CN109360571A - Processing method and processing device, storage medium, the computer equipment of credit information - Google Patents
Processing method and processing device, storage medium, the computer equipment of credit information Download PDFInfo
- Publication number
- CN109360571A CN109360571A CN201811287298.3A CN201811287298A CN109360571A CN 109360571 A CN109360571 A CN 109360571A CN 201811287298 A CN201811287298 A CN 201811287298A CN 109360571 A CN109360571 A CN 109360571A
- Authority
- CN
- China
- Prior art keywords
- credit information
- filled
- information
- speech recognition
- target item
- 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
- 238000003672 processing method Methods 0.000 title claims abstract description 19
- 238000012545 processing Methods 0.000 title claims abstract description 16
- 238000000034 method Methods 0.000 claims abstract description 25
- 230000008859 change Effects 0.000 claims description 24
- 238000001914 filtration Methods 0.000 claims description 9
- 238000013507 mapping Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 7
- 238000012790 confirmation Methods 0.000 claims description 5
- 230000010365 information processing Effects 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 abstract description 7
- 238000004883 computer application Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 230000011218 segmentation Effects 0.000 description 3
- 239000013598 vector Substances 0.000 description 3
- 241001672694 Citrus reticulata Species 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000010200 validation analysis Methods 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000004611 spectroscopical analysis Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- 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
- 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
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
Landscapes
- Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
This application discloses a kind of processing method and processing device of credit information, storage medium, computer equipments, are related to computer application technology, can be effectively reduced the difficulty that credit information is filled in, and improve credit information input efficiency.Wherein method includes: to obtain the voice messaging that currently the in blank credit information page and user input the credit information page；Speech recognition is carried out to voice messaging；According to speech recognition result, target item to be entered in the credit information page, and credit information to be filled in corresponding with target item are determined；Inquiry text box to be filled in corresponding with target item in the credit information page；By credit information to be filled in filling inquire wait fill in text box.The application is suitable for the processing of credit information.
Description
Technical field
This application involves computer application technologies, particularly with regard to the processing method and dress of a kind of credit information
It sets, storage medium, computer equipment.
Background technique
Scene of providing a loan is more universal, all trades and professions all possible applications to loan matters, but the needs when facing loan and handling
Client inputs many loan letters such as name, gender, identification card number, cell-phone number, home Tel, place province, place city, better address
Breath.
Currently, loan scene needs the credit information that inputs more, in the way of traditional be manually entered, efficiency is more low
Under, also it be easy to cause user experience bad while wasting time, and be easy that mistake occurs during filling in.And it considers
There is part population not write or application software typewriting, and then will cause the difficult problem of credit information input.
Summary of the invention
In view of this, this application provides a kind of processing method and processing device of credit information, storage medium, computers to set
Standby, main purpose is to solve to need to fill in all multi informations manually when loan transaction is handled, and wastes time very much and information
Fill in the high problem of difficulty.
According to the one aspect of the application, a kind of processing method of credit information is provided, this method comprises:
The current in blank credit information page and user is obtained to believe the voice that the credit information page inputs
Breath；
Speech recognition is carried out to the voice messaging；
According to institute's speech recognition result, determine target item to be entered in the credit information page, and with the mesh
Mark the corresponding credit information to be filled in of item；
Inquiry text box to be filled in corresponding with the target item in the credit information page；
The credit information to be filled in is inserted described in inquiring wait fill in text box.
According to further aspect of the application, a kind of processing unit of credit information is provided, which includes:
Acquiring unit, for obtaining the current in blank credit information page and user for the credit information page
The voice messaging of face input；
Recognition unit, for carrying out speech recognition to the voice messaging；
Determination unit, for determining target to be entered in the credit information page according to institute's speech recognition result
, and credit information to be filled in corresponding with the target item；
Query unit, for inquiring the text box to be filled in corresponding with the target item in the credit information page；
Fill in unit, for described in credit information the to be filled in filling is inquired wait fill in text box.
According to the another aspect of the application, a kind of storage medium is provided, is stored thereon with computer program, the journey
The processing method of above-mentioned credit information is realized when sequence is executed by processor.
According to another aspect of the application, a kind of computer equipment, including storage medium, processor and storage are provided
On a storage medium and the computer program that can run on a processor, the processor realize above-mentioned loan when executing described program
The processing method of money information.
By above-mentioned technical proposal, the processing method and processing device of credit information provided by the present application, storage medium, computer
Equipment, compared with the mode for being manually entered credit information at present, the application can obtain identification by the way of voice input automatically
The voice messaging that user inputs the credit information page, and can be automatically matched to according to the voice messaging of input accordingly to
It fills in item and needs fill substance accordingly, inquire the corresponding text box to be filled in of item to be filled in, to will recognize
Credit information content is filled out in corresponding text box.Pass through this credit information side of filling in based on speech recognition technology automation
Formula, greatly reduce credit information fills in difficulty, saves the input time of credit information, improves the input of credit information
Efficiency, solve special population to some extent applies problem on obstacle, can build good user experience.
Above description is only the general introduction of technical scheme, in order to better understand the technological means of the application,
And it can be implemented in accordance with the contents of the specification, and in order to allow above and other objects, features and advantages of the application can
It is clearer and more comprehensible, below the special specific embodiment for lifting the application.
Detailed description of the invention
The drawings described herein are used to provide a further understanding of the present application, constitutes part of this application, this Shen
Illustrative embodiments and their description please do not constitute the improper restriction to locally applying for explaining the application.In the accompanying drawings:
Fig. 1 shows a kind of flow diagram of the processing method of credit information provided by the embodiments of the present application；
Fig. 2 shows the flow diagrams of the processing method of another credit information provided by the embodiments of the present application；
Fig. 3 shows a kind of structural schematic diagram of the processing unit of credit information provided by the embodiments of the present application；
Fig. 4 shows the structural schematic diagram of the processing unit of another credit information provided by the embodiments of the present application.
Specific embodiment
The application is described in detail below with reference to attached drawing and in conjunction with the embodiments.It should be noted that not conflicting
In the case of, the features in the embodiments and the embodiments of the present application can be combined with each other.
Low efficiency is manually entered for current credit information, fills in time-consuming big problem, present embodiments provides a kind of loan
The processing method of money information, as shown in Figure 1, this method comprises:
101, the current in blank credit information page and user is obtained to believe the voice that the credit information page inputs
Breath.
In the present embodiment, can be in advance in credit information input page involved by scene of providing a loan, configuration voice is defeated
Enter button.For example, when the voice input button is by striking, by starting user interface (User Interface, UI) page control
Part starts microphone to iOS system application, and then user can pin the voice input button, can carry out voice messaging input.
Wherein, voice messaging may include input creditor's name, gender, identification card number, cell-phone number, home Tel, place province, place city,
Better address etc. needs to fill in the content on the credit information page.
For the executing subject of the present embodiment can for based on speech recognition technology carry out credit information processing device or
Equipment is configurable on client-side, for identifying to the voice messaging that user inputs, and realizes the loan that will be recognized automatically
Money information solicitation is in credit information input page.It is soft specifically third party's speech recognition can be accessed in the device or equipment in advance
Part development kit (Software Development Kit, SDK).Here speech recognition SDK can be used, be divided into it is online or
Offline versions.Speech recognition technology, also referred to as automatic speech recognition (Automatic Speech Recognition, ASR),
It is computer-readable input that its target, which is vocabulary Content Transformation in the voice by the mankind, for example, key, binary coding or
Person's character string.It is different from Speaker Identification and speaker verification, the latter attempt identification or confirmation issue voice speaker and
Non- vocabulary content included in it.
102, speech recognition is carried out to voice messaging.
For the present embodiment, speech recognition, Jin Ershi are carried out to voice messaging using each word in default dictionary
Not Chu user's typing voice content.Further, in order to enrich application of the default dictionary of speech recognition under scene of providing a loan,
It can be pre-configured with the keyword that loan scene can be used, borrowed so as to subsequent according to these keywords according to speech recognition SDK
Speech recognition can also be accurately carried out under money scene.Specifically can arrange loan scene with language identification SDK provider in advance can use
The keyword arrived, convenient for carrying out the identification of voice after voice input.For example, being pre-configured with, " vehicle loan ", " housing loan ", " business is borrowed
Money ", " Accumulation Fund Loan ", " creditor's name ", " guarantor's name ", " refunding the date ", " interest ", " loan duration ", " loan
The keywords such as amount ".The predicate mark words that these indicate next to illustrate particular content there are also "Yes", " for " etc..
During being specifically based on speech recognition technology to voice messaging progress speech recognition, from speech recognition modeling
Angle says that the speech recognition system theory of mainstream is built upon on statistical-simulation spectrometry basis, and the voice inputted first is special
Levy sequence vector X=x1, x2 ... ..., xT；Again by these speech feature vectors and pre-set crucial term vector progress
Match, and then be converted to word sequence W=w1, w2 ... ..., wN, to obtain speech recognition result according to these word sequences.
103, according to speech recognition result, target item to be entered in the credit information page is determined, and corresponding with target item
Credit information to be filled in.
Wherein, target item can for creditor's name, the age, loan duration, amount of the loan etc. these in credit information page
Table entries to be entered in face.And credit information to be filled in can specifically correspond to the content for needing to fill in these table entries.
For example, the sound result recognized is " creditor's name is Zhang San ", the default pass of target item to be entered is utilized
The predetermined keyword "Yes" of keyword " creditor's name " and predicate mark words, it may be determined that be entered in the credit information page
Target item are as follows: creditor's name；And by the content after "Yes": Zhang San, as credit information to be filled in corresponding with target item.
104, inquiry text box to be filled in corresponding with target item in the credit information page.
In the present embodiment, can count in advance in the credit information page each item to be filled up a form and corresponding text box it
Between mapping relations, it is then subsequent that text box to be filled in corresponding with target item directly can be directly inquired using the mapping relations.
For example, the example based on step 103, the target item recognized are as follows: creditor's name.Using the mapping relations counted before, look into
Text box position to be filled in corresponding with the target item in current page is ask, that is, which text box be specifically directed towards.
105, by credit information to be filled in filling inquire wait fill in text box.
For example, the example based on step 104, determines credit information to be filled in corresponding with target item are as follows: Zhang San is then looking into
It askes with after text box to be filled in position corresponding to the target item, " Zhang San " is filled up to this wait fill in text box.
The processing method of middle credit information through this embodiment, can be with automatic identification voice input content, and according to voice
Input results are determined with text box corresponding to target item, credit information to be filled in and the target item inputted, by speech recognition
In fund information to be filled in filling text box out, the typing of credit information voice is realized.By this method, loan is shortened
The fill in the time of information, improve credit information fills in efficiency.
Further, as the refinement and extension of above-described embodiment specific embodiment, in order to completely illustrate the present embodiment
In specific implementation process, provide the processing method of another credit information, as shown in Fig. 2, this method comprises:
201, the current in blank credit information page and user is obtained to believe the voice that the credit information page inputs
Breath, and speech recognition is carried out to voice messaging.
For the present embodiment, carried out to help user to understand to be replaced being manually entered mode with voice input mode rapidly
Credit information is filled in, can user use for the first time voice messaging input before, at the blank position in the credit information page,
Show can using voice input button input voice come instruction information, and then user is helped to relieve using manual defeated
Other than the mode for entering credit information, it can also be inputted using voice, to improve the usage experience of user.
During speech recognition, since the voice messaging of user's input may have the feature of country dialect, it is
The voice messaging that in such a scenario can also accurately identify user's input, can configure the default pass of some provincialisms in advance
Keyword, and the mapping relations between these keywords and mandarin standard keyword are established, recognizing these provincialisms
Predetermined keyword, can use the mapping relations, be automatically converted into the speech recognition result for meeting mandarin standard.
202, speech recognition result is matched with predetermined keyword.
Wherein, in the credit information page it is each can input item have corresponding predetermined keyword.Predetermined keyword can
With according to can the corresponding gauge outfit title of input item preset.In the present embodiment, can be in speech recognition result by judging
The no mode comprising predetermined keyword determines speech recognition result and the matched matching process of predetermined keyword.
203, matched predetermined keyword if it exists, then obtain it is corresponding with matched predetermined keyword can input item conduct
Target item to be entered in the credit information page.
For example, in the credit information page, creditor's name can the corresponding predetermined keyword A of input item be " creditor's surname
Name ", if speech recognition result is " creditor's name is Zhang San ", which includes predetermined keyword A, then can
Determine that the speech recognition result is matched with predetermined keyword A, so can by the corresponding creditor's name of predetermined keyword A can be defeated
Enter item, is determined as target item to be entered in the credit information page.
204, speech recognition result is matched with each default Sentence Template respectively.
Wherein, these default Sentence Templates can previously according to it is each can input item create, each can input item can be respectively right
Answer a set of default Sentence Template, this set of default Sentence Template corresponding with target item available in the present embodiment, to voice
Recognition result is matched.Default Sentence Template can be for according to a variety of the setting to sentence pattern progress in advance of different statement syntax rules
It is fixed, for being compared and analyzed with speech recognition result.It particularly may be divided into standard Sentence Template and non-standard Sentence Template, standard
Sentence Template can correspond to the narrative order of standard syntax, and non-standard Sentence Template can correspond to the narrative order of nonstandard syntax.
For example, the default Sentence Template of standard for creditor's name target item can are as follows: " creditor's name is * * " " borrows
Money people's name is * * ", " creditor name * * " " creditor's name is * * " " * * is creditor's name " " * * is creditor's name "
Deng.If it is determined that in speech recognition result exist " creditor's name " keyword, then by speech recognition result respectively with it is above-mentioned these
Standard is preset Sentence Template and is compared and analyzed.
If according to can the corresponding predetermined keyword of input item determine in speech recognition result there is no target item, that is, be not present
Matched predetermined keyword then obtains the approximate keyword of corresponding with predetermined keyword semanteme；And by speech recognition result and language
Adopted approximation keyword is matched；Matched semantic approximate keyword if it exists, then obtain keyword approximate with matched semanteme
It is corresponding can input item as target item to be entered in the credit information page.Wherein, semantic approximate keyword and default key
Word justice is identical.
For example, " creditor ", " creditor's name ", " people of loan " etc. " are borrowed as the predetermined keyword of standard in advance
The approximate keyword of the semanteme of money people name ", and establish mapping relations.Work as speech recognition result are as follows: " creditor * * ", " creditor
Whens name * * ", " people of loan is * * ", " * * of creditor's surname " etc., wherein there is no the pre- of " creditor's name " this standard
If keyword, then semantic approximate keyword can be matched in speech recognition result, if being matched to " creditor " or " creditor
Whens name " or " people of loan " etc..Using the mapping relations between semantic approximate keyword and the predetermined keyword of standard, look into
The predetermined keyword for asking the corresponding standard of semantic approximate keyword is " creditor's name ", and then from speech recognition result,
Identify that target item to be entered in the credit information page is creditor's name.
205, from preset memory locations inquire it is corresponding with target item and with the matched default sentence pattern of speech recognition result
The corresponding default semantic resolution rules of template.
Wherein, preset memory locations can be preset according to actual needs, such as specific database, mapping table, cloud
Server etc..Default semanteme resolution rules may include be directed to the speech recognition result for meeting specific default Sentence Template into
The row resolution rules that further semanteme parses.Each Sentence Template has corresponding default semantic resolution rules, and default
Semantic resolution rules are related with target item to be entered, if target item to be entered is different, corresponding semantic parsing
Rule would also vary from.
206, using the default semantic resolution rules inquired, semantic parsing is carried out to speech recognition result, is obtained and mesh
Mark the corresponding credit information to be filled in of item.
In concrete application scene, in order to accelerate the voice recognition processing of credit information, the default language inquired is being utilized
Adopted resolution rules can default sentence matched to the speech recognition result during carrying out semantic parsing to speech recognition result
Pattern plate is judged differentiate whether the default Sentence Template is standard Sentence Template, and then realize targetedly semantic solution
Analysis, improves the voice recognition processing efficiency of credit information.Correspondingly, if being with the matched default Sentence Template of speech recognition result
Standard Sentence Template, then step 206 can specifically include: in speech recognition result, obtain except the corresponding default key of target item
The first other information except word；The filtration treatment of garbage is carried out to the first other information；By what is obtained after filtration treatment
First other information is determined as credit information to be filled in corresponding with target item.
Wherein, standard Sentence Template can are as follows: the normal word order containing the mark words such as "Yes", " for ", " being " states template.Example
Such as " creditor's name is * * ", " creditor's name is * * ", " creditor name * * " " * * is creditor's name ".If voice is known
An other result are as follows: " creditor's name is Zhang San ", then the other information obtained in addition to predetermined keyword " creditor's name " " is
Three ", and then processing is filtered to the first other information, the predicates mark words such as "Yes", " for ", " being " are filtered out, are remained after filtering out
Under content " Zhang San ", be determined as credit information to be filled in corresponding with the target item " creditor's name ".
By the above-mentioned process for carrying out semantic parsing to speech recognition result, for the matched voice of standard Sentence Template
Recognition result can fast and accurately identify credit information to be filled in corresponding with target item, and then credit information can be improved
The accuracy and efficiency filled in.
The above-mentioned voice messaging input for opposite specification, and if user does not know cannonical format, and lead to the language of input
Message breath sometimes and non-standard, in order to solve this problem, in the present embodiment as a preferred method, correspondingly, if with
The matched default Sentence Template of speech recognition result is non-standard Sentence Template, then step 206 can specifically include: obtaining voice
The second other information in recognition result in addition to target item corresponds to predetermined keyword；Referring to matched pre- with speech recognition result
If the mark words in Sentence Template, each characteristic information of flagged word segmentation in the second other information is extracted；According to inquiring
Default semantic resolution rules in characteristic information permutation and combination sequence, each characteristic information is subjected to permutation and combination, obtain with
The corresponding credit information to be filled in of target item.
Wherein, non-standard Sentence Template is that the improper word order of flagged word segmentation states template, such as creditor surname * *
Name * *；Before creditor's identification card number 9 be XXXXXXXXX, latter 9 be YYYYYYYYY；Guarantor name XX relatives word (such as brother
Brother, younger brother, father, mother, younger sister, elder sister, Husband's older sister, three one's mother's sisters etc.) YY " etc..
For example, inquiring the content if speech recognition content is " creditor's surname Zhang Mingsi " and meeting " creditor's surname XX
(wherein, " creditor " corresponds to the predetermined keyword of target item to the default Sentence Template of YY ", and " surname ", " name " are default sentence pattern mould
The mark words of plate, " opening " XX and " four " YY are two characteristic informations divided by the mark words), and Xiang Weiyu name phase to be entered
The item of pass, then the characteristic information permutation and combination sequence for including in the corresponding default semantic resolution rules of the default Sentence Template are
" XX+YY ", and then " Zhang Si " is obtained as the corresponding credit information to be filled in of target item " creditor ".
For another example inquiring content symbol if speech recognition content is " the younger brother Zhang Si that guarantor's name is Zhang San "
Close default Sentence Template (wherein, the default pass of " guarantor's name " corresponding target item of " guarantor's name is XX relatives word YY "
Keyword, " for " corresponding predicate mark words, and " younger brother " relatives word be the mark words of default Sentence Template and " are opened " Zhang San's " XX
Four " YY are two characteristic informations divided by the mark words), and the relevant item of Xiang Weiyu name to be entered.The then default sentence pattern
The characteristic information permutation and combination sequence for including in the corresponding default semantic resolution rules of template is " YY ", and then obtains " Zhang Si " work
For the corresponding credit information to be filled in of target item " guarantor's name ".
Through the above-mentioned process for carrying out semantic parsing to speech recognition result, the case where user does not know cannonical format
Under, the credit information that user utilizes voice mode input can be also accurately identified, and then accurately carry out the Auto-writing of credit information,
Improve credit information fills in efficiency.
207, inquiry text box to be filled in corresponding with target item in the credit information page.
For example, the sound result recognized is " creditor's home address is Haidian District, Beijing City ", target item is inquired are as follows:
Creditor's home address.Then inquire text box location information to be filled in corresponding to creditor's home address in current page.
If 208, having inserted information in text box wait fill in, the prompt information whether changed and inserted information is exported.
Wherein, prompt information can be text prompt information, picture prompting information, speech prompt information, visual prompts letter
Breath, light prompt information, vibration prompt information etc..
In specific application scenarios, in order to avoid the repetition typing to information, therefore there are when information in text box, then
When content input is carried out with regard to same text frame, it may appear that change prompt information.Correspondingly, in order to avoid the waste of resource, when to
It fills in text box when being sky, prompt information will not be exported, directly insert voice recognition information in corresponding text box.
For example, when inputting creditor's name, when the corresponding text box of creditor's name exists in the credit information page
When having inserted information, then the prompt information whether changed and inserted information is exported.If creditor's name pair in the credit information page
When other information being not present in the text box answered, then it is corresponding the name information recognized directly to be filled out into credit information to be filled in
In text box.
If 209, receiving the phonetic order of confirmation change, credit information to be filled in is inserted to the text to be filled in inquired
In this frame and information has been inserted in replacement.
For example, the example based on step 208, when there are it for the corresponding text box of creditor's name in the credit information page
He is judged whether to need to change information after whether output is changed and inserted the prompt information of information by user, is such as needed more
Change, then the phonetic order of voice input validation change, and then the credit information to be filled in recognized can be filled into corresponding text
In frame.
It further, can also include: output after step 208 in order to meet the change demand for having filled in credit information
Whether prompt information wait fill in be filled in credit information in text box is changed；The voice for receiving user's input changes information,
And speech recognition is carried out to voice change information, it obtains treating the change information for filling in the credit information to be filled in text box；
The credit information to be filled in filled in text box is treated according to change information to be modified.
For example, can receive the speech modification of user when speech recognition result has mistake, such as recognizing creditor's name
The corresponding credit information to be filled in of text box to be filled in be Zhang San, when voice input change when, then export and whether change wait fill out
The prompt information for writing the credit information to be filled in text box then changes voice if user speech input validation changes information
Information carries out speech recognition, after obtaining change information, then corresponding to creditor's name wait fill in loan letter according to change information
Breath is modified.
For the processing method of above-mentioned credit information, information can be inputted according to voice and read predetermined keyword, using pre-
If keyword identifies target item, and speech recognition result is matched with each default Sentence Template, according to default sentence pattern
The corresponding default semantic resolution rules of template, and then obtain credit information to be filled in corresponding with target item.Inquiry is believed in loan
Cease text box to be filled in corresponding with target item in the page, when text box is empty, directly will credit information filling be filled in
Fill in text box；When having inserted information in text box wait fill in, then the prompt information whether changed and inserted information is exported, is being received
To after the phonetic order of confirmation change, then by by credit information to be filled in filling inquire wait fill in text box and replace
Insert information.And when speech recognition result has mistake, it also can receive the speech modification of user.It is defeated to simplify credit information
The difficulty entered, and speech modification can be carried out, while reducing error rate, also improve working efficiency.
Further, the specific implementation as method shown in Fig. 1 and Fig. 2, the embodiment of the present application provide a kind of loan letter
The processing unit of breath, as shown in figure 3, the device includes: acquiring unit 31, recognition unit 32, determination unit 33, query unit
34, unit 35 is filled in.
Acquiring unit 31 can be used for obtaining the current in blank credit information page and user for credit information page
The voice messaging of face input；
Recognition unit 32 can be used for carrying out speech recognition to voice messaging；
Determination unit 33 can be used for determining target item to be entered in the credit information page according to speech recognition result, and
Credit information to be filled in corresponding with target item；
Query unit 34 can be used for inquiring the text box to be filled in corresponding with target item in the credit information page；
Fill in unit 35, can be used for inquiring credit information to be filled in filling wait fill in text box.
In specific application scenarios, in order to can ensure that obtain target item to be entered in the credit information page to be filled in,
Credit information to be filled in corresponding with target item, as shown in figure 4, determination unit 33 can specifically include: identification module 331,
Matching module 332, enquiry module 333, parsing module 334.
