CN106326640A - Medical speech control system and control method thereof - Google Patents
Medical speech control system and control method thereof Download PDFInfo
- Publication number
- CN106326640A CN106326640A CN201610665602.8A CN201610665602A CN106326640A CN 106326640 A CN106326640 A CN 106326640A CN 201610665602 A CN201610665602 A CN 201610665602A CN 106326640 A CN106326640 A CN 106326640A
- Authority
- CN
- China
- Prior art keywords
- information
- case
- module
- voice
- unit
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/9032—Query formulation
- G06F16/90332—Natural language query formulation or dialogue systems
-
- G06F19/326—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/011—Arrangements for interaction with the human body, e.g. for user immersion in virtual reality
-
- 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
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Mathematical Physics (AREA)
- General Physics & Mathematics (AREA)
- Biomedical Technology (AREA)
- Human Computer Interaction (AREA)
- Artificial Intelligence (AREA)
- Pathology (AREA)
- Computational Linguistics (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention relates to a medical speech control system and a control method thereof. A basic interaction control system comprises a speech input unit, a speech recognizing unit, a speech identification module, a semantic understanding module, a keyword extraction module, a case (report) library retrieval unit, a case (report) display/updating unit, an electronic case (report) display/updating module, a speech broadcast module and a manual confirmation unit. The invention also provides a basic interaction control method, an application interaction control system, an application interaction control method, an intelligent interaction control system and an intelligent interaction control method. The systems and the methods have the advantages that the systems are deeply integrated with hospital service; the current situation that medical personnel manually input data is relieved; fast and accurate intelligent hospital guide, intelligent cases and intelligent reports are obtained through self study updating of a knowledge base.
Description
[technical field]
The present invention relates to medical instruments field, specifically, be a kind of medical treatment speech control system and control method thereof.
[background technology]
Machine information retrieval system helps us to search, in immense information ocean, the information material wanted, and examines at present
The instrument of rope information such as query software, search engine such as google etc., mainly Keywords matching, the web page interlinkage analysis of employing
Etc. technology.But the very difficult search intention being carried out accurate definition oneself by the combination of simple key word of people, and key word
The semantic factors such as the search procedure joined does not processes word meaning combination, the semantic relation within statement.So people often have to
Spend a lot of time the results web page list to huge amount and be Artificial Cognition again to find preferable answer.
Information inquiry user is desirable for more natural, and mode defines the search request of oneself more accurately, it is desirable to be able to
Arrive the answer meeting query intention on semanteme, knowledge level exactly, and be not only the answer list matching key word.
In January, 2016, Nuance issued Dragon Drive in International CES in 2016 (CES 2016)
(driving of sound dragon) interconnection automobile speech technology.The BMW that this year will list, is all equipped with the up-to-date language of Nuance by using
Sound identification, natural language understanding (NLU), interrupt and the conversational user interface of phonetic synthesis solution, allow the user can
Intuitively use vehicle-mounted function and the Internet services easily and distractibility is preferably minimized, promoting driving safety.
At medical field, above-mentioned speech recognition, the understanding of natural language, and the intelligent retrieval of information and intelligent updating
Technology is the most well applied.Current medical voice interactive system can't realize intelligent information inquiry, identify and
Intelligent information typing, can not be fully achieved intelligence inquiry and the renewal of guiding doctor, report, case, and all these work also need to
Loaded down with trivial details manual typing operation.
In sum, needing the interactive system of a kind of intelligence medical treatment voice easily badly, it can not only realize intelligent information and look into
Ask and combine efficient identification and realize intelligent information typing, thus be no longer necessary to loaded down with trivial details manual typing information, and from level to level
According to system suggestion carry out selection one by one, the both hands of liberation doctor and eyes.In brief, i.e. intelligence is carried out by voice system
The man-machine interaction of energy, but have not been reported about this type of technology at present.
[summary of the invention]
It is an object of the invention to for the deficiency in existing medical treatment voice technology, it is provided that a kind of medical treatment voice is controlled the most alternately
System processed.
The second object of the present invention is to provide a kind of medical treatment basic interaction control method of voice.
The third object of the present invention is to provide a kind of medical treatment voice application intersection control routine.
The fourth object of the present invention is to provide a kind of medical treatment voice application interaction control method.
The fifth object of the present invention is to provide a kind of medical treatment speech-sound intelligent intersection control routine.
The sixth object of the present invention is to provide a kind of medical treatment speech-sound intelligent interaction control method.
For realizing above-mentioned first purpose, the present invention adopts the technical scheme that:
Described basic intersection control routine includes voice typing unit, speech recognition unit, sound identification module, the meaning of one's words
Understanding Module, keyword extracting module, case (report) library searching unit, case (report) display/updating block, electronic medical records
(report) display/more new module, voice broadcast module, manual confirmation unit；
Described voice typing unit, is the voice typing to case (report) information；The voice messaging of doctor passes through wheat
Gram wind directly inputs the man-machine interface control system of computer；
Described speech recognition unit includes sound identification module and meaning of one's words Understanding Module；Described sound identification module,
The speech data of doctor is converted to string data；Described meaning of one's words Understanding Module, is connected with described sound identification module,
Translate the language meaning of described string data, and can be by described case and various reports by keyword extracting module generation
Storehouse coupling coupling search key performed by retrieval unit；
Described case (report) storehouse coupling retrieval unit is that typing storage are a large amount of by standard criterion from computer
The case of personality formula typing and the paragraph of various reports or item library, by the automatic search function of computer from case and all kinds of
The paragraph of standardization of report or item library retrieve containing keyword retrieval module 123 generated all containing key word
After paragraph or entry, then the paragraph that retrieved from these by Boolean calculation or entry match the paragraph that similarity is the highest again
Or entry is as the result paragraph of the case (report) generated after this case (report) phonetic entry or entry；
Described case (report) display/updating block includes that electronic medical records (report) display/more new module and voice are broadcast
Report module；Described electronic medical records (report) display/more new module is by after this case above-mentioned and various reports phonetic entry
The case generated and the result paragraph of various reports or entry are shown in doctor's desktop display by electronics original text form；Described
Voice broadcast module be the result electronics original text of the case generated and various reports to be synthesized voice document and is broadcast by sound
Put device to report, facilitate doctor's case to being generated after oneself phonetic entry and the result paragraph of various reports or entry symbol
The judgement of conjunction property and confirmation；
Described manual confirmation unit is manual confirmation unit, and doctor is according to the voice broadcast module case to generating and each
The prompting of the result synthesis voice broadcast of class report, carries out manual confirmation whether click behaviour on terminal display to result
Make；
For realizing above-mentioned second purpose, described basic interaction control method, comprise the steps:
Step 1, case to be expressed and various reports are pressed standardization paragraph or entry, are carried out by mike by doctor
Voice typing.
Step 2, speech recognition and the meaning of one's words by computer understand that above-mentioned report voice is carried out all key words by function
Extraction.
Step 3, by key word, to the case stored by standardization paragraph or entry format in advance in computer and
Various reports library utilizes computer to retrieve, and finds out the paragraph the highest with Keywords matching degree or entry.
Step 4, the case formed after this phonetic entry that will retrieve and various reports are by standardization paragraph or entry
Computer display shows.
Step 5, the case formed after this phonetic entry that will retrieve and various reports are by standardization paragraph or entry
Reported by Audio Players.
Step 6, by audition, doctor judges that the content contrast step of voice broadcast carries out Speech Record by mike for the moment
The accordance of the content entered judges.
Step 7, as doctor thinks that the case of above-mentioned generation and the result entry of various reports do not meet or incorrect, then
Manual modification or delete this entry, and return step 1, re-start this paragraph or entry voice typing.
Step 8, as doctor confirms this paragraph above-mentioned or entry, then returns step 1, carries out the disease to be expressed of next
Example and various reports, by standardization paragraph or entry, carry out voice typing by mike.And repeat step 1 to step 7, to the completeest
Become whole electronic medical recordses and the paragraph of various reports or entry input.
For realizing above-mentioned 3rd purpose, the present invention adopts the technical scheme that:
Described application intersection control routine includes voice typing unit, speech recognition unit, sound identification module, the meaning of one's words
Understanding Module, key word or extraction of semantics module, information bank retrieval unit, information show with updating block, dialogue management unit,
System voice question and answer module, artificial speech question and answer module；
Described voice typing unit, preferred as one, it is that doctor is to patient's case information and/or the Speech Record of symptom
Enter, receive doctor individual to described patient's case information and/or the voice signal of symptom；The voice messaging of doctor passes through Mike
Wind directly inputs the man-machine interface control system of computer；
Described speech recognition unit includes sound identification module and meaning of one's words Understanding Module；Described sound identification module,
The speech data of doctor is converted to string data；Described meaning of one's words Understanding Module, is connected with described sound identification module,
Translate the language meaning of described string data, and carry extraction module by key word or language view and generate and can be retrieved by information bank
Unit performs key word or the language view block of retrieval；
Described information bank retrieval unit, preferred as one, it is to case information and/or the inspection of the information bank of symptom
Rope, typing store a large amount of case information and/or symptom composition case information and/or symptom storehouse, by meter from computer
The automatic search function of calculation machine retrieves the case information containing key word and/or symptom from case information and/or symptom storehouse；
Or carry out concept similarity calculating according to the semantic chunk that semantic understanding module generates, right from case information and/or symptom storehouse
Sentence to be selected compares with target sentence, it is thus achieved that sentence quasi-mode matching result, semantic relation structure recognition matching result and answer are accurate
Exactness score, sorts according to answer accurateness, it is thus achieved that retrieval information result；
Described information shows that with updating block be that the content to the case information retrieved Yu renewal passes through terminal use
Computer screen shows；
Described dialogue management unit includes system voice question and answer module and artificial speech question and answer module；When information show with
During updating block output display result, particularly output result is when showing indefinite, and described system voice question and answer module can be with
Suggestive question formulation output voice also submits to doctor to answer, and doctor show according to subject of question and/or combining information and more
Case information and/or the content of symptom that new unit shows are that answer is made in prompting, and are incited somebody to action back by artificial speech response means
The information answered feeds back to speech recognition unit；
For realizing above-mentioned 4th purpose, described application interaction control method, comprise the steps:
Step 1, doctor, by case information to be inquired about and/or the key word of symptom or the clinical symptoms of patient, passes through
Mike carries out voice typing.
Step 2, speech recognition and the meaning of one's words by computer understand that above-mentioned report voice is carried out all key words by function
And/or the extraction of semantic chunk.
Step 3, by key word and/or semantic chunk, utilizes the automatic search function of computer from case information and/or disease
Shape storehouse retrieves the case information containing key word, it is thus achieved that retrieval information result.
Step 4, sorts the case information retrieved according to answer accurateness, on the terminal computer display screen of doctor
Show.
Step 5, carries out step 1 to the repetition of step 4 to the information being retrieved by dialogue management module, with to retrieval
Information shows and carries out screening and/or supplementing.Until completing the inquiry of final case information and/or updating.
For realizing above-mentioned 5th purpose, the present invention adopts the technical scheme that:
Described intelligent interaction control system includes voice typing unit, speech recognition unit, sound identification module, the meaning of one's words
Understanding Module, key word or language view extraction module, information bank retrieval unit, information shows and updating block, dialogue management unit,
System voice question and answer module, artificial speech question and answer module, big data analysis unit and case intelligent updating output unit；
Described voice typing unit, preferred as one, it is the voice typing to patient's case information and/or symptom,
Receive doctor individual to described patient's case information and/or the voice signal of symptom；The voice messaging of doctor passes through mike
Directly input the man-machine interface control system of computer；
Described speech recognition unit includes sound identification module and meaning of one's words Understanding Module；Described sound identification module,
The speech data of doctor is converted to string data；Described meaning of one's words Understanding Module, is connected with described sound identification module,
Translate the language meaning of described string data, and generate can be retrieved list by information bank by key word or language view extraction module
Unit performs key word or the language view block of retrieval；
Described information bank retrieval unit, in the present embodiment, preferred as one, it is to case information and/or symptom
The retrieval of information bank, be from computer typing and store a large amount of case information and/or symptom composition case information and/or
Symptom storehouse, retrieves the case containing key word by the automatic search function of computer from case information and/or symptom storehouse
Information and/or symptom, or carry out concept similarity calculating, from case information according to the semantic chunk of meaning of one's words Understanding Module generation
And/or sentence to be selected is compared by symptom storehouse with target sentence, it is thus achieved that sentence quasi-mode matching result, semantic relation structure recognition
Join result and answer accuracy score, sort according to answer accurateness, it is thus achieved that retrieval information result.
Described information shows that with updating block be that the content to the case information retrieved Yu renewal passes through terminal use
Computer screen shows；
Described dialogue management unit includes system voice question and answer module and artificial speech question and answer module；When information show with
During updating block output display result, particularly output result is when showing indefinite, and described system voice question and answer module can be with
Suggestive question formulation output voice also submits to doctor to answer, and doctor show according to subject of question and/or combining information and more
Case information and/or the content of symptom that new unit shows are that answer is made in prompting, and are incited somebody to action back by artificial speech response means
The information answered feeds back to speech recognition unit；
Described big data analysis unit, its workflow be by embodiment by application mutual obtained by sick
The final updated result of example information is uploaded to big data acquisition server, with the big data server data acquisition to each terminal
Collection, data analysis, data process, system library update circulation self-learning function, by embodiment by apply mutual gained
To case information again carry out intelligent updating；
Described case intelligent updating output unit, is the case that will be generated above by big data analysis unit
Information intelligent updates result and feeds back to the end user computer information bank of information of uploading；
For realizing above-mentioned 6th purpose, described intelligent interaction control method, comprise the steps:
Step 1, doctor, by case information to be inquired about and/or the key word of symptom or the clinical symptoms of patient, passes through
Mike carries out voice typing.
Step 2, speech recognition and the meaning of one's words by computer understand that above-mentioned report voice is carried out all key words by function
And/or the extraction of semantic chunk.
Step 3, by key word and/or semantic chunk, utilizes the automatic search function of computer from case information and/or disease
Shape storehouse retrieves the case information containing key word, it is thus achieved that retrieval information result.
Step 4, the case information formed after this phonetic entry that will retrieve sorts according to answer accurateness, is calculating
Show on machine display screen.
Step 5, carries out step 1 to the repetition of step 4 to the information being retrieved by dialogue management module, with to retrieval
Screening that information shows and/or supplement.Until completing the inquiry of final case information and/or updating.
Step 6, is uploaded to big data acquisition server by the case information completing to update, and by big data analysis and from
Learn the intelligent updating of case information.
Step 7, feeds back to the end user computer information bank of information of uploading also by the intelligent updating result of case information
Shown by screen.
The invention has the advantages that:
1 and hospital business Deep integrating, promote clinical treatment flow process, liberation healthcare givers's craft logging data present situation,
And it is mutual to realize intelligent medical guide application by the self study renewal of a large amount of knowledge bases.
2, support unified standard and the flow process of customization, support existing IT architecture, be easy to dispose various platform knot
Close.
3, speech recognition is added natural language understanding technology and is applied to medical field, form medical treatment voice solution, from
And obtain convenient, intelligent medical guide, intelligence case, the generation of intelligence report fast and accurately.
[accompanying drawing explanation]
Accompanying drawing 1 is the medical treatment basic intersection control routine of voice 10.
Accompanying drawing 2 is medical treatment voice application intersection control routine 20.
Accompanying drawing 3 is medical treatment speech-sound intelligent intersection control routine 30.
[detailed description of the invention]
The detailed description of the invention provided the present invention below in conjunction with the accompanying drawings elaborates.
The reference and the ingredient that relate in accompanying drawing are as follows:
110,210,310. voice typing unit
120,220,320. speech recognition unit
121,221,321. sound identification module
122,222,322. meaning of one's words Understanding Module
123. keyword extracting module
130. cases (report) library searching unit
140. cases (report) display/more new module
141. electronic medical recordses (report) display and more new module
142. voice broadcast modules
150. manual confirmation unit
223,323. key words or extraction of semantics module
230,330. information bank retrieval unit
240,340. information banks show and updating block
250,350. dialogue management unit
251,351. system voice question and answer module
252,352. artificial speech question and answer module
360. big data analysis units
370. information intelligents update output unit
Embodiment 1
Refer to Fig. 1, Fig. 1 is the medical treatment basic intersection control routine of voice 10.Described basic intersection control routine 10 wraps
Include voice typing unit 110, speech recognition unit 120, sound identification module 121, meaning of one's words Understanding Module 122, keyword extraction
Module 123, case (report) library searching unit 130, case (report) display/updating block 140, electronic medical records (report) are aobvious
Show/more new module 141, voice broadcast module 142, manual confirmation unit 150.
Described voice typing unit 110 is in the present embodiment, preferred as one, is to patient's case and various reports
Voice typing, receive doctor to described patient's case and the voice signal of various reports.The voice messaging of doctor passes through wheat
Gram wind directly inputs the man-machine interface control system of computer.
Described speech recognition unit 120 includes sound identification module 121 and meaning of one's words Understanding Module 122.Described voice
Identification module 121, is converted to string data by the speech data of doctor；Described meaning of one's words Understanding Module 122, with described voice
Identification module is connected, and translates the language meaning of described string data, and generated by keyword extracting module 123 can be by
Described case and various reports storehouse coupling coupling search key performed by retrieval unit 130.
Described case (report) storehouse coupling retrieval unit 130 is that typing storage are a large amount of by standard gauge from computer
The case of plasticity form typing and the paragraph of various reports or item library, by the automatic search function of computer from case and each
The paragraph of standardization of class report or item library retrieve containing keyword retrieval module 123 generated all containing key word
Paragraph or entry after, then the paragraph that retrieved from these by Boolean calculation or entry match the section that similarity is the highest again
Fall or entry is as the case generated after this case and various reports phonetic entry and the result paragraph of various reports or bar
Mesh.
Described case (report) display/updating block 140 includes electronic medical records (report) display/more new module 141 He
Voice broadcast module 142.Described electronic medical records (report) display/more new module 141 is by this case above-mentioned and all kinds of report
The case generated after accusing phonetic entry and the result paragraph of various reports or entry are shown at doctor's desktop by electronics original text form
Display screen shows.Described voice broadcast module 142 is that the result electronics original text of the case generated and various reports is synthesized voice
File is also reported by Audio Players, facilitates doctor's case to being generated after oneself phonetic entry and various reports
Result paragraph or the judgement of entry accordance and confirmation.
Described manual confirmation unit 150 is manual confirmation unit, doctor according to voice broadcast module 142 to generate disease
The prompting of the result synthesis voice broadcast of example and various reports, carries out manual confirmation whether point on terminal display to result
Hit operation.
Medical treatment speech control system and the most mutual control method of control method, comprise the steps:
Step 1, case to be expressed and various reports are pressed standardization paragraph or entry, are carried out by mike by doctor
Voice typing.
Step 2, speech recognition and the meaning of one's words by computer understand that above-mentioned report voice is carried out all key words by function
Extraction.
Step 3, by key word, to the case stored by standardization paragraph or entry format in advance in computer and
Various reports library utilizes computer to retrieve, and finds out the paragraph the highest with Keywords matching degree or entry.
Step 4, the case formed after this phonetic entry that will retrieve and various reports are by standardization paragraph or entry
Computer display shows.
Step 5, the case formed after this phonetic entry that will retrieve and various reports are by standardization paragraph or entry
Reported by Audio Players.
Step 6, by audition, doctor judges that the content contrast step of voice broadcast carries out Speech Record by mike for the moment
The accordance of the content entered judges.
Step 7, as doctor thinks that the case of above-mentioned generation and the result entry of various reports do not meet or incorrect, then
Manual modification or delete this entry, and return step 1, re-start this paragraph or entry voice typing.
Step 8, as doctor confirms this paragraph above-mentioned or entry, then returns step 1, carries out the disease to be expressed of next
Example and various reports, by standardization paragraph or entry, carry out voice typing by mike.And repeat step 1 to step 7, to the completeest
Become whole electronic medical recordses and the paragraph of various reports or entry input.
Embodiment 2
Refer to Fig. 2, Fig. 2 is medical treatment voice application intersection control routine 20.Described application intersection control routine 20 wraps
Include voice typing unit 210, speech recognition unit 220, sound identification module 221, meaning of one's words Understanding Module 222, key word or language
Justice extraction module 223, information bank retrieval unit 230, information show and updating block 240, dialogue management unit 250, system language
Mail answers module 251, artificial speech question and answer module 252.
Described voice typing unit 210, in the present embodiment, preferred as one, be to patient's case information and/or
The voice typing of symptom, receives doctor individual to described patient's case information and/or the voice signal of symptom.The voice of doctor
Information directly inputs the man-machine interface control system of computer by mike.
Described speech recognition unit 220 includes sound identification module 221 and meaning of one's words Understanding Module 222.Described voice
Identification module 221, is converted to string data by the speech data of doctor；Described meaning of one's words Understanding Module 222, with described voice
Identification module is connected, and translates the language meaning of described string data, and is generated by key word or language view extraction module 223
Key word or the language view block of retrieval can be performed by information bank retrieval unit 230.
Described information bank retrieval unit 230, in the present embodiment, preferred as one, it is to case information and/or disease
The retrieval of the information bank of shape, from computer typing and store a large amount of case information and/or symptom composition case information and/or
Symptom storehouse, retrieves the case containing key word by the automatic search function of computer from case information and/or symptom storehouse
Information and/or symptom.Or carry out concept similarity calculating according to the semantic chunk that semantic understanding module 222 generates, believe from case
Sentence to be selected is compared by breath and/or symptom storehouse with target sentence, it is thus achieved that sentence quasi-mode matching result, semantic relation structure recognition
Matching result and answer accuracy score, sort according to answer accurateness, it is thus achieved that retrieval information result.
Described information shows that with updating block 240 be that the content to the case information retrieved with renewal is used by terminal
Family computer screen shows.
Described dialogue management unit 250 includes system voice question and answer module 251 and artificial speech question and answer module 252.When
When information shows with updating block 240 output display result, when particularly output result shows indefinite, described system voice
Question and answer module 251 can export voice with suggestive question formulation and submit to doctor to answer, and doctor is according to subject of question and/or knot
Conjunction information shows that with the case information of updating block 240 display and/or the content of symptom be that answer is made in prompting, and by artificial
The information of answer is fed back to speech recognition unit 220 by voice answering module 252.
The mutual control method of application of medical treatment speech control system and control method, comprises the steps:
Step 1, doctor, by case information to be inquired about and/or the key word of symptom or the clinical symptoms of patient, passes through
Mike carries out voice typing.
Step 2, speech recognition and the meaning of one's words by computer understand that above-mentioned report voice is carried out all key words by function
And/or the extraction of semantic chunk.
Step 3, by key word and/or semantic chunk, utilizes the automatic search function of computer from case information and/or disease
Shape storehouse retrieves the case information containing key word, it is thus achieved that retrieval information result.
Step 4, sorts the case information retrieved according to answer accurateness, on the terminal computer display screen of doctor
Show.
Step 5, carries out step 1 to the repetition of step 4 to the information being retrieved by dialogue management module, with to retrieval
Information shows and carries out screening and/or supplementing.Until completing the inquiry of final case information and/or updating.
Embodiment 3
Refer to Fig. 3, Fig. 3 is medical treatment speech-sound intelligent intersection control routine 30.Described intelligent interaction control system 30 is wrapped
Include voice typing unit 310, speech recognition unit 320, sound identification module 321, meaning of one's words Understanding Module 322, key word or language
View extraction module 323, information bank retrieval unit 330, information show and updating block 340, dialogue management unit 350, system language
Mail answers module 351, artificial speech question and answer module 352, big data analysis unit 360 and case intelligent updating output unit
370。
Described voice typing unit 310, in the present embodiment, preferred as one, be to patient's case information and/or
The voice typing of symptom, receives doctor individual to described patient's case information and/or the voice signal of symptom.The voice of doctor
Information directly inputs the man-machine interface control system of computer by mike.
Described speech recognition unit 320 includes sound identification module 321 and meaning of one's words Understanding Module 322.Described voice
Identification module 321, is converted to string data by the speech data of doctor；Described meaning of one's words Understanding Module 322, with described voice
Identification module is connected, and translates the language meaning of described string data, and is generated by key word or language view extraction module 323
Key word or the language view block of retrieval can be performed by information bank retrieval unit 330.
Described information bank retrieval unit 330, in the present embodiment, preferred as one, it is to case information and/or disease
The retrieval of the information bank of shape, from computer typing and store a large amount of case information and/or symptom composition case information and/or
Symptom storehouse, retrieves the case containing key word by the automatic search function of computer from case information and/or symptom storehouse
Information and/or symptom, or carry out concept similarity calculating according to the semantic chunk of meaning of one's words Understanding Module 322 generation, believe from case
Sentence to be selected is compared by breath and/or symptom storehouse with target sentence, it is thus achieved that sentence quasi-mode matching result, semantic relation structure recognition
Matching result and answer accuracy score, sort according to answer accurateness, it is thus achieved that retrieval information result.
Described information shows that with updating block 340 be that the content to the case information retrieved with renewal is used by terminal
Family computer screen shows.
Described dialogue management unit 350 includes system voice question and answer module 351 and artificial speech question and answer module 352.When
When information shows with updating block 340 output display result, when particularly output result shows indefinite, described system voice
Question and answer module 351 can export voice with suggestive question formulation and submit to doctor to answer, and doctor is according to subject of question and/or knot
Conjunction information shows that with the case information of updating block 340 display and/or the content of symptom be that answer is made in prompting, and by artificial
The information of answer is fed back to speech recognition unit 320 by voice answering module 352.
Described big data analysis unit 360, its workflow be by embodiment by apply mutual gained
Final updated result to case information is uploaded to big data acquisition server, with the big data server data to each terminal
Collection, data analysis, data process, system library update circulation self-learning function, by embodiment by apply mutual institute
Obtain case information again carry out intelligent updating.
Described case intelligent updating output unit 370, will be generated above by big data analysis unit
Case information intelligent updating result feeds back to the end user computer information bank of information of uploading.
The control method of the intelligent interaction of medical treatment speech control system and control method, comprises the steps:
Step 1, doctor, by case information to be inquired about and/or the key word of symptom or the clinical symptoms of patient, passes through
Mike carries out voice typing.
Step 2, speech recognition and the meaning of one's words by computer understand that above-mentioned report voice is carried out all key words by function
And/or the extraction of semantic chunk.
Step 3, by key word and/or semantic chunk, utilizes the automatic search function of computer from case information and/or disease
Shape storehouse retrieves the case information containing key word, it is thus achieved that retrieval information result.
Step 4, the case information formed after this phonetic entry that will retrieve sorts according to answer accurateness, is calculating
Show on machine display screen.
Step 5, carries out step 1 to the repetition of step 4 to the information being retrieved by dialogue management module, with to retrieval
Screening that information shows and/or supplement.Until completing the inquiry of final case information and/or updating.
Step 6, is uploaded to big data acquisition server by the case information completing to update, and by big data analysis and from
Learn the intelligent updating of case information.
Step 7, feeds back to the end user computer information bank of information of uploading also by the intelligent updating result of case information
Shown by screen.
The present invention not only limits above-mentioned three illustrated embodiments, it is an object of the invention to, at medical field, uses this
Bright principle, forms medical treatment speech control system and control method, thus obtain convenient, fast and accurately intelligent medical guide,
Intelligence case, the generation of intelligence report.
Those skilled in the art are appreciated that and realize the whole or portion that above-mentioned three kinds of embodiment methods are carried
The program that can be by step by step completes to instruct relevant hardware, and described program can be stored in a kind of computer-readable and deposit
In storage media, this program upon execution, including one or a combination set of step in embodiment method.
Additionally, each functional module in each embodiment of the present invention can be integrated in a processing module, it is also possible to be
Modules is individually physically present, it is also possible to two or more modules are integrated in a module.Above-mentioned integrated module
Both can realize to use the form of hardware, it would however also be possible to employ the form of software function module realizes.If described integrated module
Realize with the form of software function module, it is also possible to be stored in a computer read/write memory medium.Described storage is situated between
Matter can be read only memory, disk or CD etc..
The above is only the preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art
Member, on the premise of without departing from the inventive method, it is also possible to makes some improvement and supplements, and these improve and supplement and also should be regarded as
Protection scope of the present invention.
Claims (6)
1. the basic intersection control routine of medical voice, it is characterised in that described basic intersection control routine includes voice
Typing unit, speech recognition unit, sound identification module, meaning of one's words Understanding Module, keyword extracting module, the inspection of case (report) storehouse
Cable elements, case (report) display/updating block, electronic medical records (report) display/more new module, voice broadcast module, artificial
Confirmation unit；
Described voice typing unit, is the voice typing to case (report) information；The voice messaging of doctor passes through mike
Directly input the man-machine interface control system of computer；
Described speech recognition unit includes sound identification module and meaning of one's words Understanding Module；Described sound identification module, will doctor
Raw speech data is converted to string data；Described meaning of one's words Understanding Module, is connected with described sound identification module, translates
The language meaning of described string data, and can be by described case and various reports storehouse by keyword extracting module generation
Coupling search key performed by collating cable elements；
Described case (report) storehouse coupling retrieval unit is that typing storage are a large amount of by standard criterion personality from computer
The case of formula typing and the paragraph of various reports or item library, by the automatic search function of computer from case and various reports
The paragraph of standardization or item library in retrieve all paragraphs containing key word generated containing keyword retrieval module 123
Or after entry, then the paragraph that retrieved from these by Boolean calculation or entry match the highest paragraph of similarity or bar again
Mesh is as the result paragraph of the case (report) generated after this case (report) phonetic entry or entry；
Described case (report) display/updating block includes electronic medical records (report) display/more new module and voice broadcast mould
Block；Described electronic medical records (report) display/more new module is to be given birth to after this case above-mentioned and various reports phonetic entry
The case become and the result paragraph of various reports or entry are shown in doctor's desktop display by electronics original text form；Described language
It is the result electronics original text of the case generated and various reports to be synthesized voice document and passes through Audio Players that sound reports module
Report, facilitate doctor's case to being generated after oneself phonetic entry and the result paragraph of various reports or entry accordance
Judgement and confirmation；
Described manual confirmation unit is manual confirmation unit, doctor according to voice broadcast module to generate case and all kinds of report
The prompting of the result synthesis voice broadcast accused, carries out manual confirmation whether clicking operation on terminal display to result.
2. the basic interaction control method of medical voice, it is characterised in that described basic interaction control method, including as follows
Step:
Step 1, case to be expressed and various reports are pressed standardization paragraph or entry, are carried out voice by mike by doctor
Typing；
Step 2, speech recognition and the meaning of one's words by computer understand that above-mentioned report voice is carried out carrying of all key words by function
Take；
Step 3, by key word, to the case stored by standardization paragraph or entry format in advance in computer and all kinds of
Report file Cooley computer is retrieved, and finds out the paragraph the highest with Keywords matching degree or entry；
Step 4, the case formed after this phonetic entry that will retrieve and various reports by standardization paragraph or entry based on
Show on calculation machine display screen；
Step 5, the case and the various reports that are formed after this phonetic entry that will retrieve are passed through by standardization paragraph or entry
Audio Players is reported；
Step 6, by audition, doctor judges that the content contrast step of voice broadcast carries out voice typing by mike for the moment
The accordance of content judges；
Step 7, as doctor thinks that the case of above-mentioned generation and the result entry of various reports do not meet or incorrect, the most manually
Revise or delete this entry, and returning step 1, re-starting this paragraph or entry voice typing；
Step 8, as doctor confirms this paragraph above-mentioned or entry, then returns step 1, carry out next case to be expressed and
Various reports presses standardization paragraph or entry, carries out voice typing by mike.And repeat step 1 to step 7, complete to completing
The electronic medical records in portion and the paragraph of various reports or entry input.
3. a medical voice application intersection control routine, it is characterised in that described application intersection control routine includes voice
Typing unit, speech recognition unit, sound identification module, meaning of one's words Understanding Module, key word or extraction of semantics module, information bank inspection
Cable elements, information show and updating block, dialogue management unit, system voice question and answer module, artificial speech question and answer module；
Described voice typing unit, is doctor's voice typing to patient's case information and/or symptom, receives doctor individual right
Described patient's case information and/or the voice signal of symptom；The voice messaging of doctor directly inputs computer by mike
Man-machine interface control system；
Described speech recognition unit includes sound identification module and meaning of one's words Understanding Module；Described sound identification module, will doctor
Raw speech data is converted to string data；Described meaning of one's words Understanding Module, is connected with described sound identification module, translates
The language meaning of described string data, and generate can be held by information bank retrieval unit by key word or language view extraction module
The key word of line retrieval or language view block；
Described information bank retrieval unit, is to case information and/or the retrieval of the information bank of symptom, typing from computer
And store a large amount of case information and/or symptom composition case information and/or symptom storehouse, by the automatic search function of computer from
Case information and/or symptom storehouse retrieve the case information containing key word and/or symptom；Or according to semantic understanding module
The semantic chunk generated carries out concept similarity calculating, compares sentence to be selected with target sentence from case information and/or symptom storehouse
Relatively, it is thus achieved that sentence quasi-mode matching result, semantic relation structure recognition matching result and answer accuracy score, correct according to answer
Degree sequence, it is thus achieved that retrieval information result；
Described information shows that with updating block be that the content to the case information retrieved with renewal is calculated by terminal use
Machine screen shows；
Described dialogue management unit includes system voice question and answer module and artificial speech question and answer module；When information shows and updates
During unit output display result, when particularly output result shows indefinite, described system voice question and answer module can be with prompting
Property question formulation output voice submit to doctor to answer, doctor show according to subject of question and/or combining information and updates singly
The case information of unit's display and/or the content of symptom are that answer is made in prompting, and by artificial speech response means by answer
Information feeds back to speech recognition unit.
4. a medical voice application interaction control method, it is characterised in that described application interaction control method, including as follows
Step:
Step 1, doctor, by case information to be inquired about and/or the key word of symptom or the clinical symptoms of patient, passes through Mike
Wind carries out voice typing；
Step 2, by the speech recognition of computer and the meaning of one's words understand function above-mentioned report voice is carried out all key words and/or
The extraction of semantic chunk；
Step 3, by key word and/or semantic chunk, utilizes the automatic search function of computer from case information and/or symptom storehouse
In retrieve the case information containing key word, it is thus achieved that retrieval information result；
Step 4, sorts the case information retrieved according to answer accurateness, carries out on the terminal computer display screen of doctor
Display；
Step 5, carries out step 1 to the repetition of step 4 to the information being retrieved by dialogue management module, with to retrieval information
Display carries out screening and/or supplementing, until completing the inquiry of final case information and/or updating.
5. a medical speech-sound intelligent intersection control routine, it is characterised in that described intelligent interaction control system includes voice
Typing unit, speech recognition unit, sound identification module, meaning of one's words Understanding Module, key word or language view extraction module, information bank inspection
Cable elements, information show and updating block, dialogue management unit, system voice question and answer module, artificial speech question and answer module, several
According to analytic learning unit and case intelligent updating output unit；
Described voice typing unit, is the voice typing to patient's case information and/or symptom, receives doctor individual to described
Patient's case information and/or the voice signal of symptom；The voice messaging of doctor directly inputs the people of computer by mike
Machine interface control system；
Described speech recognition unit includes sound identification module and meaning of one's words Understanding Module；Described sound identification module, will doctor
Raw speech data is converted to string data；Described meaning of one's words Understanding Module, is connected with described sound identification module, translates
The language meaning of described string data, and generate can be held by information bank retrieval unit by key word or language view extraction module
The key word of line retrieval or language view block；
Described information bank retrieval unit, in the present embodiment, is to case information and/or the retrieval of the information bank of symptom, is
From computer, typing store a large amount of case information and/or symptom composition case information and/or symptom storehouse, passes through computer
Automatic search function from case information and/or symptom storehouse, retrieve the case information containing key word and/or symptom, or
Concept similarity calculating is carried out, to be selected from case information and/or symptom storehouse according to the semantic chunk that meaning of one's words Understanding Module generates
Sentence compares with target sentence, it is thus achieved that sentence quasi-mode matching result, semantic relation structure recognition matching result and answer accuracy
Score, sorts according to answer accurateness, it is thus achieved that retrieval information result；
Described information shows that with updating block be that the content to the case information retrieved with renewal is calculated by terminal use
Machine screen shows；
Described dialogue management unit includes system voice question and answer module and artificial speech question and answer module；When information shows and updates
During unit output display result, when particularly output result shows indefinite, described system voice question and answer module can be with prompting
Property question formulation output voice submit to doctor to answer, doctor show according to subject of question and/or combining information and updates singly
The case information of unit's display and/or the content of symptom are that answer is made in prompting, and by artificial speech response means by answer
Information feeds back to speech recognition unit；
Described big data analysis unit, its workflow is by being believed by the mutual obtained case of application in embodiment
The final updated result of breath is uploaded to big data acquisition server, with big data server to the data acquisition of each terminal, number
According to the circulation self-learning function analyzed, data process, system library updates, by embodiment by application mutual obtained by case
Information again carry out intelligent updating；
Described case intelligent updating output unit, is the case information that will be generated above by big data analysis unit
Intelligent updating result feeds back to the end user computer information bank of information of uploading.
6. a medical speech-sound intelligent interaction control method, it is characterised in that described intelligent interaction control method, including as follows
Step:
Step 1, doctor, by case information to be inquired about and/or the key word of symptom or the clinical symptoms of patient, passes through Mike
Wind carries out voice typing；
Step 2, by the speech recognition of computer and the meaning of one's words understand function above-mentioned report voice is carried out all key words and/or
The extraction of semantic chunk；
Step 3, by key word and/or semantic chunk, utilizes the automatic search function of computer from case information and/or symptom storehouse
In retrieve the case information containing key word, it is thus achieved that retrieval information result；
Step 4, the case information formed after this phonetic entry that will retrieve sorts according to answer accurateness, shows at computer
Show in display screen；
Step 5, carries out step 1 to the repetition of step 4 to the information being retrieved by dialogue management module, with to retrieval information
Display screening and/or supplement, until complete final case information inquiry and/or update；
Step 6, is uploaded to big data acquisition server by the case information completing to update, and by big data analysis and self study
Complete the intelligent updating of case information；
Step 7, feeds back to the end user computer information bank of information of uploading by the intelligent updating result of case information and passes through
Screen shows.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610665602.8A CN106326640A (en) | 2016-08-12 | 2016-08-12 | Medical speech control system and control method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610665602.8A CN106326640A (en) | 2016-08-12 | 2016-08-12 | Medical speech control system and control method thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106326640A true CN106326640A (en) | 2017-01-11 |
Family
ID=57739317
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610665602.8A Pending CN106326640A (en) | 2016-08-12 | 2016-08-12 | Medical speech control system and control method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106326640A (en) |
Cited By (31)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107273660A (en) * | 2017-05-17 | 2017-10-20 | 北京好运到信息科技有限公司 | The electronic health record generation method and electronic medical record system of a kind of integrated speech |
| CN107591195A (en) * | 2017-09-07 | 2018-01-16 | 北京鑫丰南格科技股份有限公司 | A kind of medical care householder method and device based on nursing calling system |
| CN107729510A (en) * | 2017-10-23 | 2018-02-23 | 深圳市前海众兴电子商务有限公司 | Information interacting method, information interactive terminal and storage medium |
| CN107742519A (en) * | 2017-10-31 | 2018-02-27 | 珠海市美瑞华医用科技有限公司 | A kind of voice entry system of intelligent control fluid delivery apparatus |
| CN107977395A (en) * | 2017-08-01 | 2018-05-01 | 北京物灵智能科技有限公司 | A kind of help user reads and understands method and the intelligent sound assistant of electronics article |
| CN108182570A (en) * | 2018-01-24 | 2018-06-19 | 成都安信思远信息技术有限公司 | A kind of case wisdom auditing system |
| CN108269205A (en) * | 2018-01-24 | 2018-07-10 | 成都安信思远信息技术有限公司 | A kind of electronic data identification systems using cloud platform |
| CN108280188A (en) * | 2018-01-24 | 2018-07-13 | 成都安信思远信息技术有限公司 | Intelligence inspection business platform based on big data |
| CN108573754A (en) * | 2017-11-29 | 2018-09-25 | 北京金山云网络技术有限公司 | Information processing method, device, electronic equipment and storage medium |
| WO2018214663A1 (en) * | 2017-05-26 | 2018-11-29 | 北京搜狗科技发展有限公司 | Voice-based data processing method and apparatus, and electronic device |
| CN108932066A (en) * | 2018-06-13 | 2018-12-04 | 北京百度网讯科技有限公司 | Method, apparatus, equipment and the computer storage medium of input method acquisition expression packet |
| CN109360616A (en) * | 2018-10-24 | 2019-02-19 | 深圳市菲森科技有限公司 | A kind of recording method of tooth detection, device, equipment and storage medium |
| CN109378083A (en) * | 2018-08-13 | 2019-02-22 | 四川省肿瘤医院 | Realize that demand knows method for distinguishing and its system for verbal communication impaired patients |
| CN109685590A (en) * | 2017-10-18 | 2019-04-26 | 北京医联蓝卡在线科技有限公司 | A kind of system and method for intelligent medicine purchase |
| CN109741825A (en) * | 2019-01-01 | 2019-05-10 | 上海依邻人合医疗技术有限公司 | A kind of management platform of chronic disease Medical Instruments |
| CN109754805A (en) * | 2019-03-06 | 2019-05-14 | 中铝视拓智能科技有限公司 | A kind of the voice input method and platform of production operation process |
| CN110010132A (en) * | 2019-04-08 | 2019-07-12 | 安徽汇迈信息科技有限公司 | A kind of electronic health record production method of integrated speech |
| CN110019698A (en) * | 2017-09-04 | 2019-07-16 | 珠海健康云科技有限公司 | A kind of intelligent Service method and system of medicine question and answer |
| CN110136703A (en) * | 2019-03-25 | 2019-08-16 | 视联动力信息技术股份有限公司 | A kind of fuzzy answer method and view networked system |
| CN110570868A (en) * | 2019-09-12 | 2019-12-13 | 深圳市华创技术有限公司 | Medical interaction method and system based on voice recognition |
| CN110867228A (en) * | 2019-11-15 | 2020-03-06 | 北京大学人民医院(北京大学第二临床医学院) | Intelligent information grabbing and evaluating method and system for wound severity of wound inpatient |
| CN111161873A (en) * | 2019-12-06 | 2020-05-15 | 广州市医康传媒信息技术有限公司 | Medical question-answering voice information processing system, method, device and storage medium |
| CN112086155A (en) * | 2020-09-11 | 2020-12-15 | 北京欧应信息技术有限公司 | Diagnosis and treatment information structured collection method based on voice input |
| WO2020253391A1 (en) * | 2019-06-21 | 2020-12-24 | 深圳壹账通智能科技有限公司 | Pre-examination information interaction method based on data analysis and related device |
| CN112297016A (en) * | 2019-07-26 | 2021-02-02 | 深圳百诺明医说科技有限公司 | Diagnosis suggestion feedback system based on user voice and medical intelligent voice robot |
| CN112802566A (en) * | 2020-12-31 | 2021-05-14 | 医渡云（北京）技术有限公司 | Method and device for encoding electronic medical record |
| CN112883707A (en) * | 2020-12-31 | 2021-06-01 | 首都医科大学宣武医院 | Emergency aid assisting method, system, equipment and storage medium based on man-machine conversation |
| CN113544787A (en) * | 2019-05-30 | 2021-10-22 | 深圳迈瑞生物医疗电子股份有限公司 | Recording method for medical operation, medical device, and storage medium |
| CN114496150A (en) * | 2022-02-14 | 2022-05-13 | 它思科技(天津)有限公司 | Medical information interaction system and control method thereof |
| CN117995427A (en) * | 2024-04-07 | 2024-05-07 | 北京惠每云科技有限公司 | Medical knowledge base construction method and device, electronic equipment and storage medium |
| CN118121312A (en) * | 2024-05-06 | 2024-06-04 | 北京壹点灵动科技有限公司 | Surgical robot system, computer-readable storage medium, and electronic device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103839211A (en) * | 2014-03-23 | 2014-06-04 | 合肥新涛信息科技有限公司 | Medical history transferring system based on voice recognition |
| CN104485105A (en) * | 2014-12-31 | 2015-04-01 | 中国科学院深圳先进技术研究院 | Electronic medical record generating method and electronic medical record system |
| CN104574246A (en) * | 2014-12-22 | 2015-04-29 | 百度在线网络技术（北京）有限公司 | Intelligent medical triage method, device and equipment |
| CN104866727A (en) * | 2015-06-02 | 2015-08-26 | 陈宽 | Deep learning-based method for analyzing medical data and intelligent analyzer thereof |
| CN105468900A (en) * | 2015-11-20 | 2016-04-06 | 邹远强 | Intelligent medical record input platform based on knowledge base |
-
2016
- 2016-08-12 CN CN201610665602.8A patent/CN106326640A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103839211A (en) * | 2014-03-23 | 2014-06-04 | 合肥新涛信息科技有限公司 | Medical history transferring system based on voice recognition |
| CN104574246A (en) * | 2014-12-22 | 2015-04-29 | 百度在线网络技术（北京）有限公司 | Intelligent medical triage method, device and equipment |
| CN104485105A (en) * | 2014-12-31 | 2015-04-01 | 中国科学院深圳先进技术研究院 | Electronic medical record generating method and electronic medical record system |
| CN104866727A (en) * | 2015-06-02 | 2015-08-26 | 陈宽 | Deep learning-based method for analyzing medical data and intelligent analyzer thereof |
| CN105468900A (en) * | 2015-11-20 | 2016-04-06 | 邹远强 | Intelligent medical record input platform based on knowledge base |
Cited By (35)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107273660A (en) * | 2017-05-17 | 2017-10-20 | 北京好运到信息科技有限公司 | The electronic health record generation method and electronic medical record system of a kind of integrated speech |
| WO2018214663A1 (en) * | 2017-05-26 | 2018-11-29 | 北京搜狗科技发展有限公司 | Voice-based data processing method and apparatus, and electronic device |
| CN107977395A (en) * | 2017-08-01 | 2018-05-01 | 北京物灵智能科技有限公司 | A kind of help user reads and understands method and the intelligent sound assistant of electronics article |
| CN110019698A (en) * | 2017-09-04 | 2019-07-16 | 珠海健康云科技有限公司 | A kind of intelligent Service method and system of medicine question and answer |
| CN107591195A (en) * | 2017-09-07 | 2018-01-16 | 北京鑫丰南格科技股份有限公司 | A kind of medical care householder method and device based on nursing calling system |
| CN109685590A (en) * | 2017-10-18 | 2019-04-26 | 北京医联蓝卡在线科技有限公司 | A kind of system and method for intelligent medicine purchase |
| CN107729510A (en) * | 2017-10-23 | 2018-02-23 | 深圳市前海众兴电子商务有限公司 | Information interacting method, information interactive terminal and storage medium |
| CN107729510B (en) * | 2017-10-23 | 2021-07-06 | 深圳市前海众兴科研有限公司 | Information interaction method, information interaction terminal and storage medium |
| CN107742519A (en) * | 2017-10-31 | 2018-02-27 | 珠海市美瑞华医用科技有限公司 | A kind of voice entry system of intelligent control fluid delivery apparatus |
| CN108573754A (en) * | 2017-11-29 | 2018-09-25 | 北京金山云网络技术有限公司 | Information processing method, device, electronic equipment and storage medium |
| CN108280188A (en) * | 2018-01-24 | 2018-07-13 | 成都安信思远信息技术有限公司 | Intelligence inspection business platform based on big data |
| CN108269205A (en) * | 2018-01-24 | 2018-07-10 | 成都安信思远信息技术有限公司 | A kind of electronic data identification systems using cloud platform |
| CN108182570A (en) * | 2018-01-24 | 2018-06-19 | 成都安信思远信息技术有限公司 | A kind of case wisdom auditing system |
| CN108932066A (en) * | 2018-06-13 | 2018-12-04 | 北京百度网讯科技有限公司 | Method, apparatus, equipment and the computer storage medium of input method acquisition expression packet |
| CN108932066B (en) * | 2018-06-13 | 2023-04-25 | 北京百度网讯科技有限公司 | Method, device, equipment and computer storage medium for acquiring expression package by input method |
| CN109378083A (en) * | 2018-08-13 | 2019-02-22 | 四川省肿瘤医院 | Realize that demand knows method for distinguishing and its system for verbal communication impaired patients |
| CN109360616A (en) * | 2018-10-24 | 2019-02-19 | 深圳市菲森科技有限公司 | A kind of recording method of tooth detection, device, equipment and storage medium |
| CN109741825A (en) * | 2019-01-01 | 2019-05-10 | 上海依邻人合医疗技术有限公司 | A kind of management platform of chronic disease Medical Instruments |
| CN109754805A (en) * | 2019-03-06 | 2019-05-14 | 中铝视拓智能科技有限公司 | A kind of the voice input method and platform of production operation process |
| CN110136703A (en) * | 2019-03-25 | 2019-08-16 | 视联动力信息技术股份有限公司 | A kind of fuzzy answer method and view networked system |
| CN110010132A (en) * | 2019-04-08 | 2019-07-12 | 安徽汇迈信息科技有限公司 | A kind of electronic health record production method of integrated speech |
| CN113544787A (en) * | 2019-05-30 | 2021-10-22 | 深圳迈瑞生物医疗电子股份有限公司 | Recording method for medical operation, medical device, and storage medium |
| WO2020253391A1 (en) * | 2019-06-21 | 2020-12-24 | 深圳壹账通智能科技有限公司 | Pre-examination information interaction method based on data analysis and related device |
| CN112297016A (en) * | 2019-07-26 | 2021-02-02 | 深圳百诺明医说科技有限公司 | Diagnosis suggestion feedback system based on user voice and medical intelligent voice robot |
| CN110570868A (en) * | 2019-09-12 | 2019-12-13 | 深圳市华创技术有限公司 | Medical interaction method and system based on voice recognition |
| CN110867228A (en) * | 2019-11-15 | 2020-03-06 | 北京大学人民医院(北京大学第二临床医学院) | Intelligent information grabbing and evaluating method and system for wound severity of wound inpatient |
| CN110867228B (en) * | 2019-11-15 | 2023-01-17 | 北京大学人民医院(北京大学第二临床医学院) | Intelligent information grabbing and evaluating method and system for wound severity of wound inpatient |
| CN111161873A (en) * | 2019-12-06 | 2020-05-15 | 广州市医康传媒信息技术有限公司 | Medical question-answering voice information processing system, method, device and storage medium |
| CN112086155A (en) * | 2020-09-11 | 2020-12-15 | 北京欧应信息技术有限公司 | Diagnosis and treatment information structured collection method based on voice input |
| CN112883707A (en) * | 2020-12-31 | 2021-06-01 | 首都医科大学宣武医院 | Emergency aid assisting method, system, equipment and storage medium based on man-machine conversation |
| CN112802566A (en) * | 2020-12-31 | 2021-05-14 | 医渡云（北京）技术有限公司 | Method and device for encoding electronic medical record |
| CN114496150A (en) * | 2022-02-14 | 2022-05-13 | 它思科技(天津)有限公司 | Medical information interaction system and control method thereof |
| CN117995427A (en) * | 2024-04-07 | 2024-05-07 | 北京惠每云科技有限公司 | Medical knowledge base construction method and device, electronic equipment and storage medium |
| CN117995427B (en) * | 2024-04-07 | 2024-06-25 | 北京惠每云科技有限公司 | Medical knowledge base construction method and device, electronic equipment and storage medium |
| CN118121312A (en) * | 2024-05-06 | 2024-06-04 | 北京壹点灵动科技有限公司 | Surgical robot system, computer-readable storage medium, and electronic device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106326640A (en) | Medical speech control system and control method thereof | |
| Luo et al. | A critical review of state‐of‐the‐art chatbot designs and applications | |
| US12080429B2 (en) | Methods and apparatus for providing guidance to medical professionals | |
| US20200311343A1 (en) | Methods and apparatus for extracting facts from a medical text | |
| US11646032B2 (en) | Systems and methods for audio processing | |
| CN111401066B (en) | Artificial intelligence-based word classification model training method, word processing method and device | |
| CN110364234B (en) | Intelligent storage, analysis and retrieval system and method for electronic medical records | |
| Goldstein et al. | Three approaches to automatic assignment of ICD-9-CM codes to radiology reports | |
| US20220405484A1 (en) | Methods for Reinforcement Document Transformer for Multimodal Conversations and Devices Thereof | |
| CN117253576B (en) | Outpatient electronic medical record generation method based on Chinese medical large model | |
| RU2488877C2 (en) | Identification of semantic relations in indirect speech | |
| US20140365239A1 (en) | Methods and apparatus for facilitating guideline compliance | |
| US20140052444A1 (en) | System and methods for matching an utterance to a template hierarchy | |
| EP2286374A1 (en) | System and method for providing question and answers with deferred type evaluation | |
| Nye et al. | Trialstreamer: mapping and browsing medical evidence in real-time | |
| US20130060793A1 (en) | Extracting information from medical documents | |
| WO2014197669A1 (en) | Methods and apparatus for providing guidance to medical professionals | |
| Wagner et al. | Applying cooperative machine learning to speed up the annotation of social signals in large multi-modal corpora | |
| CN118296121A (en) | Medical term standardization auxiliary diagnosis method based on large language model | |
| CN112948559B (en) | Audio identification method and system for assisting pharmacy service staff | |
| WO2023098971A1 (en) | Method and apparatus for self-supervised extractive question answering | |
| CN116992839B (en) | Automatic generation method, device and equipment for medical records front page | |
| CN116738998A (en) | Medical dialogue multi-granularity semantic annotation system and method based on Web | |
| CN113314236A (en) | Intelligent question-answering system for hypertension | |
| Zubke et al. | Using openEHR archetypes for automated extraction of numerical information from clinical narratives |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170111 |