CN110298770A - A kind of recipe recommendation system - Google Patents
A kind of recipe recommendation system Download PDFInfo
- Publication number
- CN110298770A CN110298770A CN201910559264.3A CN201910559264A CN110298770A CN 110298770 A CN110298770 A CN 110298770A CN 201910559264 A CN201910559264 A CN 201910559264A CN 110298770 A CN110298770 A CN 110298770A
- Authority
- CN
- China
- Prior art keywords
- user
- module
- cloud
- voice
- terminal
- 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
- 230000002452 interceptive effect Effects 0.000 claims abstract description 27
- 238000013507 mapping Methods 0.000 claims abstract description 24
- 235000006694 eating habits Nutrition 0.000 claims abstract description 21
- 230000007474 system interaction Effects 0.000 claims abstract description 7
- 235000005911 diet Nutrition 0.000 claims abstract description 5
- 230000037213 diet Effects 0.000 claims abstract description 5
- 238000000034 method Methods 0.000 claims description 46
- 230000003993 interaction Effects 0.000 claims description 32
- 230000015572 biosynthetic process Effects 0.000 claims description 11
- 238000003786 synthesis reaction Methods 0.000 claims description 11
- 238000005516 engineering process Methods 0.000 claims description 8
- 238000001914 filtration Methods 0.000 claims description 6
- 230000001755 vocal effect Effects 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 3
- 239000000523 sample Substances 0.000 claims description 3
- 235000021139 traditional diet Nutrition 0.000 claims description 3
- 238000009472 formulation Methods 0.000 claims description 2
- 239000000203 mixture Substances 0.000 claims description 2
- 238000001228 spectrum Methods 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 2
- 235000013305 food Nutrition 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 238000010411 cooking Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/9032—Query formulation
- G06F16/90332—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/12—Hotels or restaurants
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
-
- 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
- G10L2015/223—Execution procedure of a spoken command
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- Mathematical Physics (AREA)
- General Health & Medical Sciences (AREA)
- Computer Networks & Wireless Communication (AREA)
- Marketing (AREA)
- Signal Processing (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of recipe recommendation system, which includes user session interactive module, is engaged in the dialogue input and feedback for user and system；User identification module, for identification user identity；User's eating habit module, for acquiring its diet hobby relevant historical information during user is to system interaction；More wheel question and answer modules, for more wheel interactive voices between user and system, to obtain user's true intention；Menu knowledge mapping module, for being retrieved in knowledge mapping according to user's true intention.The present invention is by user identity identification, after the intentions for more taking turns the clear users of interactive voice, likes data and knowledge engine according to user's history and provides recipe recommendation for user.
Description
Technical field
The present invention relates to intelligent terminal technical field more particularly to a kind of recipe recommendation systems.
Background technique
With the development of Internet of Things, sensor, artificial intelligence technology, calculates mode (i.e. the relationship of people and computer) and occur
Profound change, from previous Framework computing mode, PC mode, the common calculating model for developing to today；Intelligent terminal towards
Developed based on personalized service direction connecting extensively, focusing on people, this personalized service is substantially a kind of interaction
Natural personalization system.And as the intelligent terminal refrigerator of recipe recommendation for, static food is only provided from cloud at present
Modal data is shown on refrigerator screen, and this kind of system has the following problems:
(1) user is interacted with touch screen, not enough naturally；Two hands are not empty during the cooking process by usual user；
(2) it cannot identify user identity, therefore can not achieve personalized recommendation；
(3) there is no user's history data, therefore recommended based on user's history hobby；
(4) lack knowledge base, only shown with static data, the retrieval and matching more by intelligence can not be provided.
So existing interaction is unnatural for users, service is not smart enough for the prior art, such as cannot be according to user
Identity does personalized service, is unable to the problems such as user's history hobby does the support for recommending, lacking knowledge base.
Summary of the invention
In view of the above-mentioned problems, recipe recommendation process is handed on intelligent terminal the invention proposes a kind of recipe recommendation system
Mutual naturality, intelligence.Pass through the multi-module interactives such as natural language, text, user identity identification, personalized recommendation, knowledge
The technologies such as map solve natural interaction and level of intelligence two large problems.So as to change traditional intelligence terminal (such as refrigerator)
There is no cloud brain, and the stiff image of tradition without natural interaction；Can according to user identity, historical custom, knowledge engine into
Row personalization recipe recommendation, and can be using multi-modal interactions such as natural language, texts, experience is more intuitive friendly；To
The level of interaction and intelligence degree of intelligent terminal are really improved, enhancing user recommends menu on the intelligent terminals such as refrigerator
Usage experience and viscosity.