Identification module 331 is particularly used in and matches speech recognition result with predetermined keyword；It is matched default if it exists
Keyword, then obtain it is corresponding with matched predetermined keyword can input item as target to be entered in the credit information page
?；
Matching module 332 is particularly used in and matches speech recognition result with each default Sentence Template respectively；
Enquiry module 333 is particularly used in the inquiry and and speech recognition corresponding with target item from preset memory locations
As a result the corresponding default semantic resolution rules of matched default Sentence Template.
Parsing module 334 is particularly used in using the default semantic resolution rules inquired, carries out to speech recognition result
Semanteme parsing, obtains credit information to be filled in corresponding with target item.
Correspondingly, in order to can ensure that obtain credit information to be filled in corresponding with target item, as shown in figure 4, determination unit
33 is specific further include: obtains module 335, filtering module 336, determining module 337.
Module 335 is obtained, if being particularly used in the matched default Sentence Template of speech recognition result is standard sentence pattern mould
When plate, in speech recognition result, obtains target item and correspond to the first other information after predetermined keyword；
Filtering module 336 is particularly used in the filtration treatment that garbage is carried out to the first other information；
Determining module 337 is particularly used in the first other information that will be obtained after filtration treatment, is determined as and target item pair
The credit information to be filled in answered.
In specific application scenarios, module 335 is obtained, specifically can also be used in the matched default sentence of speech recognition result
Pattern plate be non-standard Sentence Template when, obtain speech recognition result in addition to target item corresponds to predetermined keyword second its
Its information.
Correspondingly, in order to can ensure that obtain credit information to be filled in corresponding with target item, as shown in figure 4, determination unit
33 is specific further include: extraction module 338.
Extraction module 338 is particularly used in reference and the mark words in the matched default Sentence Template of speech recognition result,
Extract each characteristic information of flagged word segmentation in the second other information；
Module 335 is obtained, specifically can also be used according to the characteristic information arrangement in the default semantic resolution rules inquired
Each characteristic information is carried out permutation and combination, acquires credit information to be filled in corresponding with target item by built-up sequence.
In specific application scenarios, module 335 is obtained, specifically can also be used in matched predetermined keyword if it does not exist,
Then obtain the approximate keyword of corresponding with predetermined keyword semanteme；
Identification module 331 specifically can also be used to match speech recognition result with semantic approximate keyword；If it exists
Matched semantic approximate keyword, then obtain keyword approximate with matched semanteme it is corresponding can input item as credit information page
Target item to be entered in face.
Correspondingly, in order to ensure by credit information to be filled in filling inquire wait fill in text box, as shown in figure 4,
Filling in unit 35 can specifically include: output module 351 fills in module 352.
Output module 351 is particularly used in when having inserted information in text box wait fill in, and whether output, which is changed, has been inserted
The prompt information of information；
Module 352 is filled in, is particularly used in when receiving the phonetic order of confirmation change, credit information to be filled in is filled out
Enter inquire inserted information wait fill in text box and replace.
In specific application scenarios, as shown in figure 4, in order to more easily change input information, the present apparatus may also include that
Output unit 36, receiving unit 37, changing unit 38.
Output unit 36 is particularly used in the prompt for exporting and whether changing wait fill in the credit information to be filled in text box
Information；
Receiving unit 37 is particularly used in the voice change information for receiving user's input；
Changing unit 38 is particularly used in credit information the to be filled in progress treated and filled in text box according to change information
Change.
It should be noted that its of each functional unit involved by a kind of processing unit of credit information provided in this embodiment
He accordingly describes, and can describe referring to figs. 1 to the corresponding of Fig. 2, details are not described herein.
It is deposited thereon based on above-mentioned method as shown in Figure 1 to Figure 2 correspondingly, the present embodiment additionally provides a kind of storage medium
Computer program is contained, which realizes the processing side of above-mentioned credit information as shown in Figure 1 to Figure 2 when being executed by processor
Method.
Based on this understanding, the technical solution of the application can be embodied in the form of software products, which produces
Product can store in a non-volatile memory medium (can be CD-ROM, USB flash disk, mobile hard disk etc.), including some instructions
With so that computer equipment (can be personal computer, server or the network equipment an etc.) execution the application is each
Method described in implement scene.
It is above-mentioned in order to realize based on above-mentioned method as shown in Figure 1 to Figure 2, Fig. 3, virtual bench embodiment shown in Fig. 4
Purpose, the present embodiment additionally provide a kind of computer equipment, which includes storage medium and processor；Storage is situated between
Matter, for storing computer program；Processor realizes above-mentioned loan as shown in Figure 1 to Figure 2 for executing computer program
The processing method of information.
Optionally, which can also include user interface, network interface, camera, radio frequency (Radio
Frequency, RF) circuit, sensor, voicefrequency circuit, WI-FI module etc..User interface may include display screen
(Display), input unit such as keyboard (Keyboard) etc., optional user interface can also connect including USB interface, card reader
Mouthful etc..Network interface optionally may include standard wireline interface and wireless interface (such as WI-FI interface).
It will be understood by those skilled in the art that a kind of computer equipment structure provided in this embodiment is not constituted to the meter
The restriction for calculating machine equipment, may include more or fewer components, perhaps combine certain components or different component layouts.
It can also include operating system, network communication module in storage medium.Operating system is that the above-mentioned computer of management is set
The program of standby hardware and software resource, supports the operation of message handling program and other softwares and/or program.Network communication mould
Block for realizing the communication between each component in storage medium inside, and with other hardware and softwares in information processing entities equipment
Between communicate.
Through the above description of the embodiments, those skilled in the art can be understood that the application can borrow
It helps software that the mode of necessary general hardware platform is added to realize, hardware realization can also be passed through.Pass through the skill of application the application
Art scheme, compared with currently available technology, the embodiment of the present application can obtain identification user couple by the way of voice input automatically
In the credit information page input voice messaging, and can be automatically found according to the voice messaging of input accordingly item to be filled in
And the corresponding content of Auto-writing, the corresponding text box to be filled in of item to be filled in is inquired, thus the voice content that will be recognized
It fills out in corresponding text box.Further, when speech recognition result has mistake, it can receive the speech modification of user.Greatly
It reduces greatly and fills in difficulty, the input efficiency of information is improved, to reach good technical effect.
It will be appreciated by those skilled in the art that the accompanying drawings are only schematic diagrams of a preferred implementation scenario, module in attached drawing or
Process is not necessarily implemented necessary to the application.It will be appreciated by those skilled in the art that the mould in device in implement scene
Block can according to implement scene describe be distributed in the device of implement scene, can also carry out corresponding change be located at be different from
In one or more devices of this implement scene.The module of above-mentioned implement scene can be merged into a module, can also be into one
Step splits into multiple submodule.
Above-mentioned the application serial number is for illustration only, does not represent the superiority and inferiority of implement scene.Disclosed above is only the application
Several specific implementation scenes, still, the application is not limited to this, and the changes that any person skilled in the art can think of is all
The protection scope of the application should be fallen into.
Claims (10)
1. a kind of processing method of credit information characterized by comprising
Obtain the voice messaging that currently the in blank credit information page and user input the credit information page；
Speech recognition is carried out to the voice messaging；
According to institute's speech recognition result, determine target item to be entered in the credit information page, and with the target item
Corresponding credit information to be filled in；
Inquiry text box to be filled in corresponding with the target item in the credit information page；
The credit information to be filled in is inserted described in inquiring wait fill in text box.
2. determining the loan the method according to claim 1, wherein described according to institute's speech recognition result
Target item to be entered in money information page, and credit information to be filled in corresponding with the target item, specifically include:
Institute's speech recognition result is matched with predetermined keyword；
Matched predetermined keyword if it exists, then obtain it is corresponding with the matched predetermined keyword can input item conduct described in
The target item to be entered in the credit information page；
Institute's speech recognition result is matched with each default Sentence Template respectively；
From preset memory locations inquire it is corresponding with the target item and with the matched default sentence pattern of institute's speech recognition result
The corresponding default semantic resolution rules of template, wherein preserved in the preset memory locations it is different can input item, default sentence
Mapping relations between pattern plate, default semantic resolution rules three；
Using the default semantic resolution rules inquired, semantic parsing is carried out to institute's speech recognition result, is obtained and institute
State the corresponding credit information to be filled in of target item.
3. according to the method described in claim 2, it is characterized in that, the default semantic parsing rule that the utilization inquires
Then, semantic parsing is carried out to institute's speech recognition result, obtains credit information to be filled in corresponding with the target item, it is specific to wrap
It includes:
If being standard Sentence Template with the matched default Sentence Template of institute's speech recognition result, in institute's speech recognition result
In, obtain the first other information in addition to the target item corresponds to predetermined keyword；
The filtration treatment of garbage is carried out to first other information；
First other information that will be obtained after filtration treatment is determined as corresponding with the target item wait fill in loan letter
Breath.
4. according to the method described in claim 2, it is characterized in that, the default semantic parsing rule that the utilization inquires
Then, semantic parsing is carried out to institute's speech recognition result, obtains credit information to be filled in corresponding with the target item, it is specific to wrap
It includes:
If being non-standard Sentence Template with the matched default Sentence Template of institute's speech recognition result, the speech recognition is obtained
As a result the second other information in addition to the target item corresponds to predetermined keyword；
Reference and the mark words in the matched default Sentence Template of institute's speech recognition result, are extracted in second other information
The each characteristic information divided by the mark words；
According to the characteristic information permutation and combination sequence in the default semantic resolution rules inquired, by each spy
Reference breath carries out permutation and combination, obtains credit information to be filled in corresponding with the target item.
5. according to the method described in claim 2, it is characterized in that, matched predetermined keyword if it does not exist, then the method
Further include:
Obtain the approximate keyword of corresponding with predetermined keyword semanteme；
Institute's speech recognition result keyword approximate with the semanteme is matched；
Matched semantic approximate keyword if it exists, then obtaining that keyword approximate with the matched semanteme is corresponding can input item
As the target item to be entered in the credit information page.
6. credit information the to be filled in filling inquired the method according to claim 1, wherein described
It is described wait fill in text box, specifically include:
If described inserted information wait fill in text box, exports and whether change the prompt information for having inserted information；
If receiving the phonetic order of confirmation change, the credit information to be filled in is inserted to text to be filled in described in inquiring
Information has been inserted in this frame and described in replacement.
7. method according to any one of claim 1 to 6, which is characterized in that believe described wait fill in loan described
Breath filling inquire it is described wait fill in text box after, the method also includes:
Whether output changes the prompt information wait credit information to be filled in described in filling in text box；
Receive the voice change information of user's input；
It is modified to described wait credit information to be filled in described in filling in text box according to the change information.
8. a kind of processing unit of credit information characterized by comprising
Acquiring unit, it is defeated for the credit information page for obtaining the current in blank credit information page and user
The voice messaging entered；
Recognition unit, for carrying out speech recognition to the voice messaging；
Determination unit determines target item to be entered in the credit information page for according to institute's speech recognition result, and
Credit information to be filled in corresponding with the target item；
Query unit, for inquiring the text box to be filled in corresponding with the target item in the credit information page；
Fill in unit, for described in credit information the to be filled in filling is inquired wait fill in text box.
9. a kind of storage medium, is stored thereon with computer program, which is characterized in that realization when described program is executed by processor
The processing method of credit information described in any one of claims 1 to 7.
10. a kind of computer equipment, including storage medium, processor and storage can be run on a storage medium and on a processor
Computer program, which is characterized in that the processor is realized described in any one of claims 1 to 7 when executing described program
Credit information processing method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811287298.3A CN109360571A (en) | 2018-10-31 | 2018-10-31 | Processing method and processing device, storage medium, the computer equipment of credit information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811287298.3A CN109360571A (en) | 2018-10-31 | 2018-10-31 | Processing method and processing device, storage medium, the computer equipment of credit information |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109360571A true CN109360571A (en) | 2019-02-19 |
Family
ID=65347568
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811287298.3A Pending CN109360571A (en) | 2018-10-31 | 2018-10-31 | Processing method and processing device, storage medium, the computer equipment of credit information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109360571A (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110209667A (en) * | 2019-04-25 | 2019-09-06 | 深圳壹账通智能科技有限公司 | Statistical method, device and the computer equipment of balance data |
| CN111126938A (en) * | 2019-11-22 | 2020-05-08 | 中国联合网络通信集团有限公司 | Task generation method, server, electronic device, and storage medium |
| CN111128182A (en) * | 2019-12-16 | 2020-05-08 | 中国银行股份有限公司 | Intelligent voice recording method and device |
| CN111241262A (en) * | 2020-01-20 | 2020-06-05 | 深圳壹账通智能科技有限公司 | Loan qualification auditing method based on artificial intelligence and related equipment |
| CN111339910A (en) * | 2020-02-24 | 2020-06-26 | 支付宝实验室(新加坡)有限公司 | Text processing method and device and text classification model training method and device |
| CN111797606A (en) * | 2020-07-09 | 2020-10-20 | 海口科博瑞信息科技有限公司 | Data filling method, system, equipment and computer readable storage medium |
| CN111967235A (en) * | 2020-08-31 | 2020-11-20 | 平安国际智慧城市科技股份有限公司 | Form processing method and device, computer equipment and storage medium |
| CN112435116A (en) * | 2020-11-25 | 2021-03-02 | 平安普惠企业管理有限公司 | Data processing method and device based on artificial intelligence, computer equipment and medium |
| CN112863506A (en) * | 2020-12-30 | 2021-05-28 | 平安普惠企业管理有限公司 | Service information acquisition method and device, computer equipment and readable storage medium |
| CN113448963A (en) * | 2021-06-29 | 2021-09-28 | 平安普惠企业管理有限公司 | Information input method, device, equipment and storage medium |
| WO2021196458A1 (en) * | 2020-04-02 | 2021-10-07 | 深圳壹账通智能科技有限公司 | Intelligent loan entry method, and apparatus and storage medium |
| CN113778288A (en) * | 2021-08-25 | 2021-12-10 | 上海浦东发展银行股份有限公司 | Form generation method and device, computer equipment and storage medium |
| CN116663509A (en) * | 2023-08-02 | 2023-08-29 | 四川享宇科技有限公司 | Automatic information acquisition and filling robot for banking complex system |
| CN117995199A (en) * | 2024-03-22 | 2024-05-07 | 中邮消费金融有限公司 | Loan contract voice signing method, device and storage medium |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060064302A1 (en) * | 2004-09-20 | 2006-03-23 | International Business Machines Corporation | Method and system for voice-enabled autofill |
| CN101366076A (en) * | 2006-02-10 | 2009-02-11 | 西门子公司 | Method for preparing information for a speech dialogue system |
| US20120323574A1 (en) * | 2011-06-17 | 2012-12-20 | Microsoft Corporation | Speech to text medical forms |
| CN104036421A (en) * | 2014-06-15 | 2014-09-10 | 王美金 | Telephone number voice recognition based banking business application form generation system |
| CN105161104A (en) * | 2015-07-31 | 2015-12-16 | 北京云知声信息技术有限公司 | Voice processing method and device |
| CN105786797A (en) * | 2016-02-23 | 2016-07-20 | 北京云知声信息技术有限公司 | Information processing method and device based on voice input |
| CN106251865A (en) * | 2016-08-04 | 2016-12-21 | 华东师范大学 | A kind of medical treatment & health record Auto-writing method based on speech recognition |
| CN106601236A (en) * | 2016-12-22 | 2017-04-26 | 北京云知声信息技术有限公司 | Speech recognition method and apparatus |
| CN107168551A (en) * | 2017-06-13 | 2017-09-15 | 重庆小雨点小额贷款有限公司 | The input method that a kind of list is filled in |
| CN107357772A (en) * | 2017-07-04 | 2017-11-17 | 贵州小爱机器人科技有限公司 | List filling method, device and computer equipment |
| CN107423275A (en) * | 2017-06-27 | 2017-12-01 | 北京小度信息科技有限公司 | Sequence information generation method and device |
| CN107430859A (en) * | 2015-04-08 | 2017-12-01 | 谷歌公司 | Input is mapped to form fields |
| CN107591195A (en) * | 2017-09-07 | 2018-01-16 | 北京鑫丰南格科技股份有限公司 | A kind of medical care householder method and device based on nursing calling system |
| CN107632982A (en) * | 2017-09-12 | 2018-01-26 | 郑州科技学院 | The method and apparatus of voice controlled foreign language translation device |
| CN108664199A (en) * | 2018-05-07 | 2018-10-16 | 平安普惠企业管理有限公司 | List filling method, device, equipment and computer readable storage medium |
-
2018
- 2018-10-31 CN CN201811287298.3A patent/CN109360571A/en active Pending
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060064302A1 (en) * | 2004-09-20 | 2006-03-23 | International Business Machines Corporation | Method and system for voice-enabled autofill |
| CN101366076A (en) * | 2006-02-10 | 2009-02-11 | 西门子公司 | Method for preparing information for a speech dialogue system |
| US20120323574A1 (en) * | 2011-06-17 | 2012-12-20 | Microsoft Corporation | Speech to text medical forms |
| CN104036421A (en) * | 2014-06-15 | 2014-09-10 | 王美金 | Telephone number voice recognition based banking business application form generation system |
| CN107430859A (en) * | 2015-04-08 | 2017-12-01 | 谷歌公司 | Input is mapped to form fields |
| CN105161104A (en) * | 2015-07-31 | 2015-12-16 | 北京云知声信息技术有限公司 | Voice processing method and device |
| CN105786797A (en) * | 2016-02-23 | 2016-07-20 | 北京云知声信息技术有限公司 | Information processing method and device based on voice input |
| CN106251865A (en) * | 2016-08-04 | 2016-12-21 | 华东师范大学 | A kind of medical treatment & health record Auto-writing method based on speech recognition |
| CN106601236A (en) * | 2016-12-22 | 2017-04-26 | 北京云知声信息技术有限公司 | Speech recognition method and apparatus |
| CN107168551A (en) * | 2017-06-13 | 2017-09-15 | 重庆小雨点小额贷款有限公司 | The input method that a kind of list is filled in |
| CN107423275A (en) * | 2017-06-27 | 2017-12-01 | 北京小度信息科技有限公司 | Sequence information generation method and device |
| CN107357772A (en) * | 2017-07-04 | 2017-11-17 | 贵州小爱机器人科技有限公司 | List filling method, device and computer equipment |
| CN107591195A (en) * | 2017-09-07 | 2018-01-16 | 北京鑫丰南格科技股份有限公司 | A kind of medical care householder method and device based on nursing calling system |
| CN107632982A (en) * | 2017-09-12 | 2018-01-26 | 郑州科技学院 | The method and apparatus of voice controlled foreign language translation device |
| CN108664199A (en) * | 2018-05-07 | 2018-10-16 | 平安普惠企业管理有限公司 | List filling method, device, equipment and computer readable storage medium |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110209667A (en) * | 2019-04-25 | 2019-09-06 | 深圳壹账通智能科技有限公司 | Statistical method, device and the computer equipment of balance data |
| CN111126938A (en) * | 2019-11-22 | 2020-05-08 | 中国联合网络通信集团有限公司 | Task generation method, server, electronic device, and storage medium |
| CN111128182A (en) * | 2019-12-16 | 2020-05-08 | 中国银行股份有限公司 | Intelligent voice recording method and device |
| CN111128182B (en) * | 2019-12-16 | 2022-10-21 | 中国银行股份有限公司 | Intelligent voice recording method and device |
| CN111241262A (en) * | 2020-01-20 | 2020-06-05 | 深圳壹账通智能科技有限公司 | Loan qualification auditing method based on artificial intelligence and related equipment |
| CN111339910A (en) * | 2020-02-24 | 2020-06-26 | 支付宝实验室(新加坡)有限公司 | Text processing method and device and text classification model training method and device |
| CN111339910B (en) * | 2020-02-24 | 2023-11-28 | 支付宝实验室(新加坡)有限公司 | Text processing and text classification model training method and device |
| WO2021196458A1 (en) * | 2020-04-02 | 2021-10-07 | 深圳壹账通智能科技有限公司 | Intelligent loan entry method, and apparatus and storage medium |
| CN111797606A (en) * | 2020-07-09 | 2020-10-20 | 海口科博瑞信息科技有限公司 | Data filling method, system, equipment and computer readable storage medium |
| CN111967235B (en) * | 2020-08-31 | 2023-06-27 | 深圳赛安特技术服务有限公司 | Form processing method, form processing device, computer equipment and storage medium |
| CN111967235A (en) * | 2020-08-31 | 2020-11-20 | 平安国际智慧城市科技股份有限公司 | Form processing method and device, computer equipment and storage medium |
| CN112435116A (en) * | 2020-11-25 | 2021-03-02 | 平安普惠企业管理有限公司 | Data processing method and device based on artificial intelligence, computer equipment and medium |
| CN112435116B (en) * | 2020-11-25 | 2024-03-05 | 深圳市兴海物联科技有限公司 | Data processing method, device, computer equipment and medium based on artificial intelligence |
| CN112863506A (en) * | 2020-12-30 | 2021-05-28 | 平安普惠企业管理有限公司 | Service information acquisition method and device, computer equipment and readable storage medium |
| CN113448963A (en) * | 2021-06-29 | 2021-09-28 | 平安普惠企业管理有限公司 | Information input method, device, equipment and storage medium |
| CN113778288A (en) * | 2021-08-25 | 2021-12-10 | 上海浦东发展银行股份有限公司 | Form generation method and device, computer equipment and storage medium |
| CN113778288B (en) * | 2021-08-25 | 2024-10-18 | 上海浦东发展银行股份有限公司 | Form generation method, form generation device, computer equipment and storage medium |
| CN116663509A (en) * | 2023-08-02 | 2023-08-29 | 四川享宇科技有限公司 | Automatic information acquisition and filling robot for banking complex system |
| CN116663509B (en) * | 2023-08-02 | 2023-09-29 | 四川享宇科技有限公司 | Automatic information acquisition and filling robot for banking complex system |
| CN117995199A (en) * | 2024-03-22 | 2024-05-07 | 中邮消费金融有限公司 | Loan contract voice signing method, device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109360571A (en) | Processing method and processing device, storage medium, the computer equipment of credit information | |
| CN108847241B (en) | Method for recognizing conference voice as text, electronic device and storage medium | |
| CN110502608B (en) | Man-machine conversation method and man-machine conversation device based on knowledge graph | |
| US10771408B2 (en) | Chatbot system and service method thereof | |
| RU2589873C2 (en) | Input processing method and apparatus | |
| CN108040032A (en) | A kind of voiceprint authentication method, account register method and device | |
| CN111445903B (en) | Enterprise name recognition method and device | |
| CN110209667A (en) | Statistical method, device and the computer equipment of balance data | |
| CN109087639B (en) | Method, apparatus, electronic device and computer readable medium for speech recognition | |
| CN101567189A (en) | Device, method and system for correcting voice recognition result | |
| CN102549653A (en) | Speech translation system, first terminal device, speech recognition server device, translation server device, and speech synthesis server device | |
| CN111540353B (en) | Semantic understanding method, device, equipment and storage medium | |
| CN112434501B (en) | Method, device, electronic equipment and medium for intelligent generation of worksheet | |
| CN107832035B (en) | Voice input method of intelligent terminal | |
| CN113868252A (en) | Database mode matching method and device and SQL query statement generation method | |
| US20190139544A1 (en) | Voice controlling method and system | |
| JP5901694B2 (en) | Dictionary database management device, API server, dictionary database management method, and dictionary database management program | |
| CN111858966B (en) | Knowledge graph updating method and device, terminal equipment and readable storage medium | |
| CN114528851B (en) | Reply sentence determination method, reply sentence determination device, electronic equipment and storage medium | |
| CN117332062A (en) | Data processing method and related device | |
| KR20160138613A (en) | Method for auto interpreting using emoticon and apparatus using the same | |
| CN113987202A (en) | Knowledge graph-based interactive telephone calling method and device | |
| CN114047900A (en) | Service processing method and device, electronic equipment and computer readable storage medium | |
| CN113254579A (en) | Voice retrieval method and device and electronic equipment | |
| CN114078484A (en) | Method, device and storage medium for speech emotion recognition |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190219 |
|
| WD01 | Invention patent application deemed withdrawn after publication |