CN110188171A - A kind of voice search method, device, electronic equipment and storage medium - Google Patents

A kind of voice search method, device, electronic equipment and storage medium Download PDF

Info

Publication number
CN110188171A
CN110188171A CN201910464865.6A CN201910464865A CN110188171A CN 110188171 A CN110188171 A CN 110188171A CN 201910464865 A CN201910464865 A CN 201910464865A CN 110188171 A CN110188171 A CN 110188171A
Authority
CN
China
Prior art keywords
pinyin sequence
matched
information
search order
sequence
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
Application number
CN201910464865.6A
Other languages
Chinese (zh)
Inventor
李建功
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanghai United Imaging Healthcare Co Ltd
Original Assignee
Shanghai United Imaging Healthcare Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shanghai United Imaging Healthcare Co Ltd filed Critical Shanghai United Imaging Healthcare Co Ltd
Priority to CN201910464865.6A priority Critical patent/CN110188171A/en
Publication of CN110188171A publication Critical patent/CN110188171A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33Querying
    • G06F16/3331Query processing
    • G06F16/334Query execution
    • G06F16/3343Query execution using phonetics
    • GPHYSICS
    • G16INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16HHEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H10/00ICT specially adapted for the handling or processing of patient-related medical or healthcare data
    • G16H10/60ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records

Abstract

The embodiment of the invention discloses a kind of voice search method, device, electronic equipment and storage mediums, which comprises receives phonetic search order;Obtain the corresponding pinyin sequence to be matched of the phonetic search order;The pinyin sequence to be matched is matched with each pinyin sequence in default template, is obtained and the matched target pinyin sequence of pinyin sequence to be matched;Based on the corresponding relationship determination and the associated target information of target pinyin sequence between preset each pinyin sequence target information associated with it.Technical solution through the embodiment of the present invention improves the accuracy of phonetic search.

Description

A kind of voice search method, device, electronic equipment and storage medium
Technical field
The present embodiments relate to intelligent medical equipment and technologies more particularly to a kind of voice search method, device, electronics to set Standby and storage medium.
Background technique
With the fast development of artificial intelligence technology, artificial intelligence is gradually applied to every field.
For example, also resting on and passing through when medical staff wants to search the medical record information of some patient in medical field at present It is manually entered the stage that patient's name is searched, it is clear that this lookup mode efficiency is lower, is unfavorable for improving medical staff's Working efficiency.
However current intelligent sound identification technology is substantially voice being ultimately converted to corresponding text.But it is right For the name of patient, do not have stronger context semantic association information, therefore existing speech-recognition services identify Text out text can not usually match used in the real name with patient, cause to carry out patient medical record based on voice The accuracy of information searching is not high.
Summary of the invention
The embodiment of the present invention provides a kind of voice search method, device, electronic equipment and storage medium, is searched with improving voice The accuracy of rope.
In a first aspect, the embodiment of the invention provides a kind of voice search methods, which comprises
Receive phonetic search order;
Obtain the corresponding pinyin sequence to be matched of the phonetic search order;
The pinyin sequence to be matched is matched with each pinyin sequence in default template, obtain with it is described to be matched The matched target pinyin sequence of pinyin sequence;
It is spelled based on the corresponding relationship between preset each pinyin sequence target information associated with it is determining with the target The target information of sound serial correlation.
Second aspect, the embodiment of the invention also provides a kind of voice searching device, which includes:
Receiving module, for receiving phonetic search order;
Module is obtained, for obtaining the corresponding pinyin sequence to be matched of the phonetic search order;
Matching module is obtained for matching the pinyin sequence to be matched with each pinyin sequence in default template To with the matched target pinyin sequence of pinyin sequence to be matched;
Search module, for being determined based on the corresponding relationship between preset each pinyin sequence target information associated with it With the associated target information of target pinyin sequence.
The third aspect, the embodiment of the invention also provides a kind of electronic equipment, which includes:
One or more processing units;
Storage device, for storing one or more programs;
When one or more of programs are executed by one or more of processing units, so that one or more of places Manage voice search method of the device realization as described in any embodiment of the present invention.
Fourth aspect, the embodiment of the invention also provides a kind of computer readable storage mediums, are stored thereon with computer Program realizes the voice search method as described in any embodiment of the present invention when the program is executed by processing unit.
A kind of voice search method provided in an embodiment of the present invention, by obtaining the corresponding spelling to be matched of phonetic search order Sound sequence;The pinyin sequence to be matched is matched with each pinyin sequence in default template, obtain with it is described to be matched The matched target pinyin sequence of pinyin sequence;Based on the corresponding pass between preset each pinyin sequence target information associated with it The determining technological means with the associated target information of target pinyin sequence of system, realizes the mesh for improving phonetic search accuracy 's.
Detailed description of the invention
Fig. 1 is a kind of voice search method flow diagram that the embodiment of the present invention one provides;
Fig. 2 is a kind of voice search method flow diagram provided by Embodiment 2 of the present invention;
Fig. 3 is a kind of structural schematic diagram for voice searching device that the embodiment of the present invention three provides;
Fig. 4 is the hardware structural diagram for a kind of electronic equipment that the embodiment of the present invention four provides.
Specific embodiment
The present invention is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched The specific embodiment stated is used only for explaining the present invention rather than limiting the invention.It also should be noted that in order to just Only the parts related to the present invention are shown in description, attached drawing rather than entire infrastructure.
In following each embodiments, optional feature and example are provided simultaneously in each embodiment, that records in embodiment is each A feature can be combined, and form multiple optinal plans, and the embodiment of each number should not be considered merely as to a technical solution.
Embodiment one
Fig. 1 is a kind of voice search method flow diagram that the embodiment of the present invention one provides.This method is applicable to lead to Cross the case where voice transfers the medical record information or scan image information of patient.This method can be held by voice searching device Row, which can be made of software and/or hardware, and be typically integrated into terminal, and typically, the terminal includes Medical Devices. Shown in Figure 1, the method specifically comprises the following steps:
Step 110 receives phonetic search order.
Wherein, the phonetic search order refers to the language for being used to express certain demand issued by speech form, such as The speech utterance of " I wants to listen to music ".The search need that phonetic search order is conveyed described in different application scenarios is different, example Such as in medical field, the Medical Devices against receivable voice say specific name by speech form, then the demand conveyed It may be intended to transfer the medical record information of associated patient, and in intelligent sound box field, some specific people is said against intelligent sound box Name, the then demand conveyed may be intended to listen to the song of related singer.Voice search method provided in an embodiment of the present invention is intended to It improves when saying some specific patient's name by voice, transfers the medical record information or scan image information of associated patient Transfer accuracy.
Specifically, receiving phonetic search order, comprising:
The phonetic search order including object name is received by speech reception module;
Alternatively, receiving the phonetic search order including object name by associated pronunciation receiver;
Wherein, in object information registration phase, the corresponding pinyin sequence of object name is registered, and by the letter of object It ceases pinyin sequence corresponding with object name and establishes incidence relation;
It is corresponding, it include the information of at least one object with preset each associated target information of pinyin sequence.
The object name can be the proper nouns such as name, name, place name, group's name, mechanism name.The letter of the object Breath refers specifically to the associated information of object, such as the object be a singer, and the information of the object can specifically include this Album published by singer;If the object is the patient of a hospital, the information of the object be can specifically include: patient's The coherence checks information such as medical record information or scan image information;If the object is a place (such as Great Wall, Jiu Zhaigou), institute The information for stating object can specifically include sight spot information etc. around the particular geographic location or the place in the place.
(the i.e. described object by taking application scenarios " transferring the medical record information or scan image information of patient by voice " as an example For the patient of hospital) illustrate the reception mode of above-mentioned phonetic search order:
The phonetic search order including patient's name is received by the speech reception module of Medical Devices.It is understood that It is that the reception mode of this kind of phonetic search order needs to improve the hardware configuration of Medical Devices, to add corresponding language Sound receiving module and speech recognition module, this kind of mode undoubtedly increase the cost of Medical Devices.In view of having thrown in the market Enter the Medical Devices for not having speech reception module and speech recognition module used, in order to make this kind of do not have phonetic incepting function The Medical Devices of energy also can receive phonetic search order, can be accomplished in that
By receiving the phonetic search order including patient's name with the associated pronunciation receiver of Medical Devices.Wherein, With the associated pronunciation receiver of Medical Devices be independently of Medical Devices, with Medical Devices keep communication connection, dedicated for It receives voice and carries out the device of speech recognition.The reception mode of such phonetic search order need to only pre-establish Medical Devices with Communication connection between pronunciation receiver, when pronunciation receiver receives the phonetic search order for Medical Devices, Speech recognition is carried out to the phonetic search order, and recognition result is sent to the Medical Devices, makes Medical Devices into one Step carries out relevant search according to speech recognition result, so that realizing connect the Medical Devices for not having phonetic incepting function can also Receive phonetic search order.Current Medical Devices all have communication function, therefore the reception of this kind of phonetic search order substantially Mode solves the recipient of the first above-mentioned phonetic search order without improving to the existing hardware configuration of Medical Devices The problem of increasing Medical Devices cost present in formula.
It should be noted that Medical Devices described in the present embodiment can specifically refer to medical imaging equipment or for medical care The computer equipment that personnel carry out patient information registration and medical record information is checked.The medical imaging equipment is, for example, CT (Computed Tomography, computed tomography), MRI (Magnetic Resonance Imaging, magnetic resonance at Picture), DR (Digital Radiography, digitalization radiation shooting) or CR (Computed Radiography, computer Radiophotography) etc..
Further, more Medical Devices can share the pronunciation receiver, specifically, establishing every respectively Communication connection between Medical Devices and the pronunciation receiver, and every Medical Devices are identified, when needs are directed to When Present Medical inputs phonetic search order, need to input the voice letter comprising Present Medical identification information simultaneously Breath, so that speech recognition result is sent to corresponding Medical Devices according to the identification information by pronunciation receiver, makes medical treatment Equipment further carries out relevant search according to speech recognition result.Such as the phonetic search order be specially " three consulting room of internal medicine, Zhang San ", when the pronunciation receiver receives and identifies " three consulting room of internal medicine ", by the identification of current phonetic search order As a result " zhangsan " corresponding be sent to is used to register and check with " three consulting room of internal medicine " associated Medical Devices, such as doctor The computer of patient medical record information.In this way, can then greatly reduce the cost of entire intelligent medical equipment.
Further, in order to realize based on doctor oral account patient's name's information correctly transfer the patient medical record information or Person's scan image information, in patient information registration phase, system automatically carries out the corresponding pinyin sequence of the patient's name of registration Registration, and establish between the scan image information pinyin sequence corresponding with patient's name of medical record information and/or patient of patient Incidence relation.The purpose registered to the corresponding pinyin sequence of patient's name is in order to improve search precision, due to name Corresponding text information does not have context semantic relevance, thus identify that text often with true text used by name Word does not correspond to, such as speech dictation " Zhang Qian ", and the text information that system identification goes out may be " open and owe ", it is clear that true with patient Name does not correspond to, if may be based on " open and owe " search medical record information associated with it or scan image information, search result 0, search precision is lower.And scanned for by being registered to the corresponding pinyin sequence of patient's name, and based on pinyin sequence, Search precision can then be greatlyd improve.For example, speech dictation " Zhang Qian ", system identification go out corresponding pinyin sequence " zhangqian ", and it is based on " zhangqian " search and " zhangqian " associated medical record information or scan image information, Obvious this kind of way of search has high search precision in search patient medical record information or scan image information scene.
Illustratively, in patient information registration phase, when doctor is manually entered the correct name Chinese character information of patient, or By way of scanning medical insurance card when name Chinese character information input system that patient is correct, system is automatically to the patient of typing The corresponding pinyin sequence of name Chinese character information is registered, specifically, can be by searching for pair between preset Chinese character and phonetic Answer relation table to obtain the corresponding phonetic of certain specific Chinese character, or realized by specific model algorithm Chinese character is converted to it is corresponding Phonetic.If some Chinese character is polyphone, system all lists the corresponding all syllables of polyphone, and is registered, or Whole syllables can also be shown so that manual intervention operation is added, select relevant operation personnel (such as medical staff) therefrom Correct syllable, and registered.
Step 120 obtains the corresponding pinyin sequence to be matched of the phonetic search order.
Illustratively, the corresponding pinyin sequence to be matched of the phonetic search order is obtained, comprising:
Chinese character speech recognition is carried out to the phonetic search order, obtains corresponding Chinese character information;
The corresponding pinyin sequence of the Chinese character information is obtained based on the corresponding relationship between Chinese character information and phonetic;
Alternatively, carrying out syllable identification to the phonetic search order, the pinyin sequence to be matched is obtained.
Wherein, carrying out Chinese character speech recognition to the phonetic search order can be realized based on trained language model, should Language model is obtained by the text sequence training in general training text library.Further, in order to improve the accurate of speech recognition Degree, the professional corpus of text that the language model can also be in advance based on specific application area are trained to obtain, such as in name Field collects the Chinese character often used by name and forms professional corpus of text, and using the profession corpus of text to language model It is trained.Syllable is carried out to the phonetic search order and identifies that used language model can be by general training text library The corresponding syllable sequence training of text obtains.
Step 130 matches the pinyin sequence to be matched with each pinyin sequence in default template, obtains and institute State the matched target pinyin sequence of pinyin sequence to be matched.
Illustratively, the pinyin sequence to be matched is matched with each pinyin sequence in default template, obtain with The matched target pinyin sequence of pinyin sequence to be matched, comprising:
Calculate separately the editing distance between each pinyin sequence in the pinyin sequence to be matched and default template;
The smallest pinyin sequence of editing distance is determined as and the matched target pinyin sequence of pinyin sequence to be matched.
EDA (Edit-distance based algorithm, editing distance) algorithm is the matching for measuring two character strings The algorithm of degree refers between two character strings, and minimum editor's number needed for another is changed into as one.The edit operation of agreement Including a character is substituted for another character, be inserted into a character and deletes a character.For example, the spelling to be matched Sound sequence is " zhang san ", and the pinyin sequence preset in template is " zhang shan ", then to make phonetic sequence to be matched Column " zhang san " are converted to the pinyin sequence " zhang shan " in default template, then need to be inserted into character " h ", therefore to Matching the editing distance between the pinyin sequence " zhang shan " in pinyin sequence " zhang san " and default template is 1.
Step 140, based on the corresponding relationship between preset each pinyin sequence target information associated with it is determining and institute State the associated target information of target pinyin sequence.
In medical field, medical staff usually requires to be manually entered patient's name to be looked into the medical record information for transferring patient It sees, in this scenario, preset each pinyin sequence refers specifically to the corresponding pinyin sequence of patient's name seen a doctor, and preset Each associated target information of pinyin sequence includes at least one of the medical record information of patient and the scan image information of patient.Often The patient of a medical treatment can pass through patient information registration phase, at this stage when doctor is manually entered the correct name Chinese character of patient Information, or by way of scanning medical insurance card when name Chinese character information input system that patient is correct, system is automatically right The corresponding pinyin sequence of patient's name's Chinese character information of typing is registered, and by before the patient medical record information and inspection Result information (such as scan image) pinyin sequence corresponding with patient's name's Chinese character information carries out binding association, and in patient In subsequent various inspections, by medical information that inspection result information and doctor formulate (such as doctor open drug information) Pinyin sequence corresponding with the Chinese name information of patient is associated storage.Therefore, when doctor needs to check the disease of certain patient When going through information and coherence check information, the name of dictate patient is only needed, when system receives the voice comprising patient's name, from It is dynamic to carry out speech recognition, the corresponding target pinyin sequence of patient's name is obtained, and be associated with based on preset each pinyin sequence Target information between corresponding relationship it is determining with the associated target information of target pinyin sequence, be based on phonetic to realize The searching and matching method of sequence improves the search accuracy of target information.
Further, based on the corresponding relationship between preset each pinyin sequence target information associated with it is determining and institute After stating the associated target information of target pinyin sequence, further includes:
If including at least two groups with the associated target information of target pinyin sequence, by the mark of each group target information Information is shown, for operator's selection;
Wherein, the identification information of each group target information includes the clinical information of patient, for example, the name of patient, gender and Relevant inspection item information etc..Since the search strategy of this case is to be scanned for based on pinyin sequence, for word difference And sound with name, search result may be to be multiple, such as the corresponding pinyin sequence of phonetic search order received is " zhang qian " may correspond to patient " Zhang Qian ", it is also possible to corresponding patient " Zhang Qian ", at this time with target pinyin sequence " zhang qian " associated target information includes two groups, respectively medical record information or the scan image letter of patient " Zhang Qian " Breath and the medical record information or scan image information of patient " Zhang Qian ";At this point, then by the clinical information of patient " Zhang Qian " and The clinical information of patient " Zhang Qian " is shown, and operator is made further to determine that oneself is wanted according to more detailed patient information The target information of lookup.
A kind of voice search method provided in this embodiment, when receiving the phonetic search order including patient's name, Speech recognition is carried out to the phonetic search order, obtains the pinyin sequence of the patient's name, and be based on preset phonetic sequence Corresponding relationship between column and target information obtains the associated target information of pinyin sequence with the patient's name recognized, Wherein, the target information includes at least one of the medical record information of patient and the scan image information of patient, is realized logical The purpose that voice transfers patient medical record information or scan image information is crossed, without realizing again by being manually entered patient's name Patient medical record information or scan image information are transferred, the working efficiency of medical staff is improved;And by being based on phonetic Sequence carries out matching search, improves search accuracy.
Embodiment two
Fig. 2 is a kind of voice search method flow diagram provided by Embodiment 2 of the present invention.The present embodiment is with above-mentioned reality It applies in example and is optimized based on each optinal plan, to sending phonetic search order specifically before carrying out speech recognition User identity is confirmed, is unconsciously issued phonetic search order to Medical Devices to avoid non-pre-set user, is caused accidentally to grasp Make, while can also be achieved the purpose for guaranteeing that the medical record information of patient or scan image information are not leaked.Referring specifically to Fig. 2 institute Show, described method includes following steps:
Step 210 receives phonetic search order.
Step 220 extracts vocal print feature based on the phonetic search order.
Step 230 matches the vocal print feature with each vocal print template in default vocal print feature library.
If existing in step 240, the default vocal print feature library and reaching threshold value with the matching similarity of the vocal print feature Vocal print template, then obtain the corresponding pinyin sequence to be matched of the phonetic search order.
Specifically, being previously stored with the vocal print of all personnel for having phonetic search permission in the default vocal print feature library Feature, if based on the vocal print feature that current speech search command extracts, with pre-stored each vocal print in default vocal print feature library Template mismatches (i.e. matching similarity is lower than threshold value), it is determined that the user for issuing current speech search command is not have language The user of sound search permission.If the vocal print feature for existing in default vocal print feature library and being extracted based on current speech search command Reach the vocal print template of threshold value with similarity, it is determined that the user for issuing current speech search command is to have phonetic search permission User, then continue to execute subsequent step.The user for having phonetic search permission is usually medical staff.Through the above steps 230 and step 240 execution can avoid Non-medical-staff (such as patient) unconscious sending, can be used as phonetic search order Voice, the case where leading to system misoperation.It is understood that through the above steps 230 and the execution of step 240 can also be achieved The purpose for avoiding patient information from being stolen by unauthorized person.
Optionally, it is also based on Hospital Standard HIPAA (Health Insurance Portability and Accountability, health insurance carries and accountability act) Lai Jinhang user authority management, or perhaps user identity is true Recognize.Specifically, logging in relevant operation personnel by human-computer interaction interface before the phonetic search function using Medical Devices Specific account, just can be used the phonetic search function of Medical Devices after successfully logging in, software relevant to account is based on doctor Institute standard HIPAA is developed.
Step 250 matches the pinyin sequence to be matched with each pinyin sequence in default template, obtains and institute State the matched target pinyin sequence of pinyin sequence to be matched.
Step 260, based on the corresponding relationship between preset each pinyin sequence target information associated with it is determining and institute State the associated target information of target pinyin sequence.
Further, the phonetic search function of Medical Devices can also be triggered by the way that specific wake-up word is arranged, to prevent The case where maloperation.Specifically, obtaining the corresponding semantic letter of the phonetic search order when receiving phonetic search order Breath, and judge whether institute's semantic information includes default wake-up word, if so, continuing to execute the acquisition phonetic search life The step of enabling corresponding pinyin sequence.The default wake-up word is for example specifically: " small U ", then the phonetic search order needs to wrap Include wake-up word, such as the phonetic search order specifically: " small U searches the medical record information of Zhang San ".System identification to wake up word When " small U ", the step of obtaining the phonetic search order corresponding pinyin sequence is continued to execute, otherwise without any response behaviour Make.
Again alternatively, unlatching/pass of Medical Devices phonetic search function can also be realized by way of physical button is arranged It closes, the case where to prevent maloperation.Specifically, when receiving phonetic search order, judge predetermined physical key whether by It opens, if so, continuing to execute described the step of obtaining the phonetic search order corresponding pinyin sequence.
The technical solution of the present embodiment before carrying out speech recognition, is increased to hair on the basis of the above embodiments The step of user identity of phonetic search order is confirmed out realizes and avoids non-pre-set user from unconsciously issuing voice searching Rope order, the case where leading to system misoperation, while also achieving the purpose for guaranteeing that patient information is not leaked.
Embodiment three
Fig. 3 is a kind of voice searching device structural schematic diagram that the embodiment of the present invention three provides.Refering to what is shown in Fig. 3, described Voice searching device includes: receiving module 310, obtains module 320, matching module 330 and search module 340;
Wherein, receiving module 310, for receiving phonetic search order;Module 320 is obtained, is searched for obtaining the voice The corresponding pinyin sequence to be matched of rope order;Matching module 330, for will be in the pinyin sequence to be matched and default template Each pinyin sequence is matched, and is obtained and the matched target pinyin sequence of pinyin sequence to be matched;Search module 340 is used It is determined and the target pinyin sequence in based on the corresponding relationship between preset each pinyin sequence target information associated with it Associated target information.
Further, receiving module 310 is specifically used for:
The phonetic search order including patient's name is received by the speech reception module of Medical Devices;
Alternatively, by receiving the phonetic search order including patient's name with the associated pronunciation receiver of Medical Devices;
Wherein, in patient information registration phase, the corresponding pinyin sequence of patient's name is registered, and by the disease of patient The scan image information pinyin sequence corresponding with patient's name for going through information and/or patient establishes incidence relation;
It is corresponding, it include the medical record information of patient and the scanning of patient with preset each associated target information of pinyin sequence At least one of image information.
Further, described device further include: display module, if for believing with the associated target of the target pinyin sequence Breath includes at least two groups, then is shown the identification information of each group target information, for operator's selection;Wherein, each group The identification information of target information includes the clinical information of patient.
Further, obtaining module 320 includes:
Recognition unit obtains corresponding Chinese character information for carrying out Chinese character speech recognition to the phonetic search order;Or Person carries out syllable identification to the phonetic search order, obtains the pinyin sequence to be matched;
Determination unit, for obtaining the corresponding spelling of the Chinese character information based on the corresponding relationship between Chinese character information and phonetic Sound sequence;
Further, matching module 330 includes:
Computing unit, for calculating separately between each pinyin sequence in the pinyin sequence to be matched and default template Editing distance;
Determination unit, it is matched with the pinyin sequence to be matched for being determined as the smallest pinyin sequence of editing distance Target pinyin sequence.
Further, described device further include:
Authentication module, for being searched based on the voice before obtaining the corresponding pinyin sequence of the phonetic search order Vocal print feature is extracted in rope order;The vocal print feature is matched with each vocal print template in default vocal print feature library;If institute The vocal print template for existing in default vocal print feature library and reaching threshold value with the matching similarity of the vocal print feature is stated, then is continued to execute Described the step of obtaining the phonetic search order corresponding pinyin sequence.
Further, the authentication module can also be used in:
The corresponding semantic information of the phonetic search order is obtained, and judges whether institute's semantic information includes default wake-up Word, if so, continuing to execute described the step of obtaining the phonetic search order corresponding pinyin sequence;Alternatively, judgement is default Whether physical button has been turned on, if so, continuing to execute the corresponding pinyin sequence of the acquisition phonetic search order Step.
A kind of voice searching device provided in this embodiment, when receiving the phonetic search order including patient's name, Speech recognition is carried out to the phonetic search order, obtains the pinyin sequence of the patient's name, and be based on preset phonetic sequence Corresponding relationship between column and target information obtains the associated target information of pinyin sequence with the patient's name recognized, Wherein, the target information includes at least one of the medical record information of patient and the scan image information of patient, is realized logical The purpose that voice transfers patient medical record information or scan image information is crossed, without realizing again by being manually entered patient's name Patient medical record information or scan image information are transferred, the working efficiency of medical staff is improved;And by being based on phonetic Sequence carries out matching search, improves search accuracy.
Method provided by any embodiment of the invention can be performed in above-mentioned apparatus, has the corresponding functional module of execution method And beneficial effect.
Example IV
Fig. 4 is the structural schematic diagram for a kind of electronic equipment that the embodiment of the present invention four provides.Fig. 4, which is shown, to be suitable for being used in fact The block diagram of the example devices 12 of existing embodiment of the present invention.The equipment 12 that Fig. 4 is shown is only an example, should not be to this hair The function and use scope of bright embodiment bring any restrictions.
As shown in figure 4, equipment 12 is showed in the form of universal computing device.The component of equipment 12 may include but unlimited In one or more processor or processing unit 16, system storage 28, connecting different system components, (including system is deposited Reservoir 28 and processing unit 16) bus 18.
Bus 18 indicates one of a few class bus structures or a variety of, including memory bus or Memory Controller, Peripheral bus, graphics acceleration port, processor or the local bus using any bus structures in a variety of bus structures.It lifts For example, these architectures include but is not limited to industry standard architecture (ISA) bus, microchannel architecture (MAC) Bus, enhanced isa bus, Video Electronics Standards Association (VESA) local bus and peripheral component interconnection (PCI) bus.
Equipment 12 typically comprises a variety of computer system readable media.These media can be it is any can be by equipment 12 The usable medium of access, including volatile and non-volatile media, moveable and immovable medium.
System storage 28 may include the computer system readable media of form of volatile memory, such as arbitrary access Memory (RAM) 30 and/or cache memory 32.Equipment 12 may further include it is other it is removable/nonremovable, Volatile/non-volatile computer system storage medium.Only as an example, storage system 34 can be used for reading and writing irremovable , non-volatile magnetic media (Fig. 4 do not show, commonly referred to as " hard disk drive ").Although not shown in fig 4, use can be provided In the disc driver read and write to removable non-volatile magnetic disk (such as " floppy disk "), and to removable anonvolatile optical disk The CD drive of (such as CD-ROM, DVD-ROM or other optical mediums) read-write.In these cases, each driver can To be connected by one or more data media interfaces with bus 18.Memory 28 may include at least one program product, There is the program product one group (such as receiving module 310 in voice searching device, to obtain module 320,330 and of matching module Search module 340) program module, these program modules are configured to perform the function of various embodiments of the present invention.
It (such as receiving module 310 in voice searching device, obtains module 320, matching module 330 with one group and searches Rope module 340) program module 42 program/utility 40, can store in such as memory 28, such program module 42 include but is not limited to operating system, one or more application program, other program modules and program data, these examples Each of or certain combination in may include the realization of network environment.Program module 42 usually executes described in the invention Function and/or method in embodiment.
Equipment 12 can also be communicated with one or more external equipments 14 (such as keyboard, sensing equipment, display 24 etc.), Can also be enabled a user to one or more equipment interacted with the equipment 12 communication, and/or with enable the equipment 12 with One or more of the other any equipment (such as network interface card, modem etc.) communication for calculating equipment and being communicated.It is this logical Letter can be carried out by input/output (I/O) interface 22.Also, equipment 12 can also by network adapter 20 and one or The multiple networks of person (such as local area network (LAN), wide area network (WAN) and/or public network, such as internet) communication.As shown, Network adapter 20 is communicated by bus 18 with other modules of equipment 12.It should be understood that although not shown in the drawings, can combine Equipment 12 use other hardware and/or software module, including but not limited to: microcode, device driver, redundant processing unit, External disk drive array, RAID system, tape drive and data backup storage system etc..
Processing unit 16 by the program that is stored in system storage 28 of operation, thereby executing various function application and Data processing, such as realize voice search method provided by the embodiment of the present invention.
Embodiment five
The embodiment of the present invention five additionally provides a kind of computer readable storage medium, is stored thereon with computer program, should Voice search method described in any embodiment of the present invention is realized when program is executed by processor.The voice search method, packet It includes:
Receive phonetic search order;
Obtain the corresponding pinyin sequence to be matched of the phonetic search order;
The pinyin sequence to be matched is matched with each pinyin sequence in default template, obtain with it is described to be matched The matched target pinyin sequence of pinyin sequence;
It is spelled based on the corresponding relationship between preset each pinyin sequence target information associated with it is determining with the target The target information of sound serial correlation.
The computer storage medium of the embodiment of the present invention, can be using any of one or more computer-readable media Combination.Computer-readable medium can be computer-readable signal media or computer readable storage medium.It is computer-readable Storage medium for example may be-but not limited to-the system of electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor, device or Device, or any above combination.The more specific example (non exhaustive list) of computer readable storage medium includes: tool There are electrical connection, the portable computer diskette, hard disk, random access memory (RAM), read-only memory of one or more conducting wires (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD- ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.In this document, computer-readable storage Medium can be any tangible medium for including or store program, which can be commanded execution system, device or device Using or it is in connection.
Computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal, Wherein carry computer-readable program code.The data-signal of this propagation can take various forms, including but unlimited In electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media can also be that computer can Any computer-readable medium other than storage medium is read, which can send, propagates or transmit and be used for By the use of instruction execution system, device or device or program in connection.
The program code for including on computer-readable medium can transmit with any suitable medium, including --- but it is unlimited In wireless, electric wire, optical cable, RF etc. or above-mentioned any appropriate combination.
The computer for executing operation of the present invention can be write with one or more programming languages or combinations thereof Program code, described program design language include object oriented program language-such as Java, Smalltalk, C++, It further include conventional procedural programming language-such as C language or similar programming language.Program code can be complete It executes, partly executed on the user computer on the user computer entirely, being executed as an independent software package, part Part executes on the remote computer or executes on a remote computer or server completely on the user computer.It is relating to And in the situation of remote computer, remote computer can pass through the network of any kind --- including local area network (LAN) or extensively Domain net (WAN)-be connected to subscriber computer, or, it may be connected to outer computer (such as provided using Internet service Quotient is connected by internet).
Note that the above is only a better embodiment of the present invention and the applied technical principle.It will be appreciated by those skilled in the art that The invention is not limited to the specific embodiments described herein, be able to carry out for a person skilled in the art it is various it is apparent variation, It readjusts and substitutes without departing from protection scope of the present invention.Therefore, although being carried out by above embodiments to the present invention It is described in further detail, but the present invention is not limited to the above embodiments only, without departing from the inventive concept, also It may include more other equivalent embodiments, and the scope of the invention is determined by the scope of the appended claims.

Claims (10)

1. a kind of voice search method characterized by comprising
Receive phonetic search order;
Obtain the corresponding pinyin sequence to be matched of the phonetic search order;
The pinyin sequence to be matched is matched with each pinyin sequence in default template, is obtained and the phonetic to be matched The target pinyin sequence of sequences match;
Based on the corresponding relationship determination and the target phonetic sequence between preset each pinyin sequence target information associated with it Arrange associated target information.
2. the method according to claim 1, wherein the reception phonetic search order, comprising:
The phonetic search order including object name is received by speech reception module;
Alternatively, receiving the phonetic search order including object name by associated pronunciation receiver;
Wherein, in object information registration phase, the corresponding pinyin sequence of object name is registered, and by the information of object with The corresponding pinyin sequence of object name establishes incidence relation;
It is corresponding, it include the information of at least one object with preset each associated target information of pinyin sequence.
3. the method according to claim 1, wherein based on preset each pinyin sequence target letter associated with it After corresponding relationship determination and the associated target information of target pinyin sequence between breath, further includes:
If including at least two groups with the associated target information of target pinyin sequence, by the identification information of each group target information It is shown, for operator's selection;
Wherein, the identification information of each group target information includes the clinical information of patient.
4. the method according to claim 1, wherein obtaining the corresponding phonetic to be matched of the phonetic search order Sequence, comprising:
Chinese character speech recognition is carried out to the phonetic search order, obtains corresponding Chinese character information;
The corresponding pinyin sequence of the Chinese character information is obtained based on the corresponding relationship between Chinese character information and phonetic;
Alternatively, carrying out syllable identification to the phonetic search order, the pinyin sequence to be matched is obtained.
5. method according to claim 1-4, which is characterized in that by the pinyin sequence to be matched and default mould Each pinyin sequence in plate is matched, and is obtained and the matched target pinyin sequence of pinyin sequence to be matched, comprising:
Calculate separately the editing distance between each pinyin sequence in the pinyin sequence to be matched and default template;
The smallest pinyin sequence of editing distance is determined as and the matched target pinyin sequence of pinyin sequence to be matched.
6. method according to claim 1-4, which is characterized in that obtain the corresponding spelling of the phonetic search order Before sound sequence, further includes:
Vocal print feature is extracted based on the phonetic search order;
The vocal print feature is matched with each vocal print template in default vocal print feature library;
If there is the vocal print template for reaching threshold value with the matching similarity of the vocal print feature in the default vocal print feature library, Continue to execute described the step of obtaining the phonetic search order corresponding pinyin sequence.
7. method according to claim 1-4, which is characterized in that obtain the corresponding spelling of the phonetic search order Before sound sequence, further includes:
The corresponding semantic information of the phonetic search order is obtained, and judges whether institute's semantic information includes default wake-up word, If so, continuing to execute described the step of obtaining the phonetic search order corresponding pinyin sequence;
Alternatively, judging whether predetermined physical key has been turned on, if so, continuing to execute the acquisition phonetic search order The step of corresponding pinyin sequence.
8. a kind of voice searching device characterized by comprising
Receiving module, for receiving phonetic search order;
Module is obtained, for obtaining the corresponding pinyin sequence to be matched of the phonetic search order;
Matching module, for the pinyin sequence to be matched to be matched with each pinyin sequence in default template, obtain with The matched target pinyin sequence of pinyin sequence to be matched;
Search module, for based on the corresponding relationship between preset each pinyin sequence target information associated with it is determining and institute State the associated target information of target pinyin sequence.
9. a kind of electronic equipment, which is characterized in that the equipment includes:
One or more processing units;
Storage device, for storing one or more programs;
When one or more of programs are executed by one or more of processing units, so that one or more of processing fill Set the voice search method realized as described in any in claim 1-7.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that program dress processed Set the voice search method realized as described in any in claim 1-7 when execution.
CN201910464865.6A 2019-05-30 2019-05-30 A kind of voice search method, device, electronic equipment and storage medium Pending CN110188171A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910464865.6A CN110188171A (en) 2019-05-30 2019-05-30 A kind of voice search method, device, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910464865.6A CN110188171A (en) 2019-05-30 2019-05-30 A kind of voice search method, device, electronic equipment and storage medium

Publications (1)

Publication Number Publication Date
CN110188171A true CN110188171A (en) 2019-08-30

Family

ID=67719051

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910464865.6A Pending CN110188171A (en) 2019-05-30 2019-05-30 A kind of voice search method, device, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN110188171A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111667810A (en) * 2020-06-08 2020-09-15 北京有竹居网络技术有限公司 Method and device for acquiring polyphone corpus, readable medium and electronic equipment

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111667810A (en) * 2020-06-08 2020-09-15 北京有竹居网络技术有限公司 Method and device for acquiring polyphone corpus, readable medium and electronic equipment
CN111667810B (en) * 2020-06-08 2021-10-15 北京有竹居网络技术有限公司 Method and device for acquiring polyphone corpus, readable medium and electronic equipment

Similar Documents

Publication Publication Date Title
CN104380375B (en) Device for extracting information from a dialog
US10990266B2 (en) Method and system for generating transcripts of patient-healthcare provider conversations
US10943025B2 (en) Transcription data security
US9317501B2 (en) Data security system for natural language translation
US11227688B2 (en) Interface for patient-provider conversation and auto-generation of note or summary
US8983836B2 (en) Captioning using socially derived acoustic profiles
US8595620B2 (en) Document creation and management systems and methods
JP4089148B2 (en) Interpreting service method and interpreting service device
CN104714942B (en) Method and system for the content availability for natural language processing task
CN109192194A (en) Voice data mask method, device, computer equipment and storage medium
US20190172456A1 (en) Method for sharing photograph based on voice recognition, apparatus and system for the same
CN110675951A (en) Intelligent disease diagnosis method and device, computer equipment and readable medium
CN110188171A (en) A kind of voice search method, device, electronic equipment and storage medium
CN109726372A (en) Generation method, device and the computer-readable medium of work order based on message registration
WO2020093720A1 (en) Speech recognition-based information query method and device
CN110223761A (en) One kind sketching the contours data lead-in method, device, electronic equipment and storage medium
US11037575B2 (en) Server device and server client system
US7962324B2 (en) Method for globalizing support operations
JP2007293600A (en) Medical-use server device, input device, proofreading device, browsing device, voice input report system, and program
KR20190066537A (en) Photograph sharing method, apparatus and system based on voice recognition
US11017073B2 (en) Information processing apparatus, information processing system, and method of processing information
CN110033767A (en) A kind of control method of medical imaging equipment, device, equipment and storage medium
US10521555B2 (en) Video-analysis tagging of healthcare services video record
Pak-Hin Kong Speech-language services for Chinese-speaking people with aphasia (C-PWA): Considerations for assessment and intervention
CN107992457A (en) A kind of information conversion method, device, terminal device and storage medium

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
CB02 Change of applicant information
CB02 Change of applicant information

Address after: 201807 Shanghai City, north of the city of Jiading District Road No. 2258

Applicant after: Shanghai Lianying Medical Technology Co., Ltd

Address before: 201807 Shanghai City, north of the city of Jiading District Road No. 2258

Applicant before: SHANGHAI UNITED IMAGING HEALTHCARE Co.,Ltd.