WO2023029501A1

WO2023029501A1 - Smart interrogation method and apparatus, electronic device, and storage medium

Info

Publication number: WO2023029501A1
Application number: PCT/CN2022/087527
Authority: WO
Inventors: 陈淼
Original assignee: 康键信息技术（深圳）有限公司
Priority date: 2021-08-30
Filing date: 2022-04-19
Publication date: 2023-03-09
Also published as: CN113704428B; CN113704428A

Abstract

Embodiments of the present application belong to the technical field of digital medical treatment, and provide a smart interrogation method and apparatus, an electronic device, and a storage medium. The method comprises: acquiring a basic interrogation text; performing feature extraction on entity features in the basic interrogation text, and obtaining basic interrogation parameters; according to the basic interrogation parameters, screening preset interrogation templates, and obtaining a candidate interrogation template set; according to a preset filtering algorithm, filtering the interrogation templates in the candidate interrogation template set , and obtaining a target interrogation template; according to the basic interrogation parameters, determining a target node on the target interrogation template as well as a directed edge of the target node; according to the target node and the directed edge, constructing an interrogation sequential question set; and, according to the interrogation sequential question set, performing interrogation. In the embodiments of the present application, smart dialogue with a user can be achieved for interrogation, improving interrogation efficiency.

Description

Intelligent consultation method, device, electronic equipment and storage medium

This application claims the priority of the Chinese patent application with the application number 202111007751.2 submitted to the China Patent Office on August 30, 2021, and the invention title is "Intelligent consultation method, device, electronic equipment and storage medium", the entire content of which is incorporated by reference incorporated in this application.

technical field

The present application relates to the field of digital medical technology, and in particular to an intelligent consultation method, device, electronic equipment and storage medium.

Background technique

At present, in the process of user consultation, doctors often need to repeatedly ask similar questions for each user, which affects the consultation time and consultation efficiency. The inventor realizes that in related technologies, machine guidance is often used to conduct simple inquiries to users, which cannot effectively shorten the consultation time and affect the efficiency of consultation. Therefore, how to provide intelligent dialogue and consultation with users, Improving the efficiency of consultation has become a technical problem that needs to be solved urgently.

technical problem

The following is an overview of the topics described in detail in this article. This summary is not intended to limit the scope of the claims.

The main purpose of the embodiments of the present application is to propose an intelligent medical consultation method, device, electronic equipment and storage medium, aiming at realizing intelligent dialogue and consultation with users and improving consultation efficiency.

technical solution

In the first aspect, the embodiment of the present application proposes an intelligent consultation method, which includes:

Obtain basic medical inquiry text;

Carrying out feature extraction on entity features in the basic medical inquiry text to obtain basic medical inquiry parameters;

Screening the preset consultation templates according to the basic consultation parameters to obtain a set of candidate consultation templates;

Filtering the consultation templates in the set of candidate consultation templates according to a preset filtering algorithm to obtain a target consultation template;

determining the target node on the target consultation template and the directed edges of the target node according to the basic consultation parameters;

Constructing an inquiry sequence topic set according to the target node and the directed edge;

Inquiry is performed according to the question set of the order of inquiry.

In the second aspect, the embodiment of the present application proposes an intelligent medical inquiry device, which includes:

The basic medical questioning text acquisition module is used to obtain the basic medical questioning text;

The entity feature extraction module is used to extract the entity features in the basic medical inquiry text to obtain basic medical inquiry parameters;

A screening module, configured to screen preset consultation templates according to the basic consultation parameters to obtain a set of candidate consultation templates;

A target consultation template determination module, configured to filter the consultation templates in the set of candidate consultation templates according to a preset filtering algorithm to obtain a target consultation template;

A target node and directed edge determination module, configured to determine the target node on the target inquiry template and the directed edge of the target node according to the basic inquiry parameters;

An inquiry sequence topic set construction module, configured to construct an inquiry sequence topic set according to the target node and the directed edge;

The consultation module is used to conduct consultation according to the set of questions in the order of consultation.

In the third aspect, the embodiment of the present application provides an electronic device, the electronic device includes a memory, a processor, a program stored in the memory and operable on the processor, and a program for implementing the processor A data bus connecting and communicating with the memory, when the program is executed by the processor, an intelligent consultation method is implemented, wherein the intelligent consultation includes: obtaining basic medical consultation text; The entity features in the medical questioning text are extracted to obtain basic medical questioning parameters; the preset medical questioning templates are screened according to the basic medical questioning parameters to obtain a set of candidate medical questioning templates; the set of candidate medical questioning templates is obtained according to the preset filtering algorithm The consultation templates in the candidate consultation template set are filtered to obtain the target consultation template; the target nodes on the target consultation template and the directed edges of the target nodes are determined according to the basic consultation parameters; The target node and the directed edge construct an inquiry sequence topic set; conduct an inquiry according to the inquiry sequence topic set.

In the fourth aspect, the embodiment of the present application provides a computer-readable storage medium for computer-readable storage, the computer-readable storage medium stores one or more programs, and the one or more programs can be stored by one Or a plurality of processors are executed to realize a method of intelligent medical consultation, wherein the intelligent medical consultation includes: obtaining basic medical consultation text; performing feature extraction on entity features in the basic medical consultation text to obtain basic medical consultation Parameters; filter the preset consultation templates according to the basic consultation parameters to obtain a set of candidate consultation templates; filter the consultation templates in the set of candidate consultation templates according to a preset filtering algorithm to obtain Target medical inquiry template; determine the target node and the directed edge of the target node on the target medical inquiry template according to the basic medical inquiry parameters; construct a question set of question order according to the target node and the directed edge ; Inquiry is performed according to the question set of the order of inquiry.