The present invention through the following technical solutions to achieve the above objectives:
A kind of recipe recommendation system, including,
User session interactive module engages in the dialogue input and feedback for user and system；
User identification module, for identification user identity；
User's eating habit module, for acquiring its diet hobby relevant history letter during user is to system interaction
Breath；
More wheel question and answer modules, for more wheel interactive voices between user and system, to obtain user's true intention；
Menu knowledge mapping module, for being retrieved in knowledge mapping according to user's true intention.
Further scheme is the user session interactive module, including user's input and system feedback, talks with interactive side
Method includes voice dialogue interaction, text conversation interaction.
Wherein, the system feedback includes the speech synthesis feedback of fixed people, specific to the voice feedback of user.
Further scheme is the user identification module, and the method for identifying user identity includes Application on Voiceprint Recognition, face
Identification, voice and semantics recognition, text semantic identification.
Wherein, the vocal print is identified including clustering method, non-cluster method；And the prior voice enrollment status of user and
Without the mode of user's registration in advance identity.
Further scheme is user's eating habit module, and the method for obtaining user's eating habit includes that user is based on
Implicit feedback, system obtained from the explicit formulation input of text or voice, system are carried out according to user's operation are recorded according to traditional custom
The public preference information entered；Recommended method includes but is not limited to the recommendation liked based on user's history, is based on special red-letter day and spy
The recommendation of timing section, the recommendation based on locality, the collaborative filtering recommending based on user, the collaborative filtering based on article push away
It recommends.
Wherein, implicit feedback obtained from system is carried out according to user's operation includes that user is clear on the menu that screen is shown
Look at number and duration, number of clicks, the information of stay time；System includes according to the public preference information of traditional custom typing
Section, holiday catering customs information, the eating habit information of special time period, the traditional diet information of given area.
Further scheme is that more wheel question and answer modules use the conversational mode of user session interactive module；More wheel question and answer
Session method include multi-user conversation, single user session；The inquiry modes of more wheel question and answer include: that user puts question to, system is into one
Step probe into the matter and to user propose new problem or system proposed according to user's eating habit module to user suggestion, user
The problem of proposing to system suggests answer；Interaction times can be one or many between system and user；More wheels are asked
The question sentence understanding method for answering module includes semantic understanding or question sentence understanding method.
Further scheme is menu knowledge mapping module, and the construction method of menu knowledge mapping includes relational database, figure
Database；The search matching method of menu knowledge mapping includes: that the retrieval based on relational database matches, based on chart database
Search matching method.
Another aspect of the present invention provides the personalized recipe recommendation system based on refrigerator and interactive voice, system architecture point
For cloud system and terminal system:
In cloud system, all interactions between system and user are realized using natural language interaction module, wherein using
To speech recognition, semantic analysis, intention assessment and speech synthesis technique；
After cloud receives the voice data for carrying out self terminal, user is judged using the sound groove recognition technology in e based on cluster
Identity is not necessarily to customer identity registration；User and system can carry out take turns more and interact, and realized more, walked by taking turns question and answer module
Suddenly are as follows:
(1) the problem of user proposes oneself；
(2) demand of the system to user carries out suggestion or inquires to unclear aspect to user；
(3) suggestion or problem that user proposes system respond；Recommendation root of the systems taken turns in question and answer to user more
Recommend according to user's eating habit module；
Indicate that user is clearly intended to question sentence and then by knowledge mapping module in recipe knowledge mapping when system is got
Middle progress question sentence match query, to obtain the answer that user wants；Cloud service is by the API of REST style come to refrigerator end
End provides access interface；
In terminal system, voice is acquired by microphone array, waits user's input to reduce refrigerator terminal system
When system consumption, user start interaction before waken up with keyword, the time not waken up takes all in dormant state, refrigerator
The voice feedback for obtaining cloud plays to user by speaker system, and an executive program is arranged to realize in entire terminal system
With the interaction in cloud, user；Necessary wake-up algorithm and control logic are realized in terminal；
System interaction process is as follows:
Step 1: in terminal, intelligent refrigerator being waken up by keyword, microphone array is then begun to use to capture user's language
Sound；
Step 2: in terminal, once user speech is detected by the application program on intelligent refrigerator, which will
It is sent to cloud；
Step 3: beyond the clouds, voiceprint identification module operation, and the vocal print spy that cluster obtains is first passed through based on cloud backstage in advance
Identification is compared in sign library, to obtain user identity；
Step 4: cloud is represented using voice data is obtained by speech recognition, semantic analysis, domain analysis technology
The question sentence that user is intended to, is transferred to step 7 if the intention of user is very clear, is otherwise transferred to step 5；
Step 5: cloud text and the user's eating habit data constructed in advance according to the user's intention are generated to user's
It is recommended that generate and further to inquire the text of user, and issue refrigerator terminal, terminal returns to use by the voice of synthesis
Family；
Step 6: the suggestion or requirement that user proposes system respond, and are then transferred to step 4 and carry out user and are intended to point
Analysis；
Step 7: text carries out semantic retrieval, acquisition with the recipe knowledge mapping constructed in advance according to the user's intention in cloud
The recommendation results about recipe that user needs, cloud record customer interaction information and recommendation results and are accustomed to as user's history
Data, and recommendation results text or picture are returned to refrigerator terminal；
Step 8. refrigerator terminal embodies recommendation results to use in such a way that speech synthesis, text importing, image are shown
Family.
The beneficial effects of the present invention are:
The natural human-machine interaction based on language may be implemented in the present invention, can be carried out in interactive process with the voice of analog subscriber
Dialogue,
User read activate word when and in interactive process can the user that currently interacts of real-time judge, and can be with
It saves and switches different user sessions, and do not need user and realize enrollment status and phonetic feature.
When user query correlation menu, refrigerator can carry out more wheel interactions, refrigerator meeting in interactive process to user
Recommendation appropriate is done to user according to user's history preference information, is finally collected into the accurate intention of user；It then can basis
These problems knowledge based map provides accurate answer.
In the interactive process that user inquires menu, refrigerator can be liked according to the history of user, red-letter day is traditional, like phase
As other people hobby and similar food product menu recommendation.
Detailed description of the invention
It to describe the technical solutions in the embodiments of the present invention more clearly, below will be to embodiment or description of the prior art
In required practical attached drawing be briefly described, it should be apparent that, the accompanying drawings in the following description is only the one of the present embodiment
A little embodiments for those of ordinary skill in the art without creative efforts, can also be according to these
Attached drawing obtains other attached drawings.
Fig. 1 is present system block diagram；
Fig. 2 is the personalized recipe recommendation system block diagram the present invention is based on refrigerator and interactive voice.
Specific embodiment
To make the object, technical solutions and advantages of the present invention clearer, technical solution of the present invention will be carried out below
Detailed description.Obviously, the described embodiment is only a part of the embodiment of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, those of ordinary skill in the art without making creative work it is obtained it is all its
Its embodiment belongs to the range that the present invention is protected.
In any embodiment, as shown in Figure 1, a kind of recipe recommendation system of the invention, including,
User session interactive module engages in the dialogue input and feedback for user and system；
User identification module, for identification user identity；
User's eating habit module, for acquiring its diet hobby relevant history letter during user is to system interaction
Breath；
More wheel question and answer modules, for more wheel interactive voices between user and system, to obtain user's true intention；
Menu knowledge mapping module, for being retrieved in knowledge mapping according to user's true intention.
The user session interactive module, including user's input and system feedback, talking with interactive method includes voice pair
Words interaction, text conversation interaction.
Wherein, the system feedback includes the speech synthesis feedback of fixed people, specific to the voice feedback of user.
The user identification module, the method for identifying user identity include Application on Voiceprint Recognition, recognition of face, voice and language
Justice identification, text semantic identification.
Wherein, the vocal print is identified including clustering method, non-cluster method；And the prior voice enrollment status of user and
Without the mode of user's registration in advance identity.
User's eating habit module, it is aobvious based on text or voice that the method for obtaining user's eating habit includes user
Implicit feedback obtained from formula input, system are carried out according to user's operation, system are believed according to the public hobby of traditional custom typing
Breath；Recommended method includes but is not limited to the recommendation liked based on user's history, the recommendation based on special red-letter day and specific time period, base
Recommendation in locality, the collaborative filtering recommending based on user, the collaborative filtering recommending based on article.
Wherein, implicit feedback obtained from system is carried out according to user's operation includes that user is clear on the menu that screen is shown
Look at number and duration, number of clicks, the information of stay time；System includes according to the public preference information of traditional custom typing
Section, holiday catering customs information, the eating habit information of special time period, the traditional diet information of given area.
More wheel question and answer modules use the conversational mode of user session interactive module；The session methods of more wheel question and answer include
Multi-user conversation, single user session；The inquiry modes of more wheel question and answer include: that user puts question to, system further probes into the matter and to
The new problem or the suggestion that is proposed according to user's eating habit module to user of system, user that user proposes ask system proposition
Topic suggests answer；Interaction times can be one or many between system and user；The question sentence reason of more wheel question and answer modules
Solution method includes semantic understanding or question sentence understanding method.
Menu knowledge mapping module, the construction method of menu knowledge mapping include relational database, chart database；Menu is known
The search matching method for knowing map includes: the retrieval matching based on relational database, the search matching method based on chart database.
In a specific embodiment, as shown in Fig. 2, the personalized recipe of the invention based on refrigerator and interactive voice pushes away
System is recommended, system architecture is divided into cloud system and terminal system:
In cloud system, all interactions between system and user are realized using natural language interaction module, wherein using
To speech recognition, semantic analysis, intention assessment and speech synthesis technique；
After cloud receives the voice data for carrying out self terminal, user is judged using the sound groove recognition technology in e based on cluster
Identity is not necessarily to customer identity registration；User and system can carry out take turns more and interact, and realized more, walked by taking turns question and answer module
Suddenly are as follows:
(1) the problem of user proposes oneself；
(2) demand of the system to user carries out suggestion or inquires to unclear aspect to user；
(3) suggestion or problem that user proposes system respond；Recommendation root of the systems taken turns in question and answer to user more
Recommend according to user's eating habit module；
Indicate that user is clearly intended to question sentence and then by knowledge mapping module in recipe knowledge mapping when system is got
Middle progress question sentence match query, to obtain the answer that user wants；Cloud service is by the API of REST style come to refrigerator end
End provides access interface；
In terminal system, voice is acquired by microphone array, waits user's input to reduce refrigerator terminal system
When system consumption, user start interaction before waken up with keyword, the time not waken up takes all in dormant state, refrigerator
The voice feedback for obtaining cloud plays to user by speaker system, and an executive program is arranged to realize in entire terminal system
With the interaction in cloud, user；Necessary wake-up algorithm and control logic are realized in terminal；
System interaction process is as follows:
Step 1: in terminal, intelligent refrigerator being waken up by keyword, microphone array is then begun to use to capture user's language
Sound；
Step 2: in terminal, once user speech is detected by the application program on intelligent refrigerator, which will
It is sent to cloud；
Step 3: beyond the clouds, voiceprint identification module operation, and the vocal print spy that cluster obtains is first passed through based on cloud backstage in advance
Identification is compared in sign library, to obtain user identity；
Step 4: cloud is represented using voice data is obtained by speech recognition, semantic analysis, domain analysis technology
The question sentence that user is intended to, is transferred to step 7 if the intention of user is very clear, is otherwise transferred to step 5；
Step 5: cloud text and the user's eating habit data constructed in advance according to the user's intention are generated to user's
It is recommended that generate and further to inquire the text of user, and issue refrigerator terminal, terminal returns to use by the voice of synthesis
Family；
Step 6: the suggestion or requirement that user proposes system respond, and are then transferred to step 4 and carry out user and are intended to point
Analysis；
Step 7: text carries out semantic retrieval, acquisition with the recipe knowledge mapping constructed in advance according to the user's intention in cloud
The recommendation results about recipe that user needs, cloud record customer interaction information and recommendation results and are accustomed to as user's history
Data, and recommendation results text or picture are returned to refrigerator terminal；
Step 8. refrigerator terminal embodies recommendation results to use in such a way that speech synthesis, text importing, image are shown
Family.
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any
Those familiar with the art in the technical scope disclosed by the present invention, can easily think of the change or the replacement, and should all contain
Lid is within protection scope of the present invention.Specific technical features described in the above specific embodiments, in not lance
In the case where shield, can be combined in any appropriate way, in order to avoid unnecessary repetition, the present invention to it is various can
No further explanation will be given for the combination of energy.Various embodiments of the present invention can be combined randomly, only
Want it without prejudice to thought of the invention, it should also be regarded as the disclosure of the present invention.
Claims (10)
1. a kind of recipe recommendation system, which is characterized in that including,
User session interactive module engages in the dialogue input and feedback for user and system；
User identification module, for identification user identity；
User's eating habit module, for acquiring its diet hobby relevant historical information during user is to system interaction；
More wheel question and answer modules, for more wheel interactive voices between user and system, to obtain user's true intention；
Menu knowledge mapping module, for being retrieved in knowledge mapping according to user's true intention.
2. a kind of recipe recommendation system as described in claim 1, which is characterized in that the user session interactive module, including with
Family input and system feedback, talking with interactive method includes voice dialogue interaction, text conversation interaction.
3. a kind of recipe recommendation system as claimed in claim 2, which is characterized in that the system feedback includes the voice of fixed people
Synthesis feedback, specific to the voice feedback of user.
4. a kind of recipe recommendation system as described in claim 1, which is characterized in that the user identification module, identification are used
The method of family identity includes Application on Voiceprint Recognition, recognition of face, voice and semantics recognition, text semantic identification.
5. a kind of recipe recommendation system as claimed in claim 4, which is characterized in that the vocal print come identify including clustering method,
Non-cluster method；And the prior voice enrollment status of user and the mode without user's registration in advance identity.
6. a kind of recipe recommendation system as described in claim 1, which is characterized in that user's eating habit module is obtained and used
The method of family eating habit includes obtained from explicit formulation input of the user based on text or voice, system are carried out according to user's operation
Implicit feedback, system are according to the public preference information of traditional custom typing；Recommended method includes but is not limited to be based on user's history
The recommendation of hobby, the recommendation based on special red-letter day and specific time period, the recommendation based on locality, the collaborative filtering based on user
Recommend, the collaborative filtering recommending based on article.
7. a kind of recipe recommendation system as claimed in claim 6, which is characterized in that obtained from system is carried out according to user's operation
Implicit feedback includes user's browsing time and duration, number of clicks, information of stay time on the menu that screen is shown；System
Public preference information according to traditional custom typing includes section, holiday catering customs information, the eating habit of special time period letter
It ceases, the traditional diet information of given area.
8. a kind of recipe recommendation system as described in claim 1, which is characterized in that more wheel question and answer modules use user session
The conversational mode of interactive module；The session method of more wheel question and answer includes multi-user conversation, single user session；The inquiry of more wheel question and answer
Mode includes: that user puts question to, system further probes into the matter and is practised to the new problem of user's proposition or system according to user's diet
The problem of suggestion that used module is proposed to user, user propose system or suggestion answer；Interaction between system and user
Wheel number can be one or many；The question sentence understanding method of more wheel question and answer modules includes semantic understanding or question sentence understanding method.
9. a kind of recipe recommendation system as described in claim 1, which is characterized in that menu knowledge mapping module, menu knowledge graph
The construction method of spectrum includes relational database, chart database；The search matching method of menu knowledge mapping includes: based on relationship number
According to the retrieval matching in library, the search matching method based on chart database.
10. the personalized recipe recommendation system based on refrigerator and interactive voice, which is characterized in that system architecture is divided into cloud system
And terminal system:
In cloud system, all interactions between system and user are realized using natural language interaction module, wherein using language
Sound identification, semantic analysis, intention assessment and speech synthesis technique；
After cloud receives the voice data for carrying out self terminal, user's body is judged using the sound groove recognition technology in e based on cluster
Part, it is not necessarily to customer identity registration；User and system can carry out take turns more and interact, and realized by taking turns question and answer module, step more
Are as follows:
(1) the problem of user proposes oneself；
(2) demand of the system to user carries out suggestion or inquires to unclear aspect to user；
(3) suggestion or problem that user proposes system respond；Systems in more wheel question and answer to user recommendation according to
Family eating habit module is recommended；
When system get indicate user is clearly intended to question sentence and then pass through knowledge mapping module in recipe knowledge mapping into
Row question sentence match query, to obtain the answer that user wants；Cloud service mentions refrigerator terminal by the API of REST style
For access interface；
In terminal system, voice is acquired by microphone array, in order to reduce when refrigerator terminal system waits user to input
System consumption, user start to be waken up before interaction with keyword, and the time not waken up obtains cloud all in dormant state, refrigerator
The voice feedback at end plays to user by speaker system, and one executive program of setting is realized and cloud in entire terminal system
The interaction at end, user；Necessary wake-up algorithm and control logic are realized in terminal；
System interaction process is as follows:
Step 1: in terminal, intelligent refrigerator being waken up by keyword, microphone array is then begun to use to capture user speech；
Step 2: in terminal, once user speech is detected by the application program on intelligent refrigerator, which will be sent out
It is sent to cloud；
Step 3: beyond the clouds, voiceprint identification module operation, and the vocal print feature library that cluster obtains is first passed through based on cloud backstage in advance
Identification is compared, to obtain user identity；
Step 4: cloud represents user using voice data is obtained, by speech recognition, semantic analysis, the acquisition of domain analysis technology
The question sentence of intention is transferred to step 7 if the intention of user is very clear, is otherwise transferred to step 5；
Step 5: cloud text and the user's eating habit data constructed in advance according to the user's intention are generated to the suggestion of user
Or the text that further inquire user being generated, and issue refrigerator terminal, terminal returns to user by the voice synthesized；
Step 6: the suggestion or requirement that user proposes system respond, and are then transferred to step 4 and carry out user and are intended to analysis；
Step 7: text carries out semantic retrieval, acquisition user with the recipe knowledge mapping constructed in advance according to the user's intention in cloud
The recommendation results about recipe needed, cloud record customer interaction information and recommendation results as user's history and are accustomed to number
According to, and recommendation results text or picture are returned to refrigerator terminal；
Step 8. refrigerator terminal embodies recommendation results to user in such a way that speech synthesis, text importing, image are shown.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910559264.3A CN110298770A (en) | 2019-06-25 | 2019-06-25 | A kind of recipe recommendation system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910559264.3A CN110298770A (en) | 2019-06-25 | 2019-06-25 | A kind of recipe recommendation system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110298770A true CN110298770A (en) | 2019-10-01 |
Family
ID=68028862
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910559264.3A Pending CN110298770A (en) | 2019-06-25 | 2019-06-25 | A kind of recipe recommendation system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110298770A (en) |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110727778A (en) * | 2019-10-15 | 2020-01-24 | 大连中河科技有限公司 | Intelligent question-answering system for tax affairs |
| CN110992948A (en) * | 2019-11-18 | 2020-04-10 | 上海博泰悦臻电子设备制造有限公司 | Restaurant reservation method and terminal based on multiple rounds of voice interaction |
| CN111125309A (en) * | 2019-12-23 | 2020-05-08 | 中电云脑(天津)科技有限公司 | Natural language processing method and device, computing equipment and storage medium |
| CN111159539A (en) * | 2019-12-09 | 2020-05-15 | 中国科学院计算技术研究所 | Food recommendation method and system based on multi-modal information correlation analysis |
| CN111241292A (en) * | 2019-12-27 | 2020-06-05 | 珠海格力电器股份有限公司 | Menu recommendation method and device, electronic equipment and storage medium |
| CN111625699A (en) * | 2020-04-02 | 2020-09-04 | 南京邮电大学 | Internet weak credible data verification method based on intelligent outbound |
| CN112288531A (en) * | 2020-10-30 | 2021-01-29 | 广州富港万嘉智能科技有限公司 | Recommended dish generation method, computer-readable storage medium, intelligent cooking equipment and server |
| CN112418996A (en) * | 2020-11-30 | 2021-02-26 | 珠海采筑电子商务有限公司 | Recommendation method and system for elevator suppliers |
| CN112765398A (en) * | 2021-01-04 | 2021-05-07 | 珠海格力电器股份有限公司 | Information recommendation method and device and storage medium |
| CN112883170A (en) * | 2021-01-20 | 2021-06-01 | 中国人民大学 | User feedback guided self-adaptive conversation recommendation method and system |
| CN113377943A (en) * | 2021-08-16 | 2021-09-10 | 中航信移动科技有限公司 | Multi-round intelligent question-answering data processing system |
| CN113395262A (en) * | 2021-05-24 | 2021-09-14 | 杭州电子科技大学 | Multi-terminal information sharing method and device, computer equipment and storage medium |
| CN113763123A (en) * | 2021-08-12 | 2021-12-07 | 阿里巴巴（中国）有限公司 | Commodity recommendation and search method, commodity recommendation and search equipment and storage medium |
| CN113808589A (en) * | 2020-06-15 | 2021-12-17 | 中兴通讯股份有限公司 | Agent call method, computer device, and storage medium |
| CN115129967A (en) * | 2021-03-25 | 2022-09-30 | 佛山市顺德区美的电热电器制造有限公司 | Menu recommendation method, menu recommendation device, storage medium and electronic equipment |
| CN115292543A (en) * | 2022-10-10 | 2022-11-04 | 深圳市人马互动科技有限公司 | Data processing method based on voice interaction novel and related product |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105426436A (en) * | 2015-11-05 | 2016-03-23 | 百度在线网络技术（北京）有限公司 | Artificial intelligent robot based information provision method and apparatus |
| US9721008B1 (en) * | 2016-06-09 | 2017-08-01 | International Business Machines Corporation | Recipe generation utilizing natural language processing |
| CN107247736A (en) * | 2017-05-08 | 2017-10-13 | 广州索答信息科技有限公司 | The kitchen field answering method and system of a kind of knowledge based collection of illustrative plates |
| WO2019051847A1 (en) * | 2017-09-18 | 2019-03-21 | Microsoft Technology Licensing, Llc | Providing diet assistance in a session |
| CN109524011A (en) * | 2018-10-22 | 2019-03-26 | 四川虹美智能科技有限公司 | A kind of refrigerator awakening method and device based on Application on Voiceprint Recognition |
-
2019
- 2019-06-25 CN CN201910559264.3A patent/CN110298770A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105426436A (en) * | 2015-11-05 | 2016-03-23 | 百度在线网络技术（北京）有限公司 | Artificial intelligent robot based information provision method and apparatus |
| US9721008B1 (en) * | 2016-06-09 | 2017-08-01 | International Business Machines Corporation | Recipe generation utilizing natural language processing |
| CN107247736A (en) * | 2017-05-08 | 2017-10-13 | 广州索答信息科技有限公司 | The kitchen field answering method and system of a kind of knowledge based collection of illustrative plates |
| WO2019051847A1 (en) * | 2017-09-18 | 2019-03-21 | Microsoft Technology Licensing, Llc | Providing diet assistance in a session |
| CN109524011A (en) * | 2018-10-22 | 2019-03-26 | 四川虹美智能科技有限公司 | A kind of refrigerator awakening method and device based on Application on Voiceprint Recognition |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110727778A (en) * | 2019-10-15 | 2020-01-24 | 大连中河科技有限公司 | Intelligent question-answering system for tax affairs |
| CN110992948A (en) * | 2019-11-18 | 2020-04-10 | 上海博泰悦臻电子设备制造有限公司 | Restaurant reservation method and terminal based on multiple rounds of voice interaction |
| CN110992948B (en) * | 2019-11-18 | 2023-07-25 | 博泰车联网科技(上海)股份有限公司 | Restaurant reservation method and terminal based on multi-round voice interaction |
| CN111159539B (en) * | 2019-12-09 | 2023-09-22 | 中国科学院计算技术研究所 | Food recommendation method and system based on multi-mode information association analysis |
| CN111159539A (en) * | 2019-12-09 | 2020-05-15 | 中国科学院计算技术研究所 | Food recommendation method and system based on multi-modal information correlation analysis |
