Online health consultation method and system based on intelligent AI and storage medium

Abstract

The invention discloses an online health consultation method and system based on intelligent AI and a storage medium, and the method comprises the steps: obtaining the physical condition description data of a user to generate consultation information, and obtaining a plurality of corresponding question and answer pairs according to a preset large language model through the consultation information; selecting related basic health data from the basic health archive of the user, obtaining abnormal features through feature extraction, and selecting question and answer pairs corresponding to the abnormal features to obtain user corpora to supplement consultation information; generating a health condition representation of the user in a large language model by utilizing the supplemented consultation information and the abnormal features, and accessing a related domain knowledge graph to generate a health condition representation of the user in the knowledge graph; and learning representation is carried out on the fusion representation of the health condition of the user through a multi-layer perceptron, and answer data is selected and output. According to the invention, accurate analysis of the consultation content of the user is realized, more targeted and more accurate consultation feedback in the aspect of medical health is provided for the user, and the health problem of the user is explored in time.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and more specifically, to an online health consultation method, system and storage medium based on intelligent AI. Background Art

[0002] Online health consultation is a new product of Internet plus medical care, which covers various forms of health services such as health knowledge teaching, information medical inquiry, health electronic records, disease risk estimation, online consultation, online prescription, remote diagnosis, online treatment and rehabilitation examination, etc., using the Internet as a carrier and technical tool. Online medical care reveals a new direction for the development of the health industry in the future, and is of great help in solving the contradiction between uneven medical resources and the growing health and medical needs of the public. However, while online health consultation is constantly developing, it also faces many problems, such as the considerable information asymmetry between users and professional doctors.

[0003] With the continuous development and improvement of AI technology, AI-supported online health consultation will play a more important role in the future. Health consultation based on artificial intelligence technology will be able to understand human language and behavior more deeply, provide more accurate and comprehensive health advice, and provide people with more comprehensive and efficient health management services. At present, most online health consultations implemented by AI obtain consultation results by users uploading disease information or consultation information. Due to the differences in users' medical and nursing expertise and expressions, errors such as words not expressing meanings may occur, which will lead to unreliable consultation results. Therefore, how to use large models and knowledge graphs to obtain accurate user expressions, provide users with personalized precision medical services, and improve consultation efficiency is an urgent problem to be solved. Summary of the invention

[0004] In order to solve the above technical problems, the present invention proposes an online health consultation method, system and storage medium based on intelligent AI, with the aim of accurately analyzing the user's consultation content and providing users with more targeted and accurate medical and health consultation feedback.

[0005] The first aspect of the present invention provides an online health consultation method based on intelligent AI, comprising: Obtaining the user's physical condition description data and basic health records, preprocessing the physical condition description data to generate consulting information, and using the consulting information to obtain a number of corresponding question-answer pairs according to a preset large language model; Selecting relevant basic health data from the user's basic health record according to the question-answer pair, performing feature extraction on the relevant basic health data to obtain abnormal features, and further obtaining user corpus corresponding to the question-answer pair based on the abnormal features to supplement the consultation information; The supplemented consultation information and abnormal features are used to generate the user's health status representation in the large language model. In addition, the supplemented consultation information and abnormal features are connected to the knowledge graph in the relevant field to embed the supplemented consultation information and abnormal features, and the user's health status representation in the knowledge graph is generated through graph embedding; The acquired representations of the user's health status are fused, and the fused representations of the user's health status are learned and represented by a multi-layer perceptron, and the answer data for the user's inquiry information is selected and output.

[0006] In this solution, the physical condition description data is preprocessed to generate consulting information, specifically: Obtaining physical condition description data input by a user, performing two-level encoding on the physical condition description data, training a BERT model using a medical health text dataset, and using the trained BERT model to embed the physical condition description data; Obtain the feature vectors of keywords and sentences in the physical condition description data, import the feature vectors into the attention layer, use the attention mechanism to further embed the feature vectors contained in the sentences, update the keyword feature vectors through attention weight allocation, and normalize the updated keyword feature vectors to obtain keyword semantic features; Continue to perform attention operation on the updated keyword feature vector and sentence feature vector, add different weight information to the keyword feature vector and sentence feature vector, and then perform normalization processing to obtain sentence semantic features; The keyword semantic features and sentence semantic features are passed through a Bi-LSTM network to obtain bidirectional semantic features, and two-level aggregation features are obtained after aggregation and activation function processing, and consulting information is generated based on the two-level aggregation features.

[0007] In this solution, the consultation information is used to obtain several corresponding question-answer pairs according to the preset large language model, specifically: Importing the consulting information into a preset large language model, extracting relevant knowledge paragraphs according to the consulting information, generating hypothetical question-answer pairs for the relevant knowledge paragraphs based on a preset prompt template, and using the question-answer pairs to represent the questions involved in the relevant knowledge paragraphs and the corresponding answers; The question-answer pair and the relevant knowledge text are cascaded and embedded into a multidimensional vector space, and similarity comparison is used in the multidimensional vector space to perform redundancy removal on the embedded vectors, and extract health data indicators corresponding to the question-answer pair.

[0008] In this solution, relevant basic health data is selected from the user's basic health record according to the question and answer pair, and features are extracted from the relevant basic health data to obtain abnormal features, specifically: Obtain the health data indicators involved in the question-answer pair, generate search tags using the health data indicators, perform similarity calculation in the user's basic health records using the search tags, obtain basic health data that meets the similarity standard under each health data indicator, and extract the basic health data sequence corresponding to each health data indicator; The improved autoencoder model is used to build an abnormal feature extraction model. The normal data of each health data indicator is feature encoded by introducing an autoencoder model with sparse and denoising functions, and batch normalization is added after the hidden layer of the sparse denoising autoencoder. Batch normalization is used to improve the training speed of the abnormal feature extraction model, and the baseline reconstruction error corresponding to the normal data of each health data indicator is obtained. The Mahalanobis distance is used as a metric function to represent the baseline reconstruction error to obtain the abnormal analysis indicator; The basic health data sequence corresponding to each health data indicator is input into the trained abnormal feature extraction model to obtain the real-time reconstruction error, and determine whether the abnormal analysis indicator of each data sequence is greater than the preset distance threshold. If so, it is regarded as an abnormal feature.

[0009] In this solution, the supplemented consulting information and abnormal features are used to generate the user's health status representation in the large language model. In addition, the knowledge graph of the relevant field is accessed to embed the supplemented consulting information and abnormal features, and the health status representation of the user in the knowledge graph is generated through graph embedding. Specifically: Generate supplementary questions for users based on the question-answer pairs corresponding to abnormal health data, use the user's interactive corpus to supplement the consultation information, generate query representations based on the supplemented consultation information and abnormal features, and perform vector similarity retrieval in the multi-dimensional vector space where the question-answer pairs are cascaded with relevant knowledge segments; The retrieved knowledge vectors are sorted according to similarity, imported into the large language model, and the output of the large language model is aggregated to obtain the user's health status representation in the large language model; Access the knowledge graph in the medical and health-related fields, use the supplemented consulting information and abnormal features to perform initial positioning in the knowledge graph, and obtain neighbor nodes of the consulting information node and the abnormal feature node based on semantic similarity and abnormal health data similarity; Attention encoding is performed on the neighbor nodes, and higher weights are assigned to neighboring nodes with higher similarity. The vector representations of the consulting information nodes and abnormal feature nodes are updated using weight aggregation. Random walks are used to perform graph embedding representation learning according to preset rules to obtain meta-paths containing consulting information nodes and abnormal feature nodes. All meta-paths are aggregated to generate a representation of the user's health status in the knowledge graph.

[0010] In this scheme, a multi-layer perceptron is used to learn and represent the fusion representation of the user's health status, and the answer data is selected for the user's consultation information and output, specifically: Based on the large language model and domain knowledge graph, the health issues and corresponding condition evaluation system involved in the question-answer pairs and meta-paths are obtained, the health status representation is obtained after encoding, and the user's health status fusion representation and health status representation are learned using a multi-layer perceptron; Combined with the activation function operation, the predicted probability of the interactive correlation between the fusion representation of the user's health status and the health status representation is obtained, the health status representation with a predicted probability greater than a preset probability threshold is selected, and the predicted probability is used as weight information; Based on the basic health data of the user, the severity score of the corresponding health problem is evaluated by using the status evaluation system in the selected health status representation, and the severity score of the health problem is weighted by using the weight information to generate the priority of the health problem; The health issues obtained through screening and their corresponding priorities are output as answer data.

[0011] The second aspect of the present invention provides an online health consultation system based on intelligent AI, characterized in that the system includes a consultation information acquisition unit, a health data calling unit, a large language model unit, a knowledge graph unit and a consultation output unit; The consulting information acquisition unit is responsible for acquiring the user's physical condition description data and generating user consulting information after preprocessing; The health data calling unit is responsible for reading the user's basic health records within a preset time from different medical data sources; The large language model unit is responsible for obtaining question-answer pairs that may be involved in the search for consulting information, selecting relevant basic health data using the screened question-answer pairs, obtaining abnormal features using feature extraction analysis, obtaining user corpus based on the abnormal features corresponding to the question-answer pairs to supplement the consulting information, and generating a representation of the user's health status in the large language model; The knowledge graph unit is responsible for embedding the supplemented consulting information and abnormal features using the knowledge graph of the relevant field, and generating the health status representation of the user in the knowledge graph through graph embedding; The consultation output unit uses a multi-layer perceptron to learn and represent the fused representation of the user's health status, and selects answer data for the user's consultation information for output.

[0012] The third aspect of the present invention provides a computer-readable storage medium, which includes an online health consultation method program based on intelligent AI. When the online health consultation method program based on intelligent AI is executed by a processor, the steps of the online health consultation method based on intelligent AI are implemented.

[0013] Compared with the prior art, the present invention has the following beneficial effects: The present invention uses a large language model to accurately analyze user consultation content and basic health data, discover health problems and future health trends, and provide users with more targeted and accurate medical and health consultation feedback; With the help of large language models and related knowledge graphs, more comprehensive correlation relationships can be mined. By integrating the analysis results of multiple dimensions, the efficiency of health consultation can be greatly improved and the accuracy of health problem identification can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solutions in the embodiments or exemplary embodiments of the present invention, the drawings required for use in the embodiments or exemplary descriptions 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 according to the drawings without paying creative work.

[0015] Figure 1 A flow chart of an online health consultation method based on intelligent AI is shown; Figure 2 A flowchart of an embodiment for screening abnormal features in basic health data is shown; Figure 3 A flowchart of an embodiment of obtaining answer data of user consultation information is shown; Figure 4 A block diagram of an online health consultation system based on intelligent AI is shown. DETAILED DESCRIPTION

[0016] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0017] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0018] Figure 1 A flow chart of an online health consultation method based on intelligent AI is shown.

[0019] like Figure 1 As shown, this embodiment provides an online health consultation method based on intelligent AI, including: S102, obtaining the user's physical condition description data and basic health records, preprocessing the physical condition description data to generate consulting information, and using the consulting information to obtain a number of corresponding question-answer pairs according to a preset large language model; S104, selecting relevant basic health data from the basic health record of the user according to the question and answer pair, performing feature extraction on the relevant basic health data to obtain abnormal features, and further obtaining user corpus corresponding to the question and answer pair based on the abnormal features to supplement the consultation information; S106, using the supplemented consulting information and abnormal features to generate a health status representation of the user in the large language model, and also accessing the knowledge graph of the relevant field to embed the supplemented consulting information and abnormal features, and generating a health status representation of the user in the knowledge graph through graph embedding; S108, fusing the acquired representations of the user's health status, learning and representing the fused representations of the user's health status through a multi-layer perceptron, and outputting answer data for user consultation information selection.

[0020] It should be noted that the physical condition description data input by the user is obtained, the physical condition description data is encoded in two levels, the BERT model is trained through the medical health text data set, the physical condition description data is embedded and represented using the trained BERT model, and the feature vectors of the keywords and sentences in the physical condition description data are obtained using the maximum pooling operation. The maximum pooling operation can filter out abnormal information in the medical health text, compress the dimension of the vector to speed up the operation, and prevent the model from overfitting due to feature embedding. The feature vector is imported into the attention layer, and the sentence and the contained feature vector are further embedded using the attention mechanism. The keyword feature vector is updated through the attention weight distribution, and the updated keyword feature vector is normalized to obtain the keyword semantic feature.

[0021] Continue to perform attention operation on the updated keyword feature vector and sentence feature vector, add different weight information to the keyword feature vector and sentence feature vector, and then normalize them. The normalized output contains deeper sentence-level semantic information embedding. The full connection of the keyword feature vector and the sentence feature vector is used as the query vector to calculate the attention weight and obtain the sentence semantic features; the keyword semantic features and sentence semantic features are passed through the Bi-LSTM network to obtain bidirectional semantic features, and the two-level aggregation features are obtained after aggregation and activation function processing, and consulting information is generated based on the two-level aggregation features.

[0022] It should be noted that the consultation information is imported into a preset large language model such as ChatGPT, and the language understanding and generation capabilities of the large language model are used to extract relevant knowledge segments according to the consultation information, generate hypothetical question-answer pairs for the relevant knowledge segments based on the preset prompt template, and use the question-answer pairs to represent the questions and corresponding answers involved in the relevant knowledge segments; for example, if the user takes dizziness as consultation information, the large language model obtains the relevant knowledge segments of "dizziness", divides the corpus of the relevant knowledge segments, and clarifies that bad living habits, hypoglycemia, anemia, electrolyte disorders and other causes can all cause dizziness, and dizziness corresponds to health problems such as hypertension, myocardial ischemia, heart failure, and liver and kidney failure. According to the 5W1H (What, Why, Where, When, Who, How) rule, a prompt template is set to generate questions and their answers. The question-answer pairs and the relevant knowledge segments are cascaded and embedded into a multidimensional vector space, and the embedded vectors are de-redundanted by using similarity comparison in the multidimensional vector space to extract the health data indicators corresponding to the question-answer pairs.

[0023] Figure 2 A flow chart of an embodiment for screening abnormal features in basic health data is shown.

[0024] According to an embodiment of the present invention, relevant basic health data is selected from the basic health file of the user according to the question and answer pair, and features are extracted from the relevant basic health data to obtain abnormal features, specifically: S202, obtaining health data indicators involved in the question-answer pair, generating search tags using the health data indicators, performing similarity calculation in the basic health records of the user through the search tags, obtaining basic health data that meets the similarity standard under each health data indicator, and extracting the basic health data sequence corresponding to each health data indicator; S204, using the improved autoencoder model to build an abnormal feature extraction model, feature encoding the normal data of each health data indicator by introducing an autoencoder model with sparse and denoising functions, and adding batch normalization processing after the hidden layer of the sparse denoising autoencoder; S206, using batch normalization to improve the training speed of the abnormal feature extraction model, obtaining a baseline reconstruction error corresponding to normal data of each health data indicator, and expressing the baseline reconstruction error by using the Mahalanobis distance as a metric function to obtain an abnormal analysis indicator; S208, input the basic health data sequence corresponding to each health data indicator into the trained abnormal feature extraction model, obtain the real-time reconstruction error, and determine whether the abnormal analysis indicator of each data sequence is greater than the preset distance threshold. If so, it is regarded as an abnormal feature.

[0025] It should be noted that the user's health checkup data within a preset time or the examination data uploaded by the user is obtained to build the user's basic health record. The abnormal feature extraction model is constructed using the autoencoder model with added noise reduction and sparse improvement. Noise reduction adds noise to the input data, and the autoencoder is used for encoding and decoding training, so that the model learns the ability to remove noise, reduces the model's error and increases the model's generalization ability. The sparse function is introduced in the autoencoder to limit the nodes of some hidden layers. Only a limited number of nodes in the hidden layer are activated, and its sparse penalty factor It is expressed as: , Represents KL divergence, describing the difference between two distributions. represents the sparse parameter, Represents the hidden layer The average number of activations, Represents the total number of hidden layers. After adding sparse constraints, the model's ability to express data is improved, preventing the hidden layer from learning meaningless features. In addition, the batch normalization algorithm is introduced to improve the convergence speed and learning efficiency of the model, making the calculation of the hidden layer more consistent with the sensitive constraints of the nonlinear activation function.

[0026] It should be noted that, based on the question and answer pairs corresponding to the abnormal health data, supplementary questions for users are generated, and the user's interactive corpus is used to supplement the consulting information. The supplemented consulting information and abnormal features are used to generate a query representation, and vector similarity retrieval is performed in the multi-dimensional vector space where the question and answer pairs are cascaded with related knowledge segments; the retrieved knowledge vectors are obtained and sorted according to similarity, imported into the large language model, and the output of the large language model is aggregated. The output includes the user's possible physical health problems, the severity of the current health problems, symptom analysis of the health problems, etc., so as to obtain the user's health status representation in the large language model.

[0027] Access the knowledge graph in the medical and health-related fields, use the supplemented consulting information and abnormal features to perform initial positioning in the knowledge graph in the field, and obtain the neighbor nodes of the consulting information node and the abnormal feature node according to the semantic similarity and the similarity of abnormal health data; perform attention encoding on the neighbor nodes, assign higher weights to the neighboring nodes with higher similarity, use weight aggregation to update the vector representation of the consulting information node and the abnormal feature node, and use random walk strategies such as DeepWalk and metapath2vec to perform graph embedding representation learning according to preset rules such as path length and answer node type, obtain the meta-path containing the consulting information node and the abnormal feature node, and aggregate all meta-paths to generate the user's health status representation in the knowledge graph. Preferably, when obtaining the user's health status representation in the knowledge graph, adversarial training is introduced, a discriminator module is added, and the meta-path obtained by random walk is imported into the discriminator module; in the discriminator module, the random walk sequence corresponding to the meta-path is encoded using the LSTM network to obtain the path vector representation and score calculation, and its path score is obtained. , , represents the relationship between nodes in the random walk sequence, represents the learnable parameters, Represents a meta-path. Obtain the deviation between the path score and the expected score, and punish the meta-path that is greater than the preset deviation standard according to the deviation. Minimize the deviation between the path score and the expected score to guide the stacking walk for training, so as to prompt the domain knowledge graph to predict the answer in the correct path direction.

[0028] The two health status representations of the user are fused through an adaptive information fusion function to determine the health status representation of the user in the large language model and the representation of the user’s health status in the knowledge graph Proportional information , , Represents learnable weights and uses ratio information to obtain a fusion representation of the user's health status , .

[0029] Figure 3 A flow chart of obtaining answer data for user inquiry information according to an embodiment is shown.

[0030] According to an embodiment of the present invention, a multi-layer perceptron is used to learn and represent the fusion representation of the user's health status, and the answer data is selected for the user's consultation information and output, specifically: S302, obtaining the health problems and corresponding condition evaluation system involved in the question-answer pair and meta-path according to the large language model and the domain knowledge graph, obtaining the health status representation after encoding, and using the multi-layer perceptron to learn the fusion representation of the user's health status and the health status representation; S304, combining activation function operation to obtain the predicted probability of the interactive correlation between the fusion representation of the user's health status and the health status representation, selecting the health status representation whose predicted probability is greater than a preset probability threshold, and using the predicted probability as weight information; S306, based on the basic health data of the user, using the condition evaluation system in the selected health condition representation to evaluate the severity score of the corresponding health problem, and using the weight information to weight the severity score of the health problem to generate the priority of the health problem; S308, outputting the screened health issues and their corresponding priorities as answer data.

[0031] It should be noted that the multi-layer perceptron is used to fusion represent the user's health status. and health status Learning; combining activation function operation to obtain the prediction probability of interactive correlation between the fusion representation of the user's health status and the representation of the health status , expressed as: , Represents the activation function. Obtain the health problems and corresponding condition evaluation systems involved in the question-answer pairs and meta-paths, such as the dizziness problem and the evaluation system for different causes of dizziness, such as the duration of bad living habits such as staying up late, which causes dizziness of different severity levels. According to historical health problem examples, an evaluation system is built to quantify the severity, and the priority is generated in combination with the predicted probability of health problems, so as to attract users to pay attention to their own physical health.

[0032] Figure 4 A block diagram of an online health consultation system based on intelligent AI is shown.

[0033] The second aspect of the present invention provides an online health consultation system 4 based on intelligent AI, characterized in that the system includes a consultation information acquisition unit 401, a health data calling unit 402, a large language model unit 403, a knowledge graph unit 404 and a consultation output unit 405; The consulting information acquisition unit is responsible for acquiring the user's physical condition description data and generating user consulting information after preprocessing; The health data calling unit is responsible for reading the user's basic health records within a preset time from different medical data sources; The large language model unit is responsible for obtaining question-answer pairs that may be involved in the search for consulting information, selecting relevant basic health data using the screened question-answer pairs, obtaining abnormal features using feature extraction analysis, obtaining user corpus based on the abnormal features corresponding to the question-answer pairs to supplement the consulting information, and generating a representation of the user's health status in the large language model; The knowledge graph unit is responsible for embedding the supplemented consulting information and abnormal features using the knowledge graph of the relevant field, and generating the health status representation of the user in the knowledge graph through graph embedding; The consultation output unit uses a multi-layer perceptron to learn and represent the fused representation of the user's health status, and selects answer data for the user's consultation information for output.

[0034] The third aspect of the present invention provides a computer-readable storage medium, which includes an online health consultation method program based on intelligent AI. When the online health consultation method program based on intelligent AI is executed by a processor, the steps of the online health consultation method based on intelligent AI are implemented.

[0035] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0036] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0037] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0038] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: a mobile storage device, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0039] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

[0040] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. An online health consultation method based on intelligent AI, characterized in that: The following steps are involved: Obtaining the user's physical condition description data and basic health records, preprocessing the physical condition description data to generate consulting information, and using the consulting information to obtain a number of corresponding question-answer pairs according to a preset large language model; Selecting relevant basic health data from the user's basic health record according to the question-answer pair, performing feature extraction on the relevant basic health data to obtain abnormal features, and further obtaining user corpus corresponding to the question-answer pair based on the abnormal features to supplement the consultation information; The supplemented consultation information and abnormal features are used to generate the user's health status representation in the large language model. In addition, the supplemented consultation information and abnormal features are connected to the knowledge graph in the relevant field to embed the supplemented consultation information and abnormal features, and the user's health status representation in the knowledge graph is generated through graph embedding; The acquired representations of the user's health status are fused, and the fused representations of the user's health status are learned and represented by a multi-layer perceptron, and the answer data for the user's inquiry information is selected and output.

2. According to claim 1, an online health consultation method based on intelligent AI is characterized in that: The physical condition description data is preprocessed to generate consulting information, specifically: Obtaining physical condition description data input by a user, performing two-level encoding on the physical condition description data, training a BERT model using a medical health text dataset, and using the trained BERT model to embed the physical condition description data; Obtain the feature vectors of keywords and sentences in the physical condition description data, import the feature vectors into the attention layer, use the attention mechanism to further embed the sentences and the feature vectors contained therein, update the keyword feature vectors through attention weight allocation, and normalize the updated keyword feature vectors to obtain the keyword semantic features; Continue to perform attention operation on the updated keyword feature vector and sentence feature vector, add different weight information to the keyword feature vector and sentence feature vector, and then perform normalization processing to obtain sentence semantic features; The keyword semantic features and sentence semantic features are passed through a Bi-LSTM network to obtain bidirectional semantic features, and two-level aggregation features are obtained after aggregation and activation function processing, and consulting information is generated based on the two-level aggregation features.

3. According to claim 1, an online health consultation method based on intelligent AI is characterized in that: The consultation information is used to obtain a number of corresponding question-answer pairs according to a preset large language model, specifically: Importing the consulting information into a preset large language model, extracting relevant knowledge paragraphs according to the consulting information, generating hypothetical question-answer pairs for the relevant knowledge paragraphs based on a preset prompt template, and using the question-answer pairs to represent the questions involved in the relevant knowledge paragraphs and the corresponding answers; The question-answer pair and the relevant knowledge text are cascaded and embedded into a multidimensional vector space, and similarity comparison is used in the multidimensional vector space to perform redundancy removal on the embedded vectors, and extract health data indicators corresponding to the question-answer pair.

4. The online health consultation method based on intelligent AI according to claim 1, characterized in that: According to the question and answer pair, relevant basic health data is selected from the basic health file of the user, and features are extracted from the relevant basic health data to obtain abnormal features, specifically: Obtain the health data indicators involved in the question-answer pair, generate search tags using the health data indicators, perform similarity calculation in the user's basic health records using the search tags, obtain basic health data that meets the similarity standard under each health data indicator, and extract the basic health data sequence corresponding to each health data indicator; The improved autoencoder model is used to build an abnormal feature extraction model. The normal data of each health data indicator is feature encoded by introducing an autoencoder model with sparse and denoising functions, and batch normalization is added after the hidden layer of the sparse denoising autoencoder. Batch normalization is used to improve the training speed of the abnormal feature extraction model, and the baseline reconstruction error corresponding to the normal data of each health data indicator is obtained. The Mahalanobis distance is used as a metric function to represent the baseline reconstruction error to obtain the abnormal analysis indicator; The basic health data sequence corresponding to each health data indicator is input into the trained abnormal feature extraction model to obtain the real-time reconstruction error, and determine whether the abnormal analysis indicator of each data sequence is greater than the preset distance threshold. If so, it is regarded as an abnormal feature.

5. The online health consultation method based on intelligent AI according to claim 1, characterized in that: The supplemented consultation information and abnormal features are used to generate the user's health status representation in the large language model. In addition, the relevant domain knowledge graph is accessed to embed the supplemented consultation information and abnormal features, and the user's health status representation in the knowledge graph is generated through graph embedding. Specifically: Generate supplementary questions for users based on the question-answer pairs corresponding to abnormal health data, use the user's interactive corpus to supplement the consultation information, generate query representations based on the supplemented consultation information and abnormal features, and perform vector similarity retrieval in the multi-dimensional vector space where the question-answer pairs are cascaded with relevant knowledge segments; The retrieved knowledge vectors are sorted according to similarity, imported into the large language model, and the output of the large language model is aggregated to obtain the user's health status representation in the large language model; Access the knowledge graph in the medical and health-related fields, use the supplemented consulting information and abnormal features to perform initial positioning in the knowledge graph, and obtain neighbor nodes of the consulting information node and the abnormal feature node based on semantic similarity and abnormal health data similarity; Attention encoding is performed on the neighbor nodes, and higher weights are assigned to neighboring nodes with higher similarity. The vector representations of the consulting information nodes and abnormal feature nodes are updated using weight aggregation. Random walks are used to perform graph embedding representation learning according to preset rules to obtain meta-paths containing consulting information nodes and abnormal feature nodes. All meta-paths are aggregated to generate a representation of the user's health status in the knowledge graph.

6. The online health consultation method based on intelligent AI according to claim 1, characterized in that: The multi-layer perceptron is used to learn and represent the fusion representation of the user's health status, and the answer data is selected for the user's consultation information and output, specifically: Based on the large language model and domain knowledge graph, the health issues and corresponding condition evaluation system involved in the question-answer pairs and meta-paths are obtained, the health status representation is obtained after encoding, and the user's health status fusion representation and health status representation are learned using a multi-layer perceptron; Combined with the activation function operation, the predicted probability of the interactive correlation between the fusion representation of the user's health status and the health status representation is obtained, the health status representation with a predicted probability greater than a preset probability threshold is selected, and the predicted probability is used as weight information; Based on the basic health data of the user, the severity score of the corresponding health problem is evaluated by using the status evaluation system in the selected health status representation, and the severity score of the health problem is weighted by using the weight information to generate the priority of the health problem; The health issues obtained through screening and their corresponding priorities are output as answer data.

7. An online health consultation system based on intelligent AI, characterized in that: Implementing the intelligent AI-based online health consultation method as described in any one of claims 1 to 6, comprising a consultation information acquisition unit, a health data calling unit, a large language model unit, a knowledge graph unit and a consultation output unit; The consulting information acquisition unit is responsible for acquiring the user's physical condition description data and generating user consulting information after preprocessing; The health data calling unit is responsible for reading the user's basic health records within a preset time from different medical data sources; The large language model unit is responsible for obtaining question-answer pairs that may be involved in the search for consulting information, selecting relevant basic health data using the screened question-answer pairs, obtaining abnormal features using feature extraction analysis, obtaining user corpus based on the abnormal features corresponding to the question-answer pairs to supplement the consulting information, and generating a representation of the user's health status in the large language model; The knowledge graph unit is responsible for embedding the supplemented consulting information and abnormal features using the knowledge graph of the relevant field, and generating the health status representation of the user in the knowledge graph through graph embedding; The consultation output unit uses a multi-layer perceptron to learn and represent the fused representation of the user's health status, and selects answer data for the user's consultation information for output.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes an online health consultation method program based on intelligent AI. When the online health consultation method program based on intelligent AI is executed by a processor, the steps of the online health consultation method based on intelligent AI as described in any one of claims 1 to 6 are implemented.

Images