Beneficial effect

The intelligent medical questioning method, device, electronic equipment and storage medium proposed in this application can obtain basic medical questioning parameters by obtaining basic medical questioning texts and extracting entity features in the basic medical questioning texts. The feature extraction of the basic question text reduces the data space of the basic question text, making it easier to extract the required basic question parameters; and then screens the preset question templates according to the basic question parameters to obtain candidate questions A collection of diagnosis templates, eliminating templates that are less relevant to the current consultation needs. In this way, the consultation templates in the candidate consultation template set can be further filtered according to the preset filtering algorithm to obtain the target consultation template. This method shortens the screening time of consultation templates and improves the The match between the selected consultation template and the current consultation needs. After obtaining the target consultation template, determine the target node and the directed edge of the target node on the target consultation template according to the basic consultation parameters, and then construct the question set of the question order according to the target node and the directed edge, and finally according to the question order Question set for consultation. Through the identification and determination of the target nodes and directed edges of the target consultation template, the consultation process can be further optimized, making the questions in the consultation process more suitable for the current consultation needs, realizing the intelligent and The user dialogue consultation improves the efficiency of consultation.

Additional features and advantages of the application will be set forth in the description which follows, and, in part, will be obvious from the description, or may be learned by practice of the application. The objectives and other advantages of the application will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.

Description of drawings

The accompanying drawings are used to provide a further understanding of the technical solution of the present application, and constitute a part of the specification, and are used together with the embodiments of the present application to explain the technical solution of the present application, and do not constitute a limitation to the technical solution of the present application.

Fig. 1 is a flow chart of the intelligent consultation method provided by the embodiment of the present application;

Fig. 2 is the flowchart of step S102 in Fig. 1;

Fig. 3 is the flowchart of step S104 in Fig. 1;

Fig. 4 is the flowchart of step S304 in Fig. 3;

Fig. 5 is another flowchart of step S304 in Fig. 3;

Fig. 6 is the flowchart of step S105 in Fig. 1;

Fig. 7 is the flowchart of step S107 in Fig. 1;

Fig. 8 is a schematic structural diagram of an intelligent medical inquiry device provided by an embodiment of the present application;

FIG. 9 is a schematic diagram of a hardware structure of an electronic device provided by an embodiment of the present application.

Embodiments of the present invention

In order to make the purpose, technical solution and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present application, not to limit the present application.

It should be noted that although the functional modules are divided in the schematic diagram of the device, and the logical sequence is shown in the flowchart, in some cases, it can be executed in a different order than the module division in the device or the flowchart in the flowchart. steps shown or described. The terms "first", "second" and the like in the specification and claims and the above drawings are used to distinguish similar objects, and not necessarily used to describe a specific sequence or sequence.

Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the technical field to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of the present application, and are not intended to limit the present application.

First, analyze some nouns involved in this application:

Artificial intelligence (AI): It is a new technical science that studies and develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence; artificial intelligence is a branch of computer science. Intelligence attempts to understand the essence of intelligence and produce a new intelligent machine that can respond in a manner similar to human intelligence. Research in this field includes robotics, language recognition, image recognition, natural language processing, and expert systems. Artificial intelligence can simulate the information process of human consciousness and thinking. Artificial intelligence is also a theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

Natural language processing (NLP): NLP uses computers to process, understand and use human languages (such as Chinese, English, etc.). NLP belongs to a branch of artificial intelligence and is an interdisciplinary subject between computer science and linguistics. Known as computational linguistics. Natural language processing includes syntax analysis, semantic analysis, text understanding, etc. Natural language processing is often used in technical fields such as machine translation, handwritten and printed character recognition, speech recognition and text-to-speech conversion, information retrieval, information extraction and filtering, text classification and clustering, public opinion analysis and opinion mining. It involves language processing Related data mining, machine learning, knowledge acquisition, knowledge engineering, artificial intelligence research and linguistics research related to language computing, etc.

Directed graph: A directed graph D refers to an ordered triplet (V(D), A(D), ψD), where ψD) is an association function, which makes each element in A(D) ( called directed edges or arcs) corresponds to an ordered pair of elements (called vertices or points) in V(D).

Information Extraction (Information Extraction, NER): A text processing technology that extracts specified types of factual information such as entities, relationships, and events from natural language texts, and forms structured data output. Information extraction is a technique to extract specific information from text data. Text data is composed of some specific units, such as sentences, paragraphs, and chapters. Text information is composed of some small specific units, such as words, words, phrases, sentences, paragraphs, or combinations of these specific units. . Extracting noun phrases, personal names, and place names in text data is all text information extraction. Of course, the information extracted by text information extraction technology can be various types of information.

Collaborative filtering algorithm: It is a relatively well-known and commonly used recommendation algorithm. It discovers user preferences based on mining historical user behavior data, and predicts products that users may like to recommend, or finds similar users (based on users) or Items (based on items). The realization of the user-based collaborative filtering algorithm mainly needs to solve two problems. One is how to find people who have similar hobbies as you, that is, to calculate the similarity of data.

BERT (Bidirectional Encoder Representations from Transformers): It is a language representation model. BERT uses the Transformer Encoder block for connection, which is a typical two-way encoding model.

Maximum Entropy Markov Model (MEMM): It is used to calculate the conditional probability distribution of each hidden state sequence Y for a given observation sequence X, and it is to establish a joint probability for transition probability and performance probability. The statistics are conditional probabilities, not co-occurrence probabilities. Since MEMM only performs local normalization, MEMM is easy to fall into local optimum.

Conditional random field algorithm (CRF): It is a mathematical algorithm; it combines the characteristics of the maximum entropy model and the hidden Markov model, and is an undirected graph model. It has achieved good results in sequence labeling tasks such as entity recognition. The conditional random field is a typical discriminant model, and its joint probability can be written as the multiplication of several potential functions, the most commonly used of which is the linear chain conditional random field. If x=(x1, x2,...xn) represents the observed input data sequence, y=(y1, y2,...yn) represents a state sequence, given an input sequence, the CRF model of the linear chain Define the joint conditional probability of the state sequence as p(y|x)=exp{} (2-14); Z(x)={} (2-15); where: Z is the probability normalization conditional on the observation sequence x Normalization factor; fj(yi-1, yi, x, i) is an arbitrary feature function.

Long Short-Term Memory (LSTM): It is a time cyclic neural network, which is specially designed to solve the long-term dependence problem of general RNN (cyclic neural network). All RNNs have a A chain form of repeated neural network modules. In standard RNNs, this repeated structural module has only a very simple structure, such as a tanh layer. LSTM is a type of neural network that contains LSTM blocks (blocks) or others. In literature or other materials, LSTM blocks may be described as intelligent network units because they can memorize values for an indefinite length of time. There is a The gate can determine whether the input is important enough to be remembered and whether it can be output.

