CN106649238A - Voice transferring method and device - Google Patents
Voice transferring method and device Download PDFInfo
- Publication number
- CN106649238A CN106649238A CN201611187804.2A CN201611187804A CN106649238A CN 106649238 A CN106649238 A CN 106649238A CN 201611187804 A CN201611187804 A CN 201611187804A CN 106649238 A CN106649238 A CN 106649238A
- Authority
- CN
- China
- Prior art keywords
- entry contents
- default
- entry
- contents
- disaggregated model
- 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
- 238000000034 method Methods 0.000 title claims abstract description 36
- 206010020751 Hypersensitivity Diseases 0.000 claims description 31
- 230000007815 allergy Effects 0.000 claims description 31
- 230000011218 segmentation Effects 0.000 claims description 29
- 238000013518 transcription Methods 0.000 claims description 23
- 230000035897 transcription Effects 0.000 claims description 23
- 208000024891 symptom Diseases 0.000 claims description 20
- 239000000463 material Substances 0.000 claims description 10
- 238000012549 training Methods 0.000 claims description 4
- 230000001755 vocal effect Effects 0.000 abstract 3
- 238000013145 classification model Methods 0.000 abstract 2
- 229930182555 Penicillin Natural products 0.000 description 12
- JGSARLDLIJGVTE-MBNYWOFBSA-N Penicillin G Chemical compound N([C@H]1[C@H]2SC([C@@H](N2C1=O)C(O)=O)(C)C)C(=O)CC1=CC=CC=C1 JGSARLDLIJGVTE-MBNYWOFBSA-N 0.000 description 12
- 206010037660 Pyrexia Diseases 0.000 description 12
- 238000010586 diagram Methods 0.000 description 12
- 229940049954 penicillin Drugs 0.000 description 12
- 208000026935 allergic disease Diseases 0.000 description 9
- 230000008569 process Effects 0.000 description 9
- 238000004590 computer program Methods 0.000 description 7
- 206010002198 Anaphylactic reaction Diseases 0.000 description 6
- 230000036783 anaphylactic response Effects 0.000 description 6
- 208000003455 anaphylaxis Diseases 0.000 description 6
- 230000006870 function Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 201000010099 disease Diseases 0.000 description 3
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 3
- 229940079593 drug Drugs 0.000 description 3
- 239000003814 drug Substances 0.000 description 3
- 235000013399 edible fruits Nutrition 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/166—Editing, e.g. inserting or deleting
- G06F40/174—Form filling; Merging
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
-
- 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
- G16H15/00—ICT specially adapted for medical reports, e.g. generation or transmission thereof
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Medical Informatics (AREA)
- Artificial Intelligence (AREA)
- Public Health (AREA)
- Primary Health Care (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Epidemiology (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a voice transferring method and a voice transferring device, wherein the method comprises the steps of receiving a voice message input by a user, wherein the voice message includes an item content corresponding to a to-be-filled item name; identifying the voice information to obtain a verbal content corresponding to the item content; acquiring a preset item content classification model; determining a target item name corresponding to the verbal content according to the preset item content classification model; and filling the verbal content into a sheet corresponding to the target item name. Through the technical scheme, the sheet can be automatically filled through voice input, the user does not need to input manually, a user operation is reduced, and the usage experience of the user is improved.
Description
Technical field
The present invention relates to technical field of voice recognition, more particularly to a kind of speech transcription method and device.
Background technology
In correlation technique, when user is when the forms such as case are filled in, need to be filled in manually, i.e., user is by being input into text
The mode of word is filled in, and so, user operation is loaded down with trivial details, is experienced not good.
The content of the invention
The embodiment of the present invention provides a kind of speech transcription method and device, to realize that user can pass through phonetic entry
Mode fills in case form etc., the operation of user is reduced, so as to lift the experience of user.
A kind of first aspect according to embodiments of the present invention, there is provided speech transcription method, including：
The voice messaging of receiving user's input, wherein, the voice messaging includes the corresponding entry of clause name to be filled in
Content；
The voice messaging is identified, the corresponding word content of the entry contents is obtained；
Obtain default entry contents disaggregated model；
The corresponding target entry title of the word content is determined according to the default entry contents disaggregated model；
The word content is filled in into the corresponding form of the target entry title.
In this embodiment, user can by the corresponding entry contents of clause name to be filled in phonetic entry form,
Entry contents are simply entered, without the need for being input into the clause name to be filled in, so, is entered in the voice messaging to user input
Row identification is obtained after corresponding word content, automatically determines the word content by default entry contents disaggregated model corresponding
Target entry title, so as to the word content is filled up in the corresponding form of target entry title.As such, it is possible to pass through voice
The mode Auto-writing form of input, it is not necessary to which user is manually entered, and reduces the operation of user, improves the use body of user
Test.
In one embodiment, the preset table include case form, the plurality of default clause name include symptom,
Medical history, allergies, prescription, the default entry contents corpus include medical data language material.
In this embodiment, preset table can be case form, it is of course also possible to be other forms.If preset table
Lattice are case forms, then presetting clause name includes symptom, medical history, allergies, prescription, and corresponding default entry contents
Corpus include medical data language material, such as nomenclature of drug, the symptom of various diseases.So, doctor is when actually used, no
The clause name of case is needed, bar code content is directly said, just the corresponding Word message of voice messaging that doctor is input into can be filled out
In writing the form of corresponding target barcode title.For example, doctor says " 39 degree of fever ", then identify that the voice messaging is corresponding
Word content is " 39 degree of fever ", and by default entry contents disaggregated model " 39 degree of fever " corresponding target entry name is determined
Referred to as " symptom ", then " will have a fever 39 degree " under being filled up to " symptom " corresponding form.
In one embodiment, it is described to obtain default entry contents disaggregated model, including：
Obtain in the multiple default clause name and default entry corresponding with each default clause name in preset table
Hold corpus；
It is trained according to the default entry contents and the corresponding entry contents corpus, obtains described default
Entry contents disaggregated model.
In this embodiment, when default entry contents disaggregated model is obtained, can be according in the form for wanting to fill in
Default entry contents and corresponding entry contents corpus are trained, and for example, it is desirable to fill in medical history sheet, then preset bar
Mesh content is the content being likely to occur in medical history sheet, and corresponding entry contents corpus are medical data.And if it is intended to filling out
Write other forms, then using the form in default entry contents and the corresponding entry contents corpus be trained i.e.
Default entry contents disaggregated model corresponding with the form is obtained.
In one embodiment, it is described that the word content correspondence is determined according to the default entry contents disaggregated model
Target entry title, including：
Participle operation is carried out to the word content, the word segmentation result of at least one entry contents is obtained；
Institute is determined according to the word segmentation result of the default entry contents disaggregated model and at least one entry contents
State the corresponding target entry title of word content.
In this embodiment, it is determined that during the corresponding target entry title of word content, word content can carried out point
Word is operated, and then the clause name belonged to according to each word determines the corresponding target entry title of whole word content, so as to protect
The accuracy of the target entry title that card determines.
In one embodiment, it is described according in the default entry contents disaggregated model and at least one entry
The word segmentation result of appearance determines the corresponding target entry title of the word content, including：
According to the default entry contents disaggregated model, the word segmentation result for determining each entry contents belongs to each entry
The probable value of title；
The word segmentation result for counting at least one entry contents belongs to the overall probability value of each clause name；
The overall probability value highest clause name is defined as into the target entry title.
In this embodiment, according to default entry contents disaggregated model, it may be determined that the participle knot of each entry contents
Fruit belongs to the probable value of each clause name, and then count the word segmentation result of the corresponding all entry contents of whole word content
Overall probability value, according to overall probability value final affiliated target entry title is determined.For example, user says " penicillin anaphylaxis ", then right
After its participle, " penicillin " and " allergy " two word segmentation results are obtained, " mould is determined according to default entry contents disaggregated model
It is 0.5 that element " belongs to the probability of clause name " prescription ", and it is 0 that " allergy " belongs to the probability of clause name " prescription ", while determining
It is 0.5 that " penicillin " belongs to the probability of clause name " allergies ", and it is 1 that " allergy " belongs to the probability of clause name " allergies ",
The corresponding overall probability value of two clause names is then now counted, the overall probability value of entry contents " allergies " is higher, now determines
" penicillin anaphylaxis " is filled up in " allergies " corresponding form.This way it is ensured that the accuracy of the target entry for determining.
A kind of second aspect according to embodiments of the present invention, there is provided speech transcription device, including：
Receiver module, for the voice messaging of receiving user's input, wherein, the voice messaging includes entry name to be filled in
Claim corresponding entry contents；
Identification module, for being identified to the voice messaging, obtains the corresponding word content of the entry contents；
Acquisition module, for obtaining default entry contents disaggregated model；
Determining module, for determining the corresponding target of the word content according to the default entry contents disaggregated model
Clause name；
Module is filled in, for the word content to be filled in into the corresponding form of the target entry title.
In one embodiment, the acquisition module includes：
Acquisition submodule, for obtaining preset table in multiple default clause names and with each default clause name pair
The default entry contents corpus answered；
Training submodule, for being instructed according to the default entry contents and the corresponding entry contents corpus
Practice, obtain the default entry contents disaggregated model.
In one embodiment, the determining module includes：
Participle submodule, for carrying out participle operation to the word content, obtains the participle of at least one entry contents
As a result；
Determination sub-module, for according to the default entry contents disaggregated model and at least one entry contents
Word segmentation result determines the corresponding target entry title of the word content.
In one embodiment, the determination sub-module is used for：
According to the default entry contents disaggregated model, the word segmentation result for determining each entry contents belongs to each entry
The probable value of title；
The word segmentation result for counting at least one entry contents belongs to the overall probability value of each clause name；
The overall probability value highest clause name is defined as into the target entry title.
In one embodiment, the preset table include case form, the plurality of default clause name include symptom,
Medical history, allergies, prescription, the default entry contents corpus include medical data language material.
It should be appreciated that the general description of the above and detailed description hereinafter are only exemplary and explanatory, not
The present invention can be limited.
Other features and advantages of the present invention will be illustrated in the following description, also, the partly change from specification
Obtain it is clear that or being understood by implementing the present invention.The purpose of the present invention and other advantages can be by the explanations write
Specifically noted structure is realizing and obtain in book, claims and accompanying drawing.
Below by drawings and Examples, technical scheme is described in further detail.
Description of the drawings
Accompanying drawing herein is merged in specification and constitutes the part of this specification, shows the enforcement for meeting the present invention
Example, and be used to explain the principle of the present invention together with specification.
Fig. 1 is a kind of flow chart of the speech transcription method according to an exemplary embodiment.
Fig. 2 is the flow chart of step S103 in a kind of speech transcription method according to an exemplary embodiment.
Fig. 3 is the flow chart of step S104 in a kind of speech transcription method according to an exemplary embodiment.
Fig. 4 is the flow chart of step S302 in a kind of speech transcription method according to an exemplary embodiment.
Fig. 5 is a kind of block diagram of the speech transcription device according to an exemplary embodiment.
Fig. 6 is the block diagram of acquisition module in a kind of speech transcription device according to an exemplary embodiment.
Fig. 7 is the block diagram of determining module in a kind of speech transcription device according to an exemplary embodiment.
Specific embodiment
Here exemplary embodiment will be illustrated in detail, its example is illustrated in the accompanying drawings.Explained below is related to
During accompanying drawing, unless otherwise indicated, the same numbers in different accompanying drawings represent same or analogous key element.Following exemplary embodiment
Described in embodiment do not represent and the consistent all embodiments of the present invention.Conversely, they be only with it is such as appended
The example of the consistent apparatus and method of some aspects described in detail in claims, the present invention.
Fig. 1 is a kind of flow chart of the speech transcription method according to an exemplary embodiment.The speech transcription method
In being applied to terminal device, the terminal device can be mobile phone, and computer, digital broadcast terminal, messaging devices are swum
Arbitrary equipment with voice control function such as play console, tablet device, Medical Devices, body-building equipment, personal digital assistant.
As shown in figure 1, the method comprising the steps of S101-S105：
In step S101, the voice messaging of receiving user's input, wherein, voice messaging includes clause name pair to be filled in
The entry contents answered；
Clause name can be the name of tv column in form, and symptom, medical history, allergies, prescription are equal such as in case form
Belong to clause name, and its corresponding concrete fill substance is entry contents.
In step s 102, voice messaging is identified, obtains the corresponding word content of entry contents；
In step s 103, default entry contents disaggregated model is obtained；
Default entry contents disaggregated model is corresponding with preset table, different types of form, due to its clause name
Differ with entry contents, its corresponding entry contents disaggregated model without.
In step S104, the corresponding target entry name of word content is determined according to default entry contents disaggregated model
Claim；
In step S105, word content is filled in into the corresponding form of target entry title.
In this embodiment, user can by the corresponding entry contents of clause name to be filled in phonetic entry form,
Entry contents are simply entered, without the need for being input into the clause name to be filled in, so, is entered in the voice messaging to user input
Row identification is obtained after corresponding word content, automatically determines the word content by default entry contents disaggregated model corresponding
Target entry title, so as to the word content is filled up in the corresponding form of target entry title.As such, it is possible to pass through voice
The mode Auto-writing form of input, it is not necessary to which user is manually entered, and reduces the operation of user, improves the use body of user
Test.
In one embodiment, preset table includes case form, and multiple default clause names include symptom, medical history, mistake
Quick history, prescription, presetting entry contents corpus includes medical data language material.
In this embodiment, preset table can be case form, it is of course also possible to be other forms.If preset table
Lattice are case forms, then presetting clause name includes symptom, medical history, allergies, prescription, and corresponding default entry contents
Corpus include medical data language material, such as nomenclature of drug, the symptom of various diseases.So, doctor is when actually used, no
The clause name of case is needed, bar code content is directly said, just the corresponding Word message of voice messaging that doctor is input into can be filled out
In writing the form of corresponding target barcode title.For example, doctor says " 39 degree of fever ", then identify that the voice messaging is corresponding
Word content is " 39 degree of fever ", and by default entry contents disaggregated model " 39 degree of fever " corresponding target entry name is determined
Referred to as " symptom ", then " will have a fever 39 degree " under being filled up to " symptom " corresponding form.
Fig. 2 is the flow chart of step S103 in a kind of speech transcription method according to an exemplary embodiment.
As shown in Fig. 2 in one embodiment, above-mentioned steps S103 include step S201-S202：
In step s 201, the multiple default clause name and corresponding with each default clause name in preset table is obtained
Default entry contents corpus；
In step S202, it is trained according to default entry contents and corresponding entry contents corpus, obtains pre-
If entry contents disaggregated model.
In this embodiment, when default entry contents disaggregated model is obtained, can be according in the form for wanting to fill in
Default entry contents and corresponding entry contents corpus are trained, and for example, it is desirable to fill in medical history sheet, then preset bar
Mesh content is the content being likely to occur in medical history sheet, and corresponding entry contents corpus are medical data.And if it is intended to filling out
Write other forms, then using the form in default entry contents and corresponding entry contents corpus be trained by
To default entry contents disaggregated model corresponding with the form.
Fig. 3 is the flow chart of step S104 in a kind of speech transcription method according to an exemplary embodiment.
As shown in figure 3, in one embodiment, above-mentioned steps S104 include step S301-S302：
In step S301, participle operation is carried out to word content, obtain the word segmentation result of at least one entry contents；
Wherein it is possible to carry out participle operation to it according to the meaning of a word, part of speech crucial in word content etc..
In step s 302, it is true according to the word segmentation result of default entry contents disaggregated model and at least one entry contents
Determine the corresponding target entry title of word content.
In this embodiment, it is determined that during the corresponding target entry title of word content, word content can carried out point
Word is operated, and then the clause name belonged to according to each word determines the corresponding target entry title of whole word content, so as to protect
The accuracy of the target entry title that card determines.
Fig. 4 is the flow chart of step S302 in a kind of speech transcription method according to an exemplary embodiment.
As shown in figure 4, in one embodiment, above-mentioned steps S302 include step S401-S403：
In step S401, according to default entry contents disaggregated model, the word segmentation result category of each entry contents is determined
In the probable value of each clause name；
In step S402, the word segmentation result for counting at least one entry contents belongs to the total probability of each clause name
Value；
In step S403, overall probability value highest clause name is defined as into target entry title.
In this embodiment, according to default entry contents disaggregated model, it may be determined that the participle knot of each entry contents
Fruit belongs to the probable value of each clause name, and then count the word segmentation result of the corresponding all entry contents of whole word content
Overall probability value, according to overall probability value final affiliated target entry title is determined.For example, user says " penicillin anaphylaxis ", then right
After its participle, " penicillin " and " allergy " two word segmentation results are obtained, " mould is determined according to default entry contents disaggregated model
It is 0.5 that element " belongs to the probability of clause name " prescription ", and it is 0 that " allergy " belongs to the probability of clause name " prescription ", while determining
It is 0.5 that " penicillin " belongs to the probability of clause name " allergies ", and it is 1 that " allergy " belongs to the probability of clause name " allergies ",
The corresponding overall probability value of two clause names is then now counted, the overall probability value of entry contents " allergies " is higher, now determines
" penicillin anaphylaxis " is filled up in " allergies " corresponding form.This way it is ensured that the accuracy of the target entry for determining.
It is following for apparatus of the present invention embodiment, can be used for performing the inventive method embodiment.
Fig. 5 is a kind of block diagram of the speech transcription device according to an exemplary embodiment, and the device can pass through soft
Being implemented in combination with of part, hardware or both becomes some or all of of terminal device.As shown in figure 5, the speech transcription device
Including：
Receiver module 51, for the voice messaging of receiving user's input, wherein, the voice messaging includes entry to be filled in
The corresponding entry contents of title；
Clause name can be the name of tv column in form, and symptom, medical history, allergies, prescription are equal such as in case form
Belong to clause name, and its corresponding concrete fill substance is entry contents.
Identification module 52, for being identified to the voice messaging, obtains the corresponding word content of the entry contents；
Acquisition module 53, for obtaining default entry contents disaggregated model；
Default entry contents disaggregated model is corresponding with preset table, different types of form, due to its clause name
Differ with entry contents, its corresponding entry contents disaggregated model without.
Determining module 54, for determining the corresponding mesh of the word content according to the default entry contents disaggregated model
Mark clause name；
Module 55 is filled in, for the word content to be filled in into the corresponding form of the target entry title.
In this embodiment, user can by the corresponding entry contents of clause name to be filled in phonetic entry form,
Entry contents are simply entered, without the need for being input into the clause name to be filled in, so, is entered in the voice messaging to user input
Row identification is obtained after corresponding word content, automatically determines the word content by default entry contents disaggregated model corresponding
Target entry title, so as to the word content is filled up in the corresponding form of target entry title.As such, it is possible to pass through voice
The mode Auto-writing form of input, it is not necessary to which user is manually entered, and reduces the operation of user, improves the use body of user
Test.
In one embodiment, the preset table include case form, the plurality of default clause name include symptom,
Medical history, allergies, prescription, the default entry contents corpus include medical data language material.
In this embodiment, preset table can be case form, it is of course also possible to be other forms.If preset table
Lattice are case forms, then presetting clause name includes symptom, medical history, allergies, prescription, and corresponding default entry contents
Corpus include medical data language material, such as nomenclature of drug, the symptom of various diseases.So, doctor is when actually used, no
The clause name of case is needed, bar code content is directly said, just the corresponding Word message of voice messaging that doctor is input into can be filled out
In writing the form of corresponding target barcode title.For example, doctor says " 39 degree of fever ", then identify that the voice messaging is corresponding
Word content is " 39 degree of fever ", and by default entry contents disaggregated model " 39 degree of fever " corresponding target entry name is determined
Referred to as " symptom ", then " will have a fever 39 degree " under being filled up to " symptom " corresponding form.
Fig. 6 is the block diagram of acquisition module in a kind of speech transcription device according to an exemplary embodiment.
As shown in fig. 6, in one embodiment, the acquisition module 53 includes：
Acquisition submodule 61, for obtaining preset table in multiple default clause names and with each default clause name
Corresponding default entry contents corpus；
Training submodule 62, for being carried out according to the default entry contents and the corresponding entry contents corpus
Training, obtains the default entry contents disaggregated model.
In this embodiment, when default entry contents disaggregated model is obtained, can be according in the form for wanting to fill in
Default entry contents and corresponding entry contents corpus are trained, and for example, it is desirable to fill in medical history sheet, then preset bar
Mesh content is the content being likely to occur in medical history sheet, and corresponding entry contents corpus are medical data.And if it is intended to filling out
Write other forms, then using the form in default entry contents and the corresponding entry contents corpus be trained i.e.
Default entry contents disaggregated model corresponding with the form is obtained.
Fig. 7 is the block diagram of determining module in a kind of speech transcription device according to an exemplary embodiment.
As shown in fig. 7, in one embodiment, the determining module 54 includes：
Participle submodule 71, for carrying out participle operation to the word content, obtains dividing at least one entry contents
Word result；
Determination sub-module 72, for according to the default entry contents disaggregated model and at least one entry contents
Word segmentation result determine the corresponding target entry title of the word content.
In this embodiment, it is determined that during the corresponding target entry title of word content, word content can carried out point
Word is operated, and then the clause name belonged to according to each word determines the corresponding target entry title of whole word content, so as to protect
The accuracy of the target entry title that card determines.
In one embodiment, the determination sub-module 72 is used for：
According to the default entry contents disaggregated model, the word segmentation result for determining each entry contents belongs to each entry
The probable value of title；
The word segmentation result for counting at least one entry contents belongs to the overall probability value of each clause name；
The overall probability value highest clause name is defined as into the target entry title.
In this embodiment, according to default entry contents disaggregated model, it may be determined that the participle knot of each entry contents
Fruit belongs to the probable value of each clause name, and then count the word segmentation result of the corresponding all entry contents of whole word content
Overall probability value, according to overall probability value final affiliated target entry title is determined.For example, user says " penicillin anaphylaxis ", then right
After its participle, " penicillin " and " allergy " two word segmentation results are obtained, " mould is determined according to default entry contents disaggregated model
It is 0.5 that element " belongs to the probability of clause name " prescription ", and it is 0 that " allergy " belongs to the probability of clause name " prescription ", while determining
It is 0.5 that " penicillin " belongs to the probability of clause name " allergies ", and it is 1 that " allergy " belongs to the probability of clause name " allergies ",
The corresponding overall probability value of two clause names is then now counted, the overall probability value of entry contents " allergies " is higher, now determines
" penicillin anaphylaxis " is filled up in " allergies " corresponding form.This way it is ensured that the accuracy of the target entry for determining.
Those skilled in the art are it should be appreciated that embodiments of the invention can be provided as method, system or computer program
Product.Therefore, the present invention can be using complete hardware embodiment, complete software embodiment or with reference to the reality in terms of software and hardware
Apply the form of example.And, the present invention can be adopted and wherein include the computer of computer usable program code at one or more
The shape of the computer program implemented in usable storage medium (including but not limited to magnetic disc store and optical memory etc.)
Formula.
The present invention is the flow process with reference to method according to embodiments of the present invention, equipment (system) and computer program
Figure and/or block diagram are describing.It should be understood that can be by computer program instructions flowchart and/or each stream in block diagram
The combination of journey and/or square frame and flow chart and/or the flow process in block diagram and/or square frame.These computer programs can be provided
The processor of all-purpose computer, special-purpose computer, Embedded Processor or other programmable data processing devices is instructed to produce
A raw machine so that produced for reality by the instruction of computer or the computing device of other programmable data processing devices
The device of the function of specifying in present one flow process of flow chart or one square frame of multiple flow processs and/or block diagram or multiple square frames.
These computer program instructions may be alternatively stored in can guide computer or other programmable data processing devices with spy
In determining the computer-readable memory that mode works so that the instruction being stored in the computer-readable memory is produced to be included referring to
Make the manufacture of device, the command device realize in one flow process of flow chart or one square frame of multiple flow processs and/or block diagram or
The function of specifying in multiple square frames.
These computer program instructions also can be loaded in computer or other programmable data processing devices so that in meter
Series of operation steps is performed on calculation machine or other programmable devices to produce computer implemented process, so as in computer or
The instruction performed on other programmable devices is provided for realizing in one flow process of flow chart or multiple flow processs and/or block diagram one
The step of function of specifying in individual square frame or multiple square frames.
Obviously, those skilled in the art can carry out the essence of various changes and modification without deviating from the present invention to the present invention
God and scope.So, if these modifications of the present invention and modification belong to the scope of the claims in the present invention and its equivalent technologies
Within, then the present invention is also intended to comprising these changes and modification.
Claims (10)
1. a kind of speech transcription method, it is characterised in that include：
The voice messaging of receiving user's input, wherein, the voice messaging includes the corresponding entry contents of clause name to be filled in；
The voice messaging is identified, the corresponding word content of the entry contents is obtained；
Obtain default entry contents disaggregated model；
The corresponding target entry title of the word content is determined according to the default entry contents disaggregated model；
The word content is filled in into the corresponding form of the target entry title.
2. method according to claim 1, it is characterised in that the default entry contents disaggregated model of the acquisition, including：
Obtain the multiple default clause name and default entry contents instruction corresponding with each default clause name in preset table
Practice language material；
It is trained according to the default entry contents and the corresponding entry contents corpus, obtains the default bar
Mesh classifying content model.
3. method according to claim 2, it is characterised in that described true according to the default entry contents disaggregated model
Determine the corresponding target entry title of the word content, including：
Participle operation is carried out to the word content, the word segmentation result of at least one entry contents is obtained；
The text is determined according to the word segmentation result of the default entry contents disaggregated model and at least one entry contents
The corresponding target entry title of word content.
4. method according to claim 3, it is characterised in that it is described according to the default entry contents disaggregated model and
The word segmentation result of at least one entry contents determines the corresponding target entry title of the word content, including：
According to the default entry contents disaggregated model, the word segmentation result for determining each entry contents belongs to each clause name
Probable value；
The word segmentation result for counting at least one entry contents belongs to the overall probability value of each clause name；
The overall probability value highest clause name is defined as into the target entry title.
5. method according to claim 2, it is characterised in that the preset table includes case form, the plurality of pre-
If clause name includes symptom, medical history, allergies, prescription, the default entry contents corpus include medical data language material.
6. a kind of speech transcription device, it is characterised in that include：
Receiver module, for the voice messaging of receiving user's input, wherein, the voice messaging includes clause name pair to be filled in
The entry contents answered；
Identification module, for being identified to the voice messaging, obtains the corresponding word content of the entry contents；
Acquisition module, for obtaining default entry contents disaggregated model；
Determining module, for determining the corresponding target entry of the word content according to the default entry contents disaggregated model
Title；
Module is filled in, for the word content to be filled in into the corresponding form of the target entry title.
7. device according to claim 6, it is characterised in that the acquisition module includes：
Acquisition submodule, for obtaining preset table in multiple default clause names and corresponding with each default clause name
Default entry contents corpus；
Training submodule, for being trained according to the default entry contents and the corresponding entry contents corpus,
Obtain the default entry contents disaggregated model.
8. device according to claim 7, it is characterised in that the determining module includes：
Participle submodule, for carrying out participle operation to the word content, obtains the word segmentation result of at least one entry contents；
Determination sub-module, for according to the participle of the default entry contents disaggregated model and at least one entry contents
As a result the corresponding target entry title of the word content is determined.
9. device according to claim 8, it is characterised in that the determination sub-module is used for：
According to the default entry contents disaggregated model, the word segmentation result for determining each entry contents belongs to each clause name
Probable value；
The word segmentation result for counting at least one entry contents belongs to the overall probability value of each clause name；
The overall probability value highest clause name is defined as into the target entry title.
10. device according to claim 7, it is characterised in that the preset table includes case form, the plurality of pre-
If clause name includes symptom, medical history, allergies, prescription, the default entry contents corpus include medical data language material.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611187804.2A CN106649238A (en) | 2016-12-20 | 2016-12-20 | Voice transferring method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611187804.2A CN106649238A (en) | 2016-12-20 | 2016-12-20 | Voice transferring method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106649238A true CN106649238A (en) | 2017-05-10 |
Family
ID=58835212
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611187804.2A Pending CN106649238A (en) | 2016-12-20 | 2016-12-20 | Voice transferring method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106649238A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107832283A (en) * | 2017-11-27 | 2018-03-23 | 合光正锦（盘锦）机器人技术有限公司 | A kind of auxiliary based on speech recognition fills out single method and system |
| CN107967111A (en) * | 2017-12-13 | 2018-04-27 | 河北德冠隆电子科技有限公司 | A kind of expressway network toll intelligent virtual keyboard system |
| 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 |
| CN112270922A (en) * | 2020-10-20 | 2021-01-26 | 云南电网有限责任公司迪庆供电局 | Automatic filling method and device for scheduling log |
| CN113254698A (en) * | 2021-06-23 | 2021-08-13 | 江苏盖睿健康科技有限公司 | Form design method and system with auxiliary filling function |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102033964A (en) * | 2011-01-13 | 2011-04-27 | 北京邮电大学 | Text classification method based on block partition and position weight |
| CN103810293A (en) * | 2014-02-28 | 2014-05-21 | 广州云宏信息科技有限公司 | Text classification method and device based on Hadoop |
| 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 |
-
2016
- 2016-12-20 CN CN201611187804.2A patent/CN106649238A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102033964A (en) * | 2011-01-13 | 2011-04-27 | 北京邮电大学 | Text classification method based on block partition and position weight |
| CN103810293A (en) * | 2014-02-28 | 2014-05-21 | 广州云宏信息科技有限公司 | Text classification method and device based on Hadoop |
| 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 |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107832283A (en) * | 2017-11-27 | 2018-03-23 | 合光正锦（盘锦）机器人技术有限公司 | A kind of auxiliary based on speech recognition fills out single method and system |
| 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 |
| CN107967111A (en) * | 2017-12-13 | 2018-04-27 | 河北德冠隆电子科技有限公司 | A kind of expressway network toll intelligent virtual keyboard system |
| CN107967111B (en) * | 2017-12-13 | 2021-06-15 | 河北德冠隆电子科技有限公司 | Intelligent virtual keyboard system for highway networking charging |
| CN112270922A (en) * | 2020-10-20 | 2021-01-26 | 云南电网有限责任公司迪庆供电局 | Automatic filling method and device for scheduling log |
| CN112270922B (en) * | 2020-10-20 | 2022-08-02 | 云南电网有限责任公司迪庆供电局 | Automatic filling method and device for scheduling log |
| CN113254698A (en) * | 2021-06-23 | 2021-08-13 | 江苏盖睿健康科技有限公司 | Form design method and system with auxiliary filling function |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106649238A (en) | Voice transferring method and device | |
| CN106649694A (en) | Method and device for identifying user's intention in voice interaction | |
| CN106601236A (en) | Speech recognition method and apparatus | |
| CN106649696B (en) | Information classification method and device | |
| CN107871506A (en) | The awakening method and device of speech identifying function | |
| CN106653030A (en) | Punctuation mark adding method and device | |
| CN107833168A (en) | A kind of word learning method, device, system and smart pen | |
| CN106328145A (en) | Voice correction method and voice correction device | |
| US10140747B2 (en) | Method and apparatus for controlling playback speed of animation message in mobile terminal | |
| US20110267459A1 (en) | Portable apparatus for processing measurement data and method thereof | |
| CN106782529A (en) | The wake-up selected ci poem selection method and device of speech recognition | |
| CN110490444A (en) | Mark method for allocating tasks, device, system and storage medium | |
| CN106340308A (en) | Speech reply method and device | |
| CN107315688A (en) | A kind of Monkey method of testings and device | |
| CN106339917A (en) | Commodity model training method and device | |
| CN108810625A (en) | A kind of control method for playing back of multi-medium data, device and terminal | |
| CN108170785A (en) | Bootstrap technique, device and the computer readable storage medium of terminal searching operation | |
| US20140163891A1 (en) | Apparatus and method for real-time emotion recognition using heart rate variability | |
| CN107027072A (en) | A kind of video marker method, terminal and computer-readable recording medium | |
| CN106098057A (en) | Play word speed management method and device | |
| US20150243177A1 (en) | Providing an and audio and/or video component for computer-based learning | |
| CN106782516A (en) | Language material sorting technique and device | |
| CN106653003A (en) | Voice recognition method and device | |
| CN109726826B (en) | Training method and device for random forest, storage medium and electronic equipment | |
| CN104540044B (en) | A kind of video segmentation method and device |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170510 |