CN117219238A

CN117219238A - Medical information processing method, device, equipment and storage medium

Info

Publication number: CN117219238A
Application number: CN202311134759.4A
Authority: CN
Inventors: 仇鹏飞
Original assignee: Kangjian Information Technology Shenzhen Co Ltd
Current assignee: Kangjian Information Technology Shenzhen Co Ltd
Priority date: 2023-09-04
Filing date: 2023-09-04
Publication date: 2023-12-12

Abstract

The disclosure relates to a medical information processing method, a device, equipment and a storage medium, relates to the technical field of digital medical treatment, and solves the problems of low accuracy of registration results and unreasonable medical resource allocation in related technologies. The method comprises the following steps: acquiring description information of a target inquiry user, and extracting target keywords from the description information; the target keywords comprise first target entity words representing symptom characteristics of the target inquiry user and/or second target entity words representing corresponding diseases of the target inquiry user; determining a target department corresponding to the target keyword according to a mapping relation among the first entity word, the second entity word and the department included in the preset knowledge graph; the first entity word characterizes symptom characteristics, and the second entity word characterizes diseases; determining registration results corresponding to the target consultation users according to doctor registration information associated with the target departments; doctor registration information includes whether the doctor is going out and/or the remaining registration denomination.

Description

Medical information processing method, device, equipment and storage medium

Technical Field

The present disclosure relates to the field of digital medical technology, and in particular, to a medical information processing method, apparatus, device, and storage medium.

Background

In order to facilitate patient registration, on-line registration has become a popular registration method for on-line medical treatment or off-line medical treatment. In the current internet medical service platform, registered departments and doctors are screened out based on gradual retrieval and gradual selection of patients. In the registering mode, the registering system in the service platform only plays a simple display and guiding role, a patient still needs to analyze and select departments and doctors independently according to own illness state, the accuracy of registering results is completely dependent on the analysis and selection of the patient, and due to the fact that patients often lack professional medical knowledge in registering, proper departments and doctors are difficult to accurately select for registering when the departments and doctors are selected, the registering results are low in accuracy, and therefore doctor resources cannot be reasonably utilized.

Disclosure of Invention

The invention provides a medical information processing method, a device, equipment and a storage medium, which at least solve the problems of low accuracy of registration results and unreasonable medical resource allocation in the related technology. The technical scheme of the invention is as follows:

according to a first aspect of an embodiment of the present invention, there is provided a medical information processing method including: acquiring description information of a target inquiry user, and extracting target keywords from the description information; the target keywords comprise first target entity words representing symptom characteristics of the target inquiry user and/or second target entity words representing corresponding diseases of the target inquiry user; determining a target department corresponding to the target keyword according to a mapping relation among the first entity word, the second entity word and the department included in the preset knowledge graph; the first entity word characterizes symptom characteristics, and the second entity word characterizes diseases; determining registration results corresponding to the target consultation users according to doctor registration information associated with the target departments; doctor registration information includes whether the doctor is going out and/or the remaining registration denomination.

In a possible implementation manner, determining a target department corresponding to the target keyword according to a mapping relationship among a first entity word, a second entity word and the departments included in a preset knowledge graph includes: determining candidate departments corresponding to the target keywords according to the mapping relation among the first entity words, the second entity words and the departments, which are included in the preset knowledge graph; when a plurality of candidate departments are provided, generating questioning information according to first entity words corresponding to the plurality of candidate departments; pushing the questioning information to obtain reply information corresponding to the questioning information from the target questioning user account; and determining the target department from the plurality of candidate departments according to the reply information.

In another possible implementation manner, after determining a candidate department corresponding to the target keyword according to a mapping relationship among the first entity word, the second entity word and the department included in the preset knowledge graph; the method further comprises the steps of: and when the candidate department is one, determining the candidate department as the target department.

In another possible implementation manner, extracting the target keyword from the description information includes: performing word segmentation processing on the description information to obtain a plurality of segmented words; determining at least one target keyword matched with a preset word in a preset word bank from a plurality of word segments; the preset word stock includes preset words associated with disease features, symptom features, and medication features.

In another possible implementation manner, determining at least one target keyword matched with a preset word in a preset word bank from a plurality of word segments includes: determining a plurality of candidate keywords matched with preset words in a preset library from a plurality of word segments; for any one candidate keyword in the plurality of candidate keywords, determining the similarity between the candidate keyword and other candidate keywords; and determining the keywords with the similarity with the candidate keywords being larger than a similarity threshold value in other candidate keywords and any candidate keyword as a target keyword.

In another possible implementation manner, before performing word segmentation processing on the description information, the method further includes: the voice information in the description information is converted into text information.