Bi-directional Long Short-Term Memory (Bi-LSTM): It is a combination of forward LSTM and backward LSTM. It is often used to model contextual information in natural language processing tasks. On the basis of LSTM, Bi-LSTM combines the information of the input sequence in both forward and backward directions. For the output at time t, the forward LSTM layer has the information of time t and the previous time in the input sequence, and the backward LSTM layer has the information of time t and the subsequent time in the input sequence. The output of the forward LSTM layer at time t is denoted as , the output result of the backward LSTM layer at time t is denoted as , and the vectors output by the two LSTM layers can be processed by adding, averaging or connecting.

The embodiments of the present application may acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (Artificial Intelligence (AI) is a theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

Artificial intelligence basic technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation/interaction systems, and mechatronics. Artificial intelligence software technology mainly includes computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning/deep learning.

The embodiment of the present application can conduct intelligent consultation with patients based on medical cloud technology. Among them, Medical Cloud (Medical cloud), refers to the use of "cloud computing" to create a medical and health service cloud platform based on new technologies such as cloud computing, mobile technology, multimedia, 4G communication, big data, and the Internet of Things, combined with medical technology, and realizes the realization of medical resources. sharing and expansion of medical coverage. Due to the combination of cloud computing technology, medical cloud improves The efficiency of medical institutions and the convenience for residents to seek medical treatment. For example, appointment registration, electronic medical records, and medical insurance in hospitals are all products of the combination of cloud computing and the medical field. Medical cloud also has the advantages of data security, information sharing, dynamic expansion, and overall layout.

Based on this, the embodiments of the present application provide an intelligent medical consultation method, device, electronic equipment, and storage medium, which can realize intelligent dialogue and consultation with users, and improve the efficiency of medical consultation. The consultation method provided in the embodiment of the present application can be applied to intelligent diagnosis and treatment and remote consultation.

The medical inquiry method, device, electronic device, and storage medium provided in the embodiments of the present application are specifically described through the following embodiments. First, the intelligent medical inquiry method in the embodiments of the present application is described.

The intelligent consultation method provided in the embodiment of the present application relates to the field of digital medical technology. The intelligent medical inquiry method provided by the embodiment of the present application can be applied to a terminal, can also be applied to a server, and can also be software running on a terminal or a server. In some embodiments, the terminal can be a smart phone, a tablet computer, a notebook computer, a desktop computer, etc.; the server end can be configured as an independent physical server, or can be configured as a server cluster or a distributed system composed of multiple physical servers, or It can be configured as a cloud that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The server; the software can be an application to realize the consultation method, but is not limited to the above forms.

Fig. 1 is an optional flow chart of the intelligent consultation method provided by the embodiment of the present application. The method in Fig. 1 may include but not limited to steps S101 to S107.

Step S101, obtaining the basic medical inquiry text;

Step S102, performing feature extraction on entity features in the basic medical questioning text to obtain basic medical questioning parameters;

Step S103, screening the preset consultation templates according to the basic consultation parameters to obtain a set of candidate consultation templates;

Step S104, according to the preset filtering algorithm, filter the consultation templates in the candidate consultation template set to obtain the target consultation template;

Step S105, determine the target node and the directed edge of the target node on the target consultation template according to the basic consultation parameters;

Step S106, constructing a sequential question set for consultation according to the target node and the directed edge;

Step S107, conduct medical inquiry according to the question set of the order of medical inquiry.

After the above steps S101 to S107, first obtain the patient's basic medical questioning text, wherein the basic medical questioning text can be obtained through the pre-set pre-set pre-guidance system and the basic question and answer with the patient, and the basic medical questioning text is a natural language text. Feature extraction is performed on the entity features in the basic medical questioning text to obtain the basic medical questioning parameters, where the basic medical questioning parameters include age information, gender information, chief complaint information, etc. It should be noted that the chief complaint information is mainly the patient's current physical condition , a description of self-discomfort conditions, etc. By extracting the features of the basic medical questioning text, the data space of the basic medical questioning text is reduced, making it easier to extract the required basic medical questioning parameters. According to the age information, gender information and chief complaint information included in the basic consultation parameters, the preset consultation templates are screened, and the consultation templates in the consultation template library that are less relevant to the current consultation requirements are eliminated to obtain candidate questions. Diagnosis template collection. Specifically, the screening conditions can be determined according to the age range, gender requirements, and diagnostic departments corresponding to the consultation template, and according to the matching relationship between the preset screening conditions and the current patient's age information, gender information, and chief complaint information, the unqualified patients can be eliminated. Related medical questioning templates, the reserved medical questioning templates are used as a set of candidate medical questioning templates, so as to further screen the medical questioning templates according to the set of candidate medical questioning templates. For example, classify the consultation templates according to the preset gender requirements, and select the consultation templates of the same gender according to the gender of the current patient; or, according to the keywords included in the chief complaint information (such as heart, stomach, skin, brain, etc.) etc.) to determine the corresponding diagnostic department, and eliminate the consultation templates that do not belong to the diagnostic department. Furthermore, according to the preset filtering algorithm, the consultation templates in the candidate consultation template set are filtered to obtain the target consultation template. In this process, the similarity between the consultation template and the current patient's appeal can be calculated or The correlation degree is used to determine the target consultation template, and the target consultation template is used in the subsequent consultation process. In order to further optimize the consultation process, after obtaining the target consultation template, determine the target node and the directed edge of the target node on the target consultation template according to the basic consultation parameters, and then construct the consultation order according to the target node and the directed edge The question set, which integrates the questions corresponding to the target node and the questions corresponding to the next target node reached by the directed edge of the target node to form a sequential question set of questions, and finally conduct consultation according to the question set of the order of consultation, for example, the patient It can answer the questions selected in the question set of the questioning sequence. At the same time, the questioning template system can also determine the target node currently staying in the questioning process. By calculating the subsequent directed edges of the target node, the optimal effective point can be determined. To the edge, and then jump to the next target node, and then, the patient answers the question selection answer of the next target node, repeats the process of jumping to the question and answer, and finally completes the interrogation process through multiple rounds of interaction with the patient intelligent question answering. Through the identification and determination of the target nodes and directed edges of the target consultation template, the consultation process can be further optimized, making the questions in the consultation process more suitable for the current consultation needs, realizing the intelligent and The user dialogue consultation improves the efficiency of consultation.

In some medical application scenarios, in a possible implementation manner, the above data is medical data, such as personal health records, prescriptions, examination reports and other data.

In a possible implementation, the above-mentioned basic medical questioning text is a medical text, and the medical text may be a medical electronic record (Electronic Healthcare Record), electronic personal health records, including medical records, electrocardiograms, medical images, and a series of electronic records that are valuable for future reference.

Referring to FIG. 2, in some embodiments, step S102 may include but not limited to include steps S201 to S203:

Step S201, identifying entity features in the basic medical inquiry text;

Step S202, using a pre-trained sequence classifier to classify entity features;

Step S203, performing feature extraction on the entity features after classification processing to obtain basic consultation parameters.

Specifically, when performing feature extraction on the entity features in the basic medical questioning text, first identify the entity features in the basic medical questioning text, and then find the text range that constitutes the medical proper name, and use the pre-trained sequence classifier to identify the text The entity features within the range are classified. When classifying entity features, it is necessary to use a pre-trained sequence classifier to mark entity features, so that these entity parameters can carry preset labels, so as to improve classification efficiency. It should be noted that, in some specific embodiments, the pre-trained sequence classifier can be a maximum entropy Markov model (MEMM model) or a model based on a conditional random field algorithm (CRF) or a two-way long-short-term memory algorithm ( bi-LSTM) model. For example, when constructing a sequence classifier based on the bi-LSTM algorithm, in the model based on the bi-LSTM algorithm, the input word wi and character embedding, through left-to-right long-short-term memory and right-to-left long-short-term memory, make the output The concatenated positions generate a single output layer. The sequence classifier can pass the input entity features directly to the softmax classifier through this output layer, and create a probability distribution on the preset label through the softmax classifier, so as to mark and classify the entity parameters according to the probability distribution, and finally After the classification process, the entity features are extracted to obtain the basic consultation parameters. The feature extraction of the basic consultation text reduces the data space of the basic consultation text, making it easier to extract the required basic consultation parameters. Improve matching efficiency.

Please refer to FIG. 3 , in some embodiments, the basic consultation parameters include chief complaint information, and step S104 may include, but is not limited to, step S301 to step S304:

Step S301, using the pre-trained automatic text generation model to process the chief complaint information and the consultation templates in the candidate consultation template set, and generate the chief complaint text string and the medical consultation template text string;

Step S302, performing encoding processing on the chief complaint text string and the consultation template text string respectively, to obtain the chief complaint text string and the consultation template text string in the coded form;

Step S303, calculating the similarity between the chief complaint text string in coded form and the question template text string in each coded form;

Step S304, according to the size relationship between all the similarities and the size relationship between the similarity and the preset similarity threshold, the target consultation template is obtained.

Specifically, the pre-trained automatic text generation model may be a keyword-based automatic text generation model, and the text automatic generation model may perform different data processing according to the type of input data. Input the main complaint information, keywords or text sentences or fields in the consultation template to the pre-trained text automatic generation model, if the input keywords, text sentences or fields can match the preset reference text, it indicates that the current The input meets the requirements. If the current input is a keyword, select the same sentence set as the input keyword in the basic corpus, and generate a corresponding text string according to this sentence set. If the current input is a text sentence or field, you need to select a candidate sentence in the basic corpus, and determine whether the selected candidate sentence meets the requirements; wherein, the candidate sentence is that the similarity between the basic corpus and the input text sentence or field is greater than the preset Threshold statement, if the selected candidate sentence meets the requirements, the text string will be directly generated according to the candidate sentence; if the selected candidate sentence does not meet the requirements, the sentence supplement will be performed on the candidate sentence, for example, filling in synonyms, or according to the corresponding input information. The candidate sentences are copied and supplemented, and a text string is generated according to the supplemented candidate sentences. In this way, the main complaint information and the medical questioning templates in the candidate medical questioning template set can be processed more conveniently, and the chief complaint text string and the medical questioning template text string are generated. Further, the chief complaint text string and the inquiry template text string are respectively encoded by a preset encoder, which can be a BERT-based encoder, that is, by obtaining the chief complaint information and the inquiry template, and The main complaint information and the consultation template are tokenized, and the BERT token generator is constructed, and the BERT token generator is pre-trained to form a BERT encoder that meets the requirements, so that the BERT encoder can use the preset encoding function to The chief complaint text string and the consultation template text string are converted from the text form into the coded form, and the chief complaint text string in the coded form and the consultation template text string in the coded form are obtained. Furthermore, the similarity between the main complaint text string in the coded form and the question template text string in each coded form is calculated through the collaborative filtering algorithm. It should be noted that the collaborative filtering algorithm may be a Jaccard similarity coefficient method, an included angle cosine method, or a similarity measurement method such as Euclidean distance or Manhattan distance, without limitation. Finally, the target inquiry template is obtained by comparing the size of all similarities and the size of each similarity with the preset similarity threshold. This method shortens the screening time of the consultation template, and also improves the matching between the selected consultation template and the current consultation demand.

Referring to FIG. 4, in some embodiments, step S304 may include but not limited to include steps S401 to S402:

Step S401, according to the size relationship among all the similarities, determine the consultation template with the highest similarity;

Step S402, if the similarity of the medical inquiry template with the highest similarity is greater than or equal to the preset similarity threshold, use the medical inquiry template with the highest similarity as the target medical inquiry template.

