CN116612906B - Medical question-answering service method, system and equipment based on artificial intelligence - Google Patents
Medical question-answering service method, system and equipment based on artificial intelligence Download PDFInfo
- Publication number
- CN116612906B CN116612906B CN202310890237.0A CN202310890237A CN116612906B CN 116612906 B CN116612906 B CN 116612906B CN 202310890237 A CN202310890237 A CN 202310890237A CN 116612906 B CN116612906 B CN 116612906B
- Authority
- CN
- China
- Prior art keywords
- information
- inquiry
- data
- question
- user information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 20
- 238000007405 data analysis Methods 0.000 claims abstract description 37
- 230000003993 interaction Effects 0.000 claims abstract description 34
- 239000003814 drug Substances 0.000 claims description 71
- 208000024891 symptom Diseases 0.000 claims description 55
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 22
- 238000001514 detection method Methods 0.000 claims description 20
- 229940079593 drug Drugs 0.000 claims description 18
- 201000010099 disease Diseases 0.000 claims description 16
- 230000000873 masking effect Effects 0.000 claims description 13
- 238000012423 maintenance Methods 0.000 claims description 9
- 230000035945 sensitivity Effects 0.000 claims description 9
- 238000012360 testing method Methods 0.000 claims description 9
- 238000012217 deletion Methods 0.000 claims description 7
- 230000037430 deletion Effects 0.000 claims description 7
- 238000000605 extraction Methods 0.000 claims description 6
- 238000012937 correction Methods 0.000 claims description 4
- 239000012634 fragment Substances 0.000 claims description 4
- 230000003213 activating effect Effects 0.000 claims description 3
- 230000008569 process Effects 0.000 description 8
- 230000011218 segmentation Effects 0.000 description 7
- 230000005540 biological transmission Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 210000001503 joint Anatomy 0.000 description 3
- 230000000474 nursing effect Effects 0.000 description 2
- 230000032683 aging Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000009193 crawling Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000001681 protective effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H80/00—ICT specially adapted for facilitating communication between medical practitioners or patients, e.g. for collaborative diagnosis, therapy or health monitoring
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Abstract
The application discloses a medical question-answering service method, a system and equipment based on artificial intelligence, which mainly relate to the technical field of medical question-answering service and are used for solving the problems that the traditional intelligent medical question-answering scheme can not provide professional medical knowledge question-answering and personal privacy information is easy to reveal. Comprising the following steps: determining mask user information and question-answering text data corresponding to voice consultation data through a voice interaction terminal; transmitting the mask user information to a medical service center system; determining specific inquiry user information and inquiry records through a medical service center system; generating non-privacy inquiry information corresponding to the inquiry records, and sending the non-privacy inquiry information to a corresponding data analysis server; acquiring inquiry related information existing in the privacy-free inquiry information through a data analysis server, and sending the inquiry related information to a medical service center system; determining reply data by the medical service center system; and controlling the voice interaction terminal to automatically broadcast the reply data.
Description
Technical Field
The application relates to the technical field of medical question-answering service, in particular to a medical question-answering service method, system and equipment based on artificial intelligence.
Background
With the promotion of aging population, home medical consultation and nursing have grown into a huge application market, and intelligent accompanying machine equipment capable of providing service functions such as medical consultation and nursing is increasingly required by the masses.
At present, a daily intelligent question-answering machine device is generally a platform constructed by semantic retrieval, multi-channel knowledge service and a large-scale knowledge base based on natural language understanding, and the technical scheme mainly comprises the following steps: the acquisition model is used for acquiring the problems raised by the user; the question-answering model is used for finding out the question which is most matched with the user, and then giving out a corresponding answer, and the question-answering model adopts two forms of converting words into vectors and word shift distances; the output model is used for receiving the corresponding answers given by the question-answer model and outputting the answers. Or the medical question and answer information is crawled directly through a search engine such as hundred degrees.
That is, the existing daily intelligent question-answering machine equipment can only assist in answering simple non-medical professional knowledge questions and answers, cannot highlight the industrial advantages of intelligent question-answering in the medical professional field for intelligent guide diagnosis, auxiliary decision making, maintenance companion and the like, cannot assist a user in completing autonomous question-asking by the content of professional medical knowledge questions and answers, and can realize various abilities of inquiring related medicines and symptoms without going home. In addition, the medical inquiry information is personal privacy, and how to avoid leakage of the medical inquiry information in the inquiry process is also a technical problem to be solved.
Disclosure of Invention
Aiming at the defects of the prior art, the application provides a medical question-answering service method, a system and equipment based on artificial intelligence, which are used for solving the technical problems that the prior intelligent medical question-answering scheme can not provide professional medical knowledge question-answering and personal privacy information is easy to reveal.
In a first aspect, the present application provides an artificial intelligence based medical question-answering service method, the method comprising: acquiring voice medical consultation data through the voice interaction terminal, and further determining mask user information and question-answering text data corresponding to the voice consultation data; transmitting the mask user information to a medical service center system; determining specific inquiry user information and inquiry records through a medical service center system; generating non-privacy inquiry information corresponding to the inquiry records, and sending the non-privacy inquiry information to a corresponding data analysis server; acquiring inquiry related information existing in the privacy-free inquiry information through a data analysis server, and sending the inquiry related information to a medical service center system; wherein, the inquiry association information at least comprises: a consultation-related disorder name, a consultation-related drug, and a consultation-related symptom; determining the relevance between the inquiry related information and the inquiry text data through the medical service center system; when the relevance exists, determining the current reply data as inquiry relevance information; when no relevance exists, acquiring preset standard relevance information corresponding to the question-answer text data, and determining that the current answer data is the standard relevance information; and controlling the voice interaction terminal to automatically broadcast the reply data.
Further, before acquiring the voice medical consultation data through the voice interaction terminal and further determining mask user information and question-answering text data corresponding to the voice consultation data, the method comprises the following steps: acquiring the input question-answering user information and voice data corresponding to the question-answering user information through a voice interaction terminal; wherein, the question and answer user information at least comprises: a user name and a user identification card number; masking the question and answer user information based on a preset masking rule to obtain standby user information; transmitting the spare user information to the medical service center system to check whether the spare user information is a valid user in a mask user information set of the medical service center system; when the user is determined to be a valid user, the medical service center system feeds back a deleting instruction; after the deletion instruction is obtained, determining the standby user information as mask user information, and deleting question-answering user information; and determining a word interval time range, a phrase interval time range and a volume threshold range corresponding to each voice data by presetting the voice detection device so as to bind mask user information with the word interval time range, the phrase interval time range and the volume threshold range.
Further, the voice medical consultation data is obtained through the voice interaction terminal, and mask user information and question-answer text data corresponding to the voice consultation data are further determined, specifically comprising: acquiring voice medical consultation data through the voice interaction terminal; analyzing the word interval time period, the phrase interval time period and the volume actual range corresponding to the voice medical consultation data, and further determining mask user information corresponding to the voice medical consultation data according to the word interval time range, the phrase interval time range and the volume threshold range; dividing the voice medical consultation data according to the phrase interval time period to obtain a plurality of pieces of voice data, recording the continuous relation between the pieces of voice data, and determining the specific word meaning information of the pieces of voice data through a preset voice-to-word algorithm; detecting the number of characters of specific word meaning information; when the number of characters is larger than a preset number threshold, determining whether specific word information is a medicine name, and generating prompt voice of whether to consult specific medicines when the specific word information is not the medicine name; when determining to consult a specific medicine, activating a preset camera device, collecting medicine pictures to identify the medicine pictures so as to obtain specific medicine nouns and finish correction and update of specific meaning information; and generating question-answer text data according to the continuous relation corresponding to the specific word meaning information and the fragment voice data.
Further, determining, by the medical service center system, a specific interview user and an interview record, specifically includes: acquiring a mask user information set processed by a preset mask rule through a medical service center system; and comparing the obtained mask user information with the mask user information set to obtain the corresponding inquiry user information of the mask user information in the mask user information set, and further calling and obtaining the corresponding inquiry record.
Further, generating no-privacy inquiry information corresponding to the inquiry records, and sending the no-privacy inquiry information to a corresponding data analysis server, which specifically comprises the following steps: generating a random code corresponding to the inquiry record; wherein the female random code is limited to an even number; the male random code is defined as an odd number; extracting current medical history record data and past medical history record data from the inquiry records to serve as basic inquiry information; extracting preset detection information corresponding to the parity from the inquiry records based on the parity of the random code; generating privacy-free inquiry information comprising a random code, basic inquiry information and preset detection information; acquiring the running state of each data analysis server to determine that the data analysis server with the running state being an idle state is a server to be selected; transmitting sensitivity test codes to each server to be selected, and determining the server to be selected which feeds back the operation result of the sensitivity test codes for the first time as a corresponding data analysis server; determining that the server to be selected which does not upload the operation result in the preset detection time period is a katon server, and generating a maintenance task to a preset maintenance terminal.
Further, acquiring, by the data analysis server, the inquiry related information existing in the privacy-free inquiry information, specifically including: extracting actual symptoms from the privacy-free inquiry information through a preset data analysis algorithm in the data analysis server; determining associated symptoms corresponding to actual symptoms through a preset symptom associated database; determining actual symptoms and suggested associated drugs corresponding to management symptoms through a symptom-drug associated database; wherein, the associated medicine at least comprises: recommended and contraindicated.
Further, through the medical service center system, the relevance between the inquiry association information and the inquiry text data is determined; when the relevance exists, determining the current reply data as inquiry relevance information; when no relevance exists, acquiring preset standard relevance information corresponding to the question-answer text data to determine that the current answer data is the standard relevance information, wherein the method specifically comprises the following steps of: acquiring question-answering symptom names, question-answering symptom data or medicine query information corresponding to the question-answering text data according to a keyword extraction algorithm; determining a symptom standard name corresponding to the symptom name, a symptom standard description corresponding to the symptom, or a medicine standard name corresponding to the medicine inquiry information; determining whether a disease standard name, a symptom standard description or a medicine standard name exists in the inquiry association information, determining that association exists when the disease standard name, the symptom standard description or the medicine standard name exists in the inquiry association information, and determining that the current reply data is the inquiry association information; when the relevance is not present in the inquiry relation information, determining that the relevance is not present; and calling standard associated information corresponding to the question and answer text data from the medical service center system to determine that the current answer data is the standard associated information.
In a second aspect, the present application provides an artificial intelligence based medical question-answering service system, the system comprising: the voice interaction module is used for acquiring voice medical consultation data and further determining mask user information and question-answer text data corresponding to the voice consultation data; transmitting the mask user information to a medical service center module; the medical service center module is used for determining specific inquiry user information and inquiry records; generating non-privacy inquiry information corresponding to the inquiry records, and sending the non-privacy inquiry information to a corresponding data analysis module; the data analysis module is used for acquiring inquiry related information existing in the privacy-free inquiry information and sending the inquiry related information to the medical service center module; wherein, the inquiry association information at least comprises: a consultation-related disorder name, a consultation-related drug, and a consultation-related symptom; the medical service center module is also used for determining the relevance between the inquiry related information and the inquiry text data; when the relevance exists, determining the current reply data as inquiry relevance information; when no relevance exists, acquiring preset standard relevance information corresponding to the question-answer text data, and determining that the current answer data is the standard relevance information; and controlling the voice interaction module to automatically broadcast the reply data.
Further, the system also comprises a binding module which is used for acquiring the input question-answering user information and the voice data corresponding to the question-answering user information through the voice interaction terminal; wherein, the question and answer user information at least comprises: a user name and a user identification card number; masking the question and answer user information based on a preset masking rule to obtain standby user information; sending the standby user information to the medical service center module to check whether the standby user information is a valid user in the mask user information set of the medical service center module; when the medical service center module determines that the user is a valid user, the medical service center module feeds back a deleting instruction; after the deletion instruction is obtained, determining the standby user information as mask user information, and deleting question-answering user information; and determining a word interval time range, a phrase interval time range and a volume threshold range corresponding to each voice data by presetting the voice detection device so as to bind mask user information with the word interval time range, the phrase interval time range and the volume threshold range.
In a third aspect, the present application provides an artificial intelligence based medical question-answering service apparatus, the apparatus comprising: a processor; and a memory having executable code stored thereon that, when executed, causes the processor to perform an artificial intelligence based medical question-answering service method according to any one of the above.
As will be appreciated by those skilled in the art, the present application has at least the following beneficial effects:
according to the technical scheme, the mask user information and the privacy-free inquiry information are generated, so that medical data transmission without user information is realized; leakage of medical inquiry information in the inquiry process is avoided. Unlike the traditional crawling of the content of an excessively exaggerated medical knowledge question from a search engine of hundred degrees or the like, this is a situation that creates a disconcerting mind. The application is based on the following: the old disease is old, and the search history inquiry records can provide the content of the professional medical knowledge questions and answers. Therefore, the application is in butt joint with the medical service center system to acquire the inquiry records of the user, and the inquiry related information is acquired by expanding the inquiry records, so that the butt joint of the aged and old disease-derived consultation information and the inquiry records is realized; in addition, when the old diseases are not involved, the application can preset standard association information according to the old diseases, and can dock question-answer text data with the standard association information.
Drawings
Some embodiments of the present disclosure are described below with reference to the accompanying drawings, in which:
fig. 1 is a flowchart of a medical question-answering service method based on artificial intelligence according to an embodiment of the present application.
Fig. 2 is a schematic diagram of an internal structure of a medical question-answering service system based on artificial intelligence according to an embodiment of the present application.
Fig. 3 is a schematic diagram of an internal structure of an artificial intelligence-based medical question-answering service device according to an embodiment of the present application.
Detailed Description
It should be understood by those skilled in the art that the embodiments described below are only preferred embodiments of the present disclosure, and do not represent that the present disclosure can be realized only by the preferred embodiments, which are merely for explaining the technical principles of the present disclosure, not for limiting the scope of the present disclosure. Based on the preferred embodiments provided by the present disclosure, all other embodiments that may be obtained by one of ordinary skill in the art without inventive effort shall still fall within the scope of the present disclosure.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises an element.
The following describes the technical scheme provided by the embodiment of the application in detail through the attached drawings.
The embodiment of the application provides a medical question-answering service method based on artificial intelligence, which mainly comprises the following steps as shown in fig. 1:
step 110, acquiring voice medical consultation data through a voice interaction terminal, and further determining mask user information and question-answer text data corresponding to the voice consultation data; the masked user information is sent to the healthcare center system.
The application is developed based on medical inquiry information, which is mainly stored in a server (medical service center system) of a medical institution. That is, the medical service center system is a server arranged inside a medical unit and capable of acquiring inquiry user information and inquiry records inside the medical unit, performing data processing, and performing data transmission.
The voice interaction terminal may be any possible device or apparatus capable of acquiring voice for voice analysis and data transmission. In order to achieve the aim of providing medical consultation for all elderly users in a family by a voice interaction terminal, and combining the situation that the number of the elderly in the family is small, the application discloses a method for comparing the subsequent acquired data by acquiring the word interval time range, the phrase interval time range and the volume threshold range of each elderly speaking in advance, thereby realizing the purpose of enabling the voice interaction terminal to quickly determine the user information corresponding to the consultation voice from a plurality of bound users. The method does not need to use a complex voice recognition algorithm to carry out identity recognition, and is quicker and more trouble-free.
The specific process of pre-acquiring the word interval time range, the phrase interval time range and the volume threshold range of each elder speaking may be: acquiring the input question-answering user information and voice data corresponding to the question-answering user information through a voice interaction terminal; wherein, the question and answer user information at least comprises: a user name and a user identification card number; masking the question and answer user information based on a preset masking rule to obtain standby user information; transmitting the spare user information to the medical service center system to check whether the spare user information is a valid user in a mask user information set of the medical service center system; when the user is determined to be a valid user, the medical service center system feeds back a deleting instruction; after a deletion instruction is obtained, determining the spare user information as mask user information, and deleting the question-answering user information (user privacy data is deleted from the source, so that the real incapability of revealing privacy is realized); and determining a word interval time range, a phrase interval time range and a volume threshold range corresponding to each voice data by presetting the voice detection device so as to bind mask user information with the word interval time range, the phrase interval time range and the volume threshold range.
It should be noted that the voice data may be voice data collected according to a preset section of text; the specifics thereof can be determined by one skilled in the art in light of the actual situation. The preset masking rules may be any feasible rules capable of hiding personal privacy information. The medical service center system comprises certain hospital consultation user data (including consultation user information and consultation records); the mask user information set is all hospital consultation user information processed by the medical service center system based on the same preset mask rule. Therefore, under the condition of not revealing personal privacy, the butt joint of the user and the in-hospital inquiry user data is realized. The method of obtaining word time intervals from speech data may be any feasible method.
In this step, the voice medical consultation data is acquired through the voice interaction terminal, so as to determine mask user information and question-answer text data corresponding to the voice consultation data, which may specifically be:
(1) Acquiring voice medical consultation data through the voice interaction terminal; and analyzing the word interval time period, the phrase interval time period and the volume actual range corresponding to the voice medical consultation data, and further determining mask user information corresponding to the voice medical consultation data according to the word interval time range, the phrase interval time range and the volume threshold range.
(2) Because the application detects the phrase interval time period, the voice medical consultation data is directly segmented according to the phrase interval time period during voice recognition so as to obtain a plurality of pieces of voice data, the continuous relation among the pieces of voice data is recorded, and the specific word meaning information of the pieces of voice data is determined through a preset voice-to-word algorithm (for example, a STM 32-based voice detection algorithm, tensorflow and the like). Because the application relates to medicine consultation, the medicine often relates to more complex medicine nouns, when the number of characters is larger than a preset number threshold, the specific word meaning information is likely to be the medicine nouns, and when the specific word meaning information is found to be not the medicine nouns after retrieval, the situation that the old can not accurately speak the medicine nouns can exist, so the application generates prompt voice of whether to consult the specific medicine. Because old people often eat empty medicines when consulting medicines, medicine packages are stored, when determining to consult specific medicines, a preset camera device is activated, medicine pictures are collected to identify medicine pictures so as to obtain specific medicine nouns, and correction and update of specific word meaning information are completed; and generating question-answer text data according to the continuous relation corresponding to the specific word meaning information and the fragment voice data.
Finally, the specific implementation of this step of sending the mask user information to the healthcare center system may be any feasible manner, and the present application is not limited herein.
Step 120, determining specific inquiry user information and inquiry records through a medical service center system; generating non-privacy inquiry information corresponding to the inquiry records, and sending the non-privacy inquiry information to a corresponding data analysis server.
In this step, a specific inquiry user and an inquiry record are determined by the medical service center system, which may be specifically: acquiring a mask user information set processed by a preset mask rule through a medical service center system; and comparing the obtained mask user information with the mask user information set to obtain the corresponding inquiry user information of the mask user information in the mask user information set, and further calling and obtaining the corresponding inquiry record.
In this step, no-privacy inquiry information corresponding to the inquiry record is generated, and the no-privacy inquiry information is sent to a corresponding data analysis server, which may specifically be: generating a random code corresponding to the inquiry record; wherein the female random code is limited to an even number; the male random code is defined as an odd number; extracting current medical history record data and past medical history record data from the inquiry records to serve as basic inquiry information; extracting preset detection information corresponding to the parity from the inquiry records based on the parity of the random code; generating privacy-free inquiry information comprising a random code, basic inquiry information and preset detection information; acquiring the running state of each data analysis server to determine that the data analysis server with the running state being an idle state is a server to be selected; transmitting sensitivity test codes to each server to be selected, and determining the server to be selected which feeds back the operation result of the sensitivity test codes for the first time as a corresponding data analysis server; determining that the server to be selected which does not upload the operation result in the preset detection time period is a katon server, and generating a maintenance task to a preset maintenance terminal.
It should be noted that the preset detection information corresponding to the parity may be determined by a person skilled in the art according to the actual situation. The sensitivity test code is any feasible mathematical applet with a run time in the range of 2 to 5 seconds.
And 130, acquiring inquiry related information existing in the privacy-free inquiry information through the data analysis server, and transmitting the inquiry related information to the medical service center system.
As an example, this step may be specifically: extracting actual symptoms from the privacy-free inquiry information through a preset data analysis algorithm in the data analysis server; determining associated symptoms corresponding to actual symptoms through a preset symptom associated database; determining actual symptoms and suggested associated drugs corresponding to management symptoms through a symptom-drug associated database; wherein, the associated medicine at least comprises: recommended and contraindicated.
Step 140, determining the relevance between the inquiry association information and the inquiry text data through the medical service center system; when the relevance exists, determining the current reply data as inquiry relevance information; when no relevance exists, acquiring preset standard relevance information corresponding to the question-answer text data, and determining that the current answer data is the standard relevance information; and controlling the voice interaction terminal to automatically broadcast the reply data.
Specifically, the present step may be: obtaining question-answering symptom names, question-answering symptom data or medicine query information corresponding to the question-answering text data from the question-answering text data through a keyword extraction algorithm; it should be noted that, unlike the conventional keyword extraction algorithm, the word segmentation and word segmentation work is required. The question-answering text data is a plurality of specific word meaning information spliced based on continuous relations, namely, word segmentation is completed, and the word segmentation effect is achieved when the word segmentation is obtained (the word segmentation is performed by a person in the voice medical consultation data input process in a conscious manner) unlike computer word segmentation. And only a program related to the weight in a keyword extraction algorithm is required to be operated, so that the question-answering symptom name, question-answering symptom data or medicine query information corresponding to the question-answering text data can be obtained. And determining a disease standard name corresponding to the question-answer disease name, a symptom standard description corresponding to the question-answer symptom or a medicine standard name corresponding to the medicine inquiry information (which can be completed by fuzzy classification). Determining whether a disease standard name, a symptom standard description or a medicine standard name exists in the inquiry association information, determining that association exists when the disease standard name, the symptom standard description or the medicine standard name exists in the inquiry association information, and determining that the current reply data is the inquiry association information; when the relevance is not present in the inquiry relation information, determining that the relevance is not present; and calling standard associated information corresponding to the question and answer text data from the medical service center system to determine that the current answer data is the standard associated information. It should be noted that, the medical service center system has a direct correspondence relationship between the disease standard name, the symptom standard description, and the drug standard name and the standard association information. The standard association information consists of a disease standard name, a symptom standard description and a medicine standard name. The acquisition process of specific standard association information is imported by those skilled in the art.
In addition, fig. 2 is a schematic diagram of an artificial intelligence-based medical question-answering service system according to an embodiment of the present application. As shown in fig. 2, the system provided by the embodiment of the present application mainly includes:
the voice interaction module 210 is configured to obtain voice medical consultation data, and further determine mask user information and question-answer text data corresponding to the voice consultation data; the masked user information is sent to the healthcare center module 220.
It should be noted that, the voice interaction module 210 may be a terminal device placed at a place where the user uses the device.
A medical service center module 220 for determining specific inquiry user information and inquiry records; the privacy-free inquiry information corresponding to the inquiry records is generated, and the privacy-free inquiry information is sent to the corresponding data analysis module 230.
The medical service center module 220 is a system, a server, etc. that contains user data (including user information and records) of a certain hospital.
In addition, the system also comprises a binding module,
the voice interaction terminal is used for acquiring the input question-answering user information and voice data corresponding to the question-answering user information; wherein, the question and answer user information at least comprises: a user name and a user identification card number; masking the question and answer user information based on a preset masking rule to obtain standby user information; sending the spare user information to the healthcare center module 220 to check whether it is a valid user in the masked user information set of the healthcare center module 220; when the user is determined to be a valid user, the medical service center module 220 feeds back a deletion instruction; after the deletion instruction is obtained, determining the standby user information as mask user information, and deleting question-answering user information; and determining a word interval time range, a phrase interval time range and a volume threshold range corresponding to each voice data by presetting the voice detection device so as to bind mask user information with the word interval time range, the phrase interval time range and the volume threshold range.
The data analysis module 230 is configured to obtain the related information of the interview existing in the privacy-free information of the interview, and send the related information of the interview to the medical service center module 220; wherein, the inquiry association information at least comprises: inquiry-related disorder name, inquiry-related drug, and inquiry-related symptoms.
It should be noted that, the data analysis module 230 may be any feasible server capable of performing data analysis and data transmission.
The medical service center module 220 is further configured to determine a relevance between the inquiry association information and the inquiry text data; when the relevance exists, determining the current reply data as inquiry relevance information; when no relevance exists, acquiring preset standard relevance information corresponding to the question-answer text data, and determining that the current answer data is the standard relevance information; and controlling the voice interaction module to automatically broadcast the reply data.
It should be noted that the voice interaction module may be any feasible device or apparatus capable of playing data.
The method embodiment of the application is based on the same inventive concept, and the embodiment of the application also provides medical question-answering service equipment based on artificial intelligence. As shown in fig. 3, the apparatus includes: a processor; and a memory having executable code stored thereon that, when executed, causes the processor to perform an artificial intelligence based medical question-answering service method as in the above embodiments.
Specifically, the server side obtains voice medical consultation data through the voice interaction terminal, and further determines mask user information and question-answer text data corresponding to the voice consultation data; transmitting the mask user information to a medical service center system; determining specific inquiry user information and inquiry records through a medical service center system; generating non-privacy inquiry information corresponding to the inquiry records, and sending the non-privacy inquiry information to a corresponding data analysis server; acquiring inquiry related information existing in the privacy-free inquiry information through a data analysis server, and sending the inquiry related information to a medical service center system; wherein, the inquiry association information at least comprises: a consultation-related disorder name, a consultation-related drug, and a consultation-related symptom; determining the relevance between the inquiry related information and the inquiry text data through the medical service center system; when the relevance exists, determining the current reply data as inquiry relevance information; when no relevance exists, acquiring preset standard relevance information corresponding to the question-answer text data, and determining that the current answer data is the standard relevance information; and controlling the voice interaction terminal to automatically broadcast the reply data.
Thus far, the technical solution of the present disclosure has been described in connection with the foregoing embodiments, but it is easily understood by those skilled in the art that the protective scope of the present disclosure is not limited to only these specific embodiments. The technical solutions in the above embodiments may be split and combined by those skilled in the art without departing from the technical principles of the present disclosure, and equivalent modifications or substitutions may be made to related technical features, which all fall within the scope of the present disclosure.
Claims (3)
1. A medical question-answering service method based on artificial intelligence, the method comprising:
acquiring the input question-answering user information and voice data corresponding to the question-answering user information through a voice interaction terminal; wherein, the question and answer user information at least comprises: a user name and a user identification card number; masking the question and answer user information based on a preset masking rule to obtain standby user information; transmitting the spare user information to the medical service center system to check whether the spare user information is a valid user in a mask user information set of the medical service center system; when the user is determined to be a valid user, the medical service center system feeds back a deleting instruction; after the deletion instruction is obtained, determining the standby user information as mask user information, and deleting question-answering user information; determining a word interval time range, a phrase interval time range and a volume threshold range corresponding to each voice data through a preset sound detection device so as to bind mask user information with the word interval time range, the phrase interval time range and the volume threshold range;
acquiring voice medical consultation data through the voice interaction terminal, and further determining mask user information and question-answering text data corresponding to the voice consultation data; the method specifically comprises the following steps: acquiring voice medical consultation data through the voice interaction terminal; analyzing the word interval time period, the phrase interval time period and the volume actual range corresponding to the voice medical consultation data, and further determining mask user information corresponding to the voice medical consultation data according to the word interval time range, the phrase interval time range and the volume threshold range; dividing the voice medical consultation data according to the phrase interval time period to obtain a plurality of pieces of voice data, recording the continuous relation between the pieces of voice data, and determining the specific word meaning information of the pieces of voice data through a preset voice-to-word algorithm; detecting the number of characters of specific word meaning information; when the number of characters is larger than a preset number threshold, determining whether specific word information is a medicine name, and generating prompt voice of whether to consult specific medicines when the specific word information is not the medicine name; when determining to consult a specific medicine, activating a preset camera device, collecting medicine pictures to identify the medicine pictures so as to obtain specific medicine nouns and finish correction and update of specific meaning information; generating question-answer text data according to the continuous relation corresponding to the specific word meaning information and the fragment voice data;
transmitting the mask user information to a medical service center system;
determining specific inquiry user information and inquiry records through a medical service center system; the method specifically comprises the following steps: acquiring a mask user information set processed by a preset mask rule through a medical service center system; comparing the obtained mask user information with the mask user information set to obtain corresponding inquiry user information of the mask user information in the mask user information set, and further calling and obtaining a corresponding inquiry record;
generating non-privacy inquiry information corresponding to the inquiry records, and sending the non-privacy inquiry information to a corresponding data analysis server; the method specifically comprises the following steps: generating a random code corresponding to the inquiry record; wherein the female random code is limited to an even number; the male random code is defined as an odd number; extracting current medical history record data and past medical history record data from the inquiry records to serve as basic inquiry information; extracting preset detection information corresponding to the parity from the inquiry records based on the parity of the random code; generating privacy-free inquiry information comprising a random code, basic inquiry information and preset detection information; acquiring the running state of each data analysis server to determine that the data analysis server with the running state being an idle state is a server to be selected; transmitting sensitivity test codes to each server to be selected, and determining the server to be selected which feeds back the operation result of the sensitivity test codes for the first time as a corresponding data analysis server; determining that a server to be selected without uploading an operation result in a preset detection time period is a katon server, and generating a maintenance task to a preset maintenance terminal;
acquiring inquiry related information existing in the privacy-free inquiry information through a data analysis server, and sending the inquiry related information to a medical service center system; wherein, the inquiry association information at least comprises: a consultation-related disorder name, a consultation-related drug, and a consultation-related symptom;
determining the relevance between the inquiry related information and the inquiry text data through the medical service center system; when the relevance exists, determining the current reply data as inquiry relevance information; when no relevance exists, acquiring preset standard relevance information corresponding to the question-answer text data, and determining that the current answer data is the standard relevance information; the method specifically comprises the following steps: acquiring question-answering symptom names, question-answering symptom data or medicine query information corresponding to the question-answering text data according to a keyword extraction algorithm; determining a symptom standard name corresponding to the symptom name, a symptom standard description corresponding to the symptom, or a medicine standard name corresponding to the medicine inquiry information; determining whether a disease standard name, a symptom standard description or a medicine standard name exists in the inquiry association information, determining that association exists when the disease standard name, the symptom standard description or the medicine standard name exists in the inquiry association information, and determining that the current reply data is the inquiry association information; when the relevance is not present in the inquiry relation information, determining that the relevance is not present; the standard association information corresponding to the question and answer text data is called from the medical service center system to determine that the current answer data is the standard association information;
and controlling the voice interaction terminal to automatically broadcast the reply data.
2. An artificial intelligence based medical question-answering service system, the system comprising:
the binding module is used for acquiring the input question-answering user information and voice data corresponding to the question-answering user information through the voice interaction terminal; wherein, the question and answer user information at least comprises: a user name and a user identification card number; masking the question and answer user information based on a preset masking rule to obtain standby user information; sending the standby user information to the medical service center module to check whether the standby user information is a valid user in the mask user information set of the medical service center module; when the medical service center module determines that the user is a valid user, the medical service center module feeds back a deleting instruction; after the deletion instruction is obtained, determining the standby user information as mask user information, and deleting question-answering user information; determining a word interval time range, a phrase interval time range and a volume threshold range corresponding to each voice data through a preset sound detection device so as to bind mask user information with the word interval time range, the phrase interval time range and the volume threshold range;
the voice interaction module is used for acquiring voice medical consultation data and further determining mask user information and question-answer text data corresponding to the voice consultation data; the method specifically comprises the following steps: acquiring voice medical consultation data through the voice interaction terminal; analyzing the word interval time period, the phrase interval time period and the volume actual range corresponding to the voice medical consultation data, and further determining mask user information corresponding to the voice medical consultation data according to the word interval time range, the phrase interval time range and the volume threshold range; dividing the voice medical consultation data according to the phrase interval time period to obtain a plurality of pieces of voice data, recording the continuous relation between the pieces of voice data, and determining the specific word meaning information of the pieces of voice data through a preset voice-to-word algorithm; detecting the number of characters of specific word meaning information; when the number of characters is larger than a preset number threshold, determining whether specific word information is a medicine name, and generating prompt voice of whether to consult specific medicines when the specific word information is not the medicine name; when determining to consult a specific medicine, activating a preset camera device, collecting medicine pictures to identify the medicine pictures so as to obtain specific medicine nouns and finish correction and update of specific meaning information; generating question-answer text data according to the continuous relation corresponding to the specific word meaning information and the fragment voice data; transmitting the mask user information to a medical service center module;
the medical service center module is used for determining specific inquiry user information and inquiry records; the method specifically comprises the following steps: acquiring a mask user information set processed by a preset mask rule through a medical service center system; comparing the obtained mask user information with the mask user information set to obtain corresponding inquiry user information of the mask user information in the mask user information set, and further calling and obtaining a corresponding inquiry record; generating non-privacy inquiry information corresponding to the inquiry records, and sending the non-privacy inquiry information to a corresponding data analysis module; the method specifically comprises the following steps: generating a random code corresponding to the inquiry record; wherein the female random code is limited to an even number; the male random code is defined as an odd number; extracting current medical history record data and past medical history record data from the inquiry records to serve as basic inquiry information; extracting preset detection information corresponding to the parity from the inquiry records based on the parity of the random code; generating privacy-free inquiry information comprising a random code, basic inquiry information and preset detection information; acquiring the running state of each data analysis server to determine that the data analysis server with the running state being an idle state is a server to be selected; transmitting sensitivity test codes to each server to be selected, and determining the server to be selected which feeds back the operation result of the sensitivity test codes for the first time as a corresponding data analysis server; determining that a server to be selected without uploading an operation result in a preset detection time period is a katon server, and generating a maintenance task to a preset maintenance terminal;
the data analysis module is used for acquiring inquiry related information existing in the privacy-free inquiry information and sending the inquiry related information to the medical service center module; wherein, the inquiry association information at least comprises: a consultation-related disorder name, a consultation-related drug, and a consultation-related symptom;
the medical service center module is also used for determining the relevance between the inquiry related information and the inquiry text data; when the relevance exists, determining the current reply data as inquiry relevance information; when no relevance exists, acquiring preset standard relevance information corresponding to the question-answer text data, and determining that the current answer data is the standard relevance information; the method specifically comprises the following steps: acquiring question-answering symptom names, question-answering symptom data or medicine query information corresponding to the question-answering text data according to a keyword extraction algorithm; determining a symptom standard name corresponding to the symptom name, a symptom standard description corresponding to the symptom, or a medicine standard name corresponding to the medicine inquiry information; determining whether a disease standard name, a symptom standard description or a medicine standard name exists in the inquiry association information, determining that association exists when the disease standard name, the symptom standard description or the medicine standard name exists in the inquiry association information, and determining that the current reply data is the inquiry association information; when the relevance is not present in the inquiry relation information, determining that the relevance is not present; the standard association information corresponding to the question and answer text data is called from the medical service center system to determine that the current answer data is the standard association information; and controlling the voice interaction module to automatically broadcast the reply data.
3. An artificial intelligence based medical question-answering service device, the device comprising:
a processor;
and a memory having executable code stored thereon that, when executed, causes the processor to perform an artificial intelligence based medical question-answering service method according to claim 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310890237.0A CN116612906B (en) | 2023-07-20 | 2023-07-20 | Medical question-answering service method, system and equipment based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310890237.0A CN116612906B (en) | 2023-07-20 | 2023-07-20 | Medical question-answering service method, system and equipment based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116612906A CN116612906A (en) | 2023-08-18 |
| CN116612906B true CN116612906B (en) | 2023-11-10 |
Family
ID=87676877
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310890237.0A Active CN116612906B (en) | 2023-07-20 | 2023-07-20 | Medical question-answering service method, system and equipment based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116612906B (en) |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106250708A (en) * | 2016-08-16 | 2016-12-21 | 广州比特软件科技有限公司 | A kind of on-line consulting method and system |
| CN107818823A (en) * | 2017-12-05 | 2018-03-20 | 成都法线网络科技有限公司 | A kind of artificial intelligence way of inquisition |
| KR20200049254A (en) * | 2018-10-31 | 2020-05-08 | 박해유 | A chat service providing system that can provide medical consultation according to customer's needs with a chat robot |
| KR20200061097A (en) * | 2018-11-23 | 2020-06-02 | 주식회사 굿모닝 | Intelligent medical consulting service system and method |
| CN111949758A (en) * | 2019-05-16 | 2020-11-17 | 北大医疗信息技术有限公司 | Medical question and answer recommendation method, recommendation system and computer readable storage medium |
| CN112102954A (en) * | 2020-09-02 | 2020-12-18 | 南京江北新区科技投资集团有限公司 | Big data analysis cloud platform system capable of providing intelligent medical service |
| CN112786176A (en) * | 2021-02-22 | 2021-05-11 | 北京融威众邦电子技术有限公司 | Intelligent self-service diagnosis method and device and computer equipment |
| CN113472806A (en) * | 2021-07-14 | 2021-10-01 | 斑马网络技术有限公司 | Voice interaction method, device, system, equipment and storage medium for protecting privacy |
| KR20210135397A (en) * | 2020-05-05 | 2021-11-15 | 이동섭 | System for providing medical counseling service |
| CN114334181A (en) * | 2021-11-24 | 2022-04-12 | 北京大学人民医院 | Method and system for realizing information intercommunication between medical institution and patient |
| JP2022105862A (en) * | 2021-01-05 | 2022-07-15 | 株式会社島津製作所 | Medical consultation information acquisition system, medical consultation information acquisition method, and computer program |
| WO2022160596A1 (en) * | 2021-01-26 | 2022-08-04 | 北京搜狗科技发展有限公司 | Inquiry information processing method and apparatus, and medium |
| CN115910319A (en) * | 2022-10-11 | 2023-04-04 | 佛山市第一人民医院（中山大学附属佛山医院） | Otology inquiry assisting method and device, electronic equipment and storage medium |
-
2023
- 2023-07-20 CN CN202310890237.0A patent/CN116612906B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106250708A (en) * | 2016-08-16 | 2016-12-21 | 广州比特软件科技有限公司 | A kind of on-line consulting method and system |
| CN107818823A (en) * | 2017-12-05 | 2018-03-20 | 成都法线网络科技有限公司 | A kind of artificial intelligence way of inquisition |
| KR20200049254A (en) * | 2018-10-31 | 2020-05-08 | 박해유 | A chat service providing system that can provide medical consultation according to customer's needs with a chat robot |
| KR20200061097A (en) * | 2018-11-23 | 2020-06-02 | 주식회사 굿모닝 | Intelligent medical consulting service system and method |
| CN111949758A (en) * | 2019-05-16 | 2020-11-17 | 北大医疗信息技术有限公司 | Medical question and answer recommendation method, recommendation system and computer readable storage medium |
| KR20210135397A (en) * | 2020-05-05 | 2021-11-15 | 이동섭 | System for providing medical counseling service |
| CN112102954A (en) * | 2020-09-02 | 2020-12-18 | 南京江北新区科技投资集团有限公司 | Big data analysis cloud platform system capable of providing intelligent medical service |
| JP2022105862A (en) * | 2021-01-05 | 2022-07-15 | 株式会社島津製作所 | Medical consultation information acquisition system, medical consultation information acquisition method, and computer program |
| WO2022160596A1 (en) * | 2021-01-26 | 2022-08-04 | 北京搜狗科技发展有限公司 | Inquiry information processing method and apparatus, and medium |
| CN112786176A (en) * | 2021-02-22 | 2021-05-11 | 北京融威众邦电子技术有限公司 | Intelligent self-service diagnosis method and device and computer equipment |
| CN113472806A (en) * | 2021-07-14 | 2021-10-01 | 斑马网络技术有限公司 | Voice interaction method, device, system, equipment and storage medium for protecting privacy |
| CN114334181A (en) * | 2021-11-24 | 2022-04-12 | 北京大学人民医院 | Method and system for realizing information intercommunication between medical institution and patient |
| CN115910319A (en) * | 2022-10-11 | 2023-04-04 | 佛山市第一人民医院（中山大学附属佛山医院） | Otology inquiry assisting method and device, electronic equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 智能问答系统在医学领域的应用研究;贺佳;杜建强;聂斌;熊旺平;罗计根;;医学信息(第14期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116612906A (en) | 2023-08-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112786194A (en) | Medical image diagnosis guide inspection system, method and equipment based on artificial intelligence | |
| Willis | Analysis of the cognitive interview in questionnaire design | |
| Kaplan | Cooperative responses from a portable natural language query system | |
| KR102217457B1 (en) | A chat service providing system that can provide medical consultation according to customer's needs with a chat robot | |
| US20140129246A1 (en) | Extension of clinical guidelines based on clinical expert recommendations | |
| CN111401066A (en) | Artificial intelligence-based word classification model training method, word processing method and device | |
| CN109522397B (en) | Information processing method and device | |
| US20020194026A1 (en) | System and method for managing data and documents | |
| WO2021208444A1 (en) | Method and apparatus for automatically generating electronic cases, a device, and a storage medium | |
| CN112837772A (en) | Pre-inquiry case history generation method and device | |
| Steinmetz et al. | From natural language questions to SPARQL queries: a pattern-based approach | |
| CN115394393A (en) | Intelligent diagnosis and treatment data processing method and device, electronic equipment and storage medium | |
| CN114360678A (en) | Information processing method, device, equipment and storage medium | |
| US20230253124A1 (en) | Method for machine-assisted automated continuation of conversations between the user, software system, and health expert. | |
| CN116612906B (en) | Medical question-answering service method, system and equipment based on artificial intelligence | |
| CN112037904A (en) | Online diagnosis and treatment data processing method and device, computer equipment and storage medium | |
| Aultman et al. | A broader understanding of care managers’ attitudes of advance care planning: A concurrent nested design | |
| AU2020265819A1 (en) | System and method for phrase comparison consolidation and reconciliation | |
| CN116682579A (en) | Information recommendation method, device, equipment and storage medium based on inquiry intention | |
| CN116168844A (en) | Medical data processing system based on big data analysis | |
| CN113192619A (en) | Object matching method, device, equipment and storage medium | |
| CN111967235A (en) | Form processing method and device, computer equipment and storage medium | |
| JP2023514023A (en) | Question retrieval device, question retrieval method, device, and storage medium | |
| CN113728322A (en) | Emotion detection using medical cues | |
| Adesina et al. | Text messaging and retrieval techniques for a mobile health information system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |