CN108111491A - A kind of cell phone application voice storage management system based on artificial intelligence - Google Patents
A kind of cell phone application voice storage management system based on artificial intelligence Download PDFInfo
- Publication number
- CN108111491A CN108111491A CN201711288501.4A CN201711288501A CN108111491A CN 108111491 A CN108111491 A CN 108111491A CN 201711288501 A CN201711288501 A CN 201711288501A CN 108111491 A CN108111491 A CN 108111491A
- Authority
- CN
- China
- Prior art keywords
- data
- user
- module
- voice
- storage
- 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.)
- Granted
Links
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 13
- 238000000605 extraction Methods 0.000 claims abstract description 10
- 238000004891 communication Methods 0.000 claims abstract description 8
- 238000000034 method Methods 0.000 claims abstract 2
- 238000012549 training Methods 0.000 claims description 13
- 230000001360 synchronised effect Effects 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 8
- 238000006243 chemical reaction Methods 0.000 claims description 7
- 238000013480 data collection Methods 0.000 claims description 7
- 230000005540 biological transmission Effects 0.000 claims description 5
- 238000012546 transfer Methods 0.000 claims description 5
- 238000007619 statistical method Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 5
- 239000000284 extract Substances 0.000 description 4
- 238000010801 machine learning Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 102000041248 APP family Human genes 0.000 description 1
- 108091061431 APP family Proteins 0.000 description 1
- 241000208340 Araliaceae Species 0.000 description 1
- 241001672694 Citrus reticulata Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000009172 bursting Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 230000007935 neutral effect Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M1/00—Substation equipment, e.g. for use by subscribers
- H04M1/72—Mobile telephones; Cordless telephones, i.e. devices for establishing wireless links to base stations without route selection
- H04M1/724—User interfaces specially adapted for cordless or mobile telephones
- H04M1/72403—User interfaces specially adapted for cordless or mobile telephones with means for local support of applications that increase the functionality
-
- 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
- G10L15/02—Feature extraction for speech recognition; Selection of recognition unit
-
- 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
- G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
- G10L15/063—Training
-
- 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
- G10L15/08—Speech classification or search
-
- 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
- G10L15/08—Speech classification or search
- G10L15/18—Speech classification or search using natural language modelling
- G10L15/1815—Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/08—Network architectures or network communication protocols for network security for authentication of entities
- H04L63/0876—Network architectures or network communication protocols for network security for authentication of entities based on the identity of the terminal or configuration, e.g. MAC address, hardware or software configuration or device fingerprint
-
- 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
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1095—Replication or mirroring of data, e.g. scheduling or transport for data synchronisation between network nodes
-
- 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
- H04L67/50—Network services
- H04L67/55—Push-based network services
-
- 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
- G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
- G10L15/063—Training
- G10L2015/0631—Creating reference templates; Clustering
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Power Engineering (AREA)
- Computer Hardware Design (AREA)
- Computer Security & Cryptography (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Telephonic Communication Services (AREA)
Abstract
The invention discloses a kind of cell phone application voices based on artificial intelligence to store management system, APP clients, server and the management client of communication connection, APP clients receive voice data, image data and the lteral data of input, lteral data will be changed into after language data process, the voice data, image data and lteral data form storage data, and will store data sending to server storage；Server is classified after carrying out feature extraction to the voice data of reception, generate phonetic feature disaggregated model, classify after also carrying out feature extraction to lteral data or picture, generative semantics category set, and the request based on cell-phone customer terminal, push is with asking most proper phonetic feature classification or semantic classification to APP clients；Management client realizes information management to each user in server, update to phonetic feature disaggregated model and semantic classification collection and issues some common notifications.
Description
Technical field
The invention belongs to the communications fields, and in particular to a kind of cell phone application voice storage management system based on artificial intelligence.
Background technology
With social progress, floating population's frequency both domestic and external is gone to increase significantly, what average family was particularly often gone on business
Business people there is an urgent need to one based on personal intelligence storage management system, helps it manage, need to quickly look for, anti-loss weight
Article is wanted, improves study, office and life efficiency, facilitates its trip, family life, commercial needs.
