CN114611735A

CN114611735A - Internet registration method, device, equipment and storage medium for hospitalizing

Info

Publication number: CN114611735A
Application number: CN202210289575.4A
Authority: CN
Inventors: 张海艳
Original assignee: Kangjian Information Technology Shenzhen Co Ltd
Current assignee: Kangjian Information Technology Shenzhen Co Ltd
Priority date: 2022-03-23
Filing date: 2022-03-23
Publication date: 2022-06-10
Also published as: WO2023178971A1

Abstract

The invention relates to the technical field of big data, and discloses a hospitalizing internet registration method, a hospitalizing internet registration device, hospitalizing internet registration equipment and a hospitalizing internet registration storage medium. The method comprises the following steps: receiving a registration request, and acquiring illness state data and identity information of a user according to the registration request; carrying out feature extraction on the disease condition data to obtain a plurality of disease condition features of the disease condition data; matching in a preset medical database according to the plurality of disease conditions to obtain candidate symptoms matched with the plurality of disease conditions; determining a target registration department matched with the user according to the candidate symptoms; acquiring all doctors in a target registration department, respectively calculating the matching degrees of all doctors according to the disease condition characteristics, and determining a target registration object from all doctors according to the matching degrees; and generating registration information of the user according to the identity information and the target registration object, and pushing the registration information to the client. The invention shortens the operation steps of user registration, only needs to input expected conditions to find the number source for direct registration, and improves the efficiency of on-line registration of the user.

Description

Internet registration method, device, equipment and storage medium for hospitalizing

Technical Field

The invention relates to the technical field of big data and the field of digital medical treatment, in particular to a hospitalizing internet registration method, a hospitalizing internet registration device, hospitalizing internet registration equipment and a hospitalizing internet registration storage medium.

Background

The conventional online internet hospital common registration system comprises an appointment registration mode and a current day registration mode, the two registration schemes are similar in operation steps, the mode of obtaining a registration source is single, a user needs to select a department first, then selects a corresponding doctor and then selects time to see a real registration source, the operation steps are multiple, and the user cannot quickly and visually find the required registration source.

Meanwhile, the user can not compare the number sources transversely and longitudinally, and particularly, when some new users do not know how to operate or what department number source needs to be hung, the appropriate number is difficult to hang, so that the problem that the patient often hangs wrong numbers and the like is caused. Therefore, how to solve the problem of the user registration difficulty and improve the registration efficiency becomes a technical problem to be solved by the technical personnel in the field at present.

Disclosure of Invention

The invention mainly aims to improve the efficiency of on-line registration of a user by shortening the operation steps of registration of the user and only inputting expected conditions to find a registration source for direct registration.

The invention provides an Internet registration method for medical treatment, which comprises the following steps: receiving a registration reservation request, and acquiring disease data and identity information of a user according to the registration reservation request; carrying out feature extraction on the disease condition data to obtain a plurality of disease condition features of the disease condition data; matching in a preset medical database according to the plurality of disease condition characteristics to obtain candidate symptoms matched with the plurality of disease condition characteristics; determining a target registration department matched with the user according to the candidate symptom; acquiring all doctors in the target registration department, respectively calculating the matching degrees of all doctors according to the disease condition characteristics, and determining a target registration object from all doctors according to the matching degrees; and generating registration information of the user according to the identity information and the target registration object, and pushing the registration information to a client.

Optionally, in a first implementation manner of the first aspect of the present invention, the receiving a registration reservation request, and acquiring the disease condition data and the identity information of the user according to the registration reservation request includes: receiving a reservation registration request, and analyzing the reservation registration request to obtain voice symptom data carried in the reservation registration request; carrying out format conversion on the voice symptom data to obtain text symptom data in a text format; and performing semantic recognition on the text symptom information to obtain illness state data and identity information of the user.

Optionally, in a second implementation manner of the first aspect of the present invention, the performing feature extraction on the disease condition data to obtain a plurality of disease condition features of the disease condition data includes: deleting stop words in the disease condition data, and performing word segmentation processing on the deleted disease condition data to obtain target disease condition words; converting the target disease condition words into disease condition word vectors, and calculating the weight of the disease condition word vectors; and selecting the target disease condition word vector with the weight larger than a preset weight value from the disease condition word vectors, and generating a plurality of disease condition characteristics of the disease condition data according to the target disease condition word vector.

Optionally, in a third implementation manner of the first aspect of the present invention, the matching in a preset medical database according to a plurality of disease condition characteristics, and obtaining candidate symptoms matching with the plurality of disease condition characteristics includes: acquiring a medical knowledge map corresponding to the plurality of disease conditions from a preset medical database, and calculating the matching degree between each disease condition field in the medical knowledge map and each of the plurality of disease conditions; when the matching degree between each disease state field and each of the disease state characteristics is smaller than a preset threshold value, matching the target field symptom most similar to the disease state characteristics in the medical knowledge map; and taking the target field symptom as a candidate symptom matched with a plurality of disease characteristics.

Optionally, in a fourth implementation of the first aspect of the present invention, the matching, in the medical knowledge-map, field symptoms that are most similar to the plurality of disease-condition features comprises: calculating, for each field symptom in the medical knowledge-graph, a textual similarity between the field symptom and a plurality of the condition features; and according to the text similarity, obtaining a target field symptom with similarity exceeding a preset threshold value with the disease condition characteristics from the field symptoms.

Optionally, in a fifth implementation manner of the first aspect of the present invention, the determining, according to the candidate symptom, a target registration department matching the user includes: acquiring candidate registered departments corresponding to the candidate symptoms, and respectively calculating confidence degrees between the symptoms and the registered departments on the basis of a preset similarity calculation method; and determining a target registration department matched with the user according to the confidence.

Optionally, in a sixth implementation manner of the first aspect of the present invention, the obtaining all doctors in the target registration department, calculating matching degrees of all doctors according to the disease characteristics, and determining a target registration object from all doctors according to the matching degrees includes: inquiring medical fields of all doctors in the target registration department, and respectively calculating first matching degrees of the disease condition characteristics and the medical fields corresponding to the doctors according to the disease condition characteristics; determining an initial registration object from the doctors according to the first matching degree, and inquiring the working time of the initial registration object, wherein the initial registration object refers to the preliminarily determined registered doctors; and calculating a second matching degree between the user and the initial registration object according to the appointment registration time of the user and the working time of the initial registration object, and determining a target registration object from the doctor according to the second matching degree.