Specifically, in order to improve the matching degree between the consultation template and the current consultation needs, the similarity between the chief complaint text string in the coded form and the text string in each coded form of the medical inquiry template is calculated through the collaborative filtering algorithm, and the chief complaint text string in the coded form is compared The size relationship between the similarity with each coded form of the query template text string determines the query template with the highest similarity; further, in order to make the configured query template more accurately match the current query requirements, It is also possible to determine whether to use the highest similarity template for consultation by comparing the similarity of the highest similarity template with the preset similarity threshold. For example, if the highest similarity template If the similarity is greater than or equal to the preset similarity threshold, it indicates that the consultation template with the highest similarity matches the current consultation needs and can meet the consultation requirements, and the consultation template with the highest similarity is used as the target consultation template. This method shortens the screening time of the consultation template, and also improves the matching between the selected consultation template and the current consultation demand.

Referring to FIG. 5, in some embodiments, step S304 may also include but not limited to include steps S501 to S502:

Step S501, according to the size relationship among all the similarities, determine the consultation template with the highest similarity;

Step S502, if the similarity of the question template with the highest similarity is less than the preset similarity threshold, obtain a preset reference question template, and use the preset reference question template as a target question template.

In order to make the consultation process go smoothly, the similarity between the chief complaint text string in the coded form and the consultation template text string in each coded form is calculated through the collaborative filtering algorithm, and the chief complaint text string in the coded form is compared with the consultation template in each coded form. The size relationship between the similarities of template text strings, after determining the highest similarity inquiry template, compare the similarity of the highest similarity inquiry template with the size of the preset similarity threshold, if the highest similarity inquiry template If the similarity of the template is less than the preset similarity threshold, it indicates that the query template with the highest similarity is poorly matched with the current consultation and cannot meet the requirements of the consultation. The reference inquiry template is used as the target inquiry template. Specifically, when it is determined based on gender information, age information, and chief complaint information that there is no matching template (that is, the set of candidate templates is empty) or the template with the highest degree of similarity has a low matching degree with the current consultation needs , you need to take other ways to realize the consultation, for example, it can be to obtain a pre-set reference consultation template, and use the reference consultation template as the target consultation template, that is, construct a corresponding reference consultation sequence question set according to the reference consultation template , so as to make an inquiry according to the reference question set; it can also be prompted to switch to manual questioning when it is determined that there is no matching question template or the matching degree of the question template with the highest similarity and the current questioning demand is low. The consultation mode, through face-to-face consultation between doctors and patients, makes the consultation process go smoothly and improves the quality of consultation.

Referring to FIG. 6, step S105 in some embodiments may include but not limited to steps S601 to S604:

Step S601, according to the basic consultation parameters, determine the target node on the target consultation template;

Step S602, acquiring the script data of each directed edge of the target node;

Step S603, calculating the weight of each directed edge according to the script data;

Step S604, according to the weight of each directed edge, determine the directed edge of the target node.

In some embodiments, since the main complaint information, age information, and gender information have been obtained, the nodes that collect the same information on the target consultation template can be skipped, and the nodes that do not collect question and answer information in the nodes are used as target nodes, and then according to The order of the nodes in the directed graph can determine the directed edge corresponding to each target node. Furthermore, the script data (such as groovy script, etc.) of each directed edge of the target node and the context information of the target node are obtained, wherein the context information includes the option answer selected by the patient in history. Analyze and calculate each directed edge of the target node according to the script data and context information, and obtain the weight of each directed edge. Specifically, use the preset assignment function (such as the add_weighted_edges_from function) to assign an initial weight to each directed edge, modify and adjust the initial weight according to the script data and context information, and use the get_edge_data function to read the modified , compare the modified weight of each directed edge on the target node, and use the directed edge with the highest weight as the optimal directed edge of the target node, and use the optimal directed edge to determine the weight of the next target node position, and then determine the optimal directed edge of the next target node through weight calculation. Repeat this operation in the directed graph corresponding to the current consultation template. Through these target nodes and optimal directed edges, the order of the target nodes can be obtained. According to the order of the target nodes and the node information of each target node, construct A set of questions in the order of questions that meet the needs of the current questioning is produced, and the question set is used to make inquiries. This method can further optimize the problem by identifying and determining the target nodes and directed edges of the target questioning template. The consultation process makes the questions in the consultation process more suitable for the current consultation needs, realizes intelligent dialogue and consultation with users, and improves the efficiency of consultation.

Referring to FIG. 7, in some embodiments, step S107 may include but not limited to include steps S701 to S702:

Step S701, extracting attribute information of the target node;

In step S702, according to the attribute information, the Q&A data fed back by the client at the target node is formatted and assembled to obtain text data; the text data is used for the user to interact with Q&A.

In some embodiments, in order to feed back the consultation data in time, it is also necessary to extract the attribute information of the target node according to actual needs. According to the attribute information of the target node, the format of the Q&A data fed back by the client at the target node is assembled to obtain text data. Display textual data feedback to the user for question-and-answer interaction. For example, the question and option information of the data obtained by the external dynamic call node is packaged into a text node format and displayed to the user, waiting for the user to perform the next round of interaction. Through the question and answer information returned in the previous step of the question template, the user can answer the selected answers to the questions in the question set of the question sequence. At the same time, the question template system can also determine the current target node in the question process. The subsequent directed edge is calculated to determine the optimal directed edge, and then jumps to the next target node, and answers the question selection answer of the next target node, repeating the process of jumping to the question and answer. Finally, through multiple rounds of interaction with the user, the question-and-answer interaction during the consultation process can be completed.

In the embodiment of the present application, by obtaining the basic medical questioning text, the entity features in the basic medical questioning text are extracted to obtain the basic medical questioning parameters. This method can realize the feature extraction of the basic medical questioning text and reduce the size of the basic medical questioning text. The data space makes it easier to extract the required basic consultation parameters; and then filter the preset consultation templates according to the age information, gender information and chief complaint information included in the basic consultation parameters to obtain a set of candidate consultation templates , eliminating the consultation templates that are less relevant to the current consultation needs. In this way, the consultation templates in the candidate consultation template set can be further filtered according to the preset filtering algorithm to obtain the target consultation template. This method shortens the screening time of consultation templates and improves the The match between the selected consultation template and the current consultation needs. After obtaining the target consultation template, determine the target node and the directed edge of the target node on the target consultation template according to the basic consultation parameters, and then construct the question set of the question order according to the target node and the directed edge, and finally according to the question order Question set for consultation. Through the identification and determination of the target nodes and directed edges of the target consultation template, the consultation process can be further optimized, making the questions in the consultation process more suitable for the current consultation needs, realizing the intelligent and The user dialogue consultation improves the efficiency of consultation.

Please refer to Fig. 8, the embodiment of the present application also provides an intelligent medical consultation device, which can realize the above-mentioned intelligent medical consultation method, and the device includes:

A basic medical questioning text acquisition module 801, configured to obtain basic medical questioning texts;

The entity feature extraction module 802 is used to extract the entity features in the basic medical inquiry text to obtain the basic medical inquiry parameters;

The screening module 803 is used to screen the preset consultation templates according to the basic consultation parameters to obtain a set of candidate consultation templates;

The target medical inquiry template determination module 804 is used to filter the medical question templates in the candidate medical question template set according to the preset filtering algorithm to obtain the target medical question template;

Target node and directed edge determination module 805, used to determine the target node and the directed edge of the target node on the target consultation template according to the basic consultation parameters;

An inquiry sequence topic set construction module 806, configured to construct an inquiry sequence topic set according to the target node and the directed edge;

The medical inquiry module 807 is used to conduct medical inquiry according to the sequence of question sets.

In some specific embodiments, when the entity feature extraction module 802 performs feature extraction on the entity features in the basic medical inquiry text to obtain the basic medical inquiry parameters, it is mainly used to identify the entity features in the basic medical inquiry text; The sequence classifier classifies the entity features; extracts the features of the entity features after the classification process, and obtains the basic consultation parameters.

In some specific embodiments, when the target consultation template determination module 804 performs feature extraction on the entity features in the basic consultation text to obtain the basic consultation parameters, it is mainly used to use the pre-trained text automatic generation model to analyze the chief complaint information and The question templates in the candidate question template set are processed to generate the chief complaint text string and the question template text string; the chief complaint text string and the question template text string are respectively encoded to obtain the chief complaint text string and the coded form Inquiry template text string; calculate the similarity between the main complaint text string in the coded form and each coded form of the inquiry template text string; according to the size relationship between all similarities and the size relationship between the similarity and the preset similarity threshold , to get the target consultation template. . Wherein, the target consultation template is obtained according to the size relationship between all the similarities and the size relationship between the similarity and the preset similarity threshold. , the inquiry template with the highest similarity can be determined according to the size relationship between all similarities; if the similarity of the inquiry template with the highest similarity is greater than or equal to the preset similarity threshold, the inquiry template with the highest similarity The template serves as the target consultation template. If the similarity of the question template with the highest similarity is less than the preset similarity threshold, a preset reference question template is obtained, and the preset reference question template is used as a target question template.

In another specific embodiment, when the target node and directed edge determination module 805 determines the target node and the directed edge of the target node on the target consultation template according to the basic consultation parameters, it is mainly used to, according to the basic consultation parameters, Determine the target node on the target consultation template; obtain the script data of each directed edge of the target node; calculate the weight of each directed edge according to the script data; determine the weight of each directed edge according to the weight of each directed edge There is an edge.

In another specific embodiment, the inquiry module 807 is mainly used to extract the attribute information of the target node when conducting an inquiry according to the question set of the order of inquiry; and to assemble the format of the question and answer data fed back by the client at the target node according to the attribute information , get the text data; the text data is used for the user to conduct question-and-answer interactions.

The embodiment of the present application also provides an electronic device, the electronic device includes: a memory, a processor, a program stored in the memory and operable on the processor, and a data bus for realizing connection and communication between the processor and the memory , when the program is executed by the processor, the above-mentioned intelligent interrogation method is realized. The electronic device may be any intelligent terminal including a tablet computer, a vehicle-mounted computer, and the like.

Please refer to FIG. 9. FIG. 9 illustrates a hardware structure of an electronic device in another embodiment. The electronic device includes:

The processor 901 may be implemented by a general-purpose CPU (Central Processing Unit, central processing unit), a microprocessor, an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), or one or more integrated circuits, and is used to execute related programs, so as to realize The technical scheme provided by the embodiment of the present application;

The memory 902 may be implemented in the form of a read-only memory (ReadOnlyMemory, ROM), a static storage device, a dynamic storage device, or a random access memory (RandomAccessMemory, RAM). The memory 902 can store operating systems and other application programs. When implementing the technical solutions provided by the embodiments of this specification through software or firmware, the relevant program codes are stored in the memory 902, and are invoked by the processor 901 to execute an intelligent Inquiry method;

The input/output interface 903 is used to realize information input and output;

The communication interface 904 is used to realize the communication and interaction between the device and other devices, and the communication can be realized through a wired method (such as USB, network cable, etc.), or can be realized through a wireless method (such as a mobile network, WIFI, Bluetooth, etc.); and

Bus 905, which transfers information between various components of the device (such as processor 901, memory 902, input/output interface 903, and communication interface 904);

The processor 901 , the memory 902 , the input/output interface 903 and the communication interface 904 are connected to each other within the device through the bus 805 .

Among them, the intelligent interrogation improved by the embodiment of the present application includes: obtaining the basic interrogation text; performing feature extraction on the entity features in the basic interrogation text to obtain the basic interrogation parameters; Perform screening to obtain a set of candidate consultation templates; filter the consultation templates in the set of candidate consultation templates according to the preset filtering algorithm to obtain the target consultation template; determine the target on the target consultation template according to the basic consultation parameters The directed edge of the node and the target node; according to the target node and the directed edge, construct the question set of the order of consultation; conduct the consultation according to the set of questions of the order of inquiry.

An embodiment of the present application also provides a computer-readable storage medium for computer-readable storage. The computer-readable storage medium may be non-volatile or volatile. The computer-readable storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement an intelligent medical inquiry method, wherein the intelligent medical inquiry includes: obtaining basic medical inquiry text; Feature extraction is performed on the entity features in the basic question text to obtain basic question parameters; the preset question templates are screened according to the basic question parameters to obtain a set of candidate question templates; the candidate question Filter the inquiry templates in the diagnosis template set to obtain the target inquiry template; determine the target node and the directed edge of the target node on the target inquiry template according to the basic inquiry parameters; construct the inquiry according to the target node and the directed edge Sequential topic set; conduct interrogation according to the sequential topic set.

As a non-transitory computer-readable storage medium, memory can be used to store non-transitory software programs and non-transitory computer-executable programs. In addition, the memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid-state storage devices. In some embodiments, the memory optionally includes memory located remotely from the processor, and these remote memories may be connected to the processor via a network. Examples of the aforementioned networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The embodiments described in the embodiments of the present application are to illustrate the technical solutions of the embodiments of the present application more clearly, and do not constitute a limitation to the technical solutions provided by the embodiments of the present application. Those skilled in the art know that with the evolution of technology and new For the emergence of application scenarios, the technical solutions provided by the embodiments of the present application are also applicable to similar technical problems.

Those skilled in the art can understand that the technical solutions shown in Figures 1-7 do not constitute a limitation to the embodiments of the present application, and may include more or fewer steps than those shown in the illustrations, or combine certain steps, or be different A step of.

The device embodiments described above are only illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place, or may be distributed to multiple network units. Part or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

Those of ordinary skill in the art can understand that all or some of the steps in the methods disclosed above, the functional modules/units in the system, and the device can be implemented as software, firmware, hardware, and an appropriate combination thereof.

In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, each unit may exist separately physically, or two or more units may be integrated into one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

If the integrated unit is realized in the form of a software function unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or part of the contribution to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium , including multiple instructions to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the method in each embodiment of the present application. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM for short), random access memory (Random Access Memory, RAM for short), magnetic disk or optical disk, etc., which can store programs. medium.

The preferred embodiments of the embodiments of the present application have been described above with reference to the accompanying drawings, which does not limit the scope of rights of the embodiments of the present application. Any modifications, equivalent replacements and improvements made by those skilled in the art without departing from the scope and essence of the embodiments of the present application shall fall within the scope of rights of the embodiments of the present application.

Claims

A kind of intelligent interrogation method, wherein, described method comprises:

Obtain basic medical inquiry text;

Carrying out feature extraction on entity features in the basic medical inquiry text to obtain basic medical inquiry parameters;

Screening the preset consultation templates according to the basic consultation parameters to obtain a set of candidate consultation templates;

Filtering the consultation templates in the set of candidate consultation templates according to a preset filtering algorithm to obtain a target consultation template;

determining the target node on the target consultation template and the directed edges of the target node according to the basic consultation parameters;

Constructing an inquiry sequence topic set according to the target node and the directed edge;

Inquiry is performed according to the question set of the order of inquiry.
The intelligent medical inquiry method according to claim 1, wherein the step of performing feature extraction on entity features in the basic medical questioning text to obtain basic medical questioning parameters includes:

Identifying entity features in the basic medical questioning text;

Classifying the entity features by using a pre-trained sequence classifier;

Feature extraction is performed on the entity features after classification processing to obtain basic consultation parameters.
The intelligent medical inquiry method according to claim 1, wherein the basic medical inquiry parameters include chief complaint information, and the medical inquiry templates in the candidate medical inquiry template set are filtered according to a preset filtering algorithm to obtain The steps of the target interview template, including:

Using a pre-trained automatic text generation model to process the chief complaint information and the medical questioning templates in the candidate medical questioning template set to generate chief complaint text strings and medical questioning template text strings;

Carry out coding processing to described chief complaint text string and described medical inquiry template text string respectively, obtain the chief complaint text string of coded form and the medical inquiry template text string of coded form;

Calculate the similarity between the main complaint text string in the coded form and each of the question template text strings in the coded form;

According to the magnitude relationship between all the similarities and the magnitude relationship between the similarity and a preset similarity threshold, a target consultation template is obtained.
The intelligent medical inquiry method according to claim 3, wherein, the step of obtaining the target medical inquiry template according to the size relationship between all the similarities and the size relationship between the similarity and the preset similarity threshold ,include:

According to the size relationship among all the similarities, determine the inquiry template with the highest similarity;

If the similarity of the question template with the highest similarity is greater than or equal to a preset similarity threshold, the question template with the highest similarity is used as the target question template.
The intelligent medical inquiry method according to claim 3, wherein, the step of obtaining the target medical inquiry template according to the size relationship between all the similarities and the size relationship between the similarity and the preset similarity threshold ,Also includes:

According to the size relationship among all the similarities, determine the inquiry template with the highest similarity;

If the similarity of the query template with the highest similarity is less than the preset similarity threshold, a preset reference query template is obtained, and the preset reference query template is used as a target query template.
According to the intelligent medical consultation method according to any one of claims 1 to 5, wherein the step of determining the target node on the target medical consultation template and the directed edge of the target node by the basic medical consultation parameters comprises:

determining a target node on the target medical inquiry template according to the basic medical inquiry parameters;

Obtain the script data of each directed edge of the target node;

Calculate the weight of each directed edge according to the script data;

Determine the directed edge of the target node according to the weight of each directed edge.
The intelligent medical inquiry method according to any one of claims 1 to 5, wherein the step of conducting medical inquiry according to the question set of the order of medical inquiry includes:

extracting attribute information of the target node;

According to the attribute information, the question and answer data fed back by the user terminal at the target node is formatted and assembled to obtain text data; the text data is used for the user to perform question and answer interaction.
An intelligent medical interrogation device, wherein the device includes:

The basic medical questioning text acquisition module is used to obtain the basic medical questioning text;

The entity feature extraction module is used to extract the entity features in the basic medical inquiry text to obtain basic medical inquiry parameters;

A screening module, configured to screen preset consultation templates according to the basic consultation parameters to obtain a set of candidate consultation templates;

A target consultation template determination module, configured to filter the consultation templates in the set of candidate consultation templates according to a preset filtering algorithm to obtain a target consultation template;

A target node and directed edge determination module, configured to determine the target node on the target inquiry template and the directed edge of the target node according to the basic inquiry parameters;

An inquiry sequence topic set construction module, configured to construct an inquiry sequence topic set according to the target node and the directed edge;

The consultation module is used to conduct consultation according to the set of questions in the order of consultation.
An electronic device, wherein the electronic device includes a memory, a processor, a program stored on the memory and operable on the processor, and a program for realizing the connection between the processor and the memory A data bus for communication, when the program is executed by the processor, an intelligent medical inquiry method is implemented, wherein the intelligent medical inquiry method includes:

Obtain basic medical inquiry text;

Carrying out feature extraction on entity features in the basic medical inquiry text to obtain basic medical inquiry parameters;

Screening the preset consultation templates according to the basic consultation parameters to obtain a set of candidate consultation templates;

Filtering the consultation templates in the set of candidate consultation templates according to a preset filtering algorithm to obtain a target consultation template;

determining the target node on the target consultation template and the directed edges of the target node according to the basic consultation parameters;

Constructing an inquiry sequence topic set according to the target node and the directed edge;

Inquiry is performed according to the question set of the order of inquiry.
The electronic device according to claim 9, wherein the step of performing feature extraction on entity features in the basic medical questioning text to obtain basic medical questioning parameters includes:

Identifying entity features in the basic medical questioning text;

Classifying the entity features by using a pre-trained sequence classifier;

Feature extraction is performed on the entity features after classification processing to obtain basic consultation parameters.
The electronic device according to claim 9, wherein the basic consultation parameters include chief complaint information, and the consultation templates in the set of candidate consultation templates are filtered according to a preset filtering algorithm to obtain the target question Steps to diagnose the template, including:

Using a pre-trained automatic text generation model to process the chief complaint information and the medical questioning templates in the candidate medical questioning template set to generate chief complaint text strings and medical questioning template text strings;

Carry out coding processing to described chief complaint text string and described medical inquiry template text string respectively, obtain the chief complaint text string of coded form and the medical inquiry template text string of coded form;

Calculate the similarity between the main complaint text string in the coded form and each of the question template text strings in the coded form;

According to the magnitude relationship between all the similarities and the magnitude relationship between the similarity and a preset similarity threshold, a target consultation template is obtained.
The electronic device according to claim 11, wherein the step of obtaining the target consultation template according to the size relationship between all the similarities and the size relationship between the similarity and a preset similarity threshold includes :

According to the size relationship among all the similarities, determine the inquiry template with the highest similarity;

If the similarity of the question template with the highest similarity is greater than or equal to a preset similarity threshold, the question template with the highest similarity is used as the target question template.
The electronic device according to claim 11, wherein the step of obtaining the target consultation template according to the size relationship between all the similarities and the size relationship between the similarity and the preset similarity threshold is also include:

According to the size relationship among all the similarities, determine the inquiry template with the highest similarity;

If the similarity of the query template with the highest similarity is less than the preset similarity threshold, a preset reference query template is obtained, and the preset reference query template is used as a target query template.
The electronic device according to any one of claims 9 to 13, wherein the step of determining the target nodes on the target consultation template and the directed edges of the target nodes by the basic consultation parameters includes:

determining a target node on the target medical inquiry template according to the basic medical inquiry parameters;

Obtain the script data of each directed edge of the target node;

Calculate the weight of each directed edge according to the script data;

Determine the directed edge of the target node according to the weight of each directed edge.
A computer-readable storage medium for computer-readable storage, wherein the computer-readable storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to Realize a kind of intelligent interrogation method, wherein, described intelligent interrogation method comprises:

Obtain basic medical inquiry text;

Carrying out feature extraction on entity features in the basic medical inquiry text to obtain basic medical inquiry parameters;

Screening the preset consultation templates according to the basic consultation parameters to obtain a set of candidate consultation templates;

Filtering the consultation templates in the set of candidate consultation templates according to a preset filtering algorithm to obtain a target consultation template;

determining the target node on the target consultation template and the directed edges of the target node according to the basic consultation parameters;

Constructing an inquiry sequence topic set according to the target node and the directed edge;

Inquiry is performed according to the question set of the order of inquiry.
The computer-readable storage medium according to claim 15, wherein the step of performing feature extraction on entity features in the basic medical questioning text to obtain basic medical questioning parameters includes:

Identifying entity features in the basic medical questioning text;

Classifying the entity features by using a pre-trained sequence classifier;

Feature extraction is performed on the entity features after classification processing to obtain basic consultation parameters.
The computer-readable storage medium according to claim 15, wherein the basic consultation parameters include chief complaint information, and the consultation templates in the set of candidate consultation templates are filtered according to a preset filtering algorithm, The steps to obtain the target consultation template include:

Using a pre-trained automatic text generation model to process the chief complaint information and the medical questioning templates in the candidate medical questioning template set to generate chief complaint text strings and medical questioning template text strings;

Carry out coding processing to described chief complaint text string and described medical inquiry template text string respectively, obtain the chief complaint text string of coded form and the medical inquiry template text string of coded form;

Calculate the similarity between the main complaint text string in the coded form and each of the question template text strings in the coded form;

According to the magnitude relationship between all the similarities and the magnitude relationship between the similarity and a preset similarity threshold, a target consultation template is obtained.
The computer-readable storage medium according to claim 17, wherein, according to the size relationship between all the similarities and the size relationship between the similarity and the preset similarity threshold, the target consultation template is obtained. steps, including:

According to the size relationship among all the similarities, determine the inquiry template with the highest similarity;

If the similarity of the question template with the highest similarity is greater than or equal to a preset similarity threshold, the question template with the highest similarity is used as the target question template.
The computer-readable storage medium according to claim 17, wherein, according to the size relationship between all the similarities and the size relationship between the similarity and the preset similarity threshold, the target consultation template is obtained. steps, also include:

According to the size relationship among all the similarities, determine the inquiry template with the highest similarity;

If the similarity of the query template with the highest similarity is less than the preset similarity threshold, a preset reference query template is obtained, and the preset reference query template is used as a target query template.
The computer-readable storage medium according to any one of claims 15 to 19, wherein the basic consultation parameters determine the target node on the target consultation template and the step of the directed edge of the target node, comprising :

determining a target node on the target medical inquiry template according to the basic medical inquiry parameters;

Obtain the script data of each directed edge of the target node;

Calculate the weight of each directed edge according to the script data;

Determine the directed edge of the target node according to the weight of each directed edge.