CN109213777A - A kind of voice-based recipe processing method and system - Google Patents
A kind of voice-based recipe processing method and system Download PDFInfo
- Publication number
- CN109213777A CN109213777A CN201710530374.8A CN201710530374A CN109213777A CN 109213777 A CN109213777 A CN 109213777A CN 201710530374 A CN201710530374 A CN 201710530374A CN 109213777 A CN109213777 A CN 109213777A
- Authority
- CN
- China
- Prior art keywords
- recipe
- hot word
- voice
- information
- word
- 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 9
- 238000000034 method Methods 0.000 claims abstract description 41
- 238000012545 processing Methods 0.000 claims abstract description 17
- 238000001914 filtration Methods 0.000 claims abstract description 12
- 230000011218 segmentation Effects 0.000 claims abstract description 8
- 235000013305 food Nutrition 0.000 claims description 18
- 239000000463 material Substances 0.000 claims description 14
- 238000010411 cooking Methods 0.000 claims description 13
- 239000004615 ingredient Substances 0.000 claims description 5
- 230000000694 effects Effects 0.000 claims description 3
- 241001247821 Ziziphus Species 0.000 description 9
- 238000010586 diagram Methods 0.000 description 7
- 239000000284 extract Substances 0.000 description 5
- 235000013399 edible fruits Nutrition 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 235000015277 pork Nutrition 0.000 description 4
- 238000001228 spectrum Methods 0.000 description 4
- 244000273928 Zingiber officinale Species 0.000 description 3
- 235000006886 Zingiber officinale Nutrition 0.000 description 3
- 235000008397 ginger Nutrition 0.000 description 3
- 235000008534 Capsicum annuum var annuum Nutrition 0.000 description 2
- 240000008384 Capsicum annuum var. annuum Species 0.000 description 2
- 241000233866 Fungi Species 0.000 description 2
- 241000287828 Gallus gallus Species 0.000 description 2
- 241001506047 Tremella Species 0.000 description 2
- 235000017166 Bambusa arundinacea Nutrition 0.000 description 1
- 235000017491 Bambusa tulda Nutrition 0.000 description 1
- 244000082204 Phyllostachys viridis Species 0.000 description 1
- 235000015334 Phyllostachys viridis Nutrition 0.000 description 1
- 239000011425 bamboo Substances 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005266 casting Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 239000000571 coke Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 239000003337 fertilizer Substances 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/284—Lexical analysis, e.g. tokenisation or collocates
-
- 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
- G10L15/28—Constructional details of speech recognition systems
- G10L15/30—Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Acoustics & Sound (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
Present invention discloses a kind of voice-based recipe processing methods, comprising steps of receiving voice request information；Voice request information is simultaneously converted to text information by identification voice request information；Word segmentation processing is carried out to text information, target word therein is extracted and carries out hot word filtering；Filter result is matched with corresponding hot word set in preset hot word expansion library and obtains matching result, semantic retrieval is carried out according to matching result and feeds back corresponding recipe information.Disclosed method can liberate user's both hands, and user is made to retrieve recipe information by voice mode, while also solve the compatibility issue between the accuracy rate and recipe platform of semantic retrieval.Present invention further teaches a kind of voice-based recipe processing systems.
Description
Technical field
The present invention relates to recipe intelligent cooking fields, more specifically to a kind of voice-based recipe processing method.
The present invention also discloses a kind of voice-based recipe processing system.
Background technique
The rapid development of science and technology, deep changes people's lives, no exception in recipe and culinary area.
In the young people based on after 80s, after 90s, more and more people cook by recipe, and are capable of providing the platform of recipe
And app, often have the defects that not smart enough, user must can be inquired corresponding by the operation such as pressing or sliding
Recipe, or jump to the corresponding position of recipe, this greatly reduces user experience.
On the other hand, although the technologies such as speech recognition can be applied in recipe process field, existing voice
Cloud platform predominantly towards masses, often takes its most common meaning to be understood when parsing to voice messaging, and
The meaning work of recipe this specific area is cast out, therefore user retrieves recipe by phonological means and cannot often expire
The answer of meaning.Than more typical, when user inquires " how jujube cake is cooked ", it is sent into parsing meeting of the voice cloud platform to " jujube cake "
Common meaning " bad luck " is taken, mistake is understood completely in the result so as to cause whole sentence.
Simultaneously as the resource of existing voice cloud platform and recipe cloud platform is there is no complete intercommunication, and different foods
Difference is individually present for the attribute tags of recipe in spectrum cloud platform again, and the inquiry language used by user cannot be flat with recipe cloud
When the attribute tags exact matching of platform, user can not equally obtain corresponding content.For example, in a certain recipe cloud platform, to can
The attribute tags of happy chicken wings are " food ", then user must talk about art, the recipe of feedback using " what food eats " in inquiry
It just will include coke chicken wing in information, and art if " what stoke of midnight eats " used to be inquired, then can not obtain corresponding result.
Summary of the invention
The present invention is to solve above-mentioned the technical problems existing in the prior art, provides a kind of voice-based recipe processing
Method, this method can be directed to the voice request of user, provide corresponding recipe information for user, make user need not manual operation
Recipe can be screened and cooked according to recipe.Present invention further teaches a kind of voice-based recipe processing systems.
In order to achieve the above objectives, The technical solution adopted by the invention is as follows:
A kind of voice-based recipe processing method, comprising steps of receiving voice request information；Identify voice request information
And voice request information is converted into text information；Word segmentation processing is carried out to text information, target word therein is extracted and carries out
Hot word filtering；Filter result is matched with corresponding hot word set in preset hot word expansion library and obtains matching result, according to
Matching result carries out semantic retrieval and feeds back corresponding recipe information.
Further, word segmentation processing is carried out to text information, extracts the step of target word therein carries out hot word filtering
It include: the target word extracted according to part of speech and the degree of correlation in text information, according to preset priority orders in target word
It is screened in the unisonance dictionary of language and determines filter result.
Further, it includes the hot word set expanded for the attribute tags of recipe that hot word, which expands library,；And/or it is directed to
The hot word set that the content of text of recipe is expanded.
Further, method further include: semantic identification is carried out according to matching result, judges whether to feed back according to identification result
It is detached from the encyclopaedic knowledge in recipe, feeds back corresponding encyclopaedic knowledge when the judgment result is yes.
Further, method further include: obtain automatic cooking program corresponding with recipe, call automatic cooking program control
Kitchen appliance equipment processed is cooked according to recipe.
Further, if failing to obtain corresponding with recipe automatic cooking program, according to the content of text of recipe into
Row is shown or casting.
Further, the attribute tags of recipe include at least following one: style of cooking label, taste label, time tag with
And effect label.
Further, the content of text of recipe includes at least following one: recipe name, food materials auxiliary material, is cooked food materials major ingredient
Step of preparing food and culinary art patch scholar.
Present invention further teaches a kind of voice-based recipe processing systems.
A kind of voice-based recipe processing system, including middle control terminal, speech cloud and recipe cloud further include hot word filter
Dictionary and hot word expand library, and middle control terminal is used to carry out voice request information for receiving voice request information, speech cloud
Speech recognition and semantic understanding, are converted to text information after voice request information is identified, text information is sent into hot word and filters word
Library carries out hot word filtering, and resulting filter result feeding hot word expansion library matches with corresponding hot word set obtains matching knot
Fruit carries out semantic retrieval in recipe cloud according to matching result and feeds back corresponding recipe information.
Further, middle control terminal is kitchen house keeper robot or intelligent kitchen appliance equipment.
Technical solution of the present invention has the beneficial effect that:
Disclosed voice-based recipe processing method can be improved user for recipe and carry out semantic retrieval
Accuracy rate, user, which need not carry out inquiry using fixed words art, can be obtained corresponding recipe content；Meanwhile this method also solves
Compatibility issue between different recipe cloud platforms.The present invention also discloses a kind of voice-based recipe processing system accordingly
System.
Detailed description of the invention
Fig. 1 is the step block diagram of the method for the invention wherein embodiment；
Fig. 2 is the schematic diagram of the method for the invention wherein recipe of an embodiment；
Fig. 3 is the recipe process flow diagram of the method for the invention wherein embodiment；
Fig. 4 is the configuration diagram of system of the present invention.
Specific embodiment
More detailed description is done to technical solution provided by the present invention below by way of the drawings and specific embodiments:
Attached drawing 1 discloses the specific embodiment of the method for the invention.As shown in Figure 1, it is the method for the invention
Step block diagram discloses in the embodiment:
A kind of voice-based recipe processing method, comprising steps of
Step 101, voice request information is received；
Step 102, it identifies voice request information and voice request information is converted into text information；
Step 103, word segmentation processing is carried out to text information, extracts target word therein and carries out hot word filtering；
Step 104, filter result is matched with corresponding hot word set in preset hot word expansion library and obtains matching knot
Fruit carries out semantic retrieval according to the matching result and feeds back corresponding recipe information.
In the embodiment, by speech recognition technology, after the voice request information of user is converted to text information, lead to
Cross and word segmentation processing carried out to text information, extract target word therein and carry out hot word filtering, thus make originally due to unexpected winner,
The specialized word in the recipe field that field is partially narrow and is rejected is retained and parses, and the filter result remained will further be made
For the basis of subsequent expansion and semantic retrieval.And filter result expands corresponding hot word set in library with preset hot word and matches
Matching result is obtained, filter result can be expanded in semantic and words art, so as to make user need not be using solid
Surely art is talked about, it is diversified to be inquired and obtain desired result；Moreover, the hot word, which expands library, to put down different recipe clouds
The recipe attribute tags of platform are unified and are concluded, and solve the compatibility issue between different recipe cloud platforms, even if user
The recipe attribute tags of art and recipe cloud platform are inconsistent if inquiry, can similarly obtain desired knot after expanding
Fruit.
It is described that word segmentation processing is carried out to the text information in the present invention wherein an embodiment, extract target therein
The step of word progress hot word filtering includes: the target word extracted in text information according to part of speech and the degree of correlation, according to pre-
If priority orders screened in the unisonance dictionary of the target word determine filter result.Due to existing speech recognition skill
Art is to convert voice signals into phonetic and form text in turn according to certain specific corresponding word of determine the probability phonetic institute
Information, and what usual voice cloud platform was taken is the highest word of probability in full field, rather than it is directed to recipe field probability highest
Word, therefore the specialized word in recipe field is easy to be rejected during speech recognition, final so as to cause user
There is very large deviation in the result of acquisition and answer and practical intention.And the method for the invention can according to part of speech and the degree of correlation,
Target word is extracted in text information, and screens determination in the unisonance dictionary of target word according to preset priority orders
Filter result is rejected so as to avoid the specialized word in recipe field since unexpected winner, field are partially narrow, it is ensured that speech recognition
As a result accuracy.Specifically, it by taking jujube cake as an example, when user inquires " how jujube cake is cooked ", is identified by speech recognition technology
The voice request information is simultaneously converted into text information, later according to part of speech and the degree of correlation, " jujube cake " belong to noun and with food
Spectrum is related, therefore extracts as target word, in unisonance dictionary, pronounce comprising " jujube cake " (phonetic of speech recognition are as follows:
Zaogao homonym) includes " bad luck ", " early doing ", " jujube cake " etc., if using probability highest in the full field of voice cloud platform
Word, then the voice request information of user will be identified that " bad luck how to do ", this is clearly to be intended to against user；But
The method of the present invention drains into " jujube cake " in three homonyms due to being provided with unisonance dictionary and having preset corresponding priority orders
Highest priority carries out screening and filtering, therefore the voice request information of user will be identified that " how jujube cake is cooked ", thus really
The intention that resulting filter result meets user is protected.
In the method for the invention wherein an embodiment, the hot word expand library include for recipe attribute tags into
The hot word set that row is expanded；And/or the hot word set expanded of content of text for recipe.The meaning that user is inquired
Figure, it is possible to be desirable to push corresponding recipe for it, it is also possible to be to jump to corresponding position for the recipe selected
Or obtain the corresponding answer in relation to recipe content.Therefore, it both may include needle that the hot word of the method for the invention setting, which expands library,
To the hot word set that the attribute tags of recipe are expanded, the hot word that can also be expanded with treasure-house for the content of text of recipe
Set.Attribute tags due to that can be directed to recipe are expanded, art and recipe cloud platform user's inquiry
Bookmark name not fully corresponds to, user remain on can obtain it is corresponding want to obtain as a result, to meet user carry out it is more
The demand of art inquiry is talked about, while also eliminating the compatibility issue between different recipe cloud platforms.And in the text of recipe
Hold the expansion carried out, the content that can help user that need not record fully according to recipe is inquired, and actual according to user
Semanteme jumps to recipe corresponding position, or is the corresponding recipe content of user feedback.In this embodiment, it is obtaining accurately
Filter result on the basis of, by with hot word expand library in corresponding hot word set matched, can further be user
Semantic retrieval is carried out, recipe required for user, or the corresponding recipe information of feedback are picked out.For example, user wants to food
Spectrum is retrieved, for the content query " recommending the Hunan dish being fond of eating a bit for me " of certain recipe cloud platform, if the recipe cloud is flat
Platform is labeled as " Hunan cuisine " (agreeing to Hunan dish) rather than " Hunan dish " for the attribute tags of recipe, the case where not expanding
Under, then user can not obtain " Hunan dish " relevant recipe；Likewise, if another recipe cloud platform for recipe attribute
Label for labelling is " group Buddhist nunnery Hunan cuisine ", equally can not also be obtained according to " recommending the Hunan dish being fond of eating a bit for me " progress inquiry relevant
Recipe.And the method for the invention is preset with hot word and expands library, by some related foods due to expanding related step comprising hot word
The word of spectrum attribute tags is stored in hot word and expands library for being expanded, such as establishes the hot word collection specifically for style of cooking label
It closes, the different calls of wherein " Hunan cuisine ", local dish even relevant to Hunan cuisine etc. is all classified as one kind, i.e., be by " Hunan cuisine " expansion
" Hunan cuisine ", " Hunan dish ", " group Buddhist nunnery Hunan cuisine ", " western Hunan dish " " Tujia's dish ", " Yueyang dish " etc., in this way, no matter user is with wherein
Any call is inquired that art can all match with the recipe attribute tags of recipe cloud platform if inquiry, thus according to
The true intention of user obtains recipe required for user, and one side user need not art be inquired according to fixation, another
Aspect also solves the compatibility issue between different recipe cloud platforms.
In the method for the invention wherein an embodiment, the attribute tags of the recipe include at least following one: dish
It is label, taste label, time tag and effect label.
The method of the invention wherein the hot word in an embodiment expand library can also be comprising the content of text for recipe
The hot word set expanded.It is as shown in Figure 2, be the method for the invention wherein in an embodiment recipe schematic diagram.Mesh
There are many content for including in preceding most of recipes, for example, would generally comprising recipe name, brief introduction, food materials major ingredient, food materials auxiliary material,
The contents such as cooking step, culinary art patch scholar.Since recipe content is more, user's needs could be in the phase of recipe by pressing or sliding
Information required for finding oneself at position is answered, causes user that can not liberate both hands, is very inconvenient to operate.And institute of the present invention
The method of stating can allow user to retrieve and interact by way of voice, to improve the convenience of operation.Fig. 2 is disclosed
A wherein recipe in the method for the invention, it includes pork (fertilizer that the part content of text of the recipe, which has recorded food materials major ingredient,
It is thin), dried bamboo shoots, agaric it is dry etc..If user when cooking according to the recipe, inquires " pork puts how many ", due to recipe
Content of text in actually record is " pork (girth of a garment) ", and words art used by user is not completely right with content of text
It answers, thus is also required to expand the content of text of recipe, could be obtained required for user later as a result, informing that user needs
Put pork 200g.Likewise, it is dry for agaric, it needs to expand in library in hot word and the title of " agaric is dry " is uniformly returned
Class, such as " agaric is dry, fresh agaric, small agaric, black fungus, agaric, tremella, tremella " is all unified concludes, so no matter user with
" agaric puts how many ", " black fungus puts how many ", " fresh agaric puts how many " etc. any one words art inquired, can
It is found from recipe as a result, informing that user needs to put agaric and does 6g.
In the method for the invention wherein an embodiment, the content of text of the recipe includes at least following one: food
Compose title, food materials major ingredient, food materials auxiliary material, cooking step and culinary art patch scholar.
As shown in Figure 3, it is the step block diagram of the another embodiment of the method for the invention.In this embodiment, the side
Method further include: judge whether that feedback is detached from the encyclopaedic knowledge of recipe according to identification result, feed back phase when the judgment result is yes
The encyclopaedic knowledge answered.As shown in Figure 3, identify step 305 about semanteme: carrying out semanteme in the voice request information to user
After understanding, will do it is corresponding semantic identify, to judge that it is some with the recipe based on recipe content advisories that user is intended at this time
Relevant information, which is also intended to be detached from, inquires some encyclopaedic knowledge contents in relation to cooking in recipe, and can divide situation in this way is user
It is answered, achievees the purpose that carrying out depth with user interacts.For example, user is possible to for the recipe inquiry " auxiliary material in Fig. 2
Bubble green pepper put it is several ", carry out semantic identify at this time and judge that user still seeks advice from being directed to the recipe, then can root
Inform that user needs to put bubble green pepper 2 according to recipe content；And if user proposes the other problems in relation to cooking, such as it inquires
" teaching me, once how ginger should cut ", and pass through semantic identify and have no the teaching content how cut in relation to ginger in discovery recipe, this
When be then detached from the recipe, into relation to cook encyclopaedic knowledge library in retrieved, and feed back and introduction user specifically cut ginger
Method.When being retrieved in encyclopaedic knowledge library, then recipe field might not be sticked to, it can be using probability in full field
Highest word carries out voice recognition processing.
It is as shown in Figure 3, in the method for the invention wherein an embodiment, the method also includes: obtain with it is described
The corresponding automatic cooking program of recipe calls the automatic cooking program control kitchen appliance equipment to be cooked according to the recipe
It prepares food.In the method for the invention wherein an embodiment, if failing to obtain automatic cooking program corresponding with the recipe,
It is shown or broadcasts according to the content of text of the recipe.As shown in Figure 3, about the step for determining whether automatic cooking program
Rapid 307: user is after retrieving corresponding recipe, it is generally desirable to be cooked according to recipe, can attempt at this time from cloud or
Person locally obtains automatic cooking program corresponding with the recipe, then calls automatic cooking program control kitchen appliance equipment according to this
Recipe is cooked, to further realize automatic cooking on the basis of retrieving the recipe that user wants for user.And such as
Fruit finds automatic cooking program corresponding with the recipe, then according to the step 308 for showing or broadcasting, only user shows corresponding
Recipe content, or only user broadcasts specific recipe content, completes cooking process by user oneself.
It is as shown in Figure 4, present invention further teaches a kind of voice-based recipe processing system, including middle control terminal 401,
Speech cloud 402 and recipe cloud 405, the system further include that hot word filter dictionary 403 and hot word expand library 404, middle control terminal 401
For receiving voice request information, speech cloud 402 is used to carry out speech recognition and semantic understanding, voice to voice request information
Text information is converted to after solicited message is identified, text information is sent into hot word filter dictionary 403 and carries out hot word filtering, resulting mistake
Filter result feeding hot word expansion library 404 matches with corresponding hot word set obtains matching result, according to matching result in recipe
Semantic retrieval is carried out in cloud 405 and feeds back corresponding recipe information.As shown in Figure 4, as a wherein embodiment, hot word filters word
Library 403 and hot word are expanded library 404 and are all set in speech cloud 402, but those skilled in the art it will be appreciated that, according to database
Middle data volume number, hot word filter dictionary 403 and/or hot word expand library 404 can also on middle control terminal 401 local disposition.
In a wherein embodiment for system of the present invention, the middle control terminal 401 is kitchen house keeper robot or intelligence
Energy kitchen appliance equipment, control terminal 401 can be interacted by voice mode with user in this.
Above-mentioned specific embodiment is only intended to illustrate design method of the invention, for the purpose of limiting the invention can not protect
Protect range.For the deformation and conversion under the thought guidance of technical solution of the present invention, it should all be attributed to the scope of the present invention
Within.
Claims (10)
1. a kind of voice-based recipe processing method, which is characterized in that comprising steps of
Receive voice request information；
The voice request information is simultaneously converted to text information by identification voice request information；
Word segmentation processing is carried out to the text information, target word therein is extracted and carries out hot word filtering；
Filter result is matched with corresponding hot word set in preset hot word expansion library and obtains matching result, according to described
Semantic retrieval is carried out with result and feeds back corresponding recipe information.
2. being extracted the method according to claim 1, wherein described carry out word segmentation processing to the text information
The step of target word progress hot word filtering therein includes: the target word extracted in text information according to part of speech and the degree of correlation
Language screens in the unisonance dictionary of the target word according to preset priority orders and determines filter result.
3. the method according to claim 1, wherein it includes the attribute tags for recipe that the hot word, which expands library,
The hot word set expanded；And/or the hot word set expanded of content of text for recipe.
4. method according to any one of claim 1-3, which is characterized in that the method also includes: according to described
Semantic identification is carried out with result, judges whether that feedback is detached from the encyclopaedic knowledge of recipe according to identification result, is in judging result
Corresponding encyclopaedic knowledge is fed back when being.
5. according to the method described in claim 4, it is characterized in that, the method also includes: obtain it is corresponding with the recipe
Automatic cooking program, call automatic cooking program control kitchen appliance equipment to be cooked according to the recipe.
6. according to the method described in claim 5, it is characterized in that, if failing to obtain automatic cooking corresponding with the recipe
Program is then shown or broadcasts according to the content of text of the recipe.
7. according to the method described in claim 3, it is characterized in that, the attribute tags of the recipe include at least following one:
Style of cooking label, taste label, time tag and effect label.
8. according to the method described in claim 3, it is characterized in that, the content of text of the recipe includes at least following one:
Recipe name, food materials major ingredient, food materials auxiliary material, cooking step and culinary art patch scholar.
9. a kind of voice-based recipe processing system, including middle control terminal, speech cloud and recipe cloud, which is characterized in that also
Dictionary is filtered including hot word and hot word expands library, and for receiving voice request information, the speech cloud is used for the middle control terminal
Speech recognition and semantic understanding are carried out to the voice request information, are converted to text after the voice request information is identified
Information, the text information are sent into the hot word filter dictionary and carry out hot word filtering, and resulting filter result is sent into hot word and expands library
Match with corresponding hot word set and obtain matching result, carries out semantic retrieval and anti-in recipe cloud according to the matching result
Present corresponding recipe information.
10. system according to claim 9, which is characterized in that the middle control terminal is kitchen house keeper robot or intelligence
Kitchen appliance equipment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710530374.8A CN109213777A (en) | 2017-06-29 | 2017-06-29 | A kind of voice-based recipe processing method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710530374.8A CN109213777A (en) | 2017-06-29 | 2017-06-29 | A kind of voice-based recipe processing method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109213777A true CN109213777A (en) | 2019-01-15 |
Family
ID=64991736
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710530374.8A Pending CN109213777A (en) | 2017-06-29 | 2017-06-29 | A kind of voice-based recipe processing method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109213777A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111061857A (en) * | 2019-12-10 | 2020-04-24 | 珠海格力电器股份有限公司 | Menu generation method and device, electronic equipment and storage medium |
| CN112581954A (en) * | 2020-12-01 | 2021-03-30 | 杭州九阳小家电有限公司 | High-matching voice interaction method and intelligent equipment |
| CN113490011A (en) * | 2021-08-20 | 2021-10-08 | 云知声（上海）智能科技有限公司 | Atmosphere backing system and method based on ASR live broadcast room |
| TWI785959B (en) * | 2022-01-08 | 2022-12-01 | 長庚大學 | Food recording system and operation method thereof |
Citations (38)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1038555A (en) * | 1988-05-12 | 1990-01-03 | 西屋电气公司 | The Method and circuits that is used for the DC power supply voltage-regulation |
| CN1041660A (en) * | 1988-10-20 | 1990-04-25 | 长春邮电学院 | The input in Chinese device |
| CN1352450A (en) * | 2000-11-15 | 2002-06-05 | 中国科学院自动化研究所 | Voice recognition method for Chinese personal name place name and unit name |
| US20030065805A1 (en) * | 2000-06-29 | 2003-04-03 | Barnes Melvin L. | System, method, and computer program product for providing location based services and mobile e-commerce |
| CN101042867A (en) * | 2006-03-24 | 2007-09-26 | 株式会社东芝 | Apparatus, method and computer program product for recognizing speech |
| CN101154379A (en) * | 2006-09-27 | 2008-04-02 | 夏普株式会社 | Method and device for locating keywords in voice and voice recognition system |
| CN101206673A (en) * | 2007-12-25 | 2008-06-25 | 北京科文书业信息技术有限公司 | Intelligent error correcting system and method in network searching process |
| CN101286161A (en) * | 2008-05-28 | 2008-10-15 | 华中科技大学 | Intelligent Chinese request-answering system based on concept |
| CN101334999A (en) * | 2008-07-10 | 2008-12-31 | 上海言海网络信息技术有限公司 | Chinese speech recognizing system and method thereof |
| CN101411592A (en) * | 2007-10-19 | 2009-04-22 | 深圳市壹声通语音科技有限公司 | Intelligent cooking apparatus with sound control recognition function |
| CN101630333A (en) * | 2008-07-18 | 2010-01-20 | 谷歌公司 | Transliteration for query expansion |
| CN101655837A (en) * | 2009-09-08 | 2010-02-24 | 北京邮电大学 | Method for detecting and correcting error on text after voice recognition |
| CN101840406A (en) * | 2009-03-20 | 2010-09-22 | 富士通株式会社 | Place name searching device and system |
| CN101916565A (en) * | 2010-06-24 | 2010-12-15 | 北京华安天诚科技有限公司 | Voice recognition method and voice recognition device in air traffic control system |
| CN102014199A (en) * | 2010-09-16 | 2011-04-13 | 宇龙计算机通信科技(深圳)有限公司 | Information display method and terminal |
| CN102214189A (en) * | 2010-04-09 | 2011-10-12 | 腾讯科技（深圳）有限公司 | Data mining-based word usage knowledge acquisition system and method |
| US8060366B1 (en) * | 2007-07-17 | 2011-11-15 | West Corporation | System, method, and computer-readable medium for verbal control of a conference call |
| CN102483757A (en) * | 2009-08-21 | 2012-05-30 | 米科·韦内宁 | Method and means for data searching and language translation |
| CN102543082A (en) * | 2012-01-19 | 2012-07-04 | 北京赛德斯汽车信息技术有限公司 | Voice operation method for in-vehicle information service system adopting natural language and voice operation system |
| CN102591932A (en) * | 2011-12-23 | 2012-07-18 | 优视科技有限公司 | Voice search method, voice search system, mobile terminal and transfer server |
| CN102592595A (en) * | 2012-03-19 | 2012-07-18 | 安徽科大讯飞信息科技股份有限公司 | Voice recognition method and system |
| CN102867276A (en) * | 2012-08-14 | 2013-01-09 | 俞琳 | Interactive control method based on electric power operational system |
| CN102968409A (en) * | 2012-11-23 | 2013-03-13 | 海信集团有限公司 | Intelligent human-machine interaction semantic analysis method and interaction system |
| CN103049548A (en) * | 2012-12-27 | 2013-04-17 | 安徽科大讯飞信息科技股份有限公司 | FAQ (frequently asked questions) recognition system and method for electronic channel application |
| CN103903619A (en) * | 2012-12-28 | 2014-07-02 | 安徽科大讯飞信息科技股份有限公司 | Method and system for improving accuracy of speech recognition |
| CN104090955A (en) * | 2014-07-07 | 2014-10-08 | 科大讯飞股份有限公司 | Automatic audio/video label labeling method and system |
| CN104166462A (en) * | 2013-05-17 | 2014-11-26 | 北京搜狗科技发展有限公司 | Input method and system for characters |
| CN104216906A (en) * | 2013-05-31 | 2014-12-17 | 大陆汽车投资（上海）有限公司 | Voice searching method and device |
| CN104463393A (en) * | 2013-09-17 | 2015-03-25 | 中国农业科学院农业信息研究所 | Speech-based agricultural product price collection method |
| CN104537101A (en) * | 2015-01-12 | 2015-04-22 | 杏树林信息技术(北京)有限公司 | Medical information search engine system and search method |
| CN104598527A (en) * | 2014-12-26 | 2015-05-06 | 盈世信息科技(北京)有限公司 | Voice search method and device |
| CN105279227A (en) * | 2015-09-11 | 2016-01-27 | 百度在线网络技术（北京）有限公司 | Voice search processing method and device of homonym |
| CN105869622A (en) * | 2015-01-21 | 2016-08-17 | 上海羽扇智信息科技有限公司 | Method and device for detecting Chinese hot words |
| CN106030699A (en) * | 2014-10-09 | 2016-10-12 | 谷歌公司 | Hotword detection on multiple devices |
| CN106062868A (en) * | 2014-07-25 | 2016-10-26 | 谷歌公司 | Providing pre-computed hotword models |
| CN106227714A (en) * | 2016-07-14 | 2016-12-14 | 北京百度网讯科技有限公司 | A kind of method and apparatus obtaining the key word generating poem based on artificial intelligence |
| CN106373564A (en) * | 2015-07-22 | 2017-02-01 | 谷歌公司 | Individualized hotword detection models |
| CN106681523A (en) * | 2015-11-06 | 2017-05-17 | 北京奇虎科技有限公司 | Library configuration method, library configuration device and call handling method of input method |
-
2017
- 2017-06-29 CN CN201710530374.8A patent/CN109213777A/en active Pending
Patent Citations (38)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1038555A (en) * | 1988-05-12 | 1990-01-03 | 西屋电气公司 | The Method and circuits that is used for the DC power supply voltage-regulation |
| CN1041660A (en) * | 1988-10-20 | 1990-04-25 | 长春邮电学院 | The input in Chinese device |
| US20030065805A1 (en) * | 2000-06-29 | 2003-04-03 | Barnes Melvin L. | System, method, and computer program product for providing location based services and mobile e-commerce |
| CN1352450A (en) * | 2000-11-15 | 2002-06-05 | 中国科学院自动化研究所 | Voice recognition method for Chinese personal name place name and unit name |
| CN101042867A (en) * | 2006-03-24 | 2007-09-26 | 株式会社东芝 | Apparatus, method and computer program product for recognizing speech |
| CN101154379A (en) * | 2006-09-27 | 2008-04-02 | 夏普株式会社 | Method and device for locating keywords in voice and voice recognition system |
| US8060366B1 (en) * | 2007-07-17 | 2011-11-15 | West Corporation | System, method, and computer-readable medium for verbal control of a conference call |
| CN101411592A (en) * | 2007-10-19 | 2009-04-22 | 深圳市壹声通语音科技有限公司 | Intelligent cooking apparatus with sound control recognition function |
| CN101206673A (en) * | 2007-12-25 | 2008-06-25 | 北京科文书业信息技术有限公司 | Intelligent error correcting system and method in network searching process |
| CN101286161A (en) * | 2008-05-28 | 2008-10-15 | 华中科技大学 | Intelligent Chinese request-answering system based on concept |
| CN101334999A (en) * | 2008-07-10 | 2008-12-31 | 上海言海网络信息技术有限公司 | Chinese speech recognizing system and method thereof |
| CN101630333A (en) * | 2008-07-18 | 2010-01-20 | 谷歌公司 | Transliteration for query expansion |
| CN101840406A (en) * | 2009-03-20 | 2010-09-22 | 富士通株式会社 | Place name searching device and system |
| CN102483757A (en) * | 2009-08-21 | 2012-05-30 | 米科·韦内宁 | Method and means for data searching and language translation |
| CN101655837A (en) * | 2009-09-08 | 2010-02-24 | 北京邮电大学 | Method for detecting and correcting error on text after voice recognition |
| CN102214189A (en) * | 2010-04-09 | 2011-10-12 | 腾讯科技（深圳）有限公司 | Data mining-based word usage knowledge acquisition system and method |
| CN101916565A (en) * | 2010-06-24 | 2010-12-15 | 北京华安天诚科技有限公司 | Voice recognition method and voice recognition device in air traffic control system |
| CN102014199A (en) * | 2010-09-16 | 2011-04-13 | 宇龙计算机通信科技(深圳)有限公司 | Information display method and terminal |
| CN102591932A (en) * | 2011-12-23 | 2012-07-18 | 优视科技有限公司 | Voice search method, voice search system, mobile terminal and transfer server |
| CN102543082A (en) * | 2012-01-19 | 2012-07-04 | 北京赛德斯汽车信息技术有限公司 | Voice operation method for in-vehicle information service system adopting natural language and voice operation system |
| CN102592595A (en) * | 2012-03-19 | 2012-07-18 | 安徽科大讯飞信息科技股份有限公司 | Voice recognition method and system |
| CN102867276A (en) * | 2012-08-14 | 2013-01-09 | 俞琳 | Interactive control method based on electric power operational system |
| CN102968409A (en) * | 2012-11-23 | 2013-03-13 | 海信集团有限公司 | Intelligent human-machine interaction semantic analysis method and interaction system |
| CN103049548A (en) * | 2012-12-27 | 2013-04-17 | 安徽科大讯飞信息科技股份有限公司 | FAQ (frequently asked questions) recognition system and method for electronic channel application |
| CN103903619A (en) * | 2012-12-28 | 2014-07-02 | 安徽科大讯飞信息科技股份有限公司 | Method and system for improving accuracy of speech recognition |
| CN104166462A (en) * | 2013-05-17 | 2014-11-26 | 北京搜狗科技发展有限公司 | Input method and system for characters |
| CN104216906A (en) * | 2013-05-31 | 2014-12-17 | 大陆汽车投资（上海）有限公司 | Voice searching method and device |
| CN104463393A (en) * | 2013-09-17 | 2015-03-25 | 中国农业科学院农业信息研究所 | Speech-based agricultural product price collection method |
| CN104090955A (en) * | 2014-07-07 | 2014-10-08 | 科大讯飞股份有限公司 | Automatic audio/video label labeling method and system |
| CN106062868A (en) * | 2014-07-25 | 2016-10-26 | 谷歌公司 | Providing pre-computed hotword models |
| CN106030699A (en) * | 2014-10-09 | 2016-10-12 | 谷歌公司 | Hotword detection on multiple devices |
| CN104598527A (en) * | 2014-12-26 | 2015-05-06 | 盈世信息科技(北京)有限公司 | Voice search method and device |
| CN104537101A (en) * | 2015-01-12 | 2015-04-22 | 杏树林信息技术(北京)有限公司 | Medical information search engine system and search method |
| CN105869622A (en) * | 2015-01-21 | 2016-08-17 | 上海羽扇智信息科技有限公司 | Method and device for detecting Chinese hot words |
| CN106373564A (en) * | 2015-07-22 | 2017-02-01 | 谷歌公司 | Individualized hotword detection models |
| CN105279227A (en) * | 2015-09-11 | 2016-01-27 | 百度在线网络技术（北京）有限公司 | Voice search processing method and device of homonym |
| CN106681523A (en) * | 2015-11-06 | 2017-05-17 | 北京奇虎科技有限公司 | Library configuration method, library configuration device and call handling method of input method |
| CN106227714A (en) * | 2016-07-14 | 2016-12-14 | 北京百度网讯科技有限公司 | A kind of method and apparatus obtaining the key word generating poem based on artificial intelligence |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111061857A (en) * | 2019-12-10 | 2020-04-24 | 珠海格力电器股份有限公司 | Menu generation method and device, electronic equipment and storage medium |
| CN112581954A (en) * | 2020-12-01 | 2021-03-30 | 杭州九阳小家电有限公司 | High-matching voice interaction method and intelligent equipment |
| CN112581954B (en) * | 2020-12-01 | 2023-08-04 | 杭州九阳小家电有限公司 | High-matching voice interaction method and intelligent device |
| CN113490011A (en) * | 2021-08-20 | 2021-10-08 | 云知声（上海）智能科技有限公司 | Atmosphere backing system and method based on ASR live broadcast room |
| TWI785959B (en) * | 2022-01-08 | 2022-12-01 | 長庚大學 | Food recording system and operation method thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109213777A (en) | A kind of voice-based recipe processing method and system | |
| KR102125348B1 (en) | Auto-reply methods, devices, equipment, and computer-readable storage media | |
| CN110059173A (en) | A kind of intelligent kitchen question and answer assistant system of knowledge based map | |
| CN104199897B (en) | To the method and device for downloading file identification, saving and quickly searching | |
| CN106407178B (en) | A kind of session abstraction generating method, device, server apparatus and terminal device | |
| CN107705834A (en) | A kind of dietary recommendations continued system based on Recognition with Recurrent Neural Network | |
| CN108388553B (en) | Method for eliminating ambiguity in conversation, electronic equipment and kitchen-oriented conversation system | |
| KR20180115769A (en) | Microwave oven voice control method and microwave oven | |
| JP7289330B2 (en) | Novel category tag mining method and apparatus, electronic device, computer readable medium, and computer program product | |
| EP2682880A1 (en) | Set-expansion device, set-expansion method, program, and non-transitory storage medium | |
| KR101874604B1 (en) | Method for generating creation recipe | |
| CN104239442B (en) | Search result shows method and apparatus | |
| CN109683516A (en) | Auxiliary cooking method, household appliance and computer storage medium | |
| CN107870581A (en) | Cooking control method and cooking equipment | |
| CN105898525A (en) | Method of searching videos in specific video database, and video terminal thereof | |
| WO2017070011A1 (en) | Determining image captions | |
| CN110428829A (en) | The method and device of cloud voice control cooking robot | |
| CN109918619A (en) | A kind of pronunciation mask method and device based on basic dictionary mark | |
| CN114155853A (en) | Rejection method, device, equipment and storage medium | |
| CN109615009A (en) | A kind of learning Content recommended method and electronic equipment | |
| CN108922522A (en) | Control method, device, storage medium and the electronic device of equipment | |
| CN109767767A (en) | A kind of voice interactive method, system, electronic equipment and storage medium | |
| CN109446915A (en) | A kind of dish information generation method, device and electronic equipment | |
| CN107196979A (en) | Pre- system for prompting of calling out the numbers based on speech recognition | |
| US20210264493A1 (en) | Item curation with ingredient-based lens |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20190312 Address after: 310018 No. 760 Yinhai Street, Xiasha Street, Hangzhou Economic and Technological Development Zone, Zhejiang Province Applicant after: HANGZHOU JOYOUNG ONONDO ELECTRIC APPLIANCES, LTD. Address before: 310018, No. 52, No. 22, Poplar Street, Hangzhou economic and Technological Development Zone, Zhejiang Applicant before: HANGZHOU JIUYANG HOUSEHOLD ELECTRICAL APPLIANCES CO.,LTD. |
|
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 310018 No. 760 Yinhai Street, Xiasha Street, Hangzhou Economic and Technological Development Zone, Zhejiang Province Applicant after: HANGZHOU JIUYANG HOUSEHOLD ELECTRICAL APPLIANCES CO.,LTD. Address before: 310018 No. 760 Yinhai Street, Xiasha Street, Hangzhou Economic and Technological Development Zone, Zhejiang Province Applicant before: HANGZHOU JOYOUNG ONONDO ELECTRIC APPLIANCES, LTD. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190115 |