Currently on the market, the storage management system based on personal (containing family) is seldom, and receiving to sell goods inside large supermarket sets
It is standby to adapt to average family demand and expensive.Minority have storage management function cell phone application function it is very limited, very
Hardly possible helps commercial white collar, average family to improve efficiency.
To find out its cause, it is that data volume is big, article position changes frequently, user because personal (containing family) storage management has
The characteristics of more.Why tradition storage management is difficult to the needs for meeting modern and business people, mainly Item Information typing
Heavy workload, inconvenient quick modification asset position information function, can not it is multi-platform it is synchronous, lack sharing functionality and lack people
Work intelligence machine learning art.
The content of the invention
The object of the present invention is to provide a kind of cell phone application voices based on artificial intelligence to store management system, with realization pair
The management and lookup of household goods.
To achieve the above object, the present invention provides following technical scheme：
A kind of cell phone application voice storage management system based on artificial intelligence, including APP clients and the APP client
The server for holding communication connection, the management client being connected with the server communication,
The APP clients receive voice data, image data and the lteral data of input, at the voice data
Changing into lteral data after reason, the voice data, image data and lteral data form storage data, and by the storage
Data sending is to server storage；
The server is classified after carrying out feature extraction to the voice data of reception, generates phonetic feature disaggregated model, also
Lteral data or image data to reception are classified after carrying out feature extraction, generative semantics classification information collection, and based on mobile phone visitor
The request at family end, push ask most proper phonetic feature disaggregated model or semantic classification information to the APP client with described
End；
The management client realizes the information management, user authority management and safety management to each user in server,
Update to phonetic feature disaggregated model and semantic classification collection and issue some common notifications.
In the technical program, user inputs voice data, lteral data or image data by APP clients, by language
Sound data are converted into lteral data, above-mentioned voice data, lteral data or image data composition storage data, composition storage data
Lteral data both include the lteral data that directly inputs, also include the lteral data converted by voice data, those storage numbers
According to the relevant information for including storage article, which includes at least type, title and the position of storage article.Those are received
Data of receiving can be synchronized in the personal account of server.Server can be trained more than voice data, and it is special to refine voice
Sign, generates Classification of Speech Models Sets, and each Classification of Speech model corresponds to people's language feature of a region, the Classification of Speech mould
Type is pushed to APP clients, and voice data can be converted into correct lteral data, realizes rapidly input storage number
According to.Server can also be trained more than lteral data or image data, extract the content of word or picture expression, generate language
Adopted classification information collection, each semantic classification correspond to a theme, when receiving the request of APP clients transmission, server
Can semantic classification corresponding with the theme for asking to include be pushed to APP clients automatically, realize the recommendation effect to user.
Preferably, the APP clients include：
Registration module, for filling in the log-on message of user online, the user's registration information includes user's pet name, surname
Name, cell-phone number, mailbox and password；
Receiving module for receiving storage data input by user, is additionally operable to receive the voice data request based on transmission
The storage data of return, semantic classification information, phonetic feature disaggregated model；
Training module is trained for the voice data to user, obtains the personal voice recognition data collection of user；
Conversion module, for the personal voice recognition data collection based on user and the phonetic feature of the server push point
The voice data of user is converted into lteral data by class model；
Sending module, for sending the storage data to the server to store；
Display module, for parsing and showing the storage data and semantic classification information；
Synchronization module obtains newer information on the server for synchronous；
Help module, for the backup of feedback, data and the update of acquisition APP of the user to encountering problems.