| CN111125309A (en) * | 2019-12-23 | 2020-05-08 | 中电云脑(天津)科技有限公司 | Natural language processing method and device, computing equipment and storage medium |
| CN111241292A (en) * | 2019-12-27 | 2020-06-05 | 珠海格力电器股份有限公司 | Menu recommendation method and device, electronic equipment and storage medium |
| CN111625699A (en) * | 2020-04-02 | 2020-09-04 | 南京邮电大学 | Internet weak credible data verification method based on intelligent outbound |
| CN113808589A (en) * | 2020-06-15 | 2021-12-17 | 中兴通讯股份有限公司 | Agent call method, computer device, and storage medium |
| CN112288531A (en) * | 2020-10-30 | 2021-01-29 | 广州富港万嘉智能科技有限公司 | Recommended dish generation method, computer-readable storage medium, intelligent cooking equipment and server |
| CN112418996A (en) * | 2020-11-30 | 2021-02-26 | 珠海采筑电子商务有限公司 | Recommendation method and system for elevator suppliers |
| CN112765398A (en) * | 2021-01-04 | 2021-05-07 | 珠海格力电器股份有限公司 | Information recommendation method and device and storage medium |
| CN112883170A (en) * | 2021-01-20 | 2021-06-01 | 中国人民大学 | User feedback guided self-adaptive conversation recommendation method and system |
| CN112883170B (en) * | 2021-01-20 | 2023-08-18 | 中国人民大学 | User feedback guided self-adaptive dialogue recommendation method and system |
| CN115129967A (en) * | 2021-03-25 | 2022-09-30 | 佛山市顺德区美的电热电器制造有限公司 | Menu recommendation method, menu recommendation device, storage medium and electronic equipment |
| CN113395262A (en) * | 2021-05-24 | 2021-09-14 | 杭州电子科技大学 | Multi-terminal information sharing method and device, computer equipment and storage medium |
| CN113763123A (en) * | 2021-08-12 | 2021-12-07 | 阿里巴巴（中国）有限公司 | Commodity recommendation and search method, commodity recommendation and search equipment and storage medium |
| CN113377943B (en) * | 2021-08-16 | 2022-03-25 | 中航信移动科技有限公司 | Multi-round intelligent question-answering data processing system |
| CN113377943A (en) * | 2021-08-16 | 2021-09-10 | 中航信移动科技有限公司 | Multi-round intelligent question-answering data processing system |
| CN115292543A (en) * | 2022-10-10 | 2022-11-04 | 深圳市人马互动科技有限公司 | Data processing method based on voice interaction novel and related product |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110298770A (en) | A kind of recipe recommendation system | |
| JP7418526B2 (en) | Dynamic and/or context-specific hotwords to trigger automated assistants | |
| US20210081056A1 (en) | Vpa with integrated object recognition and facial expression recognition | |
| US10977452B2 (en) | Multi-lingual virtual personal assistant | |
| CN111459290B (en) | Interactive intention determining method and device, computer equipment and storage medium | |
| US11289100B2 (en) | Selective enrollment with an automated assistant | |
| US11100922B1 (en) | System and methods for triggering sequences of operations based on voice commands | |
| CN105895087B (en) | Voice recognition method and device | |
| CN114207710A (en) | Detecting and/or registering a thermal command to trigger a response action by an automated assistant | |
| US20220246140A1 (en) | Dynamic and/or context-specific hot words to invoke automated assistant | |
| KR102420564B1 (en) | Method and device for providing information | |
| US9213558B2 (en) | Method and apparatus for tailoring the output of an intelligent automated assistant to a user | |
| US9786281B1 (en) | Household agent learning | |
| CN114041283A (en) | Automated assistant engaged with pre-event and post-event input streams | |
| EP3259754B1 (en) | Method and device for providing information | |
| CN109189980A (en) | The method and electronic equipment of interactive voice are carried out with user | |
| CN110110169A (en) | Man-machine interaction method and human-computer interaction device | |
| US10672379B1 (en) | Systems and methods for selecting a recipient device for communications | |
| US20090150341A1 (en) | Generation of alternative phrasings for short descriptions | |
| CN117235354A (en) | User personalized service strategy and system based on multi-mode large model | |
| GB2583887A (en) | Intelligent automated personal assistant for recipe selection | |
| US12094454B2 (en) | Multimodal intent understanding for automated assistant | |
| CN111198733A (en) | Startup picture display method, terminal device and storage medium | |
| US20220036887A1 (en) | Information processing device, information processing method, and program | |
| CN118301237A (en) | Intelligent assistant control method, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191001 |
|
| RJ01 | Rejection of invention patent application after publication |