0003] However, in actual use, existing artificial intelligence technology can only provide prescriptions for medicine and food based on TCM consultation reports, and most recommendations cannot output the influencing parameters of the specific cause of the disease in the consultation, and thus cannot provide prescriptions for medicine and food corresponding to the symptoms based on the specific cause of the disease in the consultation. Summary of the invention

[0004] In order to solve the problems of the prior art, the embodiment of the present invention provides a method and system for predicting the results of urology Chinese medicine consultation using a large language model, including:

[0005] On the one hand, a method for predicting the results of urology Chinese medicine consultation using a large language model is provided, the method comprising:

[0006] Acquire disease description data; the disease description data includes at least one of text data and image data;

[0007] Preprocessing the disease description data and obtaining autocorrelation parameters between the disease description data;

[0008] Build a prediction model based on the large language model;

[0009] The prediction model is trained according to the preprocessed disease description data and the autocorrelation parameter to obtain a trained prediction model; the output of the trained prediction model is core keyword data, and the core keyword data is used as reference data for medical consultation and drug recommendation;

[0010] Establishing a self-correction model, wherein the self-correction model is used to correct parameters in the large language model;

[0011] Recording feedback data related to the core keyword data in real time;

[0012] Inputting the feedback data into the self-correction model and outputting an adjustment value;

[0013] According to the adjustment value, the parameters in the large language model are adjusted in real time.

[0014] Optionally, preprocessing the disease description data and obtaining the autocorrelation parameters between the disease description data includes:

[0015] Extracting keywords from the disease description data;

[0016] Classify the keywords logically and structure them;

[0017] According to a preset recognition model, the self-correlation parameters between the keywords are obtained.

[0018] Optionally, constructing a prediction model according to the large language model includes:

[0019] Constructing a basic large language model, wherein the input of the basic large language model is a keyword and the output is a core keyword;

[0020] A basic probability neural network is constructed, wherein the input of the basic probability neural network is the core keyword, and the output is the core keyword data and the probability of the corresponding lesion.

[0021] Optionally, the predictive model is trained according to the preprocessed disease description data and the autocorrelation parameter, and obtaining the trained predictive model includes:

[0022] Setting a first evaluation model corresponding to the basic large language model and a second evaluation model corresponding to the basic probabilistic neural network;

[0023] Training the prediction model according to the preprocessed disease description data and the autocorrelation parameter;

[0024] According to the first evaluation model and the second evaluation model, a completion condition of the prediction model is set.

[0025] Optionally, the establishing of the self-correcting model includes:

[0026] Setting a correction function, the correction function being used to indicate the correlation between the feedback data and the parameters in the large language model;

[0027] A feedback data acquisition model is set up through a large language model, and the feedback data acquisition model is used to obtain the doctor's secondary description and operation based on the core keyword data;

[0028] A self-correction model is established according to the correction function and the feedback data acquisition model, wherein the input of the self-correction model is a correction keyword and the output is an adjustment value.

[0029] Optionally, the real-time recording of feedback data related to the core keyword data includes:

[0030] Obtaining the doctor's secondary description and operation based on the core keyword data;

[0031] The secondary description and operation are preprocessed to obtain correction keywords.

[0032] Optionally, adjusting the parameters in the large language model in real time according to the adjustment value includes:

[0033] converting the secondary descriptions and operations into disease description data;

[0034] The trained prediction model is trained again according to the disease description data.

[0035] Optionally, the method further includes:

[0036] The image data is recognized and converted into text data.

[0037] On the other hand, a system for predicting the results of urology consultation with traditional Chinese medicine using a large language model is provided, the system comprising a client and a processing device, wherein:

[0038] The client is used to obtain disease description data; the disease description data includes at least one of text data and image data;

[0039] The processing device is used to pre-process the disease description data and obtain the autocorrelation parameters between the disease description data;

[0040] The processing device is used to construct a prediction model based on the large language model;

[0041] The processing device is used to train the prediction model according to the preprocessed disease description data and the autocorrelation parameter to obtain a trained prediction model; the output of the trained prediction model is core keyword data, and the core keyword data is used as reference data for medical consultation and drug recommendation;

[0042] The processing device is used to establish a self-correction model, and the self-correction model is used to correct parameters in the large language model;

[0043] The client is used to record feedback data related to the core keyword data in real time;

[0044] The processing device is used to input the feedback data into the self-correction model and output an adjustment value;

[0045] The processing device is used to adjust the parameters in the large language model in real time according to the adjustment value.

[0046] Optionally, the processing device is specifically used for:

[0047] Extracting keywords from the disease description data;

[0048] Classify the keywords logically and structure them;

[0049] According to a preset recognition model, the self-correlation parameters between the keywords are obtained.

[0050] Optionally, the processing device is specifically used for:

[0051] Constructing a basic large language model, wherein the input of the basic large language model is a keyword and the output is a core keyword;

[0052] A basic probability neural network is constructed, wherein the input of the basic probability neural network is the core keyword, and the output is the core keyword data and the probability of the corresponding lesion.

[0053] Optionally, the processing device is specifically used for:

[0054] Setting a first evaluation model corresponding to the basic large language model and a second evaluation model corresponding to the basic probabilistic neural network;

[0055] Training the prediction model according to the preprocessed disease description data and the autocorrelation parameter;

[0056] According to the first evaluation model and the second evaluation model, a completion condition of the prediction model is set.

[0057] Optionally, the processing device is specifically used for:

[0058] Setting a correction function, the correction function being used to indicate the correlation between the feedback data and the parameters in the large language model;

[0059] A feedback data acquisition model is set up through a large language model, and the feedback data acquisition model is used to obtain the doctor's secondary description and operation based on the core keyword data;

[0060] A self-correction model is established according to the correction function and the feedback data acquisition model, wherein the input of the self-correction model is a correction keyword and the output is an adjustment value.

[0061] Optionally, the processing device is specifically used for:

[0062] Obtaining the doctor's secondary description and operation based on the core keyword data;

[0063] The secondary description and operation are preprocessed to obtain correction keywords.

[0064] Optionally, the processing device is specifically used for:

[0065] converting the secondary descriptions and operations into disease description data;

[0066] The trained prediction model is trained again according to the disease description data.

[0067] Optionally, the processing device is specifically used for:

[0068] The image data is recognized and converted into text data.

[0069] The present invention has at least the following beneficial effects:

[0070] 1. Preprocess the disease description data and obtain the autocorrelation parameters between the disease description data; build a prediction model based on the large language model; output the core keyword data used to describe the lesion to predict the specific cause of the disease in the consultation, thereby improving the accuracy;

[0071] 2. By real-time recording of feedback data related to core keyword data; inputting feedback data into the self-correction model and outputting adjustment values; adjusting the parameters in the large language model in real time according to the adjustment values, the continuous use and adjustment based on feedback data further realize the continuous refinement of the prediction model in the specific knowledge field of urology, thereby further realizing the prediction of the specific cause of the consultation and improving accuracy.

[0072] 3. The present invention outputs core keyword data through a prediction model, and uses the above core keyword data as reference data to apply to medical consultation and symptom-related food and medicine recommendations; thereby establishing a more accurate, fast, and high-quality food and medicine prescription recommendation system, which helps urology patients quickly find suitable food and medicine prescriptions and save costs for doctors and patients. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0074] Figure 1 A schematic flow chart of a method for building a perception capability for a robot's long-range tasks provided by an embodiment of the present invention;

[0075] Figure 2A schematic diagram of a system for building a perception capability for a robot's long-range tasks provided by an embodiment of the present invention;

[0076] Figure 3 A schematic diagram of the structure of a perception capability building device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0077] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution in the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiment of the present invention. Obviously, the described embodiment is only a part of the embodiment of the present invention, not all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0078] The method and system for predicting the results of urology TCM consultation using a large language model described in the embodiment of the present invention, after training the large language model (i.e., the prediction model in this article), outputs core keyword data and the correlation between the core keyword data. The above core keyword data and the correlation between the core keyword data are used as reference data to be applied to consultation and symptom-related medicine and food recommendations; thereby establishing a more accurate, fast, and high-quality medicine and food prescription recommendation system, which helps urology patients quickly find suitable medicine and food prescriptions and save costs for doctors and patients.

[0079] The above training process is achieved by fine-tuning the large language model based on urology clinical case data, classic Chinese medicine textbooks and Chinese medicine consultation reports. The embodiment of the present invention takes urology clinical case data as an example to illustrate the technical effect that can be achieved by the method described in the embodiment of the present invention.

[0080] It should be noted that the system for predicting the results of urology TCM consultation using a large language model described in the embodiment of the present invention, in addition to executing the method for predicting the results of urology TCM consultation using a large language model described in the embodiment of the present invention, also includes a series of functions such as data preprocessing, knowledge base management, continuous iterative optimization, large language model API access, large language model fine-tuning, testing and optimization, interface design and development, system testing and optimization, and daily maintenance.

[0081] Reference Figure 1 As shown, a method for predicting the results of urology TCM consultation using a large language model is provided, and the method includes:

[0082] 101. Obtain disease description data;

[0083] Wherein, the disease description data includes at least one of text data and image data;

[0084] The sources of the above disease description data text data include diagnosis reports, consultation data entered by doctors, and disease description data entered by patients (such as input through an online consultation system);

[0085] Among them, some disease description data are image data, such as diagnosis reports, pictures of lesion sites uploaded by doctors, and pictures of lesion sites uploaded by patients.

[0086] 102. Preprocess the disease description data and obtain the autocorrelation parameters between the disease description data;

[0087] 103. Build a prediction model based on the large language model;

[0088] 104. Training the prediction model according to the preprocessed disease description data and the autocorrelation parameter to obtain a trained prediction model;

[0089] The output of the trained prediction model is core keyword data and the correlation between the core keyword data. The core keyword data and the correlation between the core keyword data are used as reference data to be applied to medical consultation and drug recommendation.

[0090] 105. Establish a self-correction model, which is used to correct the parameters in the large language model;

[0091] 106. Record feedback data related to core keyword data in real time;

[0092] 107. Input the feedback data into the self-correction model and output the adjustment value;

[0093] 108. According to the adjustment value, the parameters in the large language model are adjusted in real time.

[0094] Optional, see Figure 2 As shown, the disease description data is preprocessed, and the autocorrelation parameters between the disease description data are obtained, including:

[0095] 201. Extract keywords from disease description data;

[0096] Specifically, for text data, the above process is:

[0097] Keywords in text data are identified through a large language model, and the embodiment of the present invention does not limit the training process of the large language model.

[0098] For image data, according to its source, the above process can be specifically as follows:

[0099] Setting standard keywords corresponding to the recognition results, wherein the standard keywords correspond to the feature images;

[0100] According to the deep image recognition algorithm, the feature image is identified;

[0101] Based on a neural network (such as a probabilistic neural network), the feature image is classified to obtain standard keywords corresponding to the feature image;

[0102] Obtaining description text of the feature image, such as a diagnosis report, or a lesion description text input by a patient or a doctor;

[0103] Identify keywords in the description text through a large language model;

[0104] Setting the identified keywords and standard keywords as keywords of the image data;

[0105] 202. Classify keywords logically and structure them;

[0106] 203. According to a preset recognition model, obtain the self-correlation parameters between keywords.

[0107] The above process can be specifically described as follows:

[0108] Set up a causal model (such as a structural equation model), whose input data is any two keywords and whose output is the autocorrelation parameter (i.e., correlation) between the two keywords;

[0109] Optionally, based on the large language model, building a prediction model includes:

[0110] Build a basic large language model, the input of the basic large language model is keywords, and the output is core keywords;

[0111] Construct a basic probabilistic neural network, the input of which is the core keyword, and the output is the core keyword data and the probability of the corresponding lesion.

[0112] Optionally, the prediction model is trained according to the preprocessed disease description data and the autocorrelation parameter, and the trained prediction model is obtained including:

[0113] Setting a first evaluation model corresponding to the basic large language model and a second evaluation model corresponding to the basic probabilistic neural network;

[0114] The prediction model is trained based on the preprocessed disease description data and the autocorrelation parameters;

[0115] According to the first estimation model and the second estimation model, a completion condition of the prediction model is set.

[0116] Optionally, building a self-correcting model includes:

[0117] Setting a correction function, the correction function is used to indicate the correlation between the feedback data and the parameters in the large language model;

[0118] Through the large language model, a feedback data acquisition model is set up to obtain the doctor's secondary description and operation based on the core keyword data;

[0119] A model is obtained based on the correction function and feedback data, and a self-correction model is established. The input of the self-correction model is the correction keyword, and the output is the adjustment value.

[0120] Optionally, real-time recording of feedback data related to core keyword data includes:

[0121] Obtain secondary descriptions and operations of doctors based on core keyword data;

[0122] Preprocess the secondary description and operations to obtain correction keywords.

[0123] Optionally, adjusting parameters in the large language model in real time according to the adjustment value includes:

[0124] converting secondary descriptions and operations into disease description data;

[0125] The trained prediction model is trained again based on the disease description data.

[0126] Optionally, the method further includes:

[0127] The image data is recognized and converted into text data. The method described in the embodiment of the present invention may also be specifically:

[0128] Step 1: Obtain medical consultation reports and prescription data samples from traditional Chinese medicine hospitals, clean and organize them into symptom and prescription data samples;

[0129] Step 2: The data samples are combined with prescriptions of medicinal and edible homology to construct a data set, where the data set includes a training set and a validation set;

[0130] Step 3: vectorize each data sample in the data set to obtain a data sample vector;

[0131] Step 4: Classify the data sample vectors, build multiple category sample vector libraries, and create indexes;

[0132] Step 5: Select training data samples from each data set and vectorize the symptoms in the training data samples;

[0133] Step 6: Retrieve data sample vectors similar to the symptom vector from the sample vector library;

[0134] Step 7: Use the vector conversion model to convert the retrieved similar data sample vectors and prescription vectors back to data samples and symptoms. Use prompt splicing to fuse the retrieved data samples with the symptoms as additional context information to construct enhanced input.

[0135] Step 8: Fine-tune the large language model using the constructed augmented input and intelligent batching strategy.

[0136] Step 9: Calculate the similarity between the urology symptom vector and each data sample vector in the private knowledge base;

[0137] Step 10: According to the similarity calculation results, select N data sample vectors similar to the symptom vector;

[0138] Step 11: Convert these N data sample vectors back to symptom and prescription data samples;

[0139] Step 12: Finally, use the reasoning ability of the large language model to summarize the prescription data sample into a unique prescription result.

[0140] Reference Figure 3 As shown, a urology Chinese medicine consultation result prediction system using a large language model is provided, the system includes a client and a processing device, wherein:

[0141] The client is used to obtain disease description data; the disease description data includes at least one of text data and image data;

[0142] The processing device is used to pre-process the disease description data and obtain the autocorrelation parameters between the disease description data;

[0143] The processing device is used to build a prediction model based on the large language model;

[0144] The processing device is used to train the prediction model according to the pre-processed disease description data and the self-correlation parameter to obtain the trained prediction model; the output of the trained prediction model is core keyword data, and the core keyword data is used to describe the lesion;

[0145] The processing device is used to establish a self-correction model, and the self-correction model is used to correct parameters in the large language model;

[0146] The client is used to record feedback data related to core keyword data in real time;

[0147] The processing device is used to input the feedback data into the self-correction model and output the adjustment value;

[0148] The processing device is used to adjust the parameters in the large language model in real time according to the adjustment value.

[0149] Optionally, the processing device is specifically used for:

[0150] Extract keywords from disease description data;

[0151] Logically classify keywords and structure them;

[0152] According to the preset recognition model, the self-correlation parameters between keywords are obtained.

[0153] Optionally, the processing device is used:

[0154] Build a basic large language model, the input of the basic large language model is keywords, and the output is core keywords;

[0155] Construct a basic probabilistic neural network, the input of which is the core keyword, and the output is the core keyword data and the probability of the corresponding lesion.

[0156] Optionally, the processing device is used:

[0157] Setting a first evaluation model corresponding to the basic large language model and a second evaluation model corresponding to the basic probabilistic neural network;

[0158] The prediction model is trained based on the preprocessed disease description data and the autocorrelation parameters;

[0159] According to the first estimation model and the second estimation model, a completion condition of the prediction model is set.

[0160] Optionally, the processing device is used:

[0161] Setting a correction function, the correction function is used to indicate the correlation between the feedback data and the parameters in the large language model;

[0162] Through the large language model, a feedback data acquisition model is set up to obtain the doctor's secondary description and operation based on the core keyword data;

[0163] A model is obtained based on the correction function and feedback data, and a self-correction model is established. The input of the self-correction model is the correction keyword, and the output is the adjustment value.

[0164] Optionally, the processing device is used:

[0165] Obtain secondary descriptions and operations of doctors based on core keyword data;

[0166] Preprocess the secondary description and operations to obtain correction keywords.

[0167] Optionally, the processing device is used:

[0168] converting secondary descriptions and operations into disease description data;

[0169] The trained prediction model is trained again based on the disease description data.

[0170] Optionally, the processing device is used:

[0171] Recognize image data and convert it into text data.

[0172] The system described in the embodiment of the present invention may be specifically:

[0173] The selection of the basic large language model is based on the characteristics of the business scenario, which is to recommend Chinese medicine urology prescriptions that are both medicinal and edible, understand the Chinese medicine health consultation report and find the text data that reflects the symptoms. The process includes data preparation, customization of the large language model, model training, and effect evaluation.

[0174] Fine-tuning of the large language model includes collating a specific data set of TCM health consultation reports on urology, and training the model using paired data of task input and output, so that the language model can better master the ability to solve tasks by reading text. Fine-tuning can enable the large language model to produce more accurate and high-quality answers when recommending urology prescriptions of traditional Chinese medicine with the same origin as food, and significantly reduce the delay time when answering specific questions.

[0175] Private knowledge base construction: The collected data is cleaned using artificial intelligence technology to remove redundant, erroneous or irrelevant information. The cleaned data is classified according to a certain logic, and keywords are extracted and structured for subsequent processing. Natural language processing, machine learning and other technologies are used to deeply process and analyze the data to improve the intelligence level of the knowledge base. A fully functional and easy-to-use private knowledge base is constructed to provide strong support for the development of a recommendation system for urology prescriptions of traditional Chinese medicines with the same origin of medicine and food.

[0176] In terms of system architecture design, the application layer demonstrates a high degree of flexibility, integrating multiple interactive channels such as websites, telephone hotlines, and WeChat public accounts, while reserving interfaces to be compatible with more innovative interactive methods that may be introduced in the future.

[0177] The service scheduling layer has built a comprehensive and sophisticated management system, covering everything from intelligent identification and accurate classification of problems to efficient management and maintenance of the knowledge base; from real-time monitoring and feedback of service quality to seamless integration of manual assistance and intelligent transfer mechanisms; to in-depth data analysis and customized report generation, as well as all-round guarantees of system stability and security.

[0178] The resource layer focuses on selecting the best service resources and carefully selects industry-leading service resources to support the fine-tuning and pre-training process of the model. It aims to improve the overall service intelligence level and response efficiency through high-quality data and algorithm optimization.

[0179] At the bottom layer of the deployment architecture, we adopted an integration strategy, deeply integrating private knowledge bases into the system, and introduced a series of top large language models including iFlytek Spark, Tencent Hunyuan, Alibaba YiQianwen and Baidu Wenxin.

[0180] The system deployment mainly includes two parts, the recommendation system and the knowledge base system.

[0181] The specific content of the recommendation system is as follows: When a urology TCM health consultation report is input into the system, the system will first determine the symptom content in the report text. Subsequently, the system will quickly retrieve the most relevant answer texts from its database. Next, with the help of artificial intelligence technology of large language models, the system will generate a concise final answer. At the same time, the recommendation system can also be connected to multiple channels such as websites and WeChat public accounts to form a complete recommendation system for urology prescriptions of traditional Chinese medicine with the same origin of medicine and food.

[0182] The knowledge base system ensures that the knowledge base reflects the latest urology-related prescriptions of medicinal and edible homology by analyzing the updating frequency and timeliness of the content, so as to achieve the optimization effect of updating the existing symptoms to correspond with the new urology prescriptions of medicinal and edible homology and supplementing the missing content.

[0183] In terms of daily maintenance, system administrators can make full use of platform functions and deeply analyze user log data. This process not only involves verifying the accuracy of question classification and ensuring the comprehensiveness of keyword extraction, but also covers the accuracy assessment of speech analysis technology, which is used as a basis for judging whether necessary fine-tuning and optimization of large language models and knowledge bases are needed. Subsequently, a series of systematic testing and iterative optimization measures are implemented to significantly improve the quality of system recommendations and user experience.

[0184] The above specific embodiments may be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0185] The technical features of the above embodiments may be arbitrarily combined (as long as there is no contradiction in the combination of these technical features). To make the description concise, not all possible combinations of the technical features in the above embodiments are described; these embodiments that are not explicitly written should also be considered to be within the scope of this specification.

[0186] The present invention is described in more detail through general description and specific embodiments. It should be noted that, without departing from the concept of the present invention, it is obvious that several variations and improvements can be made to these specific embodiments, which all belong to the protection scope of this application. Therefore, the protection scope of the patent of this application shall be subject to the attached claims.

[0187] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for predicting the results of urology consultation with traditional Chinese medicine using a large language model, characterized in that: The method comprises: Acquire disease description data; the disease description data includes at least one of text data and image data; Preprocessing the disease description data and obtaining autocorrelation parameters between the disease description data; Build a prediction model based on the large language model; The prediction model is trained according to the preprocessed disease description data and the autocorrelation parameter to obtain a trained prediction model; the output of the trained prediction model is core keyword data, and the core keyword data is used as reference data for medical consultation and drug recommendation; Establishing a self-correction model, wherein the self-correction model is used to correct parameters in the large language model; Recording feedback data related to the core keyword data in real time; Inputting the feedback data into the self-correction model and outputting an adjustment value; According to the adjustment value, the parameters in the large language model are adjusted in real time.

2. The method according to claim 1, characterized in that The disease description data is preprocessed, and the autocorrelation parameters between the disease description data are obtained, including: Extracting keywords from the disease description data; Classify the keywords logically and structure them; According to a preset recognition model, the self-correlation parameters between the keywords are obtained.

3. The method according to claim 2, characterized in that The construction of the prediction model according to the large language model includes: Constructing a basic large language model, wherein the input of the basic large language model is a keyword and the output is a core keyword; A basic probability neural network is constructed, wherein the input of the basic probability neural network is the core keyword, and the output is the core keyword data and the probability of the corresponding lesion.

4. The method according to claim 3, characterized in that: The step of training the prediction model according to the preprocessed disease description data and the autocorrelation parameter to obtain the trained prediction model comprises: Setting a first evaluation model corresponding to the basic large language model and a second evaluation model corresponding to the basic probabilistic neural network; Training the prediction model according to the preprocessed disease description data and the autocorrelation parameter; According to the first evaluation model and the second evaluation model, a completion condition of the prediction model is set.

5. The method according to claim 4, characterized in that The self-correction model establishment comprises: Setting a correction function, the correction function being used to indicate the correlation between the feedback data and the parameters in the large language model; A feedback data acquisition model is set up through a large language model, and the feedback data acquisition model is used to obtain the doctor's secondary description and operation based on the core keyword data; A self-correction model is established according to the correction function and the feedback data acquisition model, wherein the input of the self-correction model is a correction keyword and the output is an adjustment value.

6. The method according to claim 5, characterized in that The real-time recording of feedback data related to the core keyword data includes: Obtaining the doctor's secondary description and operation based on the core keyword data; The secondary description and operation are preprocessed to obtain correction keywords.

7. The method according to claim 6, characterized in that The real-time adjustment of the parameters in the large language model according to the adjustment value comprises: converting the secondary descriptions and operations into disease description data; The trained prediction model is trained again according to the disease description data.

8. The method according to claim 1, characterized in that The method further comprises: The image data is recognized and converted into text data.

9. A urology Chinese medicine consultation result prediction system using a large language model, characterized in that: The system comprises a client and a processing device, wherein: The client is used to obtain disease description data; the disease description data includes at least one of text data and image data; The processing device is used to pre-process the disease description data and obtain the autocorrelation parameters between the disease description data; The processing device is used to construct a prediction model based on the large language model; The processing device is used to train the prediction model according to the preprocessed disease description data and the autocorrelation parameter to obtain a trained prediction model; the output of the trained prediction model is core keyword data, and the core keyword data is used as reference data for medical consultation and drug recommendation; The processing device is used to establish a self-correction model, and the self-correction model is used to correct parameters in the large language model; The client is used to record feedback data related to the core keyword data in real time; The processing device is used to input the feedback data into the self-correction model and output an adjustment value; The processing device is used to adjust the parameters in the large language model in real time according to the adjustment value.

10. The system according to claim 9, characterized in that The processing equipment is specifically used for: Extracting keywords from the disease description data; Classify the keywords logically and structure them; According to a preset recognition model, the self-correlation parameters between the keywords are obtained.

Images