CN114420242A

CN114420242A - Medical auxiliary information display method, system, equipment and medium based on voice input

Info

Publication number: CN114420242A
Application number: CN202210075343.9A
Authority: CN
Inventors: 王林
Original assignee: Ping An International Smart City Technology Co Ltd
Current assignee: Ping An International Smart City Technology Co Ltd
Priority date: 2022-01-22
Filing date: 2022-01-22
Publication date: 2022-04-29

Abstract

The embodiment of the application discloses a medical and auxiliary information display method, a medical and auxiliary information display system, medical and auxiliary information display equipment and a medium based on voice input, wherein the medical and auxiliary information display method based on voice input is applied to a voice medical and auxiliary system, the voice medical and auxiliary system comprises a microphone, a medical and auxiliary processor and a medical and auxiliary display, and the method comprises the following steps: determining candidate disease information and candidate treatment information corresponding to the candidate disease information according to the acquired disease information of the patient through a medical auxiliary processor, determining confirmed disease information according to the disease voice information and the candidate disease information input by the doctor and acquired through a microphone, determining taken medicine information according to the treatment voice information and the candidate treatment information input by the doctor and acquired through the microphone, and displaying the confirmed disease information and the taken medicine information through a medical auxiliary display. According to the embodiment of the application, the doctor's efficiency of seeing a doctor can be improved.

Description

Medical auxiliary information display method, system, equipment and medium based on voice input

Technical Field

The embodiment of the application relates to the field of Artificial Intelligence (AI), in particular to a medical and auxiliary information display method, system, equipment and medium based on voice input.

Background

When a doctor looks at a hospital, the doctor needs to make judgment and take medicines according to symptoms when the doctor faces symptoms and problems of a patient. In this process, the doctor needs to log in a Hospital Information System (HIS) and add information about the patient. Such as personal information, symptom information, and case information. The physician can then determine the patient's disease based on the user's examination report and the information described above. After a physician determines the disease from which a patient has, the disease and the corresponding medication to treat the patient may be manually entered into the HIS system.

Based on the above-mentioned doctor's flow of seeing a doctor, after confirming the disease of patient, must add or select the medicine and enter the system, however, in this process, the name of disease and the name of medicine are the rare word mostly, the degree of difficulty of doctor's manual input is big, and is inefficient, and the mode of selecting or pulling down the page to look for, because the sequencing of different diseases is different in order, the inefficiency of operation.

Disclosure of Invention

The embodiment of the application discloses a medical auxiliary information display method, a medical auxiliary information display system, medical auxiliary information display equipment and a medical auxiliary information display medium based on voice input, which are used for improving doctor seeing efficiency.

The first aspect discloses a medical and auxiliary information display method based on voice input, which is applied to a voice medical and auxiliary system, wherein the voice medical and auxiliary system comprises a microphone, a medical and auxiliary processor and a medical and auxiliary display, and the method comprises the following steps: determining candidate disease information and candidate treatment information corresponding to the candidate disease information according to the acquired disease information of the patient through the medical auxiliary processor, determining confirmed disease information according to the disease voice information input by the doctor and the candidate disease information acquired through the microphone, determining medicine taking information according to the treatment voice information input by the doctor and the candidate treatment information acquired through the microphone, and displaying the confirmed disease information and the medicine taking information through the medical auxiliary display.

In the embodiment of the application, under the condition that the doctor inputs the disease voice information and the treatment voice information, the confirmed disease information and the medicine information can be determined based on the voice information, the candidate disease information and the candidate treatment information, so that the manual input times of the doctor can be reduced, and the efficiency of the doctor for reporting (an electronic prescription, a medical record list and the like) for a patient is improved. In addition, when the voice information is directly converted, the semantic conversion range is large, even the disease range is large, the probability of selecting the correct information from massive data is smaller than that of selecting the correct information from a small amount of information, therefore, the candidate disease information and the candidate treatment information can be determined in advance, and the accuracy of the confirmed disease information and the medicine information can be improved.

As a possible implementation manner, the determining candidate disease information and candidate treatment information corresponding to the candidate disease information according to the acquired disease information of the patient includes: matching diseases similar to the disease information of the patient from a disease database to obtain candidate disease information, wherein the candidate disease information comprises N diseases, N is a positive integer, and the disease database comprises the corresponding relation between various diseases and the disease information; and matching the drug information of the N diseases from a treatment database to obtain candidate treatment information, wherein the candidate treatment information comprises treatment drugs corresponding to the N diseases, and the treatment database comprises the corresponding relation between a plurality of diseases and the drug information.

In the embodiment of the application, the voice medical assistance system can determine the diseases possibly suffered by the patient firstly, the diseases can be obtained by operation based on the case database, and the obtained candidate disease information and the range of the candidate treatment information can be ensured to cover the diseases and the medicines determined for the doctor, so that the voice range input by the doctor can be reduced in advance, and the accuracy of outputting the confirmed diseases and taking the medicines by the voice medical assistance system is ensured.

As a possible implementation, the determining diagnosed disease information according to the disease voice information and the candidate disease information collected by the microphone and input by the doctor comprises: inputting disease voice information input by a doctor and acquired by the microphone into a disease feature extraction model to acquire disease features; matching the disease characteristics with the disease characteristics of the voice information of each disease in the candidate disease information to obtain the disease matching degree of each disease; and determining the disease with the highest disease matching degree in the candidate disease information as the confirmed disease to obtain the confirmed disease information. In the embodiment of the application, the voice medical assistance system can determine the diseases possibly suffered by the patient firstly, the diseases can be obtained by calculation based on the case database, the range of the acquired candidate disease information can be ensured to cover the diseases determined by the doctor, the range of the voice information input by the doctor can be reduced in advance, and the accuracy of converting the disease voice information into the confirmed disease information can be ensured. In addition, the disease options are sorted according to the sequence of the matching degree from large to small, so that the doctor is more likely to select the disease options in the former sequence, the possibility that the user pulls down the disease options is reduced, and the operation efficiency of the doctor can be improved.

As a possible implementation manner, in the case that the treatment voice information includes medicine voice information, the determining to take medicine information according to the treatment voice information and the candidate treatment information includes: inputting the medicine voice information into a medicine feature extraction model to obtain medicine features; matching the medicine characteristics with the medicine characteristics of the medicine voice information of each disease in the candidate treatment information to obtain the corresponding medicine matching degree of each disease; and determining the medicine information corresponding to the disease with the highest medicine matching degree in the candidate treatment information as the medicine to be taken to obtain the medicine to be taken information.

In the embodiment of the application, the voice medical assistance system can display the pre-selected candidate treatment information, so that a doctor can directly select one of the candidate treatment information, and the accuracy of the doctor in determining to take the medicine can be ensured. In addition, the medicine options are sorted according to the sequence of the matching degree from large to small, so that the doctor is more likely to select the medicine options in the former sequence, the possibility that the user pulls down the medicine options is reduced, and the operation efficiency of the doctor can be improved.

As a possible implementation, the treatment voice information further includes plan voice information, and the determining candidate disease information according to the acquired disease condition information of the patient and the candidate treatment information corresponding to the candidate disease information further include: matching scheme information of the N diseases from a treatment database to obtain candidate treatment information, wherein the candidate treatment information comprises scheme medicines corresponding to the N diseases, and the treatment database comprises corresponding relations between a plurality of diseases and the scheme information; the method further comprises the following steps: inputting the scheme voice information acquired by the microphone and input by a doctor into a scheme feature extraction model through the medical auxiliary processor to acquire scheme features; matching the scheme characteristics with the scheme characteristics of the scheme voice information of each disease in the candidate treatment information to obtain the corresponding scheme matching degree of each disease; determining the scheme information of the disease with the highest scheme matching degree in the candidate treatment information as a treatment scheme to obtain treatment scheme information; and displaying the treatment scheme information through the medical auxiliary display.

In the embodiment of the application, for the treatment scheme of the existing diseases, the voice medical assistance system can also be matched through the voice information, so that the treatment scheme can be directly determined, the doctor can also reduce the input time cost, and the seeing efficiency is improved.

As a possible implementation, the method further comprises: adjusting the confirmed disease information and the taken medicine information through the medical auxiliary processor; the displaying the diagnosed disease information and the taken medicine information through the medical auxiliary display comprises: and displaying the adjusted information of the diagnosed diseases and the adjusted information of the taken medicines.

In the embodiment of the application, the voice medical assistant system provides a disease and medicine ensuring scheme, so that under the condition that the selected diseases in the current case database and the treatment database are incorrect, correct information capable of ensuring the determined diseases and medicines is provided for a doctor, and the completeness of the scheme can be ensured. Therefore, the problem of wrong voice prediction caused by insufficient range of a case database and a treatment database or imperfect algorithm can be solved at a very small probability, and the correctness of the diagnosis report issued by a doctor is ensured.

As a possible implementation, after determining diagnosed disease information according to the disease voice information input by the doctor and the candidate disease information collected by the microphone, the determining to take medicine information according to the treatment voice information input by the doctor and the candidate treatment information collected by the microphone comprises: screening pre-selected drug information from the candidate treatment information based on the diagnosed disease information; and determining the taken medicine from the pre-selected medicine information based on the treatment voice information input by the doctor and collected by the microphone, so as to obtain the taken medicine information.

In the embodiment of the application, the voice medical assistant system can further narrow the range of the used medicines based on the diagnosed disease information which is selected by the doctor, namely, the pre-selected medicine information. Thereby further improving the accuracy of the matched medicine.

A second aspect discloses a voice medical assistance system, which includes a microphone, a medical assistance processor, and a medical assistance display: the microphone is used for collecting disease voice information and treatment voice information input by a doctor; the medical auxiliary processor is used for determining candidate disease information and candidate treatment information corresponding to the candidate disease information according to the acquired disease information of the patient; determining diagnosed disease information according to the disease voice information and the candidate disease information, and determining medicine taking information according to the treatment voice information and the candidate treatment information; the medical auxiliary display is used for displaying the confirmed disease information and the taken medicine information.

As a possible implementation manner, the medical assistance processor determines candidate disease information and candidate treatment information corresponding to the candidate disease information according to the acquired disease information of the patient, and is specifically configured to: matching diseases similar to the disease information of the patient from a disease database to obtain candidate disease information, wherein the candidate disease information comprises N diseases, N is a positive integer, and the disease database comprises the corresponding relation between various diseases and the disease information; and matching the drug information of the N diseases from a treatment database to obtain candidate treatment information, wherein the candidate treatment information comprises treatment drugs corresponding to the N diseases, and the treatment database comprises the corresponding relation between a plurality of diseases and the drug information.

As a possible implementation manner, the medical assistant processor determines diagnosed disease information according to the disease speech information and the candidate disease information, and is specifically configured to:

inputting disease voice information input by a doctor and acquired by the microphone into a disease feature extraction model to acquire disease features; matching the disease characteristics with the disease characteristics of the voice information of each disease in the candidate disease information to obtain the disease matching degree of each disease; and determining the disease with the highest disease matching degree in the candidate disease information as the confirmed disease to obtain the confirmed disease information.

In the embodiment of the application, the voice medical assistance system can determine the diseases possibly suffered by the patient firstly, the diseases can be obtained by calculation based on the case database, the range of the acquired candidate disease information can be ensured to cover the diseases determined by the doctor, the range of the voice information input by the doctor can be reduced in advance, and the accuracy of converting the disease voice information into the confirmed disease information can be ensured. In addition, the disease options are sorted according to the sequence of the matching degree from large to small, so that the doctor is more likely to select the disease options in the former sequence, the possibility that the user pulls down the disease options is reduced, and the operation efficiency of the doctor can be improved.

As a possible implementation manner, in the case that the treatment voice information includes medicine voice information, the medical assistant processor determines to take medicine information according to the treatment voice information and the candidate treatment information, and is specifically configured to: inputting the medicine voice information which is acquired by the microphone and input by a doctor into a medicine feature extraction model to acquire medicine features; matching the medicine characteristics with the medicine characteristics of the medicine voice information of each disease in the candidate treatment information to obtain the corresponding medicine matching degree of each disease; and determining the medicine information corresponding to the disease with the highest medicine matching degree in the candidate treatment information as the medicine to be taken to obtain the medicine to be taken information.

As a possible implementation, the treatment voice information further includes protocol voice information, and the medical assistance processor is further configured to: matching scheme information of the N diseases from a treatment database to obtain candidate treatment information, wherein the candidate treatment information comprises scheme medicines corresponding to the N diseases, and the treatment database comprises corresponding relations between a plurality of diseases and the scheme information; inputting the scheme voice information acquired by the microphone and input by a doctor into a scheme feature extraction model to acquire scheme features; matching the scheme characteristics with the scheme characteristics of the scheme voice information of each disease in the candidate treatment information to obtain the corresponding scheme matching degree of each disease; determining the scheme information of the disease with the highest scheme matching degree in the candidate treatment information as a treatment scheme to obtain treatment scheme information; the medical auxiliary display is also used for displaying the treatment scheme information.