Preferably, the server includes：
Receiving module, for receiving the storage data that the APP clients are sent；
Personal account module, for store the log-on message of personal user, storage data, user personal speech recognition number
According to collection；
Common account module, for storing semantic point of the Classification of Speech Models Sets based on different type user, the word
Class set；
Consumers' opinions feedback module, for storing personal feedback information；
User ID data, for backing up the storage data of individual account；
Voice data training module, the voice data for each user to reception are trained, and extract phonetic feature, and
Classify according to phonetic feature, form phonetic feature category set, and formed corresponding with phonetic feature category set based on different type
The Classification of Speech Models Sets of user, and will be in Classification of Speech Models Sets storage to common account module；
Word or image data training module are instructed for the lteral data or image data of each user to reception
White silk is extracted the semanteme of word or picture, and is classified based on word or picture semantic, forms semantic classification information collection, and by described in
Semantic classification information collection is stored into common account module；
Word processing module, for the lteral data based on reception, it is semantic to extract the lteral data, transfer and push with
The relevant semantic classification information of semanteme is to the APP clients；
Speech processing module, for the voice data based on reception, it is semantic to analyze the voice data, transfer and feed back with
The semantic corresponding storage data of the voice data are additionally operable to the voice data based on reception, analytic language to the APP clients
Sound feature, and phonetic feature disaggregated model corresponding with the phonetic feature is transferred to the APP clients.
Preferably, the management client includes：
Information management module is used to implement information inquiry, management, statistical analysis to user；
User authority management module is used to implement the rights management to user；
Safety management module is used to implement the safety management to user data；
Update module is used to implement the update to phonetic feature disaggregated model and semantic classification collection；
Notification module, for issuing some common notifications.
Compared with prior art, the present invention have the advantage that for：
(1) the APP clients in this storage management system can pass through language exactly at any time due to setting conversion module
Sound such as carries out storage input, changes, checks at the management, easy to operate, convenient, and adapts to be unable to crowd's application of accent, pervasive
Property is strong.
(2) APP clients are connected with server communication, can be realized the synchronization of storage data, can be looked into whenever and wherever possible
See, update, tracking the storage information of personal belongings.
(3) server is equipped with machine learning function, can be trained and be met based on the voice data of synchronous each user
The phonetic feature model of different individual's (or different geographical) accents, so can be converted into word number by voice data exactly
According to realizing the management to storing article, additionally it is possible to which the voice data based on synchronous user, which trains to obtain, meets a certain theme
Semantic classification can be pushed to recommendation of user's realization to user in the request according to user.
Description of the drawings
Fig. 1 is the structure diagram for the storage management system of the cell phone application voice based on artificial intelligence that embodiment provides；
Fig. 2 is the structure diagram for the APP clients that embodiment provides；
Fig. 3 is the structure diagram for the server that embodiment provides；
Fig. 4 is the structure diagram for the management client that embodiment provides.
Specific embodiment
To make the objectives, technical solutions, and advantages of the present invention more comprehensible, this hair with reference to the accompanying drawings and embodiments
It is bright to be described in further detail.It should be appreciated that the specific embodiments described herein are only used to explain the present invention, and
Do not limit protection scope of the present invention.
Fig. 1 is the structure diagram for the storage management system of the cell phone application voice based on artificial intelligence that embodiment provides.Ginseng
See Fig. 1, storage management system provided in this embodiment includes：APP clients 101 are communicated to connect with the APP clients 101
Server 102, with the server 102 communication connection management client 103.
The APP clients 101 receive voice data, image data and the lteral data of input, by the voice number
According to lteral data is changed into after processing, the voice data, image data and lteral data form storage data, and by described in
Storage data sending to server 102 stores；
The server 102 is classified after carrying out feature extraction to the voice data of reception, generates phonetic feature disaggregated model,
Lteral data or image data also to reception are classified after carrying out feature extraction, generative semantics classification information collection, and based on mobile phone
The request of client, the push phonetic feature disaggregated model most proper with the request or semantic classification information are objective to the APP
Family end 101；
The management client 103 realizes the information management to each user in server, user authority management and bursting tube
Reason, update to phonetic feature disaggregated model and semantic classification collection and issues some common notifications.
Fig. 2 is the structure diagram for the APP clients that embodiment provides.Referring to Fig. 2, APP client provided in this embodiment
End includes：
Registration module 201, for filling in the log-on message of user online, the user's registration information include user's pet name,
Name, cell-phone number, mailbox and password；
Receiving module 202, for receiving storage data input by user, being additionally operable to voice data of the reception based on transmission please
Seek the storage data, semantic classification information, phonetic feature disaggregated model of return；
Training module 203 is trained for the voice data to user, obtains the personal voice recognition data of user
Collection；
Conversion module 204, it is special for the voice of the personal voice recognition data collection based on user and the server push
Disaggregated model is levied, the voice data of user is converted into lteral data；
Sending module 205, for sending the storage data to the server to store；
Display module 206, for parsing and showing the storage data and semantic classification information；
Synchronization module 207 obtains newer information on the server 102 for synchronous；
Help module 208, for the backup of feedback, data and the update of acquisition APP of the user to encountering problems.
User when in use, first by the relevant information of 201 registered user of registration module, in this way, in server
The storage address of the user can be formed in 102, for storing the storage data of the user's synchronized upload.
The setting of receiving module 202 provides the input interface of storage data for client, and the storage data of input can be language
Any form such as sound, picture, word after those data input, for voice data, can be trained it, purpose is exactly
The voice print database of the user is obtained, obtains the voice data collection of the user, which describes the characteristics of speech sounds of user,
So when user inputs voice data next time again, the non-type mandarin of the user can be converted into correct word letter
Breath promotes the promptness for inputting storage data and accuracy and convenience.
The APP clients are additionally provided with conversion module 204, which can be according to the personalized voice of oneself
Voice data is converted into word by identification data set, the phonetic feature disaggregated model that can be also pushed according to server 102, by voice
Data are converted into word, in this way, old user can identify that data set realizes voice to word based on the personalized speech of oneself
Conversion, new user can be realized conversion of the voice to word based on the phonetic feature disaggregated model of recommendation, improve input storage
The accurate fixed and stability of data.
APP clients 101 are additionally provided with display module 206, in the recommendation that oneself request can be obtained based on server 102
Hold, for example, user inputs voice " go the U.S. need luggage ", server 102 can recommend some semantemes on luggage theme
Classification, the semantic classification contain the luggage and articles of some needs, are referred to convenient for user, those semantic classification information can be by aobvious
Show that module is shown.
APP clients 101 are additionally provided with help module 208, and user can realize the feedback to problem by the module, storage
The functions such as the backup of data, the update of APP.
Fig. 3 is the structure diagram for the server that embodiment provides.Referring to Fig. 3, server 102 provided in this embodiment wraps
It includes：
Receiving module 301, for receiving the storage data of the transmission of APP clients 101；
Personal account module 302, for the personal speech recognition for storing personal user's log-on message, storing data, user
Data set；
Common account module 303, it is semantic for storing the Classification of Speech Models Sets based on different type user, the word
Category set；
Consumers' opinions feedback module 304, for storing personal feedback information；
User ID data 305, for backing up the storage data of individual account；
Voice data training module 306, the voice data for each user to reception are trained, and extraction voice is special
Sign, and classify according to phonetic feature, phonetic feature category set is formed, and is formed corresponding from phonetic feature category set based on different
The Classification of Speech Models Sets of type of user, and will be in Classification of Speech Models Sets storage to common account module；
Word or image data training module 307 carry out for the lteral data or image data of each user to reception
Training is extracted the semanteme of word or picture, and is classified based on word or picture semantic, forms semantic classification information collection, and by institute
Predicate justice classification information collection is stored into common account module；
Word processing module 308 for the lteral data based on reception, extracts the lteral data semanteme, transfers and push away
It send and the relevant semantic classification of semanteme to the APP clients 101；
Speech processing module 309 for the voice data based on reception, is analyzed the voice data semanteme, is transferred and anti-
Feedback, to the APP clients 101, is additionally operable to the voice number based on reception with the semantic corresponding storage data of the voice data
According to, analysis phonetic feature, and phonetic feature disaggregated model corresponding with the phonetic feature is transferred to the APP clients 101.
The server 102 can try down the management to personal account, moreover it is possible to realize the processing to common data, specifically,
Voice data training module 306 is mainly trained a large amount of voice data of collection, and formation meets each region phonetic feature
Classification of Speech model.Specifically, voice data is trained using neutral net, to carry the voice of region pronunciation characteristics
Data, using the corresponding correct lteral data of the voice data as true value label, carry out the voice data as input data
Training obtains to describe the Classification of Speech model of the pronunciation characteristics.In this way, when user inputs one section of voice data, it can be with
Based on the Classification of Speech model, the content forwarding for exactly expressing the voice data is word.
Word or setting up for image data training module 307 are mainly used for user's recommendation information, specifically, to reception
The lteral data or picture of each user is trained, and extracts the semanteme of word or picture, and is classified based on word or picture semantic,
Semantic classification collection is formed, and will be in semantic classification collection storage to the corresponding address of the memory module common account.In such manner, it is possible to
It is asked based on user, semantic classification corresponding with the semanteme that request includes is pushed to user.
Fig. 4 is the structure diagram for the management client that embodiment provides.Referring to Fig. 4, management visitor provided in this embodiment
Family end includes：
Information management module 401 is used to implement information inquiry, management, statistical analysis to user；
User authority management module 402 is used to implement the rights management to user；
Safety management module 403 is used to implement the safety management to user data；
Update module 404 is used to implement the update to phonetic feature disaggregated model and semantic classification collection；
Notification module 405, for issuing some common notifications.
Storage system provided in this embodiment can carry out storage input by voice exactly at any time, change, check
Management, it is easy to operate, it is convenient, and adapt to be unable to crowd's application of accent, universality is strong, while can realize storage data
It is synchronous, the storage information of personal belongings can be checked, updated, tracking whenever and wherever possible.
System operatio is simple, can be shot at any time using cell phone application 1, word or voice input storage Item Information；It is multi-platform
Synchronized update back-end data；The prompting of the shared information from friends and family can also be received；Phonetic entry simplifies user's operation and carries
User experience has been risen, has saved user time cost；Machine learning carries out personalized customization；Artificial intelligence, big data statistics are used
Family preference provides more preferably services to the user.
Technical scheme and advantageous effect is described in detail in above-described specific embodiment, Ying Li
Solution is the foregoing is merely presently most preferred embodiment of the invention, is not intended to limit the invention, all principle models in the present invention
Interior done any modification, supplementary, and equivalent replacement etc. are enclosed, should all be included in the protection scope of the present invention.
Claims (4)
1. a kind of cell phone application voice storage management system based on artificial intelligence, including APP clients and the APP clients
The server of communication connection, the management client being connected with the server communication, which is characterized in that
The APP clients receive voice data, image data and the lteral data of input, after the language data process
Changing into lteral data, the voice data, image data and lteral data form storage data, and by the storage data
It is sent to server storage；
The server is classified after carrying out feature extraction to the voice data of reception, is generated phonetic feature disaggregated model, is also docked
The lteral data or image data of receipts are classified after carrying out feature extraction, generative semantics classification information collection, and based on cell-phone customer terminal
Request, push and the most proper phonetic feature disaggregated model of the request or semantic classification information to the APP clients；
The management client realizes the information management, user authority management and safety management to each user in server, to language
The update of sound tagsort model and semantic classification collection and issue some common notifications.
2. the cell phone application voice storage management system based on artificial intelligence as described in claim 1, which is characterized in that described
APP clients include：
Registration module, for filling in the log-on message of user online, the user's registration information includes user's pet name, name, hand
Machine number, mailbox and password；
Receiving module for receiving storage data input by user, is additionally operable to receive the voice data request return based on transmission
Storage data, semantic classification information, phonetic feature disaggregated model；
Training module is trained for the voice data to user, obtains the personal voice recognition data collection of user；
Conversion module, for the phonetic feature of the personal voice recognition data collection based on user and server push classification mould
The voice data of user is converted into lteral data by type；
Sending module, for sending the storage data to the server to store；
Display module, for parsing and showing the storage data and semantic classification information；
Synchronization module obtains newer information on the server for synchronous；
Help module, for the backup of feedback, data and the update of acquisition APP of the user to encountering problems.
3. the cell phone application voice storage management system based on artificial intelligence as described in claim 1, which is characterized in that described
Server includes：
Receiving module, for receiving the storage data that the APP clients are sent；
Personal account module, for store personal user's log-on message, storage data, user personal voice recognition data collection；
Common account module, for storing the Classification of Speech Models Sets based on different type user, the word semantic classification collection；
Consumers' opinions feedback module, for storing personal feedback information；
User ID data, for backing up the storage data of individual account；
Voice data training module, the voice data for each user to reception are trained, extraction phonetic feature, and according to
Phonetic feature is classified, and forms phonetic feature category set, and is formed corresponding with phonetic feature category set based on different type user
Classification of Speech Models Sets, and by Classification of Speech Models Sets storage in common account module；
Word or image data training module are trained for the lteral data or image data of each user to reception, carry
The semanteme of word or picture is taken, and is classified based on word or picture semantic, forms semantic classification information collection, and by described semantic point
Category information collection is stored into common account module；
Word processing module, for the lteral data based on reception, it is semantic to extract the lteral data, transfer and push with it is described
Semantic relevant semantic classification information is to the APP clients；
Speech processing module, for the voice data based on reception, it is semantic to analyze the voice data, transfer and feed back with it is described
The semantic corresponding storage data of voice data are additionally operable to the voice data based on reception, analysis voice is special to the APP clients
Sign, and phonetic feature disaggregated model corresponding with the phonetic feature is transferred to the APP clients.
4. the cell phone application voice storage management system based on artificial intelligence as described in claim 1, which is characterized in that described
Management client includes：
Information management module is used to implement information inquiry, management, statistical analysis to user；
User authority management module is used to implement the rights management to user；
Safety management module is used to implement the safety management to user data；
Update module is used to implement the update to phonetic feature disaggregated model and semantic classification collection；
Notification module, for issuing some common notifications.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711288501.4A CN108111491B (en) | 2017-12-07 | 2017-12-07 | Management system is accomodate to cell-phone APP pronunciation based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711288501.4A CN108111491B (en) | 2017-12-07 | 2017-12-07 | Management system is accomodate to cell-phone APP pronunciation based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108111491A true CN108111491A (en) | 2018-06-01 |
| CN108111491B CN108111491B (en) | 2020-06-19 |
Family
ID=62209129
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711288501.4A Active CN108111491B (en) | 2017-12-07 | 2017-12-07 | Management system is accomodate to cell-phone APP pronunciation based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108111491B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109255992A (en) * | 2018-11-20 | 2019-01-22 | 国网上海市电力公司 | A kind of electric power letters and calls course portable multimedia teaching box |
| CN109635209A (en) * | 2018-12-12 | 2019-04-16 | 广东小天才科技有限公司 | Learning content recommendation method and family education equipment |
| CN113066482A (en) * | 2019-12-13 | 2021-07-02 | 阿里巴巴集团控股有限公司 | Voice model updating method, voice data processing method, voice model updating device, voice data processing device and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103458056A (en) * | 2013-09-24 | 2013-12-18 | 贵阳世纪恒通科技有限公司 | Speech intention judging method based on automatic classification technology for automatic outbound system |
| US20140343927A1 (en) * | 2014-08-01 | 2014-11-20 | Almawave S.R.L. | System and method for meaning driven process and information management to improve efficiency, quality of work and overall customer satisfaction |
| CN104715334A (en) * | 2015-03-17 | 2015-06-17 | 北京在这网络科技有限公司 | Mobile APP based personal article management system |
| KR20160059026A (en) * | 2014-11-17 | 2016-05-26 | 주식회사 엘지유플러스 | Event Practicing System based on Voice Memo on Mobile, Mobile Control Server and Mobile Control Method, Mobile and Application Practicing Method therefor |
| CN106844570A (en) * | 2017-01-03 | 2017-06-13 | 珠海格力电器股份有限公司 | Article management device and method and mobile terminal |
| CN107423283A (en) * | 2017-05-26 | 2017-12-01 | 黄晓咏 | A kind of home services communication system |
-
2017
- 2017-12-07 CN CN201711288501.4A patent/CN108111491B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103458056A (en) * | 2013-09-24 | 2013-12-18 | 贵阳世纪恒通科技有限公司 | Speech intention judging method based on automatic classification technology for automatic outbound system |
| US20140343927A1 (en) * | 2014-08-01 | 2014-11-20 | Almawave S.R.L. | System and method for meaning driven process and information management to improve efficiency, quality of work and overall customer satisfaction |
| KR20160059026A (en) * | 2014-11-17 | 2016-05-26 | 주식회사 엘지유플러스 | Event Practicing System based on Voice Memo on Mobile, Mobile Control Server and Mobile Control Method, Mobile and Application Practicing Method therefor |
| CN104715334A (en) * | 2015-03-17 | 2015-06-17 | 北京在这网络科技有限公司 | Mobile APP based personal article management system |
| CN106844570A (en) * | 2017-01-03 | 2017-06-13 | 珠海格力电器股份有限公司 | Article management device and method and mobile terminal |
| CN107423283A (en) * | 2017-05-26 | 2017-12-01 | 黄晓咏 | A kind of home services communication system |
Non-Patent Citations (1)
| Title |
|---|
| B.LI,B.HOU,W.YU,X.LU,C.YANG: "Applications of artificial intelligence in", 《FRONTIERS OF INFORMATION TECHNOLOGY & ELECTRONIC ENGINEERING》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109255992A (en) * | 2018-11-20 | 2019-01-22 | 国网上海市电力公司 | A kind of electric power letters and calls course portable multimedia teaching box |
| CN109635209A (en) * | 2018-12-12 | 2019-04-16 | 广东小天才科技有限公司 | Learning content recommendation method and family education equipment |
| CN109635209B (en) * | 2018-12-12 | 2021-03-12 | 广东小天才科技有限公司 | Learning content recommendation method and family education equipment |
| CN113066482A (en) * | 2019-12-13 | 2021-07-02 | 阿里巴巴集团控股有限公司 | Voice model updating method, voice data processing method, voice model updating device, voice data processing device and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108111491B (en) | 2020-06-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11303590B2 (en) | Suggested responses based on message stickers | |
| CN109308357B (en) | Method, device and equipment for obtaining answer information | |
| CN108984650B (en) | Computer-readable recording medium and computer device | |
| CN106227786B (en) | Method and apparatus for pushed information | |
| CN103377652B (en) | A kind of method, device and equipment for carrying out speech recognition | |
| US10558655B2 (en) | Data query method supporting natural language, open platform, and user terminal | |
| CN103020047A (en) | Method for revising voice response and natural language dialogue system | |
| CN108111491A (en) | A kind of cell phone application voice storage management system based on artificial intelligence | |
| US20200134018A1 (en) | Mixed-initiative dialog automation with goal orientation | |
| CN112434501B (en) | Method, device, electronic equipment and medium for intelligent generation of worksheet | |
| WO2016203805A1 (en) | Information processing device, information processing system, information processing method, and program | |
| CN103577420A (en) | Method and device for inquiring user information dynamically | |
| CN107257362B (en) | Method and system for dynamically displaying events and matching chats on map according to attention degree of time | |
| CN104424304A (en) | Personalized recommendation and guide system based on context awareness information and control method | |
| CN106164941A (en) | The additional information relevant to fuzzy item in the message is provided | |
| CN108256779A (en) | A kind of enterprise's Internet of Things office all-in-one machine | |
| CN105912626A (en) | Online voice consultation system | |
| CN108595141A (en) | Pronunciation inputting method and device, computer installation and computer readable storage medium | |
| US20130198229A1 (en) | Method and device for processing continuous queries | |
| CN111768141A (en) | Voice express delivery system and express delivery sending and inquiring methods and devices | |
| CN101094436A (en) | Information inter-transferring intelligent platform | |
| CN106663112A (en) | Presenting information cards for events associated with entities | |
| CN112328871B (en) | Reply generation method, device, equipment and storage medium based on RPA module | |
| CN109299240B (en) | Chat robot knowledge display method and device | |
| KR101350978B1 (en) | System for managing personal relationship using application and method thereof |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |