Intelligent hospital guide method and device

Abstract

One or more embodiments of the invention provide an intelligent hospital guide method and device, and the method comprises the steps: obtaining a query text for hospital guide consultation, and carrying out the named entity recognition of the query text, so as to recognize a named entity and the type thereof from the query text; if the identified named entity comprises disease features, inputting the disease features into a trained prediction model, predicting a corresponding disease by the prediction model based on the disease features, and determining a department corresponding to the disease based on the graph; nodes in the graph comprise nodes representing doctor seeing features and nodes representing departments; the doctor seeing features represented by the nodes connected with the edges in the graph correspond to the departments represented by the nodes connected with the edges; the doctor-seeing characteristics at least comprise diseases; if the identified named entity comprises the doctor-seeing feature, determining a department corresponding to the doctor-seeing feature based on the graph; the departments are input into the hospital guide large model, and the hospital guide large model conducts reasoning based on the departments to generate answer texts.

Description

Technical Field

[0001] One or more embodiments of the present application relate to the field of artificial intelligence technology, and in particular, to an intelligent medical guidance method and device. Background Art

[0002] In the current medical scenario, each medical institution generally has an information desk at the entrance to assist patients who are confused due to lack of professional medical knowledge. These patients usually have questions about which department to choose for treatment, so they need to consult at the information desk to get the department corresponding to their symptoms, diseases, tests / examination items, etc.

[0003] From the patient's perspective, since there are usually not many service staff at the reception desk, patients first need to wait in line at the reception desk for consultation. Subsequently, patients need to go through a series of processes such as registration, waiting, seeing a doctor, obtaining a prescription from a doctor, and paying fees. The entire medical process is cumbersome and complicated, and often requires waiting in line. This not only wastes a lot of patients' time, but also increases their anxiety and inconvenience. From the perspective of medical institutions, their human resources are limited, and it is easy to have a shortage of human resources.

[0004] In view of the above situation, it is usually expected that some manual services can be replaced by intelligent services, especially services such as medical guidance services that are not closely related to real disease diagnosis. In this way, it can not only simplify the patient's medical process and improve efficiency, but also help medical institutions relieve human resource pressure and optimize service quality, thus helping to improve the overall medical service experience. Therefore, in practical applications, how to provide users with intelligent medical guidance services has become an urgent problem to be solved. Summary of the invention

[0005] One or more embodiments of the present application provide the following technical solutions:

[0006] The present application provides an intelligent diagnosis guidance method, the method comprising:

[0007] Acquire a query text for medical consultation, and perform named entity recognition on the query text to identify named entities from the query text and determine the type of each identified named entity;

[0008] If the identified named entities include disease feature named entities, the disease feature named entities are input into the trained prediction model, and the prediction model predicts the corresponding disease named entities based on the disease feature named entities, and determines the department named entities corresponding to the disease named entities based on the graph; wherein the nodes in the graph include visit feature nodes and department nodes, each visit feature node represents each visit feature named entity, and each department node represents each department named entity; the edges in the graph are used to connect the visit feature nodes and the department nodes, and the visit feature named entities represented by the visit feature nodes connected by each edge correspond to the department named entities represented by the department nodes connected by the edge; the visit feature named entities include at least one subtype of named entities, and the at least one subtype includes diseases;

[0009] If the identified named entities include the medical consultation feature named entity, then based on the graph, determining the department named entity corresponding to the medical consultation feature named entity;

[0010] The department named entity is input into the medical guidance model, and the medical guidance model performs reasoning based on the department named entity to generate an answer text corresponding to the query text.

[0011] The present application also provides an intelligent medical guidance device, the device comprising:

[0012] An acquisition module is used to acquire a query text for medical consultation, and perform named entity recognition on the query text to identify named entities from the query text and determine the type of each identified named entity;

[0013] The first determination module, if the identified named entities include disease feature named entities, inputs the disease feature named entities into the trained prediction model, and the prediction model predicts the corresponding disease named entities based on the disease feature named entities, and determines the department named entities corresponding to the disease named entities based on the graph; wherein the nodes in the graph include visit feature nodes and department nodes, each visit feature node represents each visit feature named entity, and each department node represents each department named entity; the edges in the graph are used to connect the visit feature nodes and the department nodes, and the visit feature named entities represented by the visit feature nodes connected by each edge correspond to the department named entities represented by the department nodes connected by the edge; the visit feature named entities include at least one subtype of named entities, and the at least one subtype includes diseases;

[0014] A second determination module, if the identified named entity includes the medical consultation feature named entity, determines, based on the graph, a department named entity corresponding to the medical consultation feature named entity;

[0015] The reasoning module inputs the department named entity into the medical guidance model, and the medical guidance model performs reasoning based on the department named entity to generate an answer text corresponding to the query text.

[0016] The present application also provides an electronic device, including:

[0017] processor;

[0018] a memory for storing processor-executable instructions;

[0019] The processor implements the steps of any of the above methods by running the executable instructions.

[0020] The present application also provides a computer-readable storage medium having computer instructions stored thereon, which implement the steps of any of the above methods when executed by a processor.

[0021] In the above technical scheme, a graph for medical guidance can be pre-constructed, and the nodes in the graph include nodes representing medical consultation feature named entities and nodes representing department named entities. The medical consultation feature named entities represented by the edge-connected nodes correspond to the department named entities represented by the edge-connected nodes. Subsequently, when a query text for medical guidance consultation is obtained, named entity recognition can be performed on the query text to identify the named entities and their types from the query text. If the identified named entities include disease feature named entities, the disease feature named entities can be first input into the trained prediction model, and the prediction model predicts the corresponding disease named entities based on the disease feature named entities, and then based on the graph, the department named entities corresponding to the disease named entities are determined. If the identified named entities include medical consultation feature named entities, the department named entities corresponding to the medical consultation feature named entities can be directly determined based on the graph, so that the department named entities can be input into the medical guidance model, and the medical guidance model can perform reasoning based on the department named entities to generate answer text corresponding to the query text, and the answer text can be used for medical guidance.

[0022] By adopting the above method, intelligent medical guidance service is realized, which can not only simplify the patient's medical process and improve efficiency, but also help medical institutions relieve human resource pressure and optimize service quality, thus helping to improve the overall medical service experience. In addition, in the process of providing intelligent medical guidance services, the trained prediction model and the constructed graph can be used to determine the corresponding department named entities based on various medical feature named entities in the query text used for medical guidance consultation, and the determined department named entities are integrated into the real input of the medical guidance model, so that when the medical guidance model generates the answer text corresponding to the query text, it can simultaneously consider its inherent generalized knowledge and the specific knowledge reflected by the department named entity, thereby improving the adaptability and response accuracy of the medical guidance model. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The following is a description of the accompanying drawings required for describing the exemplary embodiments, wherein:

[0024] Figure 1 It is a schematic diagram of an intelligent dialogue system shown in an exemplary embodiment of the present application.

[0025] Figure 2 It is a schematic diagram of an intelligent medical guidance process shown in an exemplary embodiment of the present application.

[0026] Figure 3A It is a schematic diagram of a diagram shown in an exemplary embodiment of the present application.

[0027] Figure 3B It is a schematic diagram of another diagram shown in an exemplary embodiment of the present application.

[0028] Figure 4 It is a flow chart of an intelligent diagnosis guidance method shown in an exemplary embodiment of the present application.

[0029] Figure 5 It is a structural schematic diagram of a device shown in an exemplary embodiment of the present application.

[0030] Figure 6 It is a block diagram of an intelligent medical guidance device shown in an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0031] Here, exemplary embodiments will be described in detail, and examples thereof are shown in the accompanying drawings. When the following description relates to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with one or more embodiments of the present application. On the contrary, they are only examples consistent with some aspects of one or more embodiments of the present application.

[0032] It should be noted that in other embodiments, the steps of the corresponding method are not necessarily performed in the order shown and described in this application. In some other embodiments, the steps included in the method may be more or less than those described in this application. In addition, a single step described in this application may be decomposed into multiple steps for description in other embodiments; and multiple steps described in this application may also be combined into a single step for description in other embodiments.

[0033] In the field of medical consultation, the Intelligent Dialogue System has become a key tool to improve efficiency and service quality. The Intelligent Dialogue System provides consulting services to patients by simulating human communication methods, including pre-consultation guidance, disease diagnosis, treatment recommendations, and drug instructions during the consultation process.

[0034] An intelligent dialogue system is an interactive system developed using artificial intelligence technology. It is designed to understand and answer questions raised by users in natural language and generate concise and clear answers. Intelligent dialogue systems are usually based on a large language model, which understands and answers questions raised by users and generates corresponding answers.

[0035] A large language model is a deep learning model trained with a large amount of text data. It can be used to generate natural language text or understand the meaning of natural language text. Large language models can handle a variety of natural language tasks, such as text classification, named entity recognition (NER), dialogue, etc., and are an important path to artificial intelligence.

[0036] In the field of natural language processing, large-scale text data sets are usually referred to as corpuses. Corpuses can contain various types of text data, such as literary works, academic papers, legal documents, news reports, daily conversations, emails, online forum posts, etc. By learning the text data in the corpus, large language models can acquire and understand the laws and patterns of natural language, thereby achieving effective processing and generation of human language.

[0037] Large language models usually use the Transformer architecture, that is, large language models are usually deep learning models based on the Transformer architecture. Deep learning models based on the Transformer architecture are a type of neural network model that uses the Transformer architecture. This model performs well in fields such as natural language processing.

[0038] Transformer is a neural network model used for sequence-to-sequence modeling. Transformer does not need to rely on recursive structures, can parallelize training and reasoning, and speed up model processing. In deep learning models based on the Transformer architecture, a multi-layer Transformer encoder is usually used to extract features from the input sequence, and a Transformer decoder is used to convert the extracted features into an output sequence. At the same time, such models usually also use a self-attention mechanism to capture long-distance dependencies in the input sequence, and use residual connections and regularization methods to accelerate training and improve model performance.

[0039] A pre-trained model is a large language model that is pre-trained on large-scale unlabeled text data. A pre-trained model is a general model that is not designed and optimized for a specific task. In order to adapt the pre-trained model to specific application scenarios and task requirements, fine-tuning is required to improve the performance of the model on specific tasks. The large language model that is finally put into use is usually a model that is further fine-tuned on the basis of the pre-trained model and is a supervised learning model based on labeled text data. Pre-training and fine-tuning are complementary processes. Pre-training enables the model to have a wide range of language understanding capabilities, while fine-tuning makes the model more professional and accurate in specific tasks.

[0040] That is, the training process of a large language model can be divided into two stages: pre-training and fine-tuning. In the pre-training stage, unsupervised learning (e.g., self-supervised learning) can be used to perform pre-training on large-scale, unlabeled text data sets (e.g., online encyclopedias, online articles, books, etc.). Specifically, the missing part or the next word can be predicted based on the context, and statistical laws and language structures such as semantics and syntax can be learned. The prediction loss can be minimized through back-propagation and optimization algorithms (e.g., gradient descent), and model parameters can be iteratively updated to gradually improve the model's ability to understand language. In the fine-tuning stage, you can select corresponding supervised learning tasks (such as text classification, named entity recognition, dialogue systems, etc.) according to specific application scenarios and task requirements, and prepare task-specific text datasets, so that you can use the pre-trained model as the starting point for fine-tuning, and use supervised learning to fine-tune on the task-specific text dataset. Specifically, you can perform the task based on the text dataset, and minimize the loss used to measure the performance of the model when processing specific tasks through back propagation and optimization algorithms (such as gradient descent), iteratively update model parameters, and gradually improve the performance of the model on specific tasks. In practical applications, fine-tuning can flexibly choose supervised learning, unsupervised learning, or semi-supervised learning methods according to specific application scenarios and the type of available data.

[0041] It should be noted that the pre-trained large language model is usually called the base model of the large language model, and the fine-tuned large language model is called the service model of the large language. The language understanding ability learned by the large language model in the pre-training and fine-tuning stages enables the large language model to understand, analyze and integrate text information, perform logical inference, knowledge reasoning or problem solving when faced with complex problems or tasks. This ability is usually called the reasoning ability of the large language model.

[0042] Large language models usually perform specific tasks under the guidance of prompt text (which can be called prompt). Prompt text is an initial text or text fragment provided to the large language model, which is intended to stimulate the model to produce corresponding output. Through the prompt text, you can clearly tell the large language model what task you expect it to perform, such as: answering a question, simulating a conversation, writing an article, translating text, etc. At the same time, the prompt text can provide the large language model with the necessary background information and context, so that the large language model can understand the logic, style, theme or position that should be followed when generating content. In addition, the prompt text can also stimulate the large language model to show its inherent knowledge reserves or specific language capabilities, such as: explaining complex concepts, citing regulations, imitating the writing style of a specific writer, etc.

[0043] In order to improve the adaptability and response accuracy of the intelligent dialogue system, an external knowledge base can be used so that when answering questions raised by users, the intelligent dialogue system no longer relies solely on the limited knowledge obtained by the large language model in the training process by learning static corpus. Instead, it can first perform information retrieval and reasoning in the external knowledge base based on the question to obtain relevant information, and then understand and answer the question based on these relevant information, and generate the corresponding answer. In other words, the external knowledge base can be combined with the large language model, and relevant information can be obtained from the external knowledge base during the model generation process to assist the model in making more accurate and comprehensive answers or decisions. Since the relevant information obtained and the context of the question are taken into account during the model generation process, it can be ensured that the generated content not only meets actual needs, but is also accurate, reliable, coherent, and natural.

[0044] In this application, since the intelligent dialogue system needs to provide users with guidance services, it means that the questions asked by users usually include personal information such as gender and age, medical history, medication history, symptoms, diseases, test / examination items, surgical operations, etc., and the answer the user expects is the department he can go to. Therefore, the relevant information obtained from the external knowledge base should be information related to the department, so as to better assist the large language model in the intelligent dialogue system to generate answers that include the department.

[0045] One or more embodiments of the present application provide a technical solution for realizing intelligent medical guidance. In the technical solution, a graph for medical guidance can be pre-constructed, and the nodes in the graph include nodes representing medical consultation feature named entities and nodes representing department named entities. The medical consultation feature named entities represented by the edge-connected nodes correspond to the department named entities represented by the edge-connected nodes. Subsequently, when a query text for medical guidance consultation is obtained, named entity recognition can be performed on the query text to identify the named entities and their types from the query text. If the identified named entities include disease feature named entities, the disease feature named entities can be first input into a trained prediction model, and the prediction model predicts the corresponding disease named entities based on the disease feature named entities, and then the department named entities corresponding to the disease named entities are determined based on the graph. If the identified named entities include medical consultation feature named entities, the department named entities corresponding to the medical consultation feature named entities can be directly determined based on the graph, so that the department named entities can be input into the medical guidance large model, and the medical guidance large model performs reasoning based on the department named entities to generate answer text corresponding to the query text, and the answer text can be used for medical guidance.

[0046] By adopting the above method, intelligent medical guidance service is realized, which can not only simplify the patient's medical process and improve efficiency, but also help medical institutions relieve human resource pressure and optimize service quality, thus helping to improve the overall medical service experience. In addition, in the process of providing intelligent medical guidance services, the trained prediction model and the constructed graph can be used to determine the corresponding department named entities based on various medical feature named entities in the query text used for medical guidance consultation, and the determined department named entities are integrated into the real input of the medical guidance model, so that when the medical guidance model generates the answer text corresponding to the query text, it can simultaneously consider its inherent generalized knowledge and the specific knowledge reflected by the department named entity, thereby improving the adaptability and response accuracy of the medical guidance model.

[0047] Please refer to Figure 1 , Figure 1 It is a schematic diagram of an intelligent dialogue system shown in an exemplary embodiment of the present application.

[0048] like Figure 1 As shown, the intelligent dialogue system may include a server and at least one client accessing the server through any type of wired or wireless network.

[0049] Among them, the above-mentioned server can correspond to a server including an independent physical host, or it can be a server cluster composed of multiple independent physical hosts; or it can correspond to a virtual server, cloud server, etc. carried by a host cluster.

[0050] The above-mentioned client may correspond to terminal devices such as smart phones, tablet computers, laptops, desktop computers, PCs (Personal Computers), PDAs (Personal Digital Assistants), wearable devices (such as smart glasses, smart watches, etc.), smart car devices or game consoles.

[0051] The user can use the intelligent dialogue service provided by the intelligent dialogue system through the client; the client and the server can implement user-oriented intelligent dialogue services through data interaction between each other.

[0052] For example, the client can output a corresponding user interface to the user, so that the user can perform operations such as inputting query text (which can be called Query or Question) and uploading documents or pictures used to assist in asking questions in the user interface, so as to ask questions to the intelligent dialogue system and use the intelligent dialogue service provided by the intelligent dialogue system. The client can send the query text input by the user to the server, and the server generates a corresponding answer text (which can be called Answer) for the query text, and outputs the answer text to the user, that is, returns the answer text to the client, and the client displays the answer text to the user through the user interface, so that the user can view the corresponding answer generated by the intelligent dialogue system, thereby realizing a user-oriented intelligent dialogue service.

[0053] Specifically, the server may be equipped with a large language model, and the intelligent dialogue system may be based on the large language model, wherein the large language model understands and answers the query text input by the user and generates an answer text corresponding to the query text.

[0054] At this time, the above-mentioned large language model can refer to the service model of the large language model. In practical applications, the constructed large language model can be pre-trained on a large-scale, unlabeled text dataset using an unsupervised learning method to obtain the basic model of the large language model; further, the dialogue task can be used as a supervised learning task during fine-tuning, and a text dataset specific to the dialogue task can be prepared, so that the basic model of the large language model can be used as the starting point for fine-tuning, and a supervised learning method can be used to fine-tune on a text dataset specific to the dialogue task to obtain the service model of the large language model.

[0055] In order to improve the adaptability and response accuracy of the above-mentioned intelligent dialogue system, the above-mentioned server can also be equipped with a knowledge base and an information retrieval component. Among them, the knowledge base is an external knowledge base relative to the large language model carried on the server, that is, the data in the external knowledge base is not the knowledge acquired by the large language model through learning during the training process, but serves as auxiliary data in the reasoning process of the large language model to assist the large language model in generating an answer text corresponding to the query text input by the user. In the reasoning process of the large language model, the information retrieval component can perform information retrieval and reasoning in the external knowledge base based on the above-mentioned query text, so as to assist the large language model in generating an answer text corresponding to the query text input by the user through the acquired relevant information. In addition, the above-mentioned server can also be equipped with a prediction model for simplifying information retrieval and reasoning in the external knowledge base to a certain extent.

[0056] In actual applications, the server may also be equipped with other functional components or functional subsystems such as a prompt generation component. These components or subsystems can work together with the large language model installed on the server to jointly generate an answer text corresponding to the query text input by the user.

[0057] Please refer to Figure 2 , Figure 2 It is a schematic diagram of an intelligent medical guidance process shown in an exemplary embodiment of the present application.

[0058] like Figure 2 As shown, in the above-mentioned intelligent medical guidance process, an external knowledge base for assisting model generation can be pre-built, and the external knowledge base can specifically be a graph.

[0059] Graphs are data stored and managed in a graphical structure. In a graph, data is stored using nodes, edges, and properties. This storage method is very suitable for expressing complex relationships between entities. In a graph, nodes represent entities, such as people, places, events, etc. Each node can have multiple attributes to describe the specific information of the entity. Edges are used to represent the relationship between nodes, such as "know", "belong to", "located in", etc. Edges can also contain attributes to describe the characteristics of the relationship, such as the strength of the relationship, the establishment time, etc. Attributes are data fields attached to nodes or edges to store specific information, such as a person's name, age, or the start date of a relationship.

[0060] For the intelligent medical guidance service, the above diagram can express the correspondence between diseases, test / examination items, surgical operations, etc. and departments, that is, which department to go to when suffering from a certain disease, needing a certain test / examination item, or needing a certain surgical operation. In this application, this information that can be used to determine the department to visit is called medical characteristics. Specifically, in the figure, nodes can be divided into medical consultation feature nodes and department nodes. A medical consultation feature node can represent a medical consultation feature named entity (i.e., the identification text of the medical consultation feature, such as: disease name text), and a department node can represent a department named entity (i.e., the identification text of the department, such as: department name text); an edge is used to connect a medical consultation feature node and a department node, wherein the medical consultation feature named entity represented by the medical consultation feature node corresponds to the department named entity represented by the department node (i.e., when the medical consultation feature is present, the patient needs to go to the department for medical consultation); the medical consultation feature named entity can include at least one subtype of named entity. Since disease is usually the determining factor for the medical consultation department, this at least one subtype can include disease. In addition, it can also include test / inspection items, surgical operations, etc. according to actual conditions and needs.

[0061] It should be noted that since a disease may have multiple disease characteristics, and the same disease characteristic may be caused by different diseases, a machine learning method can be used to obtain a prediction model for predicting the corresponding disease based on the disease characteristics through model training. In this case, the prediction model can first predict the corresponding disease based on the disease characteristics, and then perform information retrieval and reasoning in the above figure based on the disease to determine the corresponding department. Among them, the disease characteristics can not only include symptoms closely related to the disease (for example, frequent urination, urgency, difficulty urinating, urinary pain, low back pain, etc.), but also include information such as gender (for example, male, female), age, etc. that will affect the diagnosis of the disease to a certain extent. For example, men have a prostate, while women do not have a prostate. Therefore, when a male patient has the two symptoms of frequent urination and urgency, he may be diagnosed with prostate hyperplasia, but when a female patient has the two symptoms of frequent urination and urgency, he cannot be diagnosed with prostate hyperplasia; that is, gender will affect the diagnosis of the disease of prostate hyperplasia. In addition, according to actual needs, information such as medical history and medication history can also be used as disease characteristics, and this application does not impose special restrictions on this.

[0062] In order to reduce the amount of training required to obtain the large model for medical guidance, and reduce the difficulty and complexity of obtaining the large model for medical guidance, knowledge distillation (KD) can be used to extract medical guidance-related knowledge from the service model of the large language model that can provide more comprehensive services, and compress the knowledge into the basic model of another large language model, so that the basic model becomes the service model of the large language model that can provide intelligent medical guidance services, and the service model of the large language model obtained at this time can be used as the large model for medical guidance. Specifically, knowledge distillation can be performed on the preset service large model as a teacher model (i.e., the service model of the large language model that can provide more comprehensive services, such as ChatGPT, etc.) to extract medical guidance-related knowledge from the service large model, and compress the knowledge into the large language model as a student model to obtain the large model for medical guidance. When performing knowledge distillation on the service large model, the training data used can be a query text data set for medical guidance consultation, and its label can be the medical guidance answer text corresponding to the query text.

[0063] In the process of intelligent medical guidance, first, the query text used for medical guidance consultation can be obtained, and named entity recognition can be performed on the query text to identify named entities from the query text and determine the types of each identified named entity; if the identified named entities include disease characteristic named entities, the disease characteristic named entities can be first input into the above-mentioned trained prediction model, and the prediction model predicts the corresponding disease named entities based on the disease characteristic named entities, and then determines the department named entities corresponding to the disease named entities based on the above-mentioned graph; if the identified named entities include medical consultation characteristic named entities, the department named entities corresponding to the medical consultation characteristic named entities can be directly determined based on the above-mentioned graph; finally, the department named entity can be input into the above-mentioned medical guidance model, and the medical guidance model can perform reasoning based on the department named entities to generate an answer text corresponding to the query text, and the answer text can be used for medical guidance.

[0064] It should be noted that constructing the above-mentioned graph, training the above-mentioned prediction model, and training the above-mentioned guidance model can be completed in an offline manner, while using the constructed graph, the trained prediction model, and the guidance model obtained by knowledge distillation to perform intelligent guidance is completed in an online manner.

[0065] The following is a detailed description of the intelligent medical guidance method provided by this application from four aspects: graph construction, prediction model training, acquisition of the medical guidance model, and intelligent medical guidance.

[0066] 1. Graph Construction

[0067] First of all, it should be noted that in the constructed graph, nodes can be divided into medical consultation feature nodes and department nodes. A medical consultation feature node can represent a medical consultation feature named entity (i.e., the identification text of the medical consultation feature, such as: disease name text), and a department node can represent a department named entity (i.e., the identification text of the department, such as: department name text); an edge is used to connect a medical consultation feature node and a department node, wherein the medical consultation feature named entity represented by the medical consultation feature node corresponds to the department named entity represented by the department node (i.e., when the medical consultation feature is present, the patient needs to go to the department for medical consultation); the medical consultation feature named entity can include at least one subtype of named entity. Since disease is usually the determining factor for the medical department, this at least one subtype can include disease.

[0068] In some embodiments, the above graph may be constructed according to a method for constructing a knowledge graph. That is, the above graph constructed may be a knowledge graph.

[0069] In some embodiments, according to actual conditions and needs, the at least one subtype may also include one or more of the following: medical examination items; medical examination items; medical surgical operations. Among them, medical examination generally refers to the process of analyzing collected samples (such as blood, urine, tissue, etc.) through a laboratory to determine their composition, properties or status, while medical examination more broadly refers to non-laboratory operations such as physical examinations, imaging examinations (such as X-rays, CT, MRI, etc.), and endoscopy performed by doctors or other medical professionals on patients.

[0070] In the process of constructing the above graph, medical samples can be obtained, and named entity recognition can be performed on each medical sample to identify the corresponding medical visit feature named entities and department named entities from these medical samples. Among them, these medical samples usually record the patient's diagnosed disease, the recommended test / examination items and surgical operations, etc., and also record the department where the patient visited; for example, these medical samples can be open source and desensitized medical records.

[0071] For a medical sample, since a medical sample usually records a patient's diagnosed disease, recommended tests / examination items and surgical operations, etc., it also records the department where the patient visited. The visit feature named entities and department named entities obtained by performing named entity recognition on this medical sample are the corresponding visit feature named entities and department named entities.

[0072] In some embodiments, a large language model can be used to perform convenient named entity recognition. Specifically, each medical sample can be input into the large language model, and the large language model performs named entity recognition on each medical sample to identify corresponding medical visit feature named entities and department named entities from these medical samples.

[0073] At this time, the above-mentioned large language model can refer to the service model of the large language model. In practical applications, the constructed large language model can be pre-trained on a large-scale, unlabeled text dataset using an unsupervised learning method to obtain the basic model of the large language model; further, the named entity recognition task can be used as a supervised learning task during fine-tuning training, and a text dataset specific to the named entity recognition task can be prepared, so that the basic model of the large language model can be used as the starting point for fine-tuning, and a supervised learning method can be used to perform fine-tuning training on a text dataset specific to the named entity recognition task to obtain the service model of the large language model.

[0074] In some embodiments, in order to ensure the consistency of all named entity representations, the named entities identified by named entity recognition can be standardized. For example, "cardiology department", "cardiology department", and "cardiology department room" can be standardized into a standard form, namely "cardiology department".

[0075] When the corresponding medical consultation feature named entities and department named entities are identified, the above graph can be constructed based on the corresponding medical consultation feature named entities and department named entities.

[0076] For example, assuming that the medical sample 1 has identified the medical feature named entity A, the medical feature named entity B, and the department named entity M, and the medical sample 2 has identified the medical feature named entity C and the department named entity N, then it can be known that the medical feature named entity A and the medical feature named entity B correspond to the department named entity M, and the medical feature named entity C corresponds to the department named entity N, so the constructed graph can be as follows Figure 3A As shown, node A represents the medical consultation feature named entity A, node B represents the medical consultation feature named entity B, node C represents the medical consultation feature named entity C, node M represents the department named entity M, node N represents the department named entity N, node A and node M are connected by an edge, node B and node M are connected by an edge, and node C and node N are connected by an edge.

[0077] In some embodiments, in order to make the relationship between different entities more specific and clear, and to facilitate the subsequent use of the above graph to determine the department corresponding to a specific medical visit feature, a corresponding weight can be set for each edge in the graph. Specifically, for an edge used to connect a medical visit feature node and a department node, the weight of this edge can be the association degree of the medical visit feature named entity represented by this medical visit feature node relative to the department named entity represented by this department node.

[0078] In the above case, for the named entities of various subtypes (which may be referred to as target subtypes) in the named entities of the medical visit characteristics identified from the above medical samples, the named entities of the target subtype may be used as training samples, and the department named entities corresponding to the named entities of the target subtype may be used as labels of the training samples. Based on the training samples and their labels, supervised training is performed on the preset prediction model to obtain the trained prediction model. Then, the named entities of the target subtype are input into the trained prediction model, and the prediction model predicts the correlation between the named entities of the target subtype and the named entities of the department (the correlation may be the probability that the prediction model predicts the named entities of the department based on the named entities of the target subtype). Subsequently, the named entities of the medical visit characteristics and the department named entities whose correlation is greater than the preset threshold value may be determined as the corresponding named entities of the medical visit characteristics and the department named entities, and the above graph may be constructed based on the identified named entities of the medical visit characteristics and the department named entities, as well as these corresponding named entities of the medical visit characteristics and the department named entities and the correlation between the two.

[0079] It should be noted that the prediction models used to predict the relevance of named entities of different subtypes relative to named entities of various departments are usually different prediction models.

[0080] For example, assuming that for medical sample 1, medical feature named entity A, medical feature named entity B, and department named entity M are identified, and for medical sample 2, medical feature named entity C and department named entity N are identified, and the above-mentioned prediction model completed through training predicts that the correlation between medical feature named entity A and department named entity M is 0.9, the correlation between medical feature named entity B and department named entity M is 0.78, and the correlation between medical feature named entity C and department named entity N is 0.88. The preset threshold is 0.8. It can be seen that the medical feature named entity A corresponds to the department named entity M and the correlation between the two is 0.9, the medical feature named entity C corresponds to the department named entity N and the correlation between the two is 0.88. Therefore, the constructed graph can be as follows Figure 3B As shown, node A represents the medical consultation feature named entity A, node B represents the medical consultation feature named entity B, node C represents the medical consultation feature named entity C, node M represents the department named entity M, node N represents the department named entity N, node A and node M are connected by an edge with a weight of 0.9, and node C and node N are connected by an edge with a weight of 0.88.

[0081] 2. Training of prediction models

[0082] In the process of training the above prediction model, medical samples can be obtained, and named entity recognition can be performed on each medical sample to identify the corresponding disease feature named entities and disease named entities from these medical samples. Among them, these medical samples usually record the patient's personal information, symptoms, etc., and also record the patient's diagnosed disease; for example, these medical samples can be open source and desensitized medical records.

[0083] For a medical sample, since a medical sample usually records a patient's personal information, symptoms, etc., and also records the disease diagnosed by the patient, the disease feature named entities and disease named entities obtained by named entity recognition for this medical sample are the corresponding disease feature named entities and disease named entities.

[0084] In some embodiments, a large language model can be used to perform convenient named entity recognition. Specifically, each medical sample can be input into the large language model, and the large language model performs named entity recognition on each medical sample to identify corresponding disease feature named entities and disease named entities from these medical samples.

[0085] At this time, the large language model may refer to the service model of the large language model. It should be noted that, in order to ensure the consistency of the identified named entities, the large language model and the large language model used for named entity recognition in the construction process of the above figure may be the same large language model.

[0086] In some embodiments, in order to ensure the consistency of all named entity representations, the named entities identified by named entity recognition can be standardized. For example, "cardiology department", "cardiology department", and "cardiology department room" can be standardized into a standard form, namely "cardiology department".

[0087] When the corresponding disease feature named entities and disease named entities are identified, the disease feature named entities can be used as training samples, and the disease named entities corresponding to the disease feature named entities can be used as labels of the training samples. Based on the training samples and their labels, supervised training is performed on the preset prediction model to obtain the trained prediction model.

[0088] It should be noted that the prediction model used to predict the corresponding department named entity based on the medical consultation feature named entity and the prediction model used to predict the corresponding disease named entity based on the disease feature named entity are usually different prediction models.

[0089] In some embodiments, the above prediction model used to predict the corresponding disease named entity based on the disease feature named entity can specifically be a decision tree model.

[0090] 3. Obtaining the large model of the guidance

[0091] In order to reduce the amount of training required to obtain the large model for medical guidance and reduce the difficulty and complexity of obtaining the large model for medical guidance, knowledge distillation (KD) can be used to extract knowledge related to medical guidance from the service model of the large language model that can provide more comprehensive services, and compress the knowledge into the basic model of another large language model, so that the basic model becomes the service model of the large language model that can provide intelligent medical guidance services. The service model of the large language model obtained at this time can be used as the large model for medical guidance.

[0092] Knowledge distillation is a machine learning technique that is mainly used to reduce the complexity of deep learning models and improve their efficiency. The basic idea of ​​knowledge distillation is to extract knowledge from a complex, large model (called the teacher model) and "compress" it into a smaller, simpler model (called the student model). The essence of knowledge distillation lies in knowledge extraction, knowledge transfer, and knowledge compression; among them, knowledge extraction refers to extracting effective decision-making information from the teacher model, knowledge transfer refers to transferring this information to the student model in a learnable form, and knowledge compression refers to ensuring that the student model can reproduce the behavior of the teacher model on a smaller scale.

[0093] Knowledge distillation mainly includes the following steps: First, train a teacher model with excellent performance but may be more complex. Use the teacher model to predict the training data and obtain soft labels (Soft Labels); where soft labels are usually probability distributions after temperature scaling and can provide richer information than hard labels (Hard Labels). Then train a smaller student model to make its predictions as close as possible to the soft labels of the teacher model. This process may use both hard labels and soft labels as part of the loss function. Finally, evaluate the performance of the student model and make necessary adjustments to optimize its performance.

[0094] That is, we can first define a loss function to measure the difference between the prediction results of the student model and the prediction results of the teacher model. Soft targets are usually used to achieve this, that is, the output of the teacher model is used as the target of the student model, and the cross entropy loss or other similar loss functions are calculated. Subsequently, the prediction results of the teacher model can be used as auxiliary targets, combined with the original targets of the student model for training, and the model parameters of the student model can be updated by iteratively minimizing the loss function.

[0095] Specifically, knowledge distillation can be performed on a preset service model (i.e., a service model of a large language model that can provide relatively comprehensive services, such as ChatGPT, etc.) as a teacher model to extract knowledge related to medical guidance from the service model, and compress the knowledge into a large language model as a student model to obtain the medical guidance model. When performing knowledge distillation on the service model, the training data used can be a query text dataset for medical guidance consultation, and its label can be the medical guidance answer text corresponding to the query text.

[0096] 4. Intelligent medical guidance

[0097] Please refer to Figure 4 , Figure 4 It is a flow chart of an intelligent diagnosis guidance method shown in an exemplary embodiment of the present application.

[0098] like Figure 4 As shown, the above intelligent diagnosis guidance method may include the following steps:

[0099] Step 402: Acquire a query text for medical consultation, and perform named entity recognition on the query text to identify named entities from the query text and determine the type of each identified named entity.

[0100] In this embodiment, a query text for medical consultation may be obtained. When the query text is obtained, named entity recognition may be performed on the query text to identify named entities from the query text and determine the type of each identified named entity.

[0101] In some embodiments, a large language model may be used to perform named entity recognition on the query text. Specifically, the query text may be input into the large language model, and the large language model may perform named entity recognition on the query text.

[0102] At this time, the above-mentioned large language model can refer to the service model of the large language model. It should be noted that in order to ensure the consistency of the identified named entities, the large language model and the large language model used for named entity recognition in the construction of the above-mentioned graph and the training of the above-mentioned prediction model can be the same large language model.

[0103] In some embodiments, in order to ensure the consistency of all named entity representations, the named entities identified by named entity recognition can be standardized. For example, "Department of Cardiology", "Department of Cardiology", and "Department of Cardiology" can be standardized and unified into a standard form, namely, "Department of Cardiology". That is, named entity recognition can be performed on the above query text, and standardized processing can be performed on the identified named entities to determine the standardized named entities as the named entities identified from the query text, and determine the types of each identified named entity.

[0104] Step 404: If the identified named entities include disease characteristic named entities, the disease characteristic named entities are input into the trained prediction model, and the prediction model predicts the corresponding disease named entities based on the disease characteristic named entities, and determines the department named entities corresponding to the disease named entities based on the graph.

[0105] In this embodiment, if it is determined that the identified named entities include disease characteristic named entities based on the types of named entities identified from the above query text, the disease characteristic named entities can first be input into the above-mentioned trained prediction model, and the prediction model predicts the corresponding disease named entities based on the disease characteristic named entities. Then, based on the above-mentioned graph constructed, the department named entity corresponding to the disease named entity can be determined.

[0106] In some embodiments, the disease named entity predicted by the above-mentioned prediction model is usually unique. In this case, the correlation of the disease named entity with respect to each department named entity can be calculated based on the above-mentioned graph, and the department named entity with the largest correlation can be determined as the department named entity corresponding to the disease named entity. Specifically, if the edges in the graph have no weights, a department named entity can be randomly selected from the department named entities represented by all department nodes connected to the disease node representing the disease named entity through edges, as the department named entity with the highest correlation with the disease named entity; if the edges in the graph have weights, the edge with the highest weight can be selected from all the edges used to connect the disease nodes representing the disease named entity, and the department named entity represented by the department node connected by this edge can be used as the department named entity with the highest correlation with the disease named entity.

[0107] Step 406: If the identified named entities include the medical consultation feature named entity, then based on the graph, determine the department named entity corresponding to the medical consultation feature named entity.

[0108] In this embodiment, if it is determined that the identified named entities include the medical consultation feature named entities based on the types of the named entities identified from the above query text, the department named entity corresponding to the medical consultation feature named entity can be directly determined based on the above graph constructed.

[0109] In some embodiments, based on the above-mentioned graph, the correlation between the above-mentioned medical consultation feature named entity and each department named entity can be calculated, and the department named entity with the highest correlation can be determined as the department named entity corresponding to the medical consultation feature named entity. Specifically, if the edges in the graph have no weights, the department named entity represented by the department node with the largest number of connected edges can be selected from the department named entities represented by all department nodes connected to the medical consultation feature nodes representing the medical consultation feature named entity through edges, as the department named entity with the highest correlation with the medical consultation feature named entity; if the edges in the graph have weights, the department named entity represented by the department node with the largest sum of connected edge weights can be selected from the department named entities represented by all department nodes connected to the medical consultation feature nodes representing the medical consultation feature named entity through edges, as the department named entity with the highest correlation with the medical consultation feature named entity.

[0110] For example, assuming that the above query text identifies the medical consultation feature named entity A, the medical consultation feature named entity B, and the medical consultation feature named entity C, where node A representing the medical consultation feature named entity A and node M representing the department entity M are connected by an edge, node B representing the medical consultation feature named entity B and node M are connected by an edge, node C representing the medical consultation feature named entity C and node M are connected by an edge, node C and node N representing the department entity N are connected by an edge, and the edges have no weights. Since the number of edges connected to node M is 3 and the number of edges connected to node N is 1, the department entity M represented by node M can be determined as the department named entity with the highest correlation with the medical consultation feature named entity.

[0111] For another example, suppose that the above query text identifies the medical consultation feature named entity A, medical consultation feature named entity B, and medical consultation feature named entity C, where node A representing medical consultation feature named entity A and node M representing department entity M are connected by an edge with an edge weight of 0.9, node B representing medical consultation feature named entity B and node M are connected by an edge with an edge weight of 0.78, node B and node N representing department entity N are connected by an edge with an edge weight of 0.82, and node C representing medical consultation feature named entity C and node N are connected by an edge with an edge weight of 0.88. Since the sum of the weights of the edges connected to node M is 0.9+0.78=1.68, and the sum of the weights of the edges connected to node N is 0.82+0.88=1.7, the department entity N represented by node N can be determined as the department named entity with the highest correlation with the medical consultation feature named entity.

[0112] Step 408: Input the department named entity into the medical guidance model, and the medical guidance model performs reasoning based on the department named entity to generate an answer text corresponding to the query text.

[0113] In this embodiment, when the above-mentioned department named entity is determined, the department named entity can be input into the above-mentioned medical guidance model, so that the medical guidance model can perform reasoning based on the department named entity to generate an answer text corresponding to the above-mentioned query text (usually referring to the answer text containing the department named entity), and the answer text can be used for medical guidance. For example, based on the department named entity, a prompt text can be constructed to stimulate the medical guidance model to use the department named entity to perform a medical guidance task (which can be regarded as a dialogue task in essence), and the prompt text can be input into the medical guidance model, so that the medical guidance model can perform reasoning based on the department named entity under the guidance of the prompt text to generate an answer text corresponding to the query text.

[0114] In the above technical scheme, a graph for medical guidance can be pre-constructed, and the nodes in the graph include nodes representing medical consultation feature named entities and nodes representing department named entities. The medical consultation feature named entities represented by the edge-connected nodes correspond to the department named entities represented by the edge-connected nodes. Subsequently, when a query text for medical guidance consultation is obtained, named entity recognition can be performed on the query text to identify the named entities and their types from the query text. If the identified named entities include disease feature named entities, the disease feature named entities can be first input into the trained prediction model, and the prediction model predicts the corresponding disease named entities based on the disease feature named entities, and then based on the graph, the department named entities corresponding to the disease named entities are determined. If the identified named entities include medical consultation feature named entities, the department named entities corresponding to the medical consultation feature named entities can be directly determined based on the graph, so that the department named entities can be input into the medical guidance model, and the medical guidance model can perform reasoning based on the department named entities to generate answer text corresponding to the query text, and the answer text can be used for medical guidance.

[0115] By adopting the above method, intelligent medical guidance service is realized, which can not only simplify the patient's medical process and improve efficiency, but also help medical institutions relieve human resource pressure and optimize service quality, thus helping to improve the overall medical service experience. In addition, in the process of providing intelligent medical guidance services, the trained prediction model and the constructed graph can be used to determine the corresponding department named entities based on various medical feature named entities in the query text used for medical guidance consultation, and the determined department named entities are integrated into the real input of the medical guidance model, so that when the medical guidance model generates the answer text corresponding to the query text, it can simultaneously consider its inherent generalized knowledge and the specific knowledge reflected by the department named entity, thereby improving the adaptability and response accuracy of the medical guidance model.

[0116] Corresponding to the aforementioned method embodiments, the present application also provides device embodiments.

[0117] Please refer to Figure 5 , Figure 5It is a structural diagram of a device shown in an exemplary embodiment of the present application. At the hardware level, the device includes a processor 502, an internal bus 504, a network interface 506, a memory 508 and a non-volatile memory 510, and of course may also include other required hardware. One or more embodiments of the present application can be implemented based on software, such as the processor 502 reading the corresponding computer program from the non-volatile memory 510 into the memory 508 and then running it. Of course, in addition to the software implementation, one or more embodiments of the present application do not exclude other implementations, such as logic devices or a combination of software and hardware, etc., that is to say, the execution subject of the following processing flow is not limited to each logic module, but can also be hardware or logic devices.

[0118] Please refer to Figure 6 , Figure 6 It is a block diagram of an intelligent medical guidance device shown in an exemplary embodiment of the present application.

[0119] The above-mentioned intelligent diagnosis guidance device can be applied to Figure 5 The device shown is used to implement the technical solution of the present application. The device includes:

[0120] An acquisition module 602 acquires a query text for medical consultation, and performs named entity recognition on the query text to identify named entities from the query text, and determines the type of each identified named entity;

[0121] The first determination module 604, if the identified named entity includes a disease feature named entity, inputs the disease feature named entity into the trained prediction model, and the prediction model predicts the corresponding disease named entity based on the disease feature named entity, and determines the department named entity corresponding to the disease named entity based on the graph; wherein the nodes in the graph include visit feature nodes and department nodes, each visit feature node represents each visit feature named entity, and each department node represents each department named entity; the edges in the graph are used to connect the visit feature nodes and the department nodes, and the visit feature named entities represented by the visit feature nodes connected by each edge correspond to the department named entities represented by the department nodes connected by the edge; the visit feature named entity includes at least one subtype of named entity, and the at least one subtype includes disease;

[0122] A second determination module 606, if the identified named entity includes the medical consultation feature named entity, determines a department named entity corresponding to the medical consultation feature named entity based on the graph;

[0123] The reasoning module 608 inputs the department named entity into the medical guidance model, and the medical guidance model performs reasoning based on the department named entity to generate an answer text corresponding to the query text.

[0124] In some embodiments, the apparatus further comprises a prediction model training module, configured to:

[0125] Acquire a medical sample, and perform named entity recognition on the medical sample to identify corresponding disease feature named entities and disease named entities from the medical sample;

[0126] The disease characteristic named entity is used as a training sample, and the disease named entity corresponding to the disease characteristic named entity is used as a label of the training sample. Based on the training sample and its label, supervised training is performed on the prediction model.

[0127] In some embodiments, the prediction model is a decision tree model.

[0128] In some embodiments, the apparatus further comprises a graph construction module, configured to:

[0129] Acquire a medical sample, and perform named entity recognition on the medical sample to identify corresponding consultation feature named entities and department named entities from the medical sample;

[0130] The graph is constructed based on the identified corresponding medical consultation feature named entities and department named entities.

[0131] In some embodiments, each edge in the graph is set with a corresponding weight, and the weight of each edge is the correlation between the medical consultation feature named entity represented by the medical consultation feature node connected to each edge and the department named entity represented by the department node connected to the edge;

[0132] The device also includes a correlation calculation module, which is used to:

[0133] Taking various target subtypes of named entities in the identified medical visit feature named entities as training samples, and taking department named entities corresponding to the target subtypes of named entities as labels of the training samples, and performing supervised training on a preset prediction model based on the training samples and their labels;

[0134] Inputting each named entity of the target subtype into the trained prediction model, and using the prediction model to predict the relevance of each named entity of the target subtype relative to each department named entity;

[0135] The step of constructing the graph according to the identified corresponding medical consultation feature named entities and department named entities includes:

[0136] The medical consultation feature named entities and department named entities whose correlation is greater than a preset threshold are determined as corresponding medical consultation feature named entities and department named entities, and the graph is constructed based on the identified medical consultation feature named entities and department named entities, and the corresponding medical consultation feature named entities and department named entities.

[0137] In some embodiments, determining the department named entity corresponding to the named entity based on the graph includes:

[0138] Based on the graph, the relevance of the named entity to each department named entity is calculated, and the department named entity with the greatest relevance is determined as the department named entity corresponding to the named entity.

[0139] In some embodiments, the at least one subtype also includes one or more of the following: medical examination items; medical inspection items; medical surgical operations.

[0140] In some embodiments, the apparatus further comprises a knowledge distillation module, configured to:

[0141] Knowledge distillation is performed on the preset service big model as the teacher model to extract knowledge related to medical guidance from the service big model, and the knowledge is compressed into the big language model as the student model to obtain the medical guidance big model.

[0142] In some embodiments, the performing named entity recognition on the query text to identify named entities from the query text and determining the type of each identified named entity includes:

[0143] Named entity recognition is performed on the query text, and the recognized named entities are standardized to determine the standardized named entities as the named entities recognized from the query text, and the types of the recognized named entities are determined.

[0144] For the device embodiment, it basically corresponds to the method embodiment, so the relevant parts can refer to the partial description of the method embodiment. The device embodiment described above is only schematic, wherein the modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, that is, they may be located in one place, or they may be distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the technical solution of the present application.

[0145] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer, which may be in the form of a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email transceiver, a game console, a tablet computer, a wearable device or a combination of any of these devices.

[0146] In a typical configuration, a computer includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0147] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0148] Computer-readable media include permanent and non-permanent, removable and non-removable media that can store information by any method or technology. Information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, disk storage, quantum memory, graphene-based storage media or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include temporary computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0149] It should be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of further restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0150] The above specific embodiments of the present application are described. Other embodiments are within the scope of the present application. In some cases, the actions or steps recorded in the present application can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0151] The terms used in one or more embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to limit one or more embodiments of the present application. The singular forms of "a", "said" and "the" are also intended to include plural forms, unless the context clearly indicates other meanings. The term "and / or" refers to and includes any or all possible combinations of one or more associated listed items.

[0152] The description of the terms "one embodiment", "some embodiments", "example", "specific example" or "an implementation method" etc. used in one or more embodiments of the present application means that the specific features or characteristics described in conjunction with the embodiment are included in at least one embodiment of the present application. The schematic description of these terms is not necessarily for the same embodiment. Moreover, the specific features or characteristics described can be combined in a suitable manner in one or more embodiments of the present application. In addition, different embodiments and specific features or characteristics in different embodiments can be combined without contradicting each other.

[0153] It should be understood that, although the terms first, second, third, etc. may be used to describe various information in one or more embodiments of the present application, these information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of one or more embodiments of the present application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determination".

[0154] The above description is merely a preferred embodiment of one or more embodiments of the present application and is not intended to limit one or more embodiments of the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of one or more embodiments of the present application shall be included in the scope of protection of one or more embodiments of the present application.

[0155] The user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

Claims

1. An intelligent medical guidance method, the method comprising: Acquire a query text for medical consultation, and perform named entity recognition on the query text to identify named entities from the query text and determine the type of each identified named entity; If the identified named entities include disease feature named entities, the disease feature named entities are input into the trained prediction model, and the prediction model predicts the corresponding disease named entities based on the disease feature named entities, and determines the department named entities corresponding to the disease named entities based on the graph; wherein the nodes in the graph include visit feature nodes and department nodes, each visit feature node represents each visit feature named entity, and each department node represents each department named entity; the edges in the graph are used to connect the visit feature nodes and the department nodes, and the visit feature named entities represented by the visit feature nodes connected by each edge correspond to the department named entities represented by the department nodes connected by the edge; the visit feature named entities include at least one subtype of named entities, and the at least one subtype includes diseases; If the identified named entities include the medical consultation feature named entity, then based on the graph, determining the department named entity corresponding to the medical consultation feature named entity; The department named entity is input into the medical guidance model, and the medical guidance model performs reasoning based on the department named entity to generate an answer text corresponding to the query text.

2. The method according to claim 1, further comprising: Acquire a medical sample, and perform named entity recognition on the medical sample to identify corresponding disease feature named entities and disease named entities from the medical sample; The disease characteristic named entity is used as a training sample, and the disease named entity corresponding to the disease characteristic named entity is used as a label of the training sample. Based on the training sample and its label, supervised training is performed on the prediction model.

3. According to the method of claim 2, the prediction model is a decision tree model.

4. The method according to claim 1, further comprising: Acquire a medical sample, and perform named entity recognition on the medical sample to identify corresponding consultation feature named entities and department named entities from the medical sample; The graph is constructed based on the identified corresponding medical consultation feature named entities and department named entities.

5. According to the method of claim 4, each edge in the graph is set with a corresponding weight, and the weight of each edge is the correlation between the medical consultation feature named entity represented by the medical consultation feature node connected to each edge and the department named entity represented by the department node connected to the edge; The method further comprises: Taking various target subtypes of named entities in the identified medical visit feature named entities as training samples, and taking department named entities corresponding to the target subtypes of named entities as labels of the training samples, and performing supervised training on a preset prediction model based on the training samples and their labels; Inputting each named entity of the target subtype into the trained prediction model, and using the prediction model to predict the relevance of each named entity of the target subtype relative to each department named entity; The step of constructing the graph according to the identified corresponding medical consultation feature named entities and department named entities includes: The medical consultation feature named entities and department named entities whose correlation is greater than a preset threshold are determined as corresponding medical consultation feature named entities and department named entities, and the graph is constructed based on the identified medical consultation feature named entities and department named entities, and the corresponding medical consultation feature named entities and department named entities.

6. The method according to claim 1, wherein determining the department named entity corresponding to the named entity based on the graph comprises: Based on the graph, the relevance of the named entity to each department named entity is calculated, and the department named entity with the greatest relevance is determined as the department named entity corresponding to the named entity.

7. The method according to claim 1, wherein the at least one subtype further comprises one or more of the following: medical examination items; medical inspection items; medical surgical procedures.

8. The method according to claim 1, further comprising: Knowledge distillation is performed on the preset service big model as the teacher model to extract knowledge related to medical guidance from the service big model, and the knowledge is compressed into the big language model as the student model to obtain the medical guidance big model.

9. The method according to claim 1, wherein performing named entity recognition on the query text to identify named entities from the query text and determining the type of each identified named entity comprises: Named entity recognition is performed on the query text, and the recognized named entities are standardized to determine the standardized named entities as the named entities recognized from the query text, and the types of the recognized named entities are determined.

10. An intelligent medical guidance device, comprising: An acquisition module is used to acquire a query text for medical consultation, and perform named entity recognition on the query text to identify named entities from the query text and determine the type of each identified named entity; The first determination module, if the identified named entities include disease feature named entities, inputs the disease feature named entities into the trained prediction model, and the prediction model predicts the corresponding disease named entities based on the disease feature named entities, and determines the department named entities corresponding to the disease named entities based on the graph; wherein the nodes in the graph include visit feature nodes and department nodes, each visit feature node represents each visit feature named entity, and each department node represents each department named entity; the edges in the graph are used to connect the visit feature nodes and the department nodes, and the visit feature named entities represented by the visit feature nodes connected by each edge correspond to the department named entities represented by the department nodes connected by the edge; the visit feature named entities include at least one subtype of named entities, and the at least one subtype includes diseases; A second determination module, if the identified named entity includes the medical consultation feature named entity, determines, based on the graph, a department named entity corresponding to the medical consultation feature named entity; The reasoning module inputs the department named entity into the medical guidance model, and the medical guidance model performs reasoning based on the department named entity to generate an answer text corresponding to the query text.

11. An electronic device, comprising: processor; a memory for storing processor-executable instructions; The processor implements the method according to any one of claims 1 to 9 by running the executable instructions.

12. A computer-readable storage medium having computer instructions stored thereon, wherein the instructions are executed by a processor to implement the method according to any one of claims 1 to 9.

Images