As a possible implementation, the medical assistance processor is further configured to: adjusting the confirmed disease information and the taken medicine information; the medical auxiliary display displays the confirmed disease information and the taken medicine information, and is specifically used for: and displaying the adjusted information of the diagnosed diseases and the adjusted information of the taken medicines.

As a possible implementation manner, after determining diagnosed disease information according to the disease voice information input by the doctor and the candidate disease information collected by the microphone, the medical assistant processor determines to take medicine information according to the treatment voice information input by the doctor and the candidate treatment information collected by the microphone, and is specifically configured to: screening pre-selected drug information from the candidate treatment information based on the diagnosed disease information; and determining the taken medicine from the pre-selected medicine information based on the treatment voice information input by the doctor and collected by the microphone, so as to obtain the taken medicine information.

A third aspect discloses an electronic device for voice medical assistance, which may include: the medical auxiliary information display device comprises a processor, a memory, an input interface and an output interface, wherein the input interface is used for receiving information from other devices except the device, the output interface is used for outputting information to other devices except the device, and when the processor executes a computer program stored in the memory, the processor is enabled to execute the medical auxiliary information display method based on voice input disclosed by the first aspect or any embodiment of the first aspect.

A fourth aspect discloses a computer-readable storage medium, in which a computer program or computer instructions are stored, and when the computer program or the computer instructions are executed, the method for displaying medical and auxiliary information based on voice input as disclosed in the first aspect or any implementation manner of the first aspect is implemented.

A fifth aspect discloses a computer program product comprising computer program code which, when executed, causes the above-described method to be performed.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.

Fig. 1 is a schematic structural diagram of a network architecture disclosed in an embodiment of the present application;

FIG. 2 is a flowchart illustrating a method for displaying medical assistance information based on voice input according to an embodiment of the present application;

FIG. 3 is a schematic structural diagram of a speech medical assistance system disclosed in an embodiment of the present application;

FIG. 4 is a schematic diagram of an application interface disclosed in an embodiment of the present application;

FIG. 5 is a schematic diagram of another application interface disclosed in embodiments of the present application;

FIG. 6 is a schematic illustration of yet another application interface disclosed in embodiments of the present application;

fig. 7 is a schematic structural diagram of an electronic device disclosed in an embodiment of the present application.

Detailed Description

In order to better understand the embodiments of the present application, an application scenario of the embodiments of the present application is described below.

In the current process of seeing a doctor's doctor, a hospital management information system (HIS) is often used. The HIS system takes financial information, patient information and material information as main lines, and provides comprehensive and accurate various data for leaders of hospitals and managers of all departments in time through information collection, storage, transmission, statistics, analysis, comprehensive query, report output and information sharing. In the doctor treatment process, the HIS system mainly performs examination information input, electronic prescription issuing, patient medical record writing, outpatient operation treatment application forms, various medical technical examination application forms editing and the like on a patient to be treated.

However, in the above-mentioned procedure of the doctor to make reports such as electronic prescription and patient medical record through the HIS system, the doctor needs to manually input the corresponding diseases and medicines. However, the speed of manual input by the doctor is slow, and the input diseases or drugs are often uncommon words, so that the difficulty of input is high, and the efficiency of report completion by the doctor is low.

In the embodiment of the application, a medical and auxiliary information display method based on voice input is provided, and a voice medical and auxiliary system can determine candidate disease information and candidate treatment information based on collected disease information, and respectively match the acquired disease voice information (disease voice input by a doctor) and treatment voice information (medicine and/or treatment means voice input by the doctor) with the candidate disease information and the candidate treatment information to obtain confirmed disease information and medicine taking information of a patient, so that an electronic prescription, a case list and the like can be generated based on the confirmed disease information and the medicine taking information of the patient. Electronic prescriptions and case lists, etc. may be displayed for review by the physician. Therefore, doctors can directly input disease voice information and treatment voice information to the voice medical assistant system through speaking, so that electronic prescriptions, diagnosis results and the like can be generated, and the doctor seeing efficiency is improved.

Fig. 1 is a schematic structural diagram of a network architecture according to an embodiment of the present application. As shown in fig. 1, the network architecture may include a server and a client. The client may specifically include one or more terminal devices. The client and the server can be directly or indirectly connected with a network in a wired or wireless communication mode, so that the client and the server can conveniently perform data interaction through the network connection.

Wherein, each terminal device in the client can include: the intelligent terminal with the voice medical assistance function comprises an intelligent terminal with the voice medical assistance function, such as an intelligent mobile phone, a tablet computer, a notebook computer, a desktop computer, an intelligent home, a wearable device and the like.

The server can be a server corresponding to the client, namely a cloud connected to the hospital, and can be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, and a cloud server providing basic cloud computing services such as cloud service, a cloud database, cloud computing, a cloud function, cloud storage, network service, cloud communication, middleware service, domain name service, security service, CDN, big data and an artificial intelligent platform.

The client can be integrated with a collection component for collecting patient information, wherein the collection component can comprise a disease statistical system for counting the disease information of patients; a microphone may also be included for collecting voice information of the doctor.

It can be understood that the medical auxiliary information display method based on voice input provided by the present application may be executed by a computer device, and the computer device may be the client, the server, or both the client and the server. In a possible case, in a case where the voice input-based medical-assistance information display method provided by the present application is executed by a client, the client may acquire candidate disease information and candidate treatment information based on the condition information acquired by the acquisition component, determine diagnosed disease information based on the disease voice information and the candidate disease information, and determine taken-medicine information based on the treatment voice information and the candidate treatment information, and then the client may display the diagnosed disease information and the taken-medicine information. In another possible case, when the medical and auxiliary information display method based on voice input provided by the application is executed by the server and the client, the client may send the disease information, the disease voice information, and the treatment voice information acquired based on the acquisition component to the server. After receiving the disease information, the disease voice information and the treatment voice information provided by the acquisition component from the client, the server processes the disease information, the disease voice information and the treatment voice information to obtain the confirmed disease information and the medicine information, and then the server can send the confirmed disease information and the medicine information to the client. After receiving the diagnosed disease information and the medicine information from the server, the client can display the diagnosed disease information and the medicine information. It is to be understood that the above description is intended to be illustrative, and not restrictive.

Referring to fig. 2, fig. 2 is a schematic flow chart of a medical auxiliary information display method based on voice input according to an embodiment of the present application. Wherein:

the specific steps of the voice input medical and auxiliary information display method can be executed through the voice medical and auxiliary system, and the voice medical and auxiliary system can be installed on the server and/or the client. Fig. 3 is a schematic structural diagram of a speech medical assistance system disclosed in the embodiment of the present application. As shown in FIG. 3, the voice medical-assisted system may include a microphone 301, a medical-assisted processor 302, and a medical-assisted display 303. The medical secondary processor 302 may be connected to a microphone 301 and a medical secondary display 303. Wherein, the microphone 301 can collect disease voice information and treatment voice information input by doctors. The medical assistance processor 302 can determine diagnosed disease information and medication information based on the disease speech information and the treatment speech information. The medical-assistance display 303 may display information on confirmed diseases and information on drugs to be administered. At this time, the voice medical assistant system may perform, but is not limited to, the following steps:

s201, the voice medical assistant system collects disease voice information and treatment voice information.

The disease voice information comprises voice information of diseases, and the treatment voice information comprises medicine voice information and/or treatment scheme voice information.

After the doctor judges the disease condition of the patient, disease voice information (i.e., disease information for diagnosis of the patient) can be input to the microphone. The voice medical assistant system can collect disease voice information input by a doctor through the microphone 301. Similarly, after the doctor needs to take, apply or inject a medicine to the patient, the doctor can input treatment voice information (i.e. information about the medicine to be used by the patient) into the microphone. The voice medical assistant system can collect the treatment voice information input by the doctor through the microphone 301.

S202, the voice medical assistance system determines candidate disease information and candidate treatment information corresponding to the candidate disease information according to the acquired disease information of the patient; and determining confirmed disease information according to the disease voice information and the candidate disease information, and determining medicine taking information according to the treatment voice information and the candidate treatment information.

First, the voice assistant system can obtain the disease information of the patient through the assistant processor 302.

The condition information may include one or more of symptom information, case information, and image information, among others. The symptom information is physical symptom information indicating that the patient is ill, the case information may indicate history information of the patient's ill, and the image information may indicate photographed image information of the patient, such as an X-ray film or the like. In addition, the condition information may also include personal information of the patient, such as age, sex, and the like.

After the voice medical assistance system obtains the patient's condition information, the condition information from the physician input or obtained from the system may be received by the medical assistance processor 302.

In one possible embodiment, the physician may input the patient's symptom information to the voice assistant system, for example, the physician may type or speak the symptom information and personal information into the input interface. The patient may carry his or her own case report and the physician may enter case information based on the case report provided by the patient. After the patient has been filmed, an image picture (i.e., image information) can be obtained. In one case, the voice medical assistant system may acquire image information from a system within the hospital. In another case, the doctor can input the image information to the voice assistant system through the image picture provided by the patient, and the voice assistant system can obtain the image information.

Second, the voice medical-assisted system may determine candidate disease information and candidate treatment information based on the acquired condition information of the patient through the medical-assisted processor 302.

The candidate disease information is N diseases possibly suffered by the patient, and the candidate treatment information comprises treatment medicines and/or treatment schemes (means) corresponding to the N diseases. Wherein N is a positive integer.

The voice assistant system may determine candidate disease information via the assistant processor 302.

The medical assistance processor 302 may match a disease from the disease database that is similar to the patient's disease information. Wherein, the disease database is a database of diseases and symptoms stored by the voice assistant system, the disease database can comprise massive doctor diagnosis case data, and the disease database can be a database updated in real time. The candidate disease information may include information of N diseases that match the patient's condition information most closely. It is to be understood that the candidate disease information is information that the medical assistance processor 302 has diagnosed a disease that the user may have.

Because the corresponding relation between symptoms and diseases is stored in the disease database, and the symptoms of the patient are known in the disease information, the disease information can be matched with the disease database to determine the diseases which the patient may suffer from, so that several diseases which the patient may suffer from can be determined, and the candidate disease information is determined by sequencing according to the probability from high to low.

In a possible implementation manner, after acquiring the disease information, the medical assistance processor 302 may extract keywords from the disease information, and input the keywords into the disease database for searching through a search engine algorithm, that is, may query information of a corresponding disease to obtain a search result. And then selecting the first N diseases in the search result as candidate disease information. Wherein the search engine may be a search engine that searches disease information for a database of disorders.

In another possible implementation, after the medical assistant processor 302 obtains the disease information, the matching degree between the disease information and the disease information in the disease database may be calculated based on the matching model, and then the results are sorted according to the size of the matching degree, and the matching degree greater than a certain threshold is selected as N diseases in the candidate disease information. The information of the N diseases is candidate disease information, and the threshold may be a preset threshold, such as 65%, and the size of the threshold is not limited herein. The matching model may be one of a semantic model of a depth network (DSSM), a convolutional Neural network-based semantic model (CNN-DSSM), a cyclic Neural network-based semantic model (RNN-DSSM, a cyclic Neural network deep structured semantic model), a secure Neural network, a long-short term memory Neural network-based semantic model (LSTM-DSSM, long-short term memory structured semantic model), and the like. By the matching model, the accuracy of the obtained candidate disease information can be ensured.

The voice assistant system may determine candidate treatment information corresponding to the candidate disease information from the treatment database through the assistant processor 302.

After the medical assistant processor 302 acquires the candidate disease information, the treatment information corresponding to each of the N diseases may be selected from the treatment database as the candidate treatment information. Wherein, the treatment database can comprise massive disease treatment means and/or medicines. The candidate treatment information may include treatment regimen information and/or drug information. For example, the use of drugs for a disease, a surgical plan for a surgery, a rehabilitation plan for a burn patient, etc. are not limited. Aiming at the known candidate disease information, the voice medical assistant system respectively inquires the treatment information corresponding to the N diseases, and the corresponding treatment information of the N diseases corresponding to the candidate disease information is the candidate treatment information. Namely, the N diseases in the candidate disease information have corresponding relations with the treatment means and the drugs of the candidate treatment information.

In the above embodiment, the voice medical assistant system may first calculate the diseases that the patient may suffer from through the medical assistant processor 302, and the diseases can be obtained through calculation based on the case database, so that it can be ensured that the obtained candidate disease information and the range of the candidate treatment information can cover the diseases and the medicines determined by the doctor, and thus the voice range input by the doctor can be reduced in advance, so as to ensure the accuracy of the voice medical assistant system in outputting the diagnosed diseases and taking the medicines.

It should be noted that, the step execution sequence of determining the candidate disease information and the candidate treatment information according to the disease information in S201 and S202 is not limited, and S201 may be executed first to obtain the voice information of the doctor, and then to determine the candidate disease information and the candidate treatment information; the determination of the candidate disease information and the candidate treatment information based on the disease condition information may be performed first, and then S201 may be performed.

Finally, the voice medical-assisted system can determine the confirmed disease information according to the disease voice information and the candidate disease information and determine the medicine taking information according to the treatment voice information (medicine voice information) and the candidate treatment information through the medical-assisted processor 302. Alternatively, the medical assistant processor 302 may determine the treatment plan information from the treatment voice information (plan voice information) and the candidate treatment information.

After the voice medical assistance system is acquired, the medical assistance processor 302 of the voice medical assistance system can input disease voice information, which is acquired by a microphone and input by a doctor, into the disease feature extraction model to acquire disease features, and match the disease features with the disease features of the voice information of each disease in the candidate disease information to acquire a disease matching degree of each disease; and finally, determining the disease with the highest disease matching degree in the candidate disease information as the confirmed disease to obtain the confirmed disease information.

In one possible implementation, the voice medical-assistance system may convert the candidate disease information into candidate disease voice information via the medical-assistance processor 302. Wherein, the candidate disease voice information comprises the voice information of the N candidate diseases. And then, inputting the candidate disease voice information into a certain disease feature extraction model to obtain candidate disease features of the N diseases. The medical assistant processor 302 can then output the disease voice information input by the doctor and collected by the microphone to the disease feature extraction model to obtain the disease features. Then, the medical assistant processor 302 may match the disease features with the candidate disease features of the N diseases, determine the disease matching degree between the N candidate disease features and the disease features, and use one disease with the highest matching degree among the N candidate disease features as the confirmed disease information.

It should be noted that the feature extraction model or algorithm may be models such as a Convolutional Neural Network (CNN), a Recurrent Neural Network (RNN), and an RNN, or may be a vector feature extraction vector, and at this time, the disease feature extraction model may extract vector features of a disease. The algorithm for calculating the matching degree may be an edit distance algorithm (edit distance), an n-gram algorithm, a Jaro Winkler algorithm, a Soundex algorithm, and the like, without limitation.

The conversion of the candidate disease information into the candidate disease speech information may be a process of converting text (text) information into speech information (TTS), and the process involves various algorithms or models, such as a Tactron model, without limitation.

For example, the voice medical assistant system may calculate the disease matching degrees between the candidate disease features of the N diseases and the disease features, and generate a disease feature matching degree list.

TABLE 1

Serial number	Disease (candidate disease characteristics)	Degree of matching
			1	Disease 1	88.9％
2	Disease 2	72.5％
			3	Disease 3	60.1％
……	……	……
			N	Disease N	58.0％

Table 1 is a list of disease feature matching degrees disclosed in the embodiments of the present application. As shown in table 1, N diseases are included in table 1, wherein the degree of match between the disease characteristics and disease 1 in the candidate disease characteristics is 88.9%; the degree of match between the disease signature and disease 2 in the candidate disease signature is 72.5%; the matching degree between the disease characteristics and the disease 3 in the candidate disease characteristics is 60.1%; … …, respectively; the match between the disease signature and disease N in the candidate disease signature was 58.0%. The disease features are sorted from small to large according to the matching degree. At this time, the medical assistant processor 302 can select the disease 1 therein as the confirmed disease information.

In the above embodiment, the voice assistant system may first calculate the diseases that the patient may suffer from through the assistant processor 302, and the diseases can be obtained through calculation based on the case database, so as to ensure that the range of the obtained candidate disease information can cover the diseases determined by the doctor, and thus the range of the voice information input by the doctor can be narrowed in advance, and the accuracy of converting the disease voice information into the confirmed disease information can be ensured.

In another possible implementation, the voice medical-assistance system may convert the candidate disease information into candidate disease voice information through the medical-assistance processor 302. Wherein, the candidate disease voice information comprises the voice information of the N diseases. And then the voice medical assistant system can compare the disease voice information with the voice information of N diseases in the candidate disease voice information one by one, determine the matching degree between the voice information of the N diseases and the disease voice information, and sort the matching degree in the order from high to low to obtain first disease sorting information. The medical secondary display 303 may display the first disease ranking information. After the doctor views the first disease ranking information on the display screen in response, the doctor can select one disease from the first disease ranking information as the information of the diagnosed disease.

For example, the voice medical assistant system may calculate the matching degree between the disease voice information and the candidate disease voice information, and generate a disease matching degree list. The voice medical assistant system can then display based on the list of disease matching degrees. Fig. 4 is a schematic diagram of an application interface disclosed in an embodiment of the present application. As shown in (a) of fig. 4, after the voice medical assistant system acquires the above-mentioned disease matching degree list (as in table 1), a screen of (a) of fig. 4 may be displayed based on table 1. N disease options (i.e., first disease ranking information) for disease 1 through disease N in table 1 may be sequentially displayed under a pre-selected box for disease determination, and in the case where the doctor determines that the disease of the current patient is disease 1, the doctor may click on the option for disease 1. As shown in (B) of fig. 4, the voice medical assistant system may display the disease option selected by the doctor, i.e., disease 1. At this time, the voice medical assistant system can determine that the currently diagnosed disease is disease 1.

In the above embodiment, the voice medical assistant system can display the pre-selected candidate disease information, so that the doctor can directly select one of the candidate disease information, thereby ensuring the accuracy of the doctor in determining the diagnosed disease. In addition, as the disease options in (a) in fig. 4 are sorted in the order of the matching degree from high to low, the doctor is more likely to select the disease options in the earlier order, the possibility that the user pulls down the disease options is reduced, and the operation efficiency of the doctor can be improved.

The voice medical assistant system determines medicine taking information based on the treatment voice information and the candidate treatment information.

After the voice medical assistant system acquires the treatment voice information, inputting medicine voice information acquired by a microphone and input by a doctor into a medicine feature extraction model to acquire medicine features; matching the medicine characteristics with the medicine characteristics of the medicine voice information of each disease in the candidate treatment information to obtain the corresponding medicine matching degree of each disease; and determining the medicine information corresponding to the disease with the highest medicine matching degree in the candidate treatment information as the medicine to be taken to obtain the medicine to be taken information.

In one possible implementation, the voice medical-assistance system may convert the candidate treatment information into candidate treatment voice information via the medical-assistance processor 302. Wherein, the candidate treatment voice information comprises candidate drug voice information corresponding to the N diseases. And then, inputting the voice information of the candidate drugs corresponding to the N diseases into the drug feature extraction model to obtain the candidate drug features corresponding to the N diseases. The medical assistant processor 302 may then input the acquired voice information of the drug into the drug feature extraction model to acquire the drug features. Then, the candidate medicine features corresponding to the N diseases can be matched with the medicine features to obtain the corresponding medicine matching degree of each disease, and then the medicine matching degrees can be ranked from small to small, and the candidate medicine information of the disease with the highest medicine matching degree is determined as the medicine taking information. It should be noted that, the specific drug feature extraction algorithm may refer to the above-mentioned process for obtaining a diagnosed disease, and the detailed description is omitted.

For example, the voice assistant system may calculate the drug feature matching degrees of the candidate drug features corresponding to the N diseases and the drug features, and generate a drug feature matching degree list.

TABLE 2

Serial number	Medicine (candidate therapeutic characteristics)	Degree of matching
			1	Medicine 1	88.9％
2	Medicine 2	72.5％
			3	Medicine 3	60.1％
……	……	……
			M	Medicine M	58.0％

Table 2 is a list of drug feature matching degrees disclosed in the embodiments of the present application. As shown in table 2, M drugs are included in table 2, and each drug may include one or more drugs, without limitation. Wherein, the matching degree between the candidate medicine characteristics corresponding to the N diseases and the medicine 1 in the medicine characteristics is 88.9 percent; the matching degree between the candidate medicine characteristics corresponding to the N diseases and the medicine 2 in the medicine characteristics is 72.5 percent; the matching degree between the candidate medicine characteristics corresponding to the N diseases and the medicine 3 in the medicine characteristic information is 60.1 percent; … …, respectively; the matching degree between the candidate drug characteristics corresponding to the N diseases and the drug M in the drug characteristics is 58.0%. The matching degrees of the medicine characteristics are sequentially sorted from small to large. At this time, the voice medical assistant system selects the medicine 1 as the medicine taking information.

In the above embodiment, the electronic device may calculate, through the medical assistant processor 302, the medicines that may be taken by different diseases that the patient may suffer from, and these medicines may be calculated based on the treatment database, and it may be ensured that the range of the obtained candidate treatment information may cover the medicines determined for the doctor, so that the range of the voice information input by the doctor may be narrowed in advance, and the accuracy of converting the treatment voice information into the information of taking the medicines may be ensured.

In another possible implementation, the voice medical-assisted system may convert the drug candidate information into drug candidate voice information via the medical-assisted processor 302. Wherein, the candidate drug voice information comprises the voice information of the candidate drug corresponding to the N diseases. Then, the voice medical assistance system may compare the treatment voice information with the voice information of the candidate drugs for the N diseases in the candidate treatment voice information one by one, determine a matching degree between the voice information of the candidate drugs for the N diseases and the drug voice information included in the treatment voice information, and sort the matching degree in order from high to low to obtain the drug sorting information (e.g., table 2). The secondary medical display 303 may display medication order information. After the physician views the medication order information on the responsive display screen, the physician may select a medication from the medication order information as the medication to be taken.

For example, the voice medical assistant system may calculate the matching degree between the treatment voice information and the candidate treatment voice information, and generate a drug matching degree list. The voice medical assistant system can then display based on the drug matching degree list. Fig. 5 is a schematic diagram of another application interface disclosed in the embodiments of the present application. As shown in fig. 5 (a), after the voice medical assistant system acquires the above-mentioned drug matching degree list (as in table 2), a screen of fig. 5 (a) may be displayed based on table 2. The M drug options (i.e., the first drug order information) for drug 1 through drug M in table 2 may be displayed in order under the pre-selection box for taking the drugs, and the physician may click on the drug 1 option in the case where the selected drug for the current patient is confirmed to be drug 1. As shown in fig. 5 (B), the voice medical-assistance system may display the drug option selected by the doctor, i.e., drug 1. At this time, the voice medical assistant system may determine that the currently taken medicine is disease 1.

In the above embodiment, the voice medical-assisted system can display the pre-selected candidate treatment information, so that the doctor can directly select one of the candidate treatment information, thereby ensuring the accuracy of the doctor in determining to take the medicine. In addition, since the medicine options in (a) in fig. 5 are sorted in the order of the matching degree from high to low, the doctor is more likely to select the medicine options in the earlier order, the possibility that the user pulls down the medicine options is reduced, and the operation efficiency of the doctor can also be improved.

In yet another possible embodiment, the voice medical assistant system may screen the candidate treatment information or the treatment database for pre-selected drug information based on the confirmed disease information selected by the doctor, and then may determine the drug to be taken from the pre-selected drug information based on the treatment voice information to obtain the drug to be taken information. Specifically, since the diagnosed disease information is a disease determined by a doctor, the voice medical assistant system can directly delineate the scope of the pre-selected drug information based on the diagnosed disease information. When the candidate treatment information contains the medicine information corresponding to the disease in the confirmed disease information, the voice medical assistance system can directly determine the medicine for treating the corresponding disease from the candidate treatment information as the pre-selected medicine information. When the candidate treatment information does not contain the medicine information corresponding to the disease in the confirmed disease information, the voice medical assistance system can determine the medicine for treating the corresponding disease from the treatment database as the pre-selected medicine information. After the preselected medicine information is determined, the voice medical-assistance system can determine the matching degree of the second voice text and each medicine in the medicines corresponding to the preselected medicine information, and determine the preselected medicine information with the highest corresponding matching degree in the preselected medicine information as the medicine to be taken, so as to obtain the medicine to be taken information. The content of the medicine taking information determined based on the treatment voice information and the candidate treatment information in the two embodiments can be referred to, and details are not repeated.

In the above-described embodiment, the voice medical-assisted system can further narrow the range of drugs used, i.e., pre-selected drug information, based on the diagnosed disease information that the physician has selected. Thereby further improving the accuracy of the matched medicine.

It should be noted that the above-mentioned process of selecting diseases and drugs may be one or more, and the speech medical assistance system may determine the disease (may include one or more diseases) first, and then select one or more drugs for the disease, without limitation.

It should be noted that, in the case where the disease option of (a) in fig. 4 and the medicine option of (a) in fig. 5 do not have a disease or medicine required by the doctor, the doctor can type in the disease or medicine.

Optionally, the treatment voice information may include treatment protocol information in addition to the drug information.

In one possible implementation, the voice medical-assistance system may convert the candidate treatment information into candidate treatment voice information via the medical-assistance processor 302. Wherein, the candidate treatment voice information comprises candidate scheme voice information corresponding to the N diseases. And then, inputting the voice information of the candidate schemes corresponding to the N diseases into the scheme feature extraction model to obtain the candidate scheme features corresponding to the N diseases. The medical assistant processor 302 may then input the acquired plan speech information into the plan feature extraction model to acquire the plan features. Then, the candidate scheme features corresponding to the N diseases can be matched with the scheme features to obtain the scheme matching degree corresponding to each disease, then the scheme matching degrees can be ranked from small to small, and the candidate scheme information of the disease with the highest scheme matching degree is determined as the treatment scheme information. It should be noted that, the specific scheme feature extraction algorithm may refer to the above process for obtaining a diagnosed disease, and the detailed description is omitted. It should be noted that, for specific embodiments, reference may be made to the above 3 embodiments for determining the information of the taken medicine, which are not described in detail herein.

And S203, the voice medical assistant system displays the information of confirmed diseases and the information of medicines.

After the voice medical assistant system determines the diagnosed disease information and the medication information, the diagnosed disease information and the medication information may be displayed through the medical assistant display 303. In addition, the voice medical assistant system can also display the treatment scheme information.

Illustratively, fig. 6 is a schematic diagram of still another application interface disclosed in the embodiments of the present application. As shown in fig. 6, the voice medical-assisted system displays that the disease is determined to be disease 1 and the drugs taken are drug 1 and drug 3.

In one possible embodiment, the auxiliary medical display 303 may modify the diagnosed disease information and the medication information, and display the modified diagnosed disease information and the medication information. After the medical assistant display 303 is modified and the confirmed disease information and the drug information are displayed by the voice medical assistant system, the user can confirm based on the displayed confirmed disease information and the drug information, and in the case that the confirmed disease information and the drug information are displayed by the medical assistant display 303 as information determined by the doctor, a diagnosis report can be generated based on the confirmed disease information and the drug information, and the diagnosis report includes the confirmed disease information and the drug information. In the case where the displayed speech medical assistance system displays confirmed disease information and medication information as information that cannot be confirmed by the doctor, the doctor can modify the current confirmed disease information and/or medication information, for example, manually. When the physician's modifications are correct, the modified diagnosed disease information and the medication information may be determined, and the physician-assisted display 303 displays the modified diagnosed disease information and the medication information, after which a report of the diagnosis may be generated.

In the above embodiment, the voice medical assistant system provides a disease and drug assurance plan, so that in case that the selected disease in the current case database and the treatment database is incorrect, the doctor is provided with information that can ensure that the confirmed disease and drug are correct, thereby ensuring the completeness of the plan. Therefore, the problem of wrong voice prediction caused by insufficient range of a case database and a treatment database or imperfect algorithm can be solved at a very small probability, and the correctness of the diagnosis report issued by a doctor is ensured.

In the embodiments of the present application, fig. 4, fig. 5, and fig. 6 are exemplary illustrations and are not intended to be limiting.

In the embodiment of the present application, when the doctor inputs the disease voice information and the treatment voice information, the medical assistant display 303 may determine the confirmed disease information and the medication information based on the candidate disease information and the candidate treatment information estimated by the medical assistant processor 302 and the voice information, so that the number of times of manual input by the doctor may be reduced, and the efficiency of reporting for the patient by the doctor is improved. In addition, when the voice information is directly converted, the semantic conversion range is large, even the disease range is large, the probability of selecting the correct information from massive data is smaller than the probability of selecting the correct information from a small amount of information, and therefore, the medical assistant processor 302 can determine the candidate disease information and the candidate treatment information in advance, and the accuracy of the confirmed disease information and the medicine information can be improved.

As shown in fig. 3, the voice medical assistant system includes a microphone 301, a medical assistant processor 302, and a medical assistant display 303:

the microphone 301 is used for collecting disease voice information and treatment voice information input by a doctor;

the medical auxiliary processor 302 is configured to determine candidate disease information and candidate treatment information corresponding to the candidate disease information according to the acquired disease information of the patient; determining diagnosed disease information according to the disease voice information and the candidate disease information, and determining medicine taking information according to the treatment voice information and the candidate treatment information;

the medical auxiliary display 303 is used for displaying the information of the confirmed diseases and the information of the taken medicines.

As a possible implementation manner, the medical assistant processor 302 determines candidate disease information and candidate treatment information corresponding to the candidate disease information according to the acquired disease information of the patient, and is specifically configured to:

matching diseases similar to the disease information of the patient from a disease database to obtain candidate disease information, wherein the candidate disease information comprises N diseases, N is a positive integer, and the disease database comprises the corresponding relation between various diseases and the disease information;

and matching the drug information of the N diseases from a treatment database to obtain candidate treatment information, wherein the candidate treatment information comprises treatment drugs corresponding to the N diseases, and the treatment database comprises the corresponding relation between a plurality of diseases and the drug information.

As a possible implementation manner, the medical assistant processor 302 determines diagnosed disease information according to the disease speech information and the candidate disease information, and is specifically configured to:

inputting disease voice information input by a doctor and acquired by the microphone into a disease feature extraction model to acquire disease features;

matching the disease characteristics with the disease characteristics of the voice information of each disease in the candidate disease information to obtain the disease matching degree of each disease;

and determining the disease with the highest disease matching degree in the candidate disease information as the confirmed disease to obtain the confirmed disease information.

As a possible implementation manner, in the case that the treatment voice information includes medicine voice information, the medical assistant processor 302 determines to take medicine information according to the treatment voice information and the candidate treatment information, and is specifically configured to:

inputting the medicine voice information into a medicine feature extraction model to obtain medicine features;

matching the medicine characteristics with the medicine characteristics of the medicine voice information of each disease in the candidate treatment information to obtain the corresponding medicine matching degree of each disease;

and determining the medicine information corresponding to the disease with the highest medicine matching degree in the candidate treatment information as the medicine to be taken to obtain the medicine to be taken information.

As a possible implementation, the treatment voice information further includes protocol voice information, and the medical assistant processor 302 is further configured to:

matching scheme information of the N diseases from a treatment database to obtain candidate treatment information, wherein the candidate treatment information comprises scheme medicines corresponding to the N diseases, and the treatment database comprises corresponding relations between a plurality of diseases and the scheme information;

inputting the scheme voice information into a scheme feature extraction model to obtain scheme features;

matching the scheme characteristics with the scheme characteristics of the scheme voice information of each disease in the candidate treatment information to obtain the corresponding scheme matching degree of each disease;

determining the scheme information of the disease with the highest scheme matching degree in the candidate treatment information as a treatment scheme to obtain treatment scheme information;

the medical auxiliary display 303 is further configured to display the treatment plan information.

As a possible implementation, the medical assistant processor 302 is further configured to:

adjusting the confirmed disease information and the taken medicine information;

the medical auxiliary display 303 displays the information of the confirmed diseases and the information of the taken medicines, and is specifically configured to:

and displaying the adjusted information of the diagnosed diseases and the adjusted information of the taken medicines.

As a possible implementation manner, after determining the confirmed disease information according to the disease voice information input by the doctor and the candidate disease information collected by the microphone, the medical assistant processor 302 determines the medication information to be taken according to the treatment voice information input by the doctor and the candidate treatment information collected by the microphone, and is specifically configured to:

screening pre-selected drug information from the candidate treatment information based on the diagnosed disease information;

and determining the taken medicine from the pre-selected medicine information based on the treatment voice information input by the doctor and collected by the microphone, so as to obtain the taken medicine information.

Based on the above description, please refer to fig. 7, and fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure. As shown in fig. 7, the device may include a processor 701, a memory 702, an input interface 703, an output interface 704, and a bus 705. The memory 702 may be separate and may be coupled to the processor 701 by a bus 705. Wherein the input interface 703 is used for receiving information from other devices, and the output interface 704 is used for outputting, scheduling or transmitting information to other devices. The memory 702 may also be integrated with the processor 701. Bus 705 is used, among other things, to enable connections between these components.

In one embodiment, the electronic device may be a voice medical assistance system or a module in a voice medical assistance system, and when the computer program instructions stored in the memory 702 are executed, the processor 701 is configured to S201, S202, and S203 to perform the operations performed in the above embodiments, the input interface 703 is configured to receive information from other devices, and the output interface 704 is configured to output data. The electronic device or the module in the electronic device may also be configured to execute various methods in the method embodiment in fig. 2, which is not described again.

The embodiment of the application also discloses a computer readable storage medium, wherein instructions are stored on the storage medium, and the instructions execute the method in the embodiment of the method when executed.

The embodiment of the application also discloses a computer program product comprising instructions, and the instructions are executed to execute the method in the embodiment of the method.

The above-mentioned embodiments, objects, technical solutions and advantages of the present application are further described in detail, it should be understood that the above-mentioned embodiments are only examples of the present application, and are not intended to limit the scope of the present application, and any modifications, equivalent substitutions, improvements and the like made on the basis of the technical solutions of the present application should be included in the scope of the present application.

In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the application to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wire (e.g., coaxial cable, fiber optic, digital subscriber line) or wirelessly (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that incorporates one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid state disk), among others.

One of ordinary skill in the art will appreciate that all or part of the processes in the methods of the above embodiments may be implemented by hardware related to instructions of a computer program, which may be stored in a computer-readable storage medium, and when executed, may include the processes of the above method embodiments. And the aforementioned storage medium includes: various media capable of storing program codes, such as ROM or RAM, magnetic or optical disks, etc.

Claims

1. A medical and auxiliary information display method based on voice input is applied to a voice medical and auxiliary system, wherein the voice medical and auxiliary system comprises a microphone, a medical and auxiliary processor and a medical and auxiliary display, and the method comprises the following steps:

determining candidate disease information and candidate treatment information corresponding to the candidate disease information according to the acquired disease information of the patient through the medical auxiliary processor, determining confirmed disease information according to the disease voice information input by the doctor and the candidate disease information acquired through the microphone, determining medicine taking information according to the treatment voice information input by the doctor and the candidate treatment information acquired through the microphone, and displaying the confirmed disease information and the medicine taking information through the medical auxiliary display.

2. The method according to claim 1, wherein the determining candidate disease information and candidate treatment information corresponding to the candidate disease information according to the acquired disease information of the patient comprises:

3. The method of claim 1, wherein determining diagnosed disease information from the doctor-entered disease speech information and the candidate disease information collected by the microphone comprises:

4. The method of claim 1, wherein in the case that the treatment voice information includes medicine voice information, the determining to take medicine information according to the treatment voice information collected by the microphone and the candidate treatment information input by the doctor comprises:

inputting the medicine voice information which is acquired by the microphone and input by a doctor into a medicine feature extraction model to acquire medicine features;

5. The method of claim 1, wherein the treatment speech information further comprises plan speech information, and wherein the determining candidate disease information according to the acquired condition information of the patient and the candidate treatment information corresponding to the candidate disease information further comprises:

the method further comprises the following steps:

inputting the scheme voice information acquired by the microphone and input by a doctor into a scheme feature extraction model through the medical auxiliary processor to acquire scheme features; matching the scheme characteristics with the scheme characteristics of the scheme voice information of each disease in the candidate treatment information to obtain the corresponding scheme matching degree of each disease; determining the scheme information of the disease with the highest scheme matching degree in the candidate treatment information as a treatment scheme to obtain treatment scheme information;

and displaying the treatment scheme information through the medical auxiliary display.

6. The method of claim 1, further comprising:

adjusting the confirmed disease information and the taken medicine information through the medical auxiliary processor;

the displaying the diagnosed disease information and the taken medicine information through the medical auxiliary display comprises:

7. The method of claim 3, wherein after determining confirmed disease information based on the doctor-entered disease speech information and the candidate disease information collected by the microphone, the determining to take medication information based on the doctor-entered treatment speech information and the candidate treatment information collected by the microphone comprises:

8. A voice medical assistance system is characterized by comprising a microphone, a medical assistance processor and a medical assistance display:

the microphone is used for collecting disease voice information and treatment voice information input by a doctor;

the medical auxiliary processor is used for determining candidate disease information and candidate treatment information corresponding to the candidate disease information based on the acquired disease information of the patient; determining diagnosed disease information according to the disease voice information and the candidate disease information, and determining medicine taking information according to the treatment voice information and the candidate treatment information;

the medical auxiliary display is used for displaying the confirmed disease information and the taken medicine information.

9. A computer device, comprising: a processor and a memory; the processor is coupled to a memory, wherein the memory is configured to store a computer program, and the processor is configured to invoke the computer program to cause the computer device to perform the method of any of claims 1-7.

10. A computer-readable storage medium, in which a computer program or computer instructions are stored which, when executed, implement the method according to any one of claims 1 to 7.