The input method of voice, apparatus and systemTechnical field
The present invention relates to voice typing technical field, more particularly, to a kind of input method of voice, apparatus and system.
Background technology
In hospital or other care institutions vibrations, it is that nursing staff is conventional to measure the sign values such as the temperature pulse respiration of patientWork, be also understand the state of an illness a kind of means.Nursing staff can hand-held PDA (Personal Digital Assistant, againReferred to as palm PC) people that prevents or cure a disease measures sign value and then carries out typing at one's side, conventional at the PDA ends of nursing system, typing patientSign data needs to carry out typing by soft keyboard, large quantities of particularly in the case where needing to record multiple patient sign datasBeing manually entered for amount also generates great inconvenience to nursing staff.
The content of the invention
It is an object of the invention to provide a kind of input method of voice, apparatus and system, suffered from the prior art with alleviatingThe relatively complicated technical problem of person's Data Input Process.
One side according to embodiments of the present invention there is provided a kind of input system of voice, including：Data inputting mouldBlock, the typing for receiving user is instructed, and in the case where receiving the typing instruction, it is defeated to the user feedback dataEnter interface, the data input screen is used to provide data-entry-form for the user, and the typing instruction is typing targetThe instruction of the patient data of patient, the typing instruction includes the data type of patient data to be logged；Voice typing module,In the case of being voice typing in the data-entry-form, the speech data that the user sends is obtained；Semantic analysisModule, for the speech data to be identified, and using the information after identification as the patient data to be logged numberAccording to content.
Further, the data inputting module includes：Sign data typing module, for target patient described in typingSign data, wherein, the sign data of the target patient includes at least one of：Body temperature, pulse, heart rate, breathing, bloodPressure, blood oxygen saturation, stool amount, urine volume；Document data inputting module, for the assessment data of target patient described in typing, itsIn, the data of assessing are the Physical evaluation data when target patient is admitted to hospital.
Further, the sign data typing module includes：Sign data input interface, the sign data typing showsShow that interface is used to show every sign data input frame corresponding with sign data each described；Wherein, when the sign dataWhen typing module receives the instruction for the click input frame that the user sends, it is determined that receiving the typing instruction.
Further, the document data inputting module includes：Document data inputting interface, document data inputting circleFace is used to show every assessment data input frame corresponding with data are assessed each described.
Further, the speech data includes the data of following at least one type：Numerical data, lteral data；ItsIn, the numerical data includes integer and decimal, and the integer includes position integer, ten integers and hundred integers；The textDigital data includes Chinese data and/or English data.
Further, the data input screen includes：Numeric area, the numeric area is used to show that at least one is countedWord, wherein, when the patient data that the user inputs is different, at least one described digital not phase that the numeric area is shownTogether；Voice typing region, wherein, when the input system detects the operation that the user clicks on the voice typing regionWhen, it is voice typing to determine the data-entry-form；Operating area, the operating area is used to provide following at least one behaviourMake：Deletion action, shutoff operation, handover operation.
Further, the voice typing module includes：First display interface, first display interface is used to point out instituteUser is stated to start to carry out typing to the speech data；The semantic module includes：Second display interface, described second showsShow that interface is used to point out the user to start that the speech data is identified.
Other side according to embodiments of the present invention, additionally provides a kind of input method of voice, including：Receive userThe typing instruction of transmission, wherein, the typing instruction is the instruction of the sign data of typing target patient, in the typing instructionInclude the data type of patient data to be logged；After the typing instruction is got, the speech data that user sends is obtained；The speech data is identified, and using the information after identification as the patient data to be logged data content.
Further, the speech data is identified including：Extract the characteristic information included in the speech data；The characteristic information and preset data are contrasted；If found in the preset data identical with the characteristic informationData, then regard the identical data as the information after the identification；If do not found in the preset dataWith the characteristic information identical data, then prompt message is generated, to point out the user speech input to fail.
Other side according to embodiments of the present invention, additionally provides a kind of input unit of voice, including：Receive singleMember, the typing instruction for receiving user's transmission, wherein, the typing instruction is the finger of the sign data of typing target patientOrder, the typing instruction includes the data type of patient data to be logged；Acquiring unit, for referring to getting the typingAfter order, the speech data that user sends is obtained；Recognition unit, for the speech data to be identified, and will recognize itInformation afterwards as the patient data to be logged data content.
In embodiments of the present invention, the typing for receiving user by data inputting module is instructed, and is referred to receiving typingIn the case of order, to user feedback data inputting interface, so that user inputs patient data according to data input screen；When the categoryIn the case that system determines that the typing mode of user's typing patient data is voice typing, the voice number that user sends is obtainedAccording to, and the speech data is identified, to recognize the data content for obtaining patient data to be logged.Relative in the prior artTyping is carried out to patient by the way of voice typing, the workload of nursing staff can be reduced, simplifies the record of patient dataEnter process, improve the operating efficiency of nursing staff, and then it is relatively complicated to alleviate patient data Input Process in the prior artTechnical problem.
Brief description of the drawings
, below will be to specific in order to illustrate more clearly of the specific embodiment of the invention or technical scheme of the prior artThe accompanying drawing used required in embodiment or description of the prior art is briefly described, it should be apparent that, in describing belowAccompanying drawing is some embodiments of the present invention, for those of ordinary skill in the art, before creative work is not paidPut, other accompanying drawings can also be obtained according to these accompanying drawings.
Fig. 1 is a kind of schematic diagram of the input system of voice according to embodiments of the present invention；
Fig. 2 is alternatively a kind of schematic diagram of sign data input interface according to embodiments of the present invention；
Fig. 3 is alternatively a kind of schematic diagram at document data inputting interface according to embodiments of the present invention；
Fig. 4 is alternatively a kind of schematic diagram of first display interface according to embodiments of the present invention；
Fig. 5 is alternatively a kind of schematic diagram of second display interface according to embodiments of the present invention；
Fig. 6 is alternatively a kind of schematic diagram of prompting interface according to embodiments of the present invention；
Fig. 7 is a kind of flow chart of the input method of voice according to embodiments of the present invention；
Fig. 8 is a kind of schematic diagram of the input unit of voice according to embodiments of the present invention.
Embodiment
Technical scheme is clearly and completely described below in conjunction with accompanying drawing, it is clear that described implementationExample is a part of embodiment of the invention, rather than whole embodiments.Based on the embodiment in the present invention, ordinary skillThe every other embodiment that personnel are obtained under the premise of creative work is not made, belongs to the scope of protection of the invention.
In the description of the invention, it is necessary to explanation, term " " center ", " on ", " under ", "left", "right", " vertical ",The orientation or position relationship of the instruction such as " level ", " interior ", " outer " be based on orientation shown in the drawings or position relationship, merely toBe easy to the description present invention and simplify description, rather than indicate or imply signified device or element must have specific orientation,With specific azimuth configuration and operation, therefore it is not considered as limiting the invention.In addition, term " first ", " second "," the 3rd " is only used for describing purpose, and it is not intended that indicating or implying relative importance.
In the description of the invention, it is necessary to illustrate, unless otherwise clearly defined and limited, term " installation ", " phaseEven ", " connection " should be interpreted broadly, for example, it may be being fixedly connected or being detachably connected, or be integrally connected；CanTo be mechanical connection or electrical connection；Can be joined directly together, can also be indirectly connected to by intermediary, Ke YishiThe connection of two element internals.For the ordinary skill in the art, with concrete condition above-mentioned term can be understood at thisConcrete meaning in invention.
Embodiment one
There is provided a kind of embodiment of the input system of voice according to embodiments of the present invention.
Fig. 1 is a kind of schematic diagram of the input system of voice according to embodiments of the present invention, as shown in figure 1, the input systemSystem includes：Data inputting module 10, voice typing module 20 and semantic module 30, wherein, above-mentioned input system is arranged onIn PDA.
Data inputting module 10, the typing for receiving user is instructed, and in the case where receiving typing instruction, Xiang YongFamily feedback data inputting interface, data input screen is used to provide the user data-entry-form, and typing instruction is typing targetThe instruction of the patient data of patient, typing instruction includes the data type of patient data to be logged；Wherein, data input screenIt can be understood as the soft keyboard often used on terminal device.
It should be noted that assessment data when sign data and patient of the patient data including patient are admitted to hospital, specificallyData content will be specifically introduced in following embodiments.
Voice typing module 20, in the case of being voice typing in data-entry-form, obtains the language that user sendsSound data；
Wherein, data-entry-form include be manually entered with voice typing, in addition to this it is possible to including image typing withVideo typing.
That is, user can select corresponding typing mode in the soft keyboard, to realize the record to patient dataEnter.
In embodiments of the present invention, the speech data that voice typing module can be recognized includes following at least one typeData：Numerical data, lteral data, wherein, lteral data includes Chinese data and/or English data.
Wherein, numerical data includes integer and decimal, and integer includes position integer, ten integers and hundred integers.For example,Recognizable unit numbers, including, " 0 ", " 1 ", " 2 ", " 3 ", " 4 ", " 5 ", " 6 ", " 7 ", " 8 ", " 9 "；Recognizable ten digits, bagInclude " 10 ", " 20 ", " 30 ", " 40 ", " 50 ", " 60 ", " 70 ", " 80 ", " 90 "；Recognizable hundreds word, including " 100 ",“200”、“300”、“400”、“500”、“600”、“700”、“800”、“900”.In addition to this it is possible to recognize that " " punctuate is accorded withNumber；Hundred, ten, the combination of unit numbers and punctuation mark " " are also can recognize that, for example, " 136.6 ".
Semantic module 30, suffers from for speech data to be identified, and using the information after identification as to be loggedThe data content of person's data.
In embodiments of the present invention, the typing for receiving user by data inputting module is instructed, and is referred to receiving typingIn the case of order, to user feedback data inputting interface, so that user inputs patient data according to data input screen；When the categoryIn the case that system determines that the typing mode of user's typing patient data is voice typing, the voice number that user sends is obtainedAccording to, and the speech data is identified, to recognize the data content for obtaining patient data to be logged.Relative in the prior artTyping is carried out to patient by the way of voice typing, the workload of nursing staff can be reduced, simplifies the record of patient dataEnter process, improve the operating efficiency of nursing staff, and then it is relatively complicated to alleviate patient data Input Process in the prior artTechnical problem.
In an optional embodiment of the embodiment of the present invention, above-mentioned data inputting module 10 includes：Sign data is recordedEnter module and document data inputting module.
Wherein, sign data typing module, for the sign data of typing target patient, wherein, the sign of target patientData include at least one of：Body temperature, pulse, heart rate, breathing, blood pressure, blood oxygen saturation, stool amount, urine volume；
Document data inputting module, for the assessment data of typing target patient, wherein, assess data and enter for target patientPhysical evaluation data during institute.
Specifically, above-mentioned assessment data can for target patient skin it is whether normal, and the target patient tumbleHow high risk be, and whether has the data such as pipeline on the body of the target patient.
After nursing staff enters the input system, the input system will show an initial interface in a pda, and this is firstBeginning interface be used for nursing staff select data inputting module, wherein, in the initial interface, provide the user two selection mouldsBlock, that is, select the first choice module of sign data inputting module and the second selecting module of selection document data inputting module.
When user clicks on first choice module, it is determined that selection sign data inputting module, then sign data will be calledThe sign data input interface of typing module, and the sign data input interface is shown in a pda.Selected when user clicks on secondWhen selecting module, it is determined that selection document data inputting module, then document data inputting circle of document data inputting module will be calledFace, and by the paperwork data inputting interface display in a pda.
Following embodiments of the invention are specifically introduced below in conjunction with Fig. 2 to Fig. 6.
Fig. 2 is alternatively a kind of schematic diagram of sign data input interface according to embodiments of the present invention；Fig. 3 is according to this hairA kind of bright embodiment alternatively schematic diagram at document data inputting interface.
Alternatively, sign data typing display interface is used to show that every sign data is corresponding with each sign data defeatedEnter frame；Wherein, when sign data typing module receives the instruction of click input frame of user's transmission, it is determined that receiving typingInstruction.
As shown in Fig. 2 include the name of target patient in the display interface, the information such as numbering and bed, and includingThe time of measuring of sign data, the i.e., " 2017-01-2014 shown in Fig. 2:00”.Further, in the display interface, alsoIncluding every sign data, an input frame is correspondingly arranged after each sign data.When user clicks on the input frame, exampleSuch as, when clicking on the input frame of " body temperature ", it will show in radio check mark, i.e. Fig. 2 shown in symbol " 1 ", i.e. overstriking shown in symbol " 1 "Input frame.Meanwhile, by the lower section display data inputting interface at the interface, i.e. the interface in Fig. 2 shown in symbol " 2 ".
Alternatively, above-mentioned data input screen includes：Numeric area, voice typing region and operating area.
Specifically, numeric area is used to show at least one numeral, wherein, when the patient data that user inputs is different,At least one numeral that numeric area is shown is differed.
As shown in Fig. 2 when nursing staff will input the body temperature of target patient, in the numeric area of the data input screenIt is middle to show the numeral related to body temperature, for example, the numeral shown in Fig. 2：34,35,36,37,38,39,40,41 and 42, removeOutside integer part, fractional part is additionally provided with, i.e., shown in Fig. 2：" .0 ", " .1 ", " .2 ", " .3 ", " .4 ", " .5 "," .6 ", " .7 ", " .8 ", " .9 ".
When nursing staff will input the blood glucose of target patient, it will be shown and blood in the numeric area of the data input screenSugared related numeral.When nursing staff will input the blood oxygen saturation of target patient, then the number at the numeral input interfaceBlock domain will show the numeral related to blood oxygen saturation.
Voice typing region, wherein, when input system detects that user clicks on the operation in voice typing region, determine dataTyping mode is voice typing；
Wherein, voice typing region is " voice " symbol in data input screen in Fig. 2, when the input system is detectedWhen " voice " is somebody's turn to do in triggering, it is determined that current time data-entry-form is voice typing.
It should be noted that in addition to voice typing, image typing and video typing can also be set.Work as data inputtingWhen mode is image typing, two kinds of typing modes can be shown to user：Locally select and shot by camera.Work as dataWhen typing mode is video typing, two kinds of typing modes can be equally shown to user：Locally select and clapped by video cameraTake the photograph.
Operating area is used to provide following at least one operation：Deletion action, shutoff operation, handover operation；
As in Fig. 2, " emptying ", " closing " and " next " is aforesaid operations region, wherein, " emptying " is deletion in numberAccording to the deletion action of input data in frame, " closing " is closing current data input interface (that is, sign data input interface and textBook data inputting interface) shutoff operation, it is " next " to switch to the handover operation that inputs next sign data.
Alternatively, above-mentioned document data inputting interface is used to show that every assessment data and each assessment data are corresponding defeatedEnter frame.
As shown in figure 3, assessment packet includes skin, input frame corresponding with skin is Option Box, and the Option Box has threeIndividual option, i.e. normal, there is pressure sore risk and exception.Assessing data also includes pipeline, and input frame corresponding with pipeline is also optionFrame, the Option Box has two options, i.e. nothing and have.Assessing data also includes fall risk assessment, wherein, with fall riskCorresponding input frame is assessed with three options, i.e. nothing, low-risk and excessive risk.The assessment data also include training and assessed, withThe training, which assesses corresponding input frame, to be used to input related training assessment data, wherein, user can be by " importing " localSelect file, and the assessment data that this document is assessed as training, in addition, user can also be manually entered training assessmentAssessment data, and input by way of voice typing the assessment data of training assessment.
In another optional embodiment of the embodiment of the present invention, voice typing module includes：First display interface, theOne display interface is used to point out user to start to carry out typing to speech data.
Fig. 4 is alternatively a kind of schematic diagram of first display interface according to embodiments of the present invention.When user is in such as above-mentioned Fig. 2When clicking on " voice " button in shown data input screen (that is, soft keyboard), the input system will be triggered and call the first displayInterface, i.e. display interface as shown in Figure 4.As shown in Figure 4, on the surface, display is " in listening attentively to ", then that is,First display interface is used to point out to start or is carrying out typing to speech data.
In another optional embodiment of the embodiment of the present invention, semantic module includes：Second display interface, theTwo display interfaces are used to point out user to start that speech data is identified.
Fig. 5 is alternatively a kind of schematic diagram of second display interface according to embodiments of the present invention.When user is in such as above-mentioned Fig. 4After shown interface typing speech data, the input system will be triggered and call the second display interface, and ejection has in a pdaThe prompting frame of " in identification " printed words, i.e. display interface as shown in Figure 5.As shown in Figure 5, on the surface, display " identificationIn ", then that is, the second display interface is used to point out user to start that speech data is identified.
If above-mentioned semantic module, which is not analyzed, obtains related data, then will provide " you are not as speaking ... "Prompting, i.e., prompting interface as shown in Figure 6.
To sum up, in embodiments of the present invention there is provided a kind of input system of voice, the input system is known by voiceNot, the technological means such as phonetic synthesis, semantic analysis, it is convenient naturally by PDA ends microphone to allow users to, and uses nature languageSay and data input is carried out to sign data and the document record of patient.
Embodiment two
According to embodiments of the present invention, a kind of embodiment of the input method of voice is additionally provided.
Fig. 7 is a kind of flow chart of the input method of voice according to embodiments of the present invention, as shown in fig. 7, this method bagInclude following steps：
Step S702, receives the typing instruction that user sends, wherein, typing instruction is the sign data of typing target patientInstruction, typing instruction include the data type of patient data to be logged；
Specifically, the data inputting module in above-described embodiment one can be used to receive the instruction that user sends.
Wherein, patient data includes sign data and assesses data, and sign data includes at least one of：Body temperature, arteries and veinsFight, heart rate, breathing, blood pressure, blood oxygen saturation, stool amount, urine volume；Assess Physical evaluation number when data are admitted to hospital for target patientAccording to.
Step S704, after typing instruction is got, obtains the speech data that user sends；
Specifically, the voice typing module in above-described embodiment one can be used to obtain the speech data that user sends.
Step S706, speech data is identified, and using the information after identification as patient data to be logged numberAccording to content.
Specifically, it can use the semantic module in above-described embodiment one that speech data is identified, and will knowNot after information as patient data to be logged data content.
In embodiments of the present invention, the speech data that voice typing module can be recognized includes following at least one typeData：Numerical data, lteral data, wherein, lteral data includes Chinese data and/or English data.
Wherein, numerical data includes integer and decimal, and integer includes position integer, ten integers and hundred integers.For example,Recognizable unit numbers, including, " 0 ", " 1 ", " 2 ", " 3 ", " 4 ", " 5 ", " 6 ", " 7 ", " 8 ", " 9 "；Recognizable ten digits, bagInclude " 10 ", " 20 ", " 30 ", " 40 ", " 50 ", " 60 ", " 70 ", " 80 ", " 90 "；Recognizable hundreds word, including " 100 ",“200”、“300”、“400”、“500”、“600”、“700”、“800”、“900”.In addition to this it is possible to recognize that " " punctuate is accorded withNumber；Hundred, ten, the combination of unit numbers and punctuation mark " " are also can recognize that, for example, " 136.6 ".
It should be noted that the input system of the voice in above-described embodiment one uses the voice in the embodiment of the present invention twoInput method typing is carried out to the patient data of target patient.
In embodiments of the present invention, the typing for receiving user by data inputting module is instructed, and is referred to receiving typingIn the case of order, to user feedback data inputting interface, so that user inputs patient data according to data input screen；When the categoryIn the case that system determines that the typing mode of user's typing patient data is voice typing, the voice number that user sends is obtainedAccording to, and the speech data is identified, to recognize the data content for obtaining patient data to be logged.Relative in the prior artTyping is carried out to patient by the way of voice typing, the workload of nursing staff can be reduced, simplifies the record of patient dataEnter process, improve the operating efficiency of nursing staff, and then it is relatively complicated to alleviate patient data Input Process in the prior artTechnical problem.
Alternatively, speech data is identified and comprised the following steps：
Step S1, extracts the characteristic information included in speech data；
Step S2, characteristic information is contrasted with preset data；
Step S3, if found in preset data with characteristic information identical data, using identical data asInformation after identification；
Step S4, if do not found in preset data with characteristic information identical data, generate prompt message, withPoint out user speech input failure.Wherein it is possible to point out user speech input failure with the interface shown in Fig. 6.
Embodiment three
The embodiment of the present invention additionally provides a kind of input unit of voice, and the input unit of the voice is mainly used in performing sheetThe input method for the voice that inventive embodiments the above is provided, the below input to voice provided in an embodiment of the present invention is filledPut and do specific introduction.
Fig. 8 is a kind of schematic diagram of the input unit of voice according to embodiments of the present invention, as shown in figure 8, the voiceInput unit mainly includes：Receiving unit 81, acquiring unit 82 and recognition unit 83, wherein：
Receiving unit 81, the typing instruction for receiving user's transmission, wherein, typing instruction is the body of typing target patientThe instruction of data is levied, typing instruction includes the data type of patient data to be logged；
Acquiring unit 82, for after typing instruction is got, obtaining the speech data that user sends；
Recognition unit 83, patient's number to be logged is used as speech data to be identified, and using the information after identificationAccording to data content.
In embodiments of the present invention, the typing for receiving user by data inputting module is instructed, and is referred to receiving typingIn the case of order, to user feedback data inputting interface, so that user inputs patient data according to data input screen；When the categoryIn the case that system determines that the typing mode of user's typing patient data is voice typing, the voice number that user sends is obtainedAccording to, and the speech data is identified, to recognize the data content for obtaining patient data to be logged.Relative in the prior artTyping is carried out to patient by the way of voice typing, the workload of nursing staff can be reduced, simplifies the record of patient dataEnter process, improve the operating efficiency of nursing staff, and then it is relatively complicated to alleviate patient data Input Process in the prior artTechnical problem.
Alternatively, recognition unit includes：Extraction module, the characteristic information included for extracting in speech data；Contrast mouldBlock, for characteristic information to be contrasted with preset data；Determining module, for being found in preset data and characteristic informationIn the case of identical data, identical data are regard as the information after identification；Generation module, in preset data notIn the case of finding with characteristic information identical data, prompt message is generated, to point out user speech input failure.
Finally it should be noted that：Various embodiments above is merely illustrative of the technical solution of the present invention, rather than its limitations；To the greatest extentThe present invention is described in detail with reference to foregoing embodiments for pipe, it will be understood by those within the art that：Its according toThe technical scheme described in foregoing embodiments can so be modified, or which part or all technical characteristic are enteredRow equivalent substitution；And these modifications or replacement, the essence of appropriate technical solution is departed from various embodiments of the present invention technologyThe scope of scheme.