In another possible implementation manner, determining a registration result corresponding to the target inquiry user according to doctor registration information associated with the target department includes: determining one or more first target doctor accounts which are in a consultation state and have residual registry names from at least one doctor account associated with the target department; displaying a plurality of first target doctor accounts; and responding to the selected operation of the target user on a second target doctor account in the plurality of first target doctor accounts, and taking the selected second target doctor account as a registering result.

In another possible implementation manner, before determining a target department corresponding to the target keyword according to a mapping relationship between a first entity word, a second entity word and the department included in a preset knowledge graph, the method includes: for any second entity word, taking the second entity word and a department associated with the second entity word as search keywords, and searching target medical information associated with the second entity word and the department from a plurality of target webpages; and extracting the second entity word and the first entity word associated with the department from the target medical information to construct a preset knowledge graph.

According to a second aspect of an embodiment of the present invention, there is provided a medical information processing apparatus including: the extraction unit is configured to acquire the description information of the target inquiry user and extract the target keywords from the description information; the target keywords comprise first target entity words representing symptom characteristics of the target inquiry user and/or second target entity words representing corresponding diseases of the target inquiry user; the retrieval unit is configured to determine a target department corresponding to the target keyword according to a mapping relation among the first entity word, the second entity word and the department included in the preset knowledge graph; the first entity word characterizes symptom characteristics, and the second entity word characterizes diseases; the registering unit is configured to determine registering results corresponding to the target consultation users according to doctor registering information associated with the target departments; doctor registration information includes whether the doctor is going out and/or the remaining registration denomination.

In one possible implementation, the retrieving unit is specifically configured to: determining candidate departments corresponding to the target keywords according to the mapping relation among the first entity words, the second entity words and the departments, which are included in the preset knowledge graph; when a plurality of candidate departments are provided, generating questioning information according to first entity words corresponding to the plurality of candidate departments; pushing the questioning information to obtain reply information corresponding to the questioning information from the target questioning user account; and determining the target department from the plurality of candidate departments according to the reply information.

In another possible implementation, the retrieving unit is further specifically configured to: and when the candidate department is one, determining the candidate department as the target department.

In another possible implementation, the extraction unit is specifically configured to: performing word segmentation processing on the description information to obtain a plurality of segmented words; determining at least one target keyword matched with a preset word in a preset word bank from a plurality of word segments; the preset word stock includes preset words associated with disease features, symptom features, and medication features.

In another possible implementation, the extraction unit is further specifically configured to: determining a plurality of candidate keywords matched with preset words in a preset library from a plurality of word segments; for any one candidate keyword in the plurality of candidate keywords, determining the similarity between the candidate keyword and other candidate keywords; and determining the keywords with the similarity with the candidate keywords being larger than a similarity threshold value in other candidate keywords and any candidate keyword as a target keyword.

In another possible implementation, the extraction unit is specifically configured to: the voice information in the description information is converted into text information.

In another possible implementation, the registering unit is specifically configured to: determining one or more first target doctor accounts which are in a consultation state and have residual registry names from at least one doctor account associated with the target department; displaying a plurality of first target doctor accounts; and responding to the selected operation of the target user on a second target doctor account in the plurality of first target doctor accounts, and taking the selected second target doctor account as a registering result.

In another possible implementation, the extraction unit is further specifically configured to: for any second entity word, taking the second entity word and a department associated with the second entity word as search keywords, and searching target medical information associated with the second entity word and the department from a plurality of target webpages; and extracting the second entity word and the first entity word associated with the department from the target medical information to construct a preset knowledge graph.

According to a third aspect of embodiments of the present invention, there is provided a registering device configured to perform the medical information processing method of the first aspect and any one of its possible embodiments.

According to a fourth aspect of an embodiment of the present invention, there is provided an electronic device including: a processor and a memory for storing processor-executable instructions; wherein the processor is configured to execute executable instructions to implement a medical information processing method as in the first aspect and any one of its possible implementation forms.

According to a sixth aspect of embodiments of the present invention, there is provided a computer-readable storage medium having instructions stored thereon, characterized in that the instructions in the computer-readable storage medium, when executed by a processor of an electronic device, enable the electronic device to perform the medical information processing method as in the first aspect.

According to a seventh aspect of embodiments of the present disclosure, there is provided a computer program product comprising computer instructions which, when run on an electronic device, cause the electronic device to perform the medical information processing method of the first aspect and any one of its possible implementations.

The technical scheme provided by the embodiment of the invention at least has the following beneficial effects: a preset knowledge graph representing the triple relation consisting of symptom entity words, disease entity words and departments is preset. After extracting the target keywords from the description information input by the inquiry user, the target keywords have richer and more accurate mapping relation knowledge based on the preset knowledge graph, and the target departments which are associated with the target keywords and are consistent with the inquiry information can be accurately and automatically determined, so that the inquiry user (such as a patient) does not need to select the departments according to the self-diagnosis autonomous analysis of the patients, and the situation that the diagnosis guiding departments are inconsistent with the actual conditions of the inquiry user due to the lack of subjective factors such as corresponding medical professional knowledge of the inquiry user is avoided. According to the target departments corresponding to the symptoms of the inquiry users, doctors corresponding to the symptom information and the disease information of the inquiry users are led out for the inquiry users, so that reasonable and accurate allocation of doctor resources is ensured, hospital resources are reasonably utilized, the medical efficiency is improved, the medical effect is ensured, and the medical experience of the inquiry users is increased.

In addition, based on the intelligently acquired registering result, the diagnosis guiding flow and steps of the inquiring user can be simplified, so that the registering flow is simplified, and the registering efficiency is improved.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the disclosure and together with the description, serve to explain the principles of the disclosure and do not constitute an undue limitation on the disclosure.

FIG. 1 is a schematic diagram of a medical information processing system, according to an exemplary embodiment;

FIG. 2 is a flowchart illustrating a method of medical information processing according to an exemplary embodiment;

FIG. 3 is a schematic diagram of a preset knowledge-graph, according to an exemplary embodiment;

FIG. 4 is a flowchart second of a medical information processing method according to an exemplary embodiment;

FIG. 5 is a flowchart III of a medical information processing method according to an exemplary embodiment;

FIG. 6 is a block diagram of a medical information processing apparatus according to an exemplary embodiment;

Fig. 7 is a schematic diagram of an electronic device, according to an example embodiment.

Detailed Description

In order to enable those skilled in the art to better understand the technical solutions of the present disclosure, the technical solutions of the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.

It should be noted that the terms "first," "second," and the like in the description and claims of the present disclosure and in the foregoing figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the disclosure described herein may be capable of operation in sequences other than those illustrated or described herein. The implementations described in the following exemplary examples are not representative of all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present disclosure as detailed in the accompanying claims.

Before the medical information processing method provided by the embodiment of the application is described in detail, an application scene and an implementation environment related to the embodiment of the application are briefly described.

First, an application scenario according to the present application will be briefly described.

The huge population base of China causes the shortage of medical resources in China, and various hospitals can see queuing long, difficult and numerous diseases everywhere, which is a serious civil problem to be solved urgently in China. In recent years, internet medical treatment in China rapidly develops, and online medical treatment on the Internet gradually enters the field of view of the masses, so that the embarrassment of medical resource shortage is greatly relieved.

Aiming at the problems, the application provides a medical information processing method, which is provided with a preset knowledge graph representing the triple relation consisting of symptom entity words, disease entity words and departments in advance. After extracting the target keywords from the description information input by the inquiry user, the target keywords have richer and more accurate mapping relation knowledge based on the preset knowledge graph, and the target departments which are associated with the target keywords and are consistent with the inquiry information can be accurately and automatically determined, so that the inquiry user (such as a patient) does not need to select the departments according to the self-diagnosis autonomous analysis of the patients, and the situation that the diagnosis guiding departments are inconsistent with the actual conditions of the inquiry user due to the lack of subjective factors such as corresponding medical professional knowledge of the inquiry user is avoided. According to the target departments corresponding to the symptoms of the inquiry users, doctors corresponding to the symptom information and the disease information of the inquiry users are led out for the inquiry users, so that reasonable and accurate allocation of doctor resources is ensured, hospital resources are reasonably utilized, the medical efficiency is improved, the medical effect is ensured, and the medical experience of the inquiry users is increased.

Next, the following briefly describes an implementation architecture to which the present application relates.

Fig. 1 is a schematic diagram of a medical information processing system 10 provided by the present disclosure. As shown in fig. 1, the medical information processing system includes a server 101, a doctor terminal 102, and a user terminal 103, and a connection may be established between the server 101, the doctor terminal 102, and the user terminal 103 through a wired network or a wireless network. The server 101 includes a consultation platform.

In some embodiments, the target web pages for accessing the inquiry platform are provided in the browsers of the doctor terminal 102 and the user terminal 103. The doctor or the interview user accesses the interview platform based on the target web page to acquire medical information.

Illustratively, the querying user initiates a registration request on the target web page on the user terminal 103. The inquiry platform receives the registration request, so that the user terminal 103 displays a registration page. The inquiry user inputs descriptive information of the disease symptoms of the patient on the registration page. The server 101 extracts target keywords characterizing the medical features from the descriptive information. And matching the target keywords based on a pre-stored preset knowledge graph to obtain a target department matched with the target keywords. And determining a target doctor account corresponding to the target department based on the target department, and generating a registration result after the user account of the inquiring user is associated with the target doctor account. And simultaneously, the registering result is sent to a doctor terminal of the target doctor account so as to inform the target doctor corresponding to the target doctor account of the registering result.

In other embodiments, the doctor terminal 102 and the user terminal 103 are respectively provided with a consultation application program corresponding to the consultation platform provided at the terminal. The on-line registration process in the above example may be performed by the interviewing user and the interviewing doctor through programs on the corresponding terminals.

In some embodiments, the server 101 includes or is connected to a database, and the preset knowledge base may be stored in the database. The inquiry platform or doctor terminal can realize the access operation of knowledge of a preset knowledge base in the database through the server 101.

In other embodiments, the server 101 may be a single server, or may be a server cluster formed by a plurality of servers. In some implementations, the server cluster may also be a distributed cluster. The application is not limited to the specific implementation of the server 101.

Both doctor terminals and user terminals are understood as terminal devices. The terminal device may be a mobile phone, a tablet computer, a desktop, a laptop, a handheld computer, a notebook, an ultra-mobile personal computer (ultra-mobile personal computer, UMPC), a netbook, a cellular phone, a personal digital assistant (personal digital assistant, PDA), an augmented reality (augmented reality, AR) \virtual reality (VR) device, or the like, which may install and use a content community application (e.g., a express hand), and the specific form of the terminal device is not particularly limited in this disclosure. The system can perform man-machine interaction with a user through one or more modes of a keyboard, a touch pad, a touch screen, a remote controller, voice interaction or handwriting equipment and the like.

Alternatively, in the medical information processing system shown in fig. 1 described above, the server 101 may be connected to at least one terminal device. The application does not limit the number and the type of the terminal equipment.

The medical information processing method provided by the embodiment of the application can be applied to the medical information processing system in the implementation architecture shown in the foregoing figure 1; and can also be applied to a registering device. For easy understanding, the medical information processing method provided by the application is specifically described below with reference to the accompanying drawings.

Fig. 2 is a flowchart illustrating a medical information processing method according to an exemplary embodiment, which includes the following steps, as shown in fig. 2.

S21, acquiring description information of the target consultation user, and extracting target keywords from the description information.

The target keywords comprise first target entity words representing symptom characteristics of the target interviewing user and/or second target entity words representing corresponding diseases of the target interviewing user.

Specifically, the description information includes at least one or more of the following: category information, symptom information, historical sign information, historical disease information, drug information, treatment information, and historical department information for the patient user. Such as height, weight, age, gender, etc., belonging to the category information; headache, fever, tinnitus and the like belong to historical symptom information; blood pressure index parameters, blood fat index parameters and the like belong to historical sign information; historical disease information of historically diagnosed diabetes, shoulder neck disease and the like; the type or name of the allergic medicine, the type or name of the used or in-use medicine, etc. belong to medicine information; feedback information and the like fed back to a doctor's historical diagnosis report belong to processing information; the department to which the history consultation doctor belongs and the like belong to the history department information.

Further, a first target entity word is extracted from category information, symptom information, historical sign information, drug information, processing information, and historical department information in the description information. And extracting second target entity words from the historical disease information in the descriptive information, and taking the first target entity words and/or the second target entity words as target keywords.

The description information may include voice information input by the target consultation user; text information entered by the target interview user may also be included. The present application is not particularly limited with respect to the input form of the description information and the information source.

In order to facilitate the extraction of the target keywords, the voice information in the description information is converted into text information.

In the step, words which represent symptom characteristics and disease characteristics of the inquiring user in the descriptive information are converted into preset knowledge graphs which comprise target keywords, so that target departments matched with the target keywords can be accurately identified from the preset knowledge graphs, and intelligent acquisition of the target departments based on the descriptive information is realized.

S22, determining a target department corresponding to the target keyword according to a mapping relation among the first entity word, the second entity word and the department included in the preset knowledge graph.

The first entity word characterizes the symptom feature and the second entity word characterizes the disease.

In the preset knowledge graph, the first entity word corresponds to a second entity word, and the second entity word corresponds to a department.

In some implementation scenarios, when the target consultation user explicitly knows the disease, the target consultation user generally directly inputs description information corresponding to the second target entity word, and determines the department corresponding to the second target entity as the target department based on the mapping relationship between the second entity and the department in the preset knowledge graph.

When the target inquiry user is unclear to the disease, the target inquiry user can indirectly input description information corresponding to the second target entity word. Based on a mapping relation between a first entity and a second entity in a preset knowledge graph, determining the second entity corresponding to the first target entity as the second target entity; and determining the department corresponding to the second target entity as a target department based on the mapping relation between the second entity and the department.

Exemplary, as shown in fig. 3, the first entity words are chest pain, dyspnea, hypodynamia, yuzhuo and cyanosis; the second entity word is alveolar eggs; the corresponding department is respiratory department.

The preset knowledge graph is constructed in the following manner.

A plurality of second entity words characterizing the disease are preset or constructed. And for any second entity word, retrieving target medical information associated with the second entity word and the department from a plurality of target webpages by taking the second entity word and the department associated with the second entity word as retrieval keywords. For example, target medical information such as disease types, symptoms, registration departments, treatment modes, related medicines and the like is acquired from a target webpage comprising various medical information by a crawler mode such as python crawler data analysis and the like. Extracting a first entity word, a second entity word and a department from target medical information, analyzing the association relation and the inference relation among the first entity word, the second entity word and the department, and constructing a preset knowledge graph based on the inference relation and the association relation.

S23, determining registration results corresponding to the target consultation users according to doctor registration information associated with the target departments.

Doctor registration information includes whether the doctor is going out and/or the remaining registration denomination.

The department is arranged in connection with a doctor account of a doctor belonging to the department, i.e. one department corresponds to at least one doctor account. And the doctor account is associated with corresponding doctor registration information.

Specifically, from at least one doctor account associated with a target department, it is determined that doctor registration information indicates one or more first target doctor accounts in a consultation state and for which a remaining registration denomination exists. When the first target doctor account is determined to be one, the first target doctor account is used as a registering result. And displaying the plurality of first target doctor accounts for target user selection when the plurality of first target doctor accounts are determined. And responding to the selected operation of the target user on a second target doctor account in the plurality of first target doctor accounts, and taking the selected second target doctor account as a registering result.

In the step, based on doctor account information, a registration result is determined so as to ensure reasonable allocation of doctor resources.

Through the embodiment, after the target keywords are extracted from the description information input by the inquiry user, the target departments corresponding to the inquiry information and related to the target keywords can be accurately and automatically determined based on the richer and more accurate mapping relation knowledge of the preset knowledge graph, and the inquiry user (such as a patient) does not need to select the departments according to the autonomous analysis of own illness state, so that the situation that the diagnosis guiding departments are inconsistent with the actual illness state of the inquiry user due to the lack of corresponding subjective factors such as medical professional knowledge by the inquiry user is avoided. According to the target departments corresponding to the symptoms of the inquiry users, doctors corresponding to the symptom information and the disease information of the inquiry users are led out for the inquiry users, so that reasonable and accurate allocation of doctor resources is ensured, hospital resources are reasonably utilized, the medical efficiency is improved, the medical effect is ensured, and the medical experience of the inquiry users is increased.

As a refinement and extension of the foregoing embodiment, in order to fully describe the specific implementation process of the present embodiment, another medical information processing method is provided in the embodiment of the present application.

Referring to fig. 2, as shown in fig. 4, the process of extracting the target keyword in the above step S21 is specifically as follows.

S211, performing word segmentation processing on the description information to obtain a plurality of segmented words.

S212, determining at least one target keyword matched with a preset word in a preset word bank from a plurality of segmented words.

It can be understood that the word segment matched with the preset word included in the preset word library in the plurality of word segments is determined as the target keyword.

Wherein the preset word stock comprises preset words associated with disease features, symptom features and drug features.

In one embodiment, a target keyword is determined from among a plurality of segmented words, which has a high similarity to a preset word and a preset value.

In some embodiments, in order to avoid obtaining repeated target keywords and to ensure the uniqueness of each target keyword, the multiple segmented words are first aggregated, and then the aggregated segmented words are matched with preset words in a preset library.

Specifically, from a plurality of segmented words, a plurality of candidate keywords matched with preset words in a preset library are determined. And determining the similarity of any candidate keyword and other candidate keywords aiming at any candidate keyword in the plurality of candidate keywords. And aggregating the keywords with the similarity larger than the similarity threshold value with any one candidate keyword in other candidate keywords and any one candidate keyword into a target keyword. The target keyword may be a candidate keyword having a similarity with any candidate keyword greater than a similarity threshold and one candidate keyword of the any candidate keyword. The one target keyword may be a candidate keyword having a maximum similarity with respect to the candidate keywords having a similarity greater than a similarity threshold value.

Further, a keyword having a similarity with the any one candidate keyword greater than a similarity threshold, and the any one candidate keyword are deleted from the plurality of candidate keywords. And determining the similarity of any candidate keyword and other candidate keywords in the plurality of candidate keywords after deletion aiming at any candidate keyword in the plurality of candidate keywords after deletion. And aggregating the keywords with the similarity larger than the similarity threshold value with any one candidate keyword in the other candidate keywords in the deleted plurality of candidate keywords and the any one candidate keyword into a target keyword. And repeating the determining target keywords and deleting the candidate keywords corresponding to the determining target keywords in sequence until the deleted candidate keywords do not exist.

For example, for candidate keywords, word F, other candidate keywords are word A, word B, word C, word D, and word E; among other candidate keywords, the candidate keywords having a similarity with the word F greater than the similarity threshold are the word C, the word D, and the word E. After the word C, the word D, the word E and the word F are aggregated, any one candidate keyword among the word C, the word D, the word E and the word F is determined to be a target keyword. And deleting the word C, the word D, the word E and the word F from the plurality of candidate keywords to obtain a plurality of deleted candidate keywords which are the word A and the word B. And continuously comparing the similarity of the word A and the word B, if the similarity of the word A and the word B is larger than a similarity threshold value, determining any one candidate keyword in the word A and the word B as a target keyword, deleting the word A and the word B, and stopping determining the target keyword. If the similarity of the word A and the word B is smaller than or equal to the similarity threshold, determining the word A as a target keyword and deleting the word A, and determining the word B as a target keyword and deleting the word A, and stopping determining the target keyword.

Referring to fig. 2, as shown in fig. 5, the process of determining the target department in the above step S22 is specifically as follows.

S221, determining candidate departments corresponding to the target keywords according to the mapping relation among the first entity words, the second entity words and the departments, which are included in the preset knowledge graph.

And S222, when a plurality of candidate departments are provided, generating question information according to the first entity words corresponding to the plurality of candidate departments.

In some embodiments, a first entity word is preset with a sub-question information.

In a specific embodiment, sub question information corresponding to at least one first entity word other than the first target entity word in the target keyword is taken as question information in a plurality of first entity words corresponding to a plurality of candidate departments. The questioning information is a sub questioning information set corresponding to at least one first entity word.

In another embodiment, sub question information corresponding to each different first entity word among the plurality of first entity words corresponding to the plurality of candidate departments is used as question information. The different first entity words represent different first entity words from other first entity words in the plurality of first entity words; the questioning information is a sub questioning information set corresponding to each different first entity word.

And determining candidate departments as non-unique, wherein target keywords in the descriptive information indicate symptom characteristics common to a plurality of diseases. In this case, in order to determine the target subject, question information is generated based on the differentiated symptom characteristics of the plurality of diseases corresponding to the plurality of candidate subjects. The questioning information is used for questioning the target questioning user so as to determine that the questioning user has differential symptom characteristics.

S223, the questioning information is pushed so as to acquire reply information corresponding to the questioning information from the target questioning user account.

The reply message is also referred to as reply message, and is used for indicating a target differentiated first entity word in the plurality of differentiated first entity words.

The way of pushing the questioning information is one or more of the following: the questioning information or voice playing questioning information is displayed on the registering device, and the questioning information or voice playing questioning information is displayed on the user terminal of the target questioning user account. Correspondingly, the reply information is acquired as follows: the method comprises the steps of obtaining reply information input by a interviewing user in a text or voice form from registering equipment, and obtaining the reply information input by the interviewing user in a text or voice form from a user terminal of a target interviewing user account.

S224, determining a target department from the plurality of candidate departments according to the reply information.

It can be understood that the target differentiated first entity word in the plurality of differentiated first entity words in the reply information from the plurality of candidate departments is determined as the target department.

In another possible implementation, when the candidate department is one, and the candidate department is described as being unique, the candidate department is determined as the target department.

In one embodiment, the user only needs to describe his or her own illness through one or several periods, such as "yesterday starts throat pain, runny nose, sneeze", and the registration device or the user terminal recognizes the symptom keywords such as "throat pain", "runny nose", "sneeze" in the text as multiple target keywords. And then, calling a preset knowledge graph, and searching and positioning the target keywords to determine that the diseases corresponding to the target keywords are cold, namely the diseases of the patient are cold. And then, through a preset knowledge graph, continuously searching the target department to which the disease belongs, namely, entering the corresponding target department when the patient looks at the disease.

Based on the medical information processing method, patients do not need to have medical professional knowledge, and the assignment of departments can be completed only by describing own illness states through texts, so that the use difficulty of registering equipment or registering application is reduced, and the satisfaction degree of clients is improved; meanwhile, the registering process is simplified, the complicated selection steps of the patient are reduced to one sentence, the whole process can be completed, the steps of knowledge extraction, knowledge graph search and the like are not perceived by the client according to the 'one sentence condition description' of the patient, and the use effect of the user is improved.

In order to achieve the above functions, the medical information processing apparatus includes hardware structures and/or software modules that perform the respective functions. Those of skill in the art will readily appreciate that the various illustrative algorithm steps described in connection with the embodiments disclosed herein may be implemented as hardware or combinations of hardware and computer software. Whether a function is implemented as hardware or computer software driven hardware depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

The embodiment of the present disclosure also provides a medical information processing apparatus as shown in fig. 6, the apparatus including: an extraction unit 61, a retrieval unit 62 and a registration unit 63.

The extracting unit 61 is configured to acquire description information of the target consultation user, and extract the target keyword from the description information. The target keywords comprise first target entity words representing symptom characteristics of the target inquiry user and/or second target entity words representing corresponding diseases of the target inquiry user.

The retrieving unit 62 is configured to determine a target department corresponding to the target keyword according to a mapping relationship among the first entity word, the second entity word and the department included in the preset knowledge graph. Wherein the first entity word characterizes symptom characteristics and the second entity word characterizes diseases.

A registration unit 63 configured to determine a registration result corresponding to the target consultation user according to doctor registration information associated with the target department; doctor registration information includes whether the doctor is going out and/or the remaining registration denomination.

In one possible implementation, the retrieving unit 62 is specifically configured to: determining candidate departments corresponding to the target keywords according to the mapping relation among the first entity words, the second entity words and the departments, which are included in the preset knowledge graph; when a plurality of candidate departments are provided, generating questioning information according to first entity words corresponding to the plurality of candidate departments; pushing the questioning information to obtain reply information corresponding to the questioning information from the target questioning user account; and determining the target department from the plurality of candidate departments according to the reply information.

In another possible implementation, the retrieving unit 62 is further specifically configured to: and when the candidate department is one, determining the candidate department as the target department.

In another possible implementation, the extraction unit 61 is specifically configured to: performing word segmentation processing on the description information to obtain a plurality of segmented words; determining at least one target keyword matched with a preset word in a preset word bank from a plurality of word segments; the preset word stock includes preset words associated with disease features, symptom features, and medication features.

In another possible implementation, the extraction unit 61 is further specifically configured to: determining a plurality of candidate keywords matched with preset words in a preset library from a plurality of word segments; for any one candidate keyword in the plurality of candidate keywords, determining the similarity between the candidate keyword and other candidate keywords; and determining the keywords with the similarity with the candidate keywords being larger than a similarity threshold value in other candidate keywords and any candidate keyword as a target keyword.

In another possible implementation, the extraction unit 61 is specifically configured to: the voice information in the description information is converted into text information.

In another possible implementation, registration unit 63 is specifically configured to: determining one or more first target doctor accounts which are in a consultation state and have residual registry names from at least one doctor account associated with the target department; displaying a plurality of first target doctor accounts; and responding to the selected operation of the target user on a second target doctor account in the plurality of first target doctor accounts, and taking the selected second target doctor account as a registering result.

In another possible implementation, the extraction unit 61 is further specifically configured to: for any second entity word, taking the second entity word and a department associated with the second entity word as search keywords, and searching target medical information associated with the second entity word and the department from a plurality of target webpages; and extracting the second entity word and the first entity word associated with the department from the target medical information to construct a preset knowledge graph.

The specific manner in which the respective unit modules perform the operations in the above-described embodiments have been described in detail in relation to the embodiments of the method, and will not be described in detail herein.

Fig. 7 is a schematic diagram of an electronic device provided by the present application. As shown in fig. 7, the electronic device 50 may include at least one processor 501 and a memory 503 for storing processor-executable instructions. Wherein the processor 501 is configured to execute instructions in the memory 503 to implement the medical information processing method in the following embodiments.

In addition, the electronic device 50 may also include a communication bus 502, at least one communication interface 504, an input device 506, and an output device 505.

The processor 501 may be a processor (central processing units, CPU), microprocessor unit, ASIC, or one or more integrated circuits for controlling the execution of the programs of the present application.

Communication bus 502 may include a path to transfer information between the aforementioned components.

Communication interface 504, using any transceiver-like device for communicating with other devices or communication networks, such as ethernet, radio access network (radio access network, RAN), wireless local area network (wireless local area networks, WLAN), etc.

The input device 506 is for receiving an input signal and the output device 505 is for outputting a signal.

The memory 503 may be, but is not limited to, a read-only memory (ROM) or other type of static storage device that can store static information and instructions, a random access memory (random access memory, RAM) or other type of dynamic storage device that can store information and instructions, or an electrically erasable programmable read-only memory (electrically erasable programmable read-only memory, EEPROM), a compact disc (compact disc read-only memory) or other optical disk storage, optical disk storage (including compact disc, laser disc, optical disc, digital versatile disc, blu-ray disc, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and that can be accessed by a computer. The memory may be stand alone and be connected to the processing unit by a bus. The memory may also be integrated with the processing unit.

The memory 503 is used to store instructions for executing the present application, and is controlled by the processor 501 to execute the present application. The processor 501 is arranged to execute instructions stored in the memory 503 for implementing the functions of the method of the present application.

In a particular implementation, as one embodiment, processor 501 may include one or more CPUs, such as CPU0 and CPU1 in FIG. 7.

In a particular implementation, as one embodiment, electronic device 50 may include multiple processors, such as processor 501 and processor 507 in FIG. 7. Each of these processors may be a single-core (single-CPU) processor or may be a multi-core (multi-CPU) processor. A processor herein may refer to one or more devices, circuits, and/or processing cores for processing data (e.g., computer program instructions).

The electronic device includes, as shown in fig. 7: a processor 501 and a memory 503 for storing instructions executable by the processor 501; wherein the processor 501 is configured to execute executable instructions to implement a medical information processing method as any one of the possible embodiments described above. And the same technical effects can be achieved, and in order to avoid repetition, the description is omitted here.

The embodiment of the present application also provides a computer-readable storage medium, which when executed by a processor of a medical information processing apparatus or an electronic device, enables the medical information processing apparatus or the electronic device to perform the medical information processing method of any one of the possible embodiments described above. And the same technical effects can be achieved, and in order to avoid repetition, the description is omitted here.

Embodiments of the present application also provide a computer program product comprising a computer program or instructions for executing a medical information processing method according to any one of the possible embodiments described above by a processor. And the same technical effects can be achieved, and in order to avoid repetition, the description is omitted here.

Other embodiments of the application will be apparent to those skilled in the art from consideration of the specification and practice of the application disclosed herein. This application is intended to cover any variations, uses, or adaptations of the application following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the application pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the application being indicated by the following claims.

It is to be understood that the application is not limited to the precise arrangements and instrumentalities shown in the drawings, which have been described above, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the application is limited only by the appended claims.

Claims

1. A medical information processing method, characterized in that the method comprises:

acquiring description information of a target inquiry user, and extracting target keywords from the description information; the target keywords comprise first target entity words representing symptom characteristics of the target inquiry user and/or second target entity words representing diseases corresponding to the target inquiry user;

determining a target department corresponding to the target keyword according to a mapping relation among a first entity word, a second entity word and departments included in a preset knowledge graph; the first entity word characterizes symptom characteristics, and the second entity word characterizes diseases;

determining registration results corresponding to the target consultation users according to doctor registration information associated with the target departments; the doctor registration information includes whether the doctor is out of visit and/or the remaining registration denomination.

2. The method of claim 1, wherein the determining the target department corresponding to the target keyword according to the mapping relationship between the first entity word, the second entity word and the department included in the preset knowledge graph includes:

Determining candidate departments corresponding to the target keywords according to the mapping relation among the first entity words, the second entity words and the departments, which are included by the preset knowledge graph;

when a plurality of candidate departments are provided, generating questioning information according to first entity words corresponding to the plurality of candidate departments;

pushing the questioning information to obtain reply information corresponding to the questioning information from a target questioning user account;

and determining the target department from the plurality of candidate departments according to the reply information.

3. The method according to claim 2, wherein after determining a candidate department corresponding to the target keyword according to a mapping relationship among a first entity word, a second entity word and departments included in the preset knowledge graph; the method further comprises the steps of:

and when the candidate department is one, determining the candidate department as the target department.

4. The method of claim 1, wherein the extracting the target keyword from the description information comprises:

performing word segmentation processing on the description information to obtain a plurality of segmented words;

determining at least one target keyword matched with a preset word in a preset word bank from the plurality of word segments; the preset word stock includes preset words associated with disease features, symptom features, and medication features.

5. The method of claim 4, wherein determining at least one target keyword from the plurality of segmented words that matches a preset word in a preset word stock comprises:

determining a plurality of candidate keywords matched with the preset words in the preset library from the plurality of segmented words;

determining the similarity of any candidate keyword in the plurality of candidate keywords with other candidate keywords;

and determining the keywords with the similarity larger than a similarity threshold value in other candidate keywords and any candidate keyword as a target keyword.

6. The method of claim 4, wherein prior to word segmentation of the descriptive information, the method further comprises:

and converting the voice information in the description information into text information.

7. The method according to any one of claims 1 to 6, wherein the determining, according to doctor registration information associated with the target department, a registration result corresponding to the target interview user includes:

determining one or more first target doctor accounts which are in a consultation state and have residual registry names from at least one doctor account associated with the target department;

Displaying the plurality of first target doctor accounts;

and responding to the selected operation of the target user on a second target doctor account in the plurality of first target doctor accounts, and taking the selected second target doctor account as the registering result.

8. A medical information processing apparatus, characterized in that the apparatus comprises:

an extraction unit configured to acquire description information of a target consultation user, and extract a target keyword from the description information; the target keywords comprise first target entity words representing symptom characteristics of the target inquiry user and/or second target entity words representing diseases corresponding to the target inquiry user;

the retrieval unit is configured to determine a target department corresponding to the target keyword according to a mapping relation among a first entity word, a second entity word and departments included in a preset knowledge graph; the first entity word characterizes symptom characteristics, and the second entity word characterizes diseases;

the registering unit is configured to determine registering results corresponding to the target consultation users according to doctor registering information associated with the target departments; the doctor registration information includes whether the doctor is out of visit and/or the remaining registration denomination.

9. An electronic device, comprising:

a processor and a memory for storing instructions executable by the processor; wherein the processor is configured to execute the executable instructions to implement the medical information processing method of any one of claims 1-6.

10. A computer readable storage medium having instructions stored thereon, which, when executed by a processor of an electronic device, enable the electronic device to perform the medical information processing method according to any one of claims 1-6.