The invention provides a medical internet registration device in a second aspect, which comprises: the acquisition module is used for receiving a registration reservation request and acquiring disease data and identity information of a user according to the registration reservation request; the characteristic extraction module is used for carrying out characteristic extraction on the disease condition data to obtain a plurality of disease condition characteristics of the disease condition data; the matching module is used for matching in a preset medical database according to the plurality of disease condition characteristics to obtain candidate symptoms matched with the plurality of disease condition characteristics; the first determination module is used for determining a target registration department matched with the user according to the candidate symptom; the second determination module is used for acquiring all doctors in the target registration department, respectively calculating the matching degrees of all doctors according to the disease condition characteristics, and determining a target registration object from all doctors according to the matching degrees; and the generating module is used for generating registration information of the user according to the identity information and the target registration object and pushing the registration information to a client.

Optionally, in a first implementation manner of the second aspect of the present invention, the obtaining module is specifically configured to: receiving a reservation registration request, and analyzing the reservation registration request to obtain voice symptom data carried in the reservation registration request; carrying out format conversion on the voice symptom data to obtain text symptom data in a text format; and performing semantic recognition on the text symptom information to obtain illness state data and identity information of the user.

Optionally, in a second implementation manner of the second aspect of the present invention, the feature extraction module is specifically configured to: deleting stop words in the disease condition data, and performing word segmentation processing on the deleted disease condition data to obtain target disease condition words; converting the target disease word into a disease word vector, and calculating the weight of the disease word vector; and selecting the target disease condition word vector with the weight larger than a preset weight value from the disease condition word vectors, and generating a plurality of disease condition characteristics of the disease condition data according to the target disease condition word vector.

Optionally, in a third implementation manner of the second aspect of the present invention, the matching module includes: the calculation unit is used for acquiring a medical knowledge map corresponding to the plurality of disease conditions from a preset medical database and calculating the matching degree between each disease condition field in the medical knowledge map and each of the plurality of disease conditions; the matching unit is used for matching the target field symptom most similar to the disease characteristics in the medical knowledge map when the matching degree between each disease field and each of the disease characteristics is smaller than a preset threshold value; and taking the target field symptom as a candidate symptom matched with a plurality of disease characteristics.

Optionally, in a fourth implementation manner of the second aspect of the present invention, the matching unit is specifically configured to: calculating, for each field symptom in the medical knowledge-graph, a textual similarity between the field symptom and a plurality of the condition features; and according to the text similarity, obtaining a target field symptom with similarity exceeding a preset threshold value with the disease condition characteristics from the field symptoms.

Optionally, in a fifth implementation manner of the second aspect of the present invention, the first determining module is specifically configured to: acquiring candidate registered departments corresponding to the candidate symptoms, and respectively calculating confidence degrees between the symptoms and the registered departments on the basis of a preset similarity calculation method; and determining a target registration department matched with the user according to the confidence.

Optionally, in a sixth implementation manner of the second aspect of the present invention, the second determining module is specifically configured to: inquiring medical fields of all doctors in the target registration department, and respectively calculating first matching degrees of the disease condition characteristics and the medical fields corresponding to the doctors according to the disease condition characteristics; determining an initial registration object from the doctors according to the first matching degree, and inquiring the working time of the initial registration object, wherein the initial registration object refers to the preliminarily determined registered doctors; and calculating a second matching degree between the user and the initial registration object according to the appointment registration time of the user and the working time of the initial registration object, and determining a target registration object from the doctor according to the second matching degree.

In a third aspect, the present invention provides an internet registration apparatus for medical purposes, comprising: a memory having instructions stored therein and at least one processor, the memory and the at least one processor interconnected by a line;

the at least one processor invokes the instructions in the memory to cause the hospitalizing internet registration device to perform the steps of the hospitalizing internet registration method described above.

A fourth aspect of the present invention provides a computer-readable storage medium having stored therein instructions, which, when run on a computer, cause the computer to perform the steps of the above-described internet registration method for medical treatment.

According to the technical scheme provided by the invention, the condition data and the identity information of the user are acquired according to the appointment registration request by receiving the appointment registration request; carrying out feature extraction on the disease condition data to obtain a plurality of disease condition features of the disease condition data; matching in a preset medical database according to the plurality of disease conditions to obtain candidate symptoms matched with the plurality of disease conditions; determining a target registration department matched with the user according to the candidate symptoms; acquiring all doctors in a target registration department, respectively calculating the matching degrees of all doctors according to the disease condition characteristics, and determining a target registration object from all doctors according to the matching degrees; and generating registration information of the user according to the identity information and the target registration object, and pushing the registration information to the client. The invention obtains the illness state data and the identity information of the user according to the appointment register request by receiving the appointment register request; furthermore, the disease data of the user is analyzed, the registered doctors are determined from all doctors in the target registration department, the user registration operation steps are shortened, the direct registration of the registration source is found only by inputting expected conditions, and the online registration efficiency of the user is improved.

Drawings

FIG. 1 is a schematic diagram of a first embodiment of the Internet registration method for medical treatment provided by the invention;

FIG. 2 is a schematic diagram of a second embodiment of the Internet registration method for medical treatment provided by the present invention;

FIG. 3 is a schematic diagram of a third embodiment of the Internet registration method for medical treatment provided by the invention;

FIG. 4 is a schematic diagram of a fourth embodiment of the Internet registration method for medical treatment provided by the invention;

FIG. 5 is a schematic diagram of a fifth embodiment of the Internet registration method for medical treatment provided by the present invention;

FIG. 6 is a schematic view of a first embodiment of the Internet registration device for medical treatment provided by the invention;

FIG. 7 is a schematic view of a second embodiment of the Internet registration device for medical treatment provided by the invention;

fig. 8 is a schematic diagram of an embodiment of the medical internet registration device provided by the invention.

Detailed Description

According to the hospitalizing internet registration method, the hospitalizing internet registration device, the hospitalizing internet registration equipment and the hospitalizing internet registration storage medium, the appointment registration request is received, and the illness state data and the identity information of the user are obtained according to the appointment registration request; carrying out feature extraction on the disease condition data to obtain a plurality of disease condition features of the disease condition data; matching in a preset medical database according to the plurality of disease conditions to obtain candidate symptoms matched with the plurality of disease conditions; determining a target registration department matched with the user according to the candidate symptoms; acquiring all doctors in a target registration department, respectively calculating the matching degrees of all doctors according to the disease condition characteristics, and determining a target registration object from all doctors according to the matching degrees; and generating registration information of the user according to the identity information and the target registration object, and pushing the registration information to the client. The invention obtains the illness state data and the identity information of the user according to the appointment registration request by receiving the appointment registration request; furthermore, the disease data of the user is analyzed, the registered doctors are determined from all doctors in the target registration department, the user registration operation steps are shortened, the direct registration of the registration source is found only by inputting expected conditions, and the online registration efficiency of the user is improved.

The terms "first," "second," "third," "fourth," and the like in the description and in the claims, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It will be appreciated that the data so used may be interchanged under appropriate circumstances such that the embodiments described herein may be practiced otherwise than as specifically illustrated or described herein. Furthermore, the terms "comprises," "comprising," or "having," and any variations thereof, are intended to cover non-exclusive inclusions, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

For convenience of understanding, a specific flow of the embodiment of the present invention is described below, and referring to fig. 1, a first embodiment of the internet registration method for medical treatment in the embodiment of the present invention includes:

101. receiving a registration request, and acquiring disease data and identity information of a user according to the registration request;

in this embodiment, the online registration request may be understood as an appointment inquiry request input by a user in an intelligent registration platform, where the intelligent registration platform may be an app, an applet, a public number, and the like. It should be appreciated that, after an online registration request is input by a user, the intelligent registration platform obtains registration information of the online registration request, wherein the registration information includes: the system comprises user information, illness state information and registration time, wherein the user information refers to personal basic data of a user, such as name, age, gender, contact way, address, identity card and the like, the illness state information refers to body state description data of the user, such as dizziness, heaviness in head and feet, cold, chest distress and the like, and the registration time refers to the time that the user expects to visit a doctor and is generated based on different user requirements.

As an embodiment of the present invention, the collecting registration information of the online registration request includes: and acquiring a request field of the online registration request, inquiring a data table of the request field from a background database, and inquiring registration information of the online registration request according to the data table.

The request field may be understood as an identity of the online registration request, and is used to represent the registration identity of the online registration request, and the background database is used to store page data generated by the intelligent registration platform, and may be a relational database, such as a MySQL database.

102. Carrying out feature extraction on the disease condition data to obtain a plurality of disease condition features of the disease condition data;

in this embodiment, training data is obtained, where the training data includes an original feature corresponding to each sample data; training an initial feature extraction model by using the training data, and obtaining a parameter value of the initial feature extraction model; screening the parameter values of the initial characteristic extraction model to obtain the screened parameter values; reconstructing the initial feature extraction model by using the screened parameter values to obtain a reconstructed feature extraction model; inputting the training data into the reconstructed feature extraction model to obtain the derived features of each sample data; and retraining the reconstructed feature extraction model according to the derived features of each sample data and the original features corresponding to each sample data until the iteration is terminated, and obtaining the trained feature extraction model.

Specifically, in the initial feature extraction model, the weight of the screened parameter values is increased to obtain a reconstructed feature extraction model, and the weights of other parameter values in the parameter values of the initial feature extraction model are reduced, so that the training of the feature extraction model is more sensitive to the features corresponding to the parameters with higher sensitivity, and more hidden features are mined.

And further, inputting the disease condition data into the feature extraction model for feature extraction to obtain the disease condition features of the user.

103. Matching in a preset medical database according to the plurality of disease conditions to obtain candidate symptoms matched with the plurality of disease conditions;

in this embodiment, the medical database is constructed from a medical database containing a symptom pending department. The medical database containing the department to which the symptom should be registered refers to answers generated on the network by the user for questions of which department the symptom should go to register. The data sources of the data sets include, but are not limited to, social networking sites, sharing sites, searching sites, and the like. For example, when the network source is a social network site, the medical database is a message sent between friends of the user about a department to which symptoms should be hung; or when the network source is a sharing website, the medical database refers to articles, videos, voices and the like issued by the user and about the condition of the department to be hung; or, when the network source is a search website, the medical database refers to a web page result related to a symptom to be hung up by the user.

Based on the medical database, the medical database at least comprises field symptoms extracted from the medical database containing the medical database with the symptom to be hung department and a registered department corresponding to the field symptoms. Further, the medical database further includes confidence levels of the field symptoms corresponding to different registered departments, and it is understood that the higher the confidence level is, the higher the priority level of the registered department corresponding to the field symptom is pushed is. It should be noted that the medical database may be represented by a structure tree, or may be represented by an array in a fixed format, which is not limited in this embodiment. For example, the medical database is represented as an array in a fixed format, i.e., medical database { field symptom, registered department, confidence }. For example, { headache, neurology, 0.9}, { headache, neurosurgery, 0.8} are all contained in the medical database.

Alternatively, the medical database is represented in the form of a structure tree that includes a number of parent nodes and a number of child nodes connected to the parent nodes. Wherein, each node is stored with at least one character, the character stored on the father node is used for representing the field symptom, and the character stored on the son node is used for representing the registration department. The path connecting between the parent node and the child node is then used to represent the confidence that the field symptom corresponds to a registered department. Further, two parent nodes connected to each other through a path are regarded as adjacent parent nodes on which characters are stored for representing similar field symptoms.

104. Determining a target registration department matched with the user according to the candidate symptom;

in this embodiment, the above example is used to explain that, assuming that the candidate symptom matching the disease characteristic "headache" is the field symptom "headache", the registered department corresponding to the candidate symptom "headache" in the medical knowledge map database of any form includes: "neurology" and "neurosurgery". Based on this, regarding the generation of the to-be-pushed set, on the one hand, the to-be-pushed set may be generated by all registered departments corresponding to the candidate symptom "headache", that is, { neurology, neurosurgery }.

On the other hand, a plurality of registered departments can be selected from all registered departments corresponding to the candidate symptom "headache", and the registered departments are added to the set to be pushed. Specifically, obtaining confidence degrees of the candidate symptoms corresponding to different registered departments from the medical knowledge map database; and according to the obtained confidence, generating the set to be pushed by the registered departments corresponding to the candidate symptoms. That is, for the confidence that a candidate symptom corresponds to each registered department, only the registered department with the confidence exceeding a certain threshold or the highest confidence can be added to the set to be pushed as the due registered department of the disease characteristic. The specific threshold value can be flexibly set according to the actual needs of the application scenario, and is not limited herein.

105. Acquiring all doctors in a target registration department, respectively calculating the matching degrees of all doctors according to the disease condition characteristics, and determining a target registration object from all doctors according to the matching degrees;

in this embodiment, the medical fields of the medical staff in each department are queried, and the matching degree between the characteristic disease information and the medical fields is calculated; selecting the medical personnel with the matching degree larger than the preset matching degree as an initial registration object, and inquiring the medical time of the initial registration object; and calculating the association degree of the registration time and the medical time to obtain the association degree of the characteristic disease information and the medical staff in each department.

The medical field refers to the medical excellence range of the medical staff, namely the types of the medical staff treating diseases, such as neurology medical staff, brain medical staff and medical staff. The medical treatment time refers to the clinic visit time when the medical staff is not scheduled.

106. And generating registration information of the user according to the identity information and the target registration object, and pushing the registration information to the client.

In this embodiment, after the identity information of the target user is obtained and the target department and the target doctor are determined, registration information of the target user can be generated by using the identity information of the target user, the target department and the target doctor, and self-service registration is completed. In addition, for some users, the re-diagnosis registration may be performed, and at this time, the case sample associated with the target user may be found in the case database, and when the inquiry type of the target user is analyzed to be the re-diagnosis based on the case sample, the original registration information of the target user in the last inquiry may be obtained, so as to generate the registration information corresponding to the inquiry by using the original registration information. The method provided by the embodiment of the invention combines and uses various high-precision technologies, such as: artificial intelligence, face recognition, voice assistant, big data analysis and the like, help the old and all people who are not good at using electronic products, and provide a convenient and fast registration flow.

In the embodiment of the invention, the condition data and the identity information of a user are acquired according to the appointment registration request by receiving the appointment registration request; carrying out feature extraction on the disease condition data to obtain a plurality of disease condition features of the disease condition data; matching in a preset medical database according to the plurality of disease conditions to obtain candidate symptoms matched with the plurality of disease conditions; determining a target registration department matched with the user according to the candidate symptoms; acquiring all doctors in a target registration department, respectively calculating the matching degrees of all doctors according to the disease condition characteristics, and determining a target registration object from all doctors according to the matching degrees; and generating registration information of the user according to the identity information and the target registration object, and pushing the registration information to the client. The invention obtains the illness state data and the identity information of the user according to the appointment registration request by receiving the appointment registration request; furthermore, the disease data of the user is analyzed, the registered doctors are determined from all doctors in the target registration department, the user registration operation steps are shortened, the direct registration of the registration source is found only by inputting expected conditions, and the online registration efficiency of the user is improved.

Referring to fig. 2, a second embodiment of the internet registration method for medical services according to the embodiment of the present invention includes:

201. receiving a reservation registration request, and analyzing the reservation registration request to obtain voice symptom data carried in the reservation registration request;

in this embodiment, the registration terminal may preset different dialogues, the self-service registration terminal is used to inquire the uncomfortable symptoms of the target user through voice, and obtain the voice symptom information orally described by the target user, after the self-service registration terminal obtains the voice symptom information of the target user, the self-service registration terminal may convert the voice symptom information into text symptom information, and the text symptom information is further obtained through cleaning of a series of data and semantic recognition.

For example, the self-service registration terminal may send out voice inquiry information, such as "ask for something uncomfortable", and if the target user answers "eye discomfort", the symptom characteristic information of the target user may be obtained as eye discomfort. In addition, in practical application, multiple rounds of information interaction may be generated between the self-service registration terminal and the target user, in this embodiment, question-following inquiry information may be further formed according to the voice symptom information responded by the target user, and the symptom description information of the target user is obtained by recording multiple rounds of interaction information between the self-service registration terminal and the target user. For example, "eye discomfort" for the above-described target user response may make a further question "whether the eyes are dry, painful, impaired, or other symptoms" to generate detailed symptom characteristic information of the target user after further acquiring the reply information of the target user. If the answer of the target user is "eye pain", the target user may be further asked for the pain level, and so on.

202. Carrying out format conversion on the voice symptom data to obtain text symptom data in a text format;

in this embodiment, in the process of interaction between the registration terminal and the target user, the interactive content between the registration terminal and the target user may be simultaneously displayed on the screen of the registration terminal, and in addition, a symptom option may be provided on the registration terminal for the target user to select, for example, for the above-mentioned "whether the eyes are dry, painful, and have decreased vision or other symptoms" (for example, "dry eyes", "painful eyes", "decreased vision", and other symptom options are provided), the target user may trigger the screen to select one or more symptoms, and then the symptom characteristic information of the target user is obtained in combination with the selection of the target user on the symptoms.

The process that the registration terminal carries out semantic identification can be carried out at the registration terminal, also can go up to reach the high in the clouds and discern, in addition, no matter be registration terminal or when the high in the clouds carries out semantic identification, can adopt preset semantic identification system, the semantic identification system that provides based on this embodiment except can carrying out semantic identification to general mandarin, can also realize the discernment of dialect. Optionally, different language recognition systems can be established for the registration terminal according to the position attribute of the hospital where the registration terminal is deployed, so that accurate recognition of user voice is achieved, and the use experience of the user on the registration terminal is improved. In the semantic recognition process, various recognition algorithms can be adopted, such as an algorithm based on Dynamic Time Warping (Dynamic Time Warping), an algorithm based on a deep learning neural network and a convolutional neural network, and the like.

203. Performing semantic recognition on the text symptom information to obtain illness state data and identity information of the user;

in the embodiment, a text vector of a text to be recognized is obtained by using a first convolutional neural network preset in a semantic recognition model. The method comprises the steps of obtaining a text to be recognized, preprocessing the obtained text to be recognized to obtain an initialized text vector, inputting the initialized text vector into a first convolution neural network preset by a semantic recognition model, and generating a text vector for representing the text to be recognized. The preprocessing can be specifically set according to the actual application scene, for example, the preprocessing is set as word segmentation processing, that is, word segmentation marking is performed on the text to be recognized by taking a word as a unit; or setting the preprocessing as a word screening processing, that is, after word segmentation and marking are performed on the text to be recognized by taking a word as a unit, unimportant words, such as verb aids like "can, should" and so on, and explictive words like "wo, o" and so on, are removed, so as to improve the semantic recognition efficiency of the text to be recognized, where the preprocessing is not specifically limited.

Taking the preprocessing as the word segmentation processing as an example, the word segmentation processing of the text to be recognized specifically includes marking words in the text to be recognized by using an SBME marking method, namely marking a single word as S, marking the head of the word as B, marking the middle of the word as M, and marking the tail of the word as E, and generating an initialized text vector according to the marked text to be recognized.

Before semantic recognition is carried out on a text to be recognized, a semantic recognition model of the application is constructed, and a training sample set used for training the semantic recognition model is obtained, namely the training sample set can be used for training a first convolution neural network, a second convolution neural network and a third convolution neural network which are initialized, so that the semantic recognition model is obtained.

The preset second convolutional neural network is used for identifying the named entities contained in the text to be identified, the output result of the preset first convolutional neural network is used as the input of the preset second convolutional neural network and is input into the preset second convolutional neural network, and the output result is the named entities contained in the text to be identified.

And the preset third convolutional neural network is used for identifying the entity relationship contained in the text to be identified, the output result of the preset first convolutional neural network and the output result of the preset second convolutional neural network are used as the input of the preset third convolutional neural network, the preset third convolutional neural network is input, and the output result is the entity relationship among the named entities contained in the text to be identified.

204. Carrying out feature extraction on the disease condition data to obtain a plurality of disease condition features of the disease condition data;

205. matching in a preset medical database according to the plurality of disease conditions to obtain candidate symptoms matched with the plurality of disease conditions;

206. determining a target registration department matched with the user according to the candidate symptoms;

207. acquiring all doctors in a target registration department, respectively calculating the matching degrees of all doctors according to the disease condition characteristics, and determining a target registration object from all doctors according to the matching degrees;

208. and generating registration information of the user according to the identity information and the target registration object, and pushing the registration information to the client.

The steps 204-208 in this embodiment are similar to the steps 102-106 in the first embodiment, and are not described herein again.

In the embodiment of the invention, the condition data and the identity information of a user are acquired according to the appointment registration request by receiving the appointment registration request; carrying out feature extraction on the disease condition data to obtain a plurality of disease condition features of the disease condition data; matching in a preset medical database according to the plurality of disease conditions to obtain candidate symptoms matched with the plurality of disease conditions; determining a target registration department matched with the user according to the candidate symptoms; acquiring all doctors in a target registration department, respectively calculating the matching degrees of all doctors according to the disease condition characteristics, and determining a target registration object from all doctors according to the matching degrees; and generating registration information of the user according to the identity information and the target registration object, and pushing the registration information to the client. The invention obtains the illness state data and the identity information of the user according to the appointment register request by receiving the appointment register request; furthermore, the disease data of the user is analyzed, the registered doctors are determined from all doctors in the target registration department, the user registration operation steps are shortened, the direct registration of the registration source is found only by inputting expected conditions, and the online registration efficiency of the user is improved.

Referring to fig. 3, a third embodiment of the internet registration method for medical services according to the embodiment of the present invention includes:

301. receiving a registration request, and acquiring disease data and identity information of a user according to the registration request;

302. deleting stop words in the disease condition data, and performing word segmentation processing on the deleted disease condition data to obtain target disease condition words;

in this embodiment, the stop word refers to a word that has no meaning in the disease condition information, such as a mood assist word, an adverb, a preposition, a conjunctive word, and the like, and the weight can be understood as the importance of the disease condition word vector in the disease condition information.

In an optional embodiment, the deletion of the stop word can be realized by matching with the stop word in the stop word list; the word segmentation can be realized by a word segmentation algorithm, such as a Chinese character segmentation algorithm, a dictionary word segmentation algorithm, a Markov word segmentation algorithm and the like; the conversion of the disease condition Word vector can be realized by a Word vector conversion algorithm, such as a Word2vec algorithm; the weight of the disease word vector can be realized by an information concentration algorithm, such as a factor analysis algorithm, a principal component analysis algorithm and the like. The preset weight may be set to 0.6, or may be set according to an actual service scenario.

303. Converting the target disease condition words into disease condition word vectors, and calculating the weight of the disease condition word vectors;

in this embodiment, converting the target disease term into the disease term vector includes: performing word segmentation operation on a plurality of field texts in the target illness state word respectively to obtain a plurality of field word segmentation sets; vectorizing and vector combining the coded participles in the field participle sets through a pre-trained word vector model respectively to obtain disease word vectors corresponding to the field participle sets; determining that a plurality of the condition word vectors constitute the vectorized text set.

Specifically, the performing word segmentation operations on the plurality of field texts in the target condition word respectively to obtain a plurality of field word segmentation sets includes: decoding the plurality of coded texts by using decoding codes corresponding to the coding codes to obtain a plurality of decoded texts; acquiring a text corpus corresponding to the type of the decoding text set; establishing joint distribution probability of a plurality of decoding texts according to the text corpus; screening a plurality of decoding word segmentation text sets of a plurality of decoding texts based on the joint distribution probability; and encoding the decoded word segmentation texts in the plurality of decoded word segmentation text sets by using the encoding codes to obtain a plurality of field word segmentation sets.

304. Selecting a target disease word vector with the weight larger than a preset weight value from the disease word vectors, and generating a plurality of disease characteristics of the disease data according to the target disease word vector;

in this embodiment, the disease condition word vectors are sorted according to the weight values, and the disease condition word vector with the weight value greater than the chalcedony weight value is selected as the target disease condition word vector. Further, generating characteristic illness state information according to the target illness state word vector. The weight of the disease condition word vector can be realized by an information concentration algorithm, such as a factor analysis algorithm, a principal component analysis algorithm and the like.

In particular, factor analysis refers to a statistical technique that studies the extraction of commonality factors from a population of variables. Originally proposed by british psychologist c.e. spearman. The students find that a certain correlation exists among the scores of all the departments of the students, and the students with good scores of one department often have better scores of other departments, so that whether certain potential common factors exist or not is supposed, or certain common intelligence conditions influence the learning scores of the students. Factor analysis can find hidden representative factors among many variables. The number of variables can be reduced by factoring variables of the same nature, and assumptions of relationships between the variables can also be examined.

305. Matching in a preset medical database according to the plurality of disease conditions to obtain candidate symptoms matched with the plurality of disease conditions;

306. determining a target registration department matched with the user according to the candidate symptoms;

307. acquiring all doctors in a target registration department, respectively calculating the matching degrees of all doctors according to the disease condition characteristics, and determining a target registration object from all doctors according to the matching degrees;

308. and generating registration information of the user according to the identity information and the target registration object, and pushing the registration information to the client.

Steps 301 and 305-308 in this embodiment are similar to steps 101 and 103-106 in the first embodiment, and are not described herein again.

In the embodiment of the invention, the condition data and the identity information of a user are acquired according to the appointment registration request by receiving the appointment registration request; carrying out feature extraction on the disease condition data to obtain a plurality of disease condition features of the disease condition data; matching in a preset medical database according to the plurality of disease conditions to obtain candidate symptoms matched with the plurality of disease conditions; determining a target registration department matched with the user according to the candidate symptoms; acquiring all doctors in a target registration department, respectively calculating the matching degrees of all doctors according to the disease condition characteristics, and determining a target registration object from all doctors according to the matching degrees; and generating registration information of the user according to the identity information and the target registration object, and pushing the registration information to the client. The invention obtains the illness state data and the identity information of the user according to the appointment registration request by receiving the appointment registration request; furthermore, the disease condition data of the user is analyzed, the registered doctors are determined from all the doctors in the target registration department, the user registration operation steps are shortened, the registration source is searched only by inputting expected conditions, and the on-line registration efficiency of the user is improved.

Referring to fig. 4, a fourth embodiment of the internet registration method for medical treatment according to the embodiment of the present invention includes:

401. receiving a registration request, and acquiring disease data and identity information of a user according to the registration request;

402. carrying out feature extraction on the disease condition data to obtain a plurality of disease condition features of the disease condition data;

403. acquiring a medical knowledge map corresponding to a plurality of disease characteristics from a preset medical database, and calculating the matching degree between each disease field in the medical knowledge map and each of the plurality of disease characteristics;

in this embodiment, since the disease condition features are the symptoms input by the user via the client, there may be a spoken symptom description, and when performing matching search according to the disease condition features in the medical knowledge graph, it is likely that field symptoms completely matching the disease condition features cannot be directly searched.

For example, a field symptom is "headache", if the condition is characterized by "headache", it can be considered that there is a field symptom "headache" matching the condition characteristic "headache" in the medical knowledge graph, and if the condition is characterized by "headache", it is considered that there is no field symptom "headache" matching the condition characteristic "headache" in the medical knowledge graph, and only there is a field symptom "headache" similar to the condition characteristic "headache".

In this embodiment, the matching search process substantially includes: a perfect match search process, a similarity search process. Specifically, a complete matching search process is first performed to match each field symptom in the medical knowledge map with the disease condition characteristics, i.e., this step is performed.

404. Calculating text similarity between the field symptom and a plurality of disease characteristics aiming at each field symptom in the medical knowledge map;

in this embodiment, the text similarity calculation method includes, but is not limited to: the present invention is not limited to the similarity calculation based on euclidean distance, the similarity calculation based on manhattan distance, the similarity calculation based on minuscule distance, the similarity calculation based on mahalanobis distance, the similarity calculation based on cosine distance, the similarity calculation based on Jaccard coefficient, the similarity calculation based on pearson correlation coefficient, and the like.

405. According to the text similarity, obtaining a target field symptom with similarity exceeding a preset threshold value with the disease condition characteristics from the field symptoms;

in this embodiment, the medical knowledge map is represented as an array in a fixed format, i.e., medical knowledge map { field symptom, registered department, confidence }. For example, { headache, neurology, 0.9}, { headache, neurosurgery, 0.8} are included in the medical knowledge map. Alternatively, the medical knowledge-graph is represented in the form of a structural tree that includes a number of parent nodes and a number of child nodes connected to the parent nodes. At least one character is stored on each node, the characters stored on the parent node are used for representing field symptoms, and the characters stored on the child nodes are used for representing registered departments. The path connecting between the parent node and the child node is then used to represent the confidence that the field symptom corresponds to the registered department. Further, two parent nodes connected to each other through a path are regarded as adjacent parent nodes on which characters are stored for representing similar field symptoms.

For example, the medical knowledge map includes a father node "headache" and a father node "headache", and a child node "neurology" and a child node "neurosurgery" connected to the father node "headache", wherein the father node "headache" and the father node "headache" are adjacent father nodes. That is, "headache" and "headache" are regarded as field symptoms, and they are similar to each other. "department of neurology" and "department of neurosurgery" are regarded as the registered department of the field symptom "headache" or "headache", 0.9 is the confidence that the field symptom "headache" or "headache" corresponds to the registered department "department of neurology", and 0.8 is the confidence that the field symptom "headache" or "headache" corresponds to the registered department "department of neurosurgery".

Based on the above, after the input symptom requesting pushing of the registered department is extracted from the recommendation request, the candidate symptom matching the input symptom can be searched in the medical knowledge map. For example, assuming that the input symptom is "headache", no matter what form of the medical knowledge graph is based on the above, by performing a matching search, for example, for each parent node in the medical knowledge graph, matching the input symptom "headache" with characters on the parent node, it is possible to determine that the candidate symptom matching the input symptom "headache" is the field symptom "headache".

406. Determining a target registration department matched with the user according to the candidate symptoms;

407. acquiring all doctors in a target registration department, respectively calculating the matching degrees of all doctors according to the disease condition characteristics, and determining a target registration object from all doctors according to the matching degrees;

408. and generating registration information of the user according to the identity information and the target registration object, and pushing the registration information to the client.

The steps 401-.

In the embodiment of the invention, the condition data and the identity information of the user are acquired according to the appointment registration request by receiving the appointment registration request; carrying out feature extraction on the disease condition data to obtain a plurality of disease condition features of the disease condition data; matching in a preset medical database according to the plurality of disease conditions to obtain candidate symptoms matched with the plurality of disease conditions; determining a target registration department matched with the user according to the candidate symptoms; acquiring all doctors in a target registration department, respectively calculating the matching degrees of all doctors according to the disease condition characteristics, and determining a target registration object from all doctors according to the matching degrees; and generating registration information of the user according to the identity information and the target registration object, and pushing the registration information to the client. The invention obtains the illness state data and the identity information of the user according to the appointment registration request by receiving the appointment registration request; furthermore, the disease data of the user is analyzed, the registered doctors are determined from all doctors in the target registration department, the user registration operation steps are shortened, the direct registration of the registration source is found only by inputting expected conditions, and the online registration efficiency of the user is improved.

Referring to fig. 5, a fifth embodiment of the internet registration method for medical treatment according to the embodiments of the present invention includes:

501. receiving a registration request, and acquiring disease data and identity information of a user according to the registration request;

502. carrying out feature extraction on the disease condition data to obtain a plurality of disease condition features of the disease condition data;

503. matching in a preset medical database according to the plurality of disease conditions to obtain candidate symptoms matched with the plurality of disease conditions;

504. acquiring candidate registration departments corresponding to the candidate symptoms, and respectively calculating confidence degrees between the symptoms and the registration departments based on a preset similarity calculation method;

in this embodiment, the registration information of the symptom includes: at least one of a department to be hung for the symptom, a hospital where the department to be hung is located, a doctor who issues the medical database, a hospital where the doctor is located, a department where the doctor is located, and a disease symptom specialized for the doctor.

The extraction process of the registration information is explained by taking the registration information of the symptoms as an example, including the department to be registered of the symptoms and the hospital where the department to be registered is located. Specifically, first, based on a hospital and a registered department in a hospital department set, a department to be hung for obtaining the symptom and a hospital where the department to be hung is located are searched from the medical database.

Note that, the hospital and the registered department in the hospital department group are both in the form of identification information, and are formed by collecting in advance the names of the hospitals and the registered departments that actually exist in life. That is, the hospital department set is essentially a set of hospital names and registered department names. For example, "Shenzhen citizen hospital" in the hospital department collection is used to uniquely identify the truly existing Shenzhen citizen hospital, while "Shenzhen citizen famous hospital neurology" in the hospital department collection is used to uniquely identify the neurology of the truly existing Shenzhen citizen hospital.

Then, matching the text in the medical database with the hospital and the registered department in the hospital department set one by one to obtain the department to be hung and the hospital where the department to be hung is located contained in the medical database.

505. Determining a target registration department matched with the user according to the confidence coefficient;

in this embodiment, the registration information of the symptom is generated according to the department to be hung of the symptom and the hospital where the department to be hung is located. For example, registration information of symptoms { department, hospital }.

Similarly, in combination with the hospital department set, based on the pre-collected doctor set and doctor specialty disease symptom set, the registration information of the symptoms can be generated by obtaining the doctor who published the medical database, the job level of the doctor, the hospital where the doctor is located, the department where the doctor is located, the doctor specialty disease symptoms, and the like from the medical database, which is not limited in this embodiment.

It should be noted that understanding of different users about the corresponding departments of symptoms may be different, so that there may be more than one corresponding department extracted from a large amount of medical databases and the hospital where the corresponding department is located. Based on this, in the present embodiment, the confidence level that the symptom corresponds to different departments to be hung is calculated according to the registration information of the symptom.

Specifically, a confidence factor is calculated according to registration information of the symptom; and calculating the confidence level that the symptom should be hung in the department according to the confidence level factor. The confidence factor comprises at least one of a department confidence factor, a hospital confidence factor where the department is located and a doctor confidence factor. Further, according to the confidence coefficient, determining a target registration department matched with the user.

506. Inquiring medical fields of all doctors in a target registration department, and respectively calculating first matching degrees of the disease condition characteristics and the medical fields corresponding to the doctors according to the disease condition characteristics;

in this embodiment, the medical field refers to the medical excellence of the medical staff, i.e. the types of diseases that the medical staff attend a doctor, such as neurology medical staff, brain medical staff and medical staff. The medical treatment time refers to the clinic visit time when the medical personnel are not scheduled.

507. Determining an initial registration object from the doctor according to the first matching degree, and inquiring the working time of the initial registration object;

in this embodiment, the medical staff with the association degree greater than the preset threshold is selected as the target registration object of the online registration request, and the target registration object is returned to the user, so as to realize the online registration request of the user. The preset threshold may be set to 0.9, or may be set according to an actual service scenario.

508. Calculating a second matching degree between the user and the initial registration object according to the appointment registration time of the user and the working time of the initial registration object, and determining a target registration object from the doctor according to the second matching degree;

509. And generating registration information of the user according to the identity information and the target registration object, and pushing the registration information to the client.

Steps 501 to 503 and 509 in the present embodiment are similar to steps 101 to 103 and 106 in the first embodiment, and are not described again here.

With reference to fig. 6, the internet registration method for medical treatment in the embodiment of the present invention is described above, and a first embodiment of the internet registration device for medical treatment in the embodiment of the present invention includes:

an obtaining module 601, configured to receive a registration request, and obtain disease data and identity information of a user according to the registration request;

a feature extraction module 602, configured to perform feature extraction on the disease condition data to obtain a plurality of disease condition features of the disease condition data;

a matching module 603, configured to perform matching in a preset medical database according to the multiple disease conditions, so as to obtain candidate symptoms matched with the multiple disease conditions;

a first determining module 604, configured to determine a target registration department matching the user according to the candidate symptom;

a second determining module 605, configured to obtain all doctors in the target registration department, respectively calculate matching degrees of all doctors according to the disease characteristics, and determine a target registration object from all doctors according to the matching degrees;

a generating module 606, configured to generate registration information of the user according to the identity information and the target registration object, and push the registration information to a client.

Referring to fig. 7, a second embodiment of the internet registration apparatus for medical treatment according to the embodiment of the present invention specifically includes:

In this embodiment, the obtaining module 601 is specifically configured to:

receiving a reservation registration request, and analyzing the reservation registration request to obtain voice symptom data carried in the reservation registration request; carrying out format conversion on the voice symptom data to obtain text symptom data in a text format;

and performing semantic recognition on the text symptom information to obtain illness state data and identity information of the user.

In this embodiment, the feature extraction module 602 is specifically configured to:

deleting stop words in the disease condition data, and performing word segmentation processing on the deleted disease condition data to obtain target disease condition words;

converting the target disease word into a disease word vector, and calculating the weight of the disease word vector;

and selecting the target disease condition word vector with the weight larger than a preset weight value from the disease condition word vectors, and generating a plurality of disease condition characteristics of the disease condition data according to the target disease condition word vector.

In this embodiment, the matching module 603 includes:

a calculating unit 6031, configured to obtain a medical knowledge graph corresponding to the multiple disease conditions from a preset medical database, and calculate a matching degree between each disease condition field in the medical knowledge graph and each of the multiple disease conditions;

a matching unit 6032, configured to, when the matching degree between each disease field and each of the plurality of disease characteristics is smaller than a preset threshold, match a field symptom most similar to the plurality of disease characteristics in the medical knowledge graph; and taking the field symptom as a candidate symptom matched with a plurality of disease characteristics.

In this embodiment, the matching unit 6032 is specifically configured to:

calculating, for each field symptom in the medical knowledge-graph, a textual similarity between the field symptom and a plurality of the condition features;

and according to the text similarity, obtaining a target field symptom with similarity exceeding a preset threshold value with the disease condition characteristics from the field symptoms.

In this embodiment, the first determining module 604 is specifically configured to:

acquiring candidate registered departments corresponding to the candidate symptoms, and respectively calculating confidence degrees between the symptoms and the registered departments on the basis of a preset similarity calculation method;

and determining a target registration department matched with the user according to the confidence.

In this embodiment, the second determining module 605 is specifically configured to:

inquiring medical fields of all doctors in the target registration department, and respectively calculating first matching degrees of the disease condition characteristics and the medical fields corresponding to the doctors according to the disease condition characteristics;

determining an initial registration object from the doctors according to the first matching degree, and inquiring the working time of the initial registration object, wherein the initial registration object refers to the preliminarily determined registered doctors;

and calculating a second matching degree between the user and the initial registration object according to the appointment registration time of the user and the working time of the initial registration object, and determining a target registration object from the doctor according to the second matching degree.

The medical internet registration device in the embodiment of the present invention is described in detail in the above fig. 6 and fig. 7 from the perspective of the modular functional entity, and the medical internet registration device in the embodiment of the present invention is described in detail in the following from the perspective of hardware processing.

Fig. 8 is a schematic structural diagram of a medical internet registration apparatus provided by an embodiment of the present invention, where the medical internet registration apparatus 800 may have a relatively large difference due to different configurations or performances, and may include one or more processors (CPUs) 810 (e.g., one or more processors) and a memory 820, one or more storage media 830 (e.g., one or more mass storage devices) storing an application 833 or data 832. Memory 820 and storage medium 830 may be, among other things, transient or persistent storage. The program stored in the storage medium 830 may include one or more modules (not shown), each of which may include a series of instruction operations for the internet registration apparatus 800 for medical treatment. Still further, the processor 810 may be configured to communicate with the storage medium 830, and execute a series of instruction operations in the storage medium 830 on the medical internet registration apparatus 800 to implement the steps of the medical internet registration method provided by the above-described method embodiments.

The hospitalized internet registration device 800 may also include one or more power supplies 840, one or more wired or wireless network interfaces 850, one or more input-output interfaces 860, and/or one or more operating systems 831, such as Windows server, Mac OS X, Unix, Linux, FreeBSD, and so forth. Those skilled in the art will appreciate that the configuration of the medical internet registration apparatus shown in fig. 8 does not constitute a limitation of the medical internet registration apparatus provided herein, and may include more or fewer components than shown, or some components in combination, or a different arrangement of components.

The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium, or a volatile computer-readable storage medium, having stored therein instructions, which, when executed on a computer, cause the computer to perform the steps of the above-mentioned internet registration method for medical treatment.

It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a portable hard disk, a read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk, an optical disk, or other various media capable of storing program codes.

The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.

Claims

1. An internet registration method for medical treatment, which is characterized by comprising the following steps:

receiving a registration reservation request, and acquiring disease data and identity information of a user according to the registration reservation request;

carrying out feature extraction on the disease condition data to obtain a plurality of disease condition features of the disease condition data;

matching in a preset medical database according to the plurality of disease condition characteristics to obtain candidate symptoms matched with the plurality of disease condition characteristics;

determining a target registration department matched with the user according to the candidate symptom;

acquiring all doctors in the target registration department, respectively calculating the matching degrees of all doctors according to the disease condition characteristics, and determining a target registration object from all doctors according to the matching degrees;

and generating registration information of the user according to the identity information and the target registration object, and pushing the registration information to a client.

2. The internet registration method for hospitalizing of claim 1, wherein said receiving an appointment registration request, and obtaining patient data and identity information of the user according to the appointment registration request comprises:

receiving a reservation registration request, and analyzing the reservation registration request to obtain voice symptom data carried in the reservation registration request;

carrying out format conversion on the voice symptom data to obtain text symptom data in a text format;

3. The internet registration method for medical treatment according to claim 1, wherein the performing feature extraction on the disease condition data to obtain a plurality of disease condition features of the disease condition data comprises:

4. The internet registration method for medical visits according to claim 1, wherein the matching in a preset medical database according to the plurality of disease characteristics, and obtaining candidate symptoms matching the plurality of disease characteristics comprises:

acquiring a medical knowledge map corresponding to the plurality of disease conditions from a preset medical database, and calculating the matching degree between each disease condition field in the medical knowledge map and each of the plurality of disease conditions;

when the matching degree between each disease state field and each of the disease state characteristics is smaller than a preset threshold value, matching the target field symptom most similar to the disease state characteristics in the medical knowledge map;

and taking the target field symptom as a candidate symptom matched with a plurality of disease characteristics.

5. The internet registration method for hospitalizing of claim 4, wherein said matching in said medical knowledge-graph the most similar target field symptoms to a plurality of said condition features comprises:

6. The internet registration method for hospitalizing of claim 1, wherein said determining a target registration department matching said user based on said candidate symptom comprises:

7. The internet registration method for medical treatment according to claim 1, wherein the obtaining all doctors in the target registration department, respectively calculating the matching degrees of all doctors according to the disease characteristics, and determining the target registration object from all doctors according to the matching degrees comprises:

8. An internet registration apparatus for medical treatment, comprising:

the acquisition module is used for receiving a registration reservation request and acquiring disease data and identity information of a user according to the registration reservation request;

the characteristic extraction module is used for carrying out characteristic extraction on the disease condition data to obtain a plurality of disease condition characteristics of the disease condition data;

the matching module is used for matching in a preset medical database according to the plurality of disease condition characteristics to obtain candidate symptoms matched with the plurality of disease condition characteristics;

the first determination module is used for determining a target registration department matched with the user according to the candidate symptom;

the second determination module is used for acquiring all doctors in the target registration department, respectively calculating the matching degrees of all doctors according to the disease condition characteristics, and determining a target registration object from all doctors according to the matching degrees;

and the generating module is used for generating registration information of the user according to the identity information and the target registration object and pushing the registration information to a client.

9. An internet registration apparatus for medical treatment, comprising: a memory having instructions stored therein and at least one processor, the memory and the at least one processor interconnected by a line;

the at least one processor invokes the instructions in the memory to cause the hospitalization internet registration device to perform the steps of the hospitalization internet registration method of any of claims 1-7.

10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the internet registration method for medical treatment according to any one of claims 1 to 7.