CN109460454A - The interactive voice intelligent automation searching system and method for industrial supply chain data - Google Patents
The interactive voice intelligent automation searching system and method for industrial supply chain data Download PDFInfo
- Publication number
- CN109460454A CN109460454A CN201811235989.9A CN201811235989A CN109460454A CN 109460454 A CN109460454 A CN 109460454A CN 201811235989 A CN201811235989 A CN 201811235989A CN 109460454 A CN109460454 A CN 109460454A
- Authority
- CN
- China
- Prior art keywords
- speech recognition
- alexa
- user
- text
- webpage
- 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 title claims abstract description 16
- 238000000034 method Methods 0.000 title claims abstract description 15
- 230000003993 interaction Effects 0.000 claims abstract description 7
- 230000006870 function Effects 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses the interactive voice intelligent automation searching system of industrial supply chain data and methods, comprising: a voice interaction module makes an addition in webpage, for capturing audio user;One database, interacts with webpage, for storing the data of product;One AVS server, interacts with webpage, the speech recognition interface comprising Alexa, for receiving the audio user of capture and being text by speech recognition;One ASK server, it is interacted with AVS server, include Alexa Skill Kit, for by speech recognition, to recall Alexa Skill Kit after text, in ASK, each sentence to be corresponding with an operational order, incoming text will be mapped to the operational order of corresponding consulting sentence according to its meaning, and return to instruction, finally, carrying out corresponding operating to database according to instruction and being presented to the user result.The present invention can satisfy inquiry accuracy rate requirement of the user in electronic product sales data.
Description
Technical field
The present invention relates to field of computer technology, the interactive voice intelligent automation inspection of especially industrial supply chain data
Cable system and method.
Background technique
There are many products that voice turns text on the market, can convert text as retrieval for voice messaging well
Input, but often the retrieval request of a user be not in short can express clearly ground, such as user choose it is a
First said size requirement when electronic product, finished the rear requirement for wishing an additional grown place again, but at this time system incited somebody to action
The product result for meeting user's size requirements is presented, and being added again when grown place requires at this time is then in original data
A new retrieval sentence is executed, is not to be retrieved in existing search result.And the mode of interactive voice is used,
User's multiple retrieval requests expressed in interactive process can be retained, the result of retrieval is presented after determining request.Cause
This can effectively realize the friend that complex query is convenient for the user to use and increases user using interactive voice intelligent search method
Good Experience Degree.
Although Alexa has the function of good speech understanding, user can be helped to provide some simple services, it is former
Raw Alexa can not understand the information in relation to electronic product, it is therefore desirable to added with all possible retrieval for closing electronic product
Request is intended to.
In consideration of it, the purpose of the present invention is provide a convenience, close friend, succinct retrieval input mode, and intelligence for user
The data of electronic product can automatically be retrieved.
Summary of the invention
In view of the above-mentioned problems, providing industrial supply chain the invention aims to solve the deficiencies in the prior art
The interactive voice intelligent automation searching system and method for data.
In order to achieve the above objectives, the present invention is implemented according to following technical scheme:
The interactive voice intelligent automation searching system of industrial supply chain data, comprising:
One voice interaction module, makes an addition in webpage, for capturing audio user;
One database, interacts with webpage, for storing the data of product;
One AVS server, interacts with webpage, the speech recognition interface comprising Alexa, for receiving capture
Audio user and by speech recognition be text;
One ASK server, interacts with AVS server, includes Alexa Skill Kit, is used for speech recognition
To recall Alexa Skill Kit after text, in ASK, each sentence is corresponding with an operational order, incoming text
Word will be mapped to the operational order of corresponding consulting sentence according to its meaning, and instruction is returned, finally, according to instruction logarithm
Corresponding operating is carried out according to library and is presented to the user result.
In addition, the present invention also provides the interactive voice intelligent automation search method of industrial supply chain data, including it is following
Step:
S1, audio user is captured by voice interaction module;
If S2, successfully capturing audio, step S3 is continued to execute;If it is unsuccessful to capture audio, return step
S1;
S3, AVS server calls Alexa speech recognition interface;
If S4, calling the success of Alexa speech recognition interface, step S5 is continued to execute;If calling Alexa voice
Identify that interface is unsuccessful, then return step S3;
Speech recognition is called Alexa Skill Kit to carry out semantic point by S5, Alexa speech recognition interface after text
Analysis, each sentence are corresponding with an operational order, and incoming text will be mapped to corresponding consulting sentence according to its meaning
Operational order, and instruction is returned, finally, carrying out corresponding operating to database according to instruction and being presented to the user result.
Compared with prior art, the present invention is taken using Alexa Voice Service (AVS) the Lai Shixian voice of Alexa
Business function.Alexa can be very good to support English at present.First audio-frequency information function can be received and dispatched by setting up one in transmitting terminal
Module, the speech recognition module that the audio-frequency information that will acquire is transmitted to AVS carry out semantic analysis.The result of analysis is returned again
Return to transmitting terminal;Customized speech recognition module is added in the Alexa Skills Kit of Alexa;In interactive voice
It calls the intelligentized identification user of customized identification module to be desirable for any retrieval request in the process, then this is asked
It asks and is transmitted to transmitting terminal progress database retrieval operation and shows search result.By means of the present invention, language is provided a user
Sound input/output interface extracts user query request during interactive voice, meets user in electronic product and sells number
According to upper inquiry accuracy rate requirement.
Detailed description of the invention
Fig. 1 is system schematic of the invention.
Fig. 2 is flow chart of the invention.
Specific embodiment
The invention will be further described combined with specific embodiments below, the invention illustrative examples and say
It is bright to be used to explain the present invention but not as a limitation of the invention.
As shown in Figure 1, the present invention provides the interactive voice intelligent automation searching system of industrial supply chain data, it should
System includes:
One voice interaction module 1, makes an addition in webpage, for capturing audio user;
One database 2, interacts with webpage, for storing the data of product;
One AVS server 3, interacts with webpage, the speech recognition interface comprising Alexa, for receiving capture
Audio user and by speech recognition be text;
One ASK server 4, interacts with AVS server 3, includes Alexa Skill Kit, for knowing voice
Alexa Skill Kit Wei not be recalled after text, in ASK, each sentence is corresponding with an operational order, incoming
Text will be mapped to the operational order of corresponding consulting sentence according to its meaning, and instruction is returned, finally, according to instruction pair
Database carries out corresponding operating and is presented to the user result.
As shown in Fig. 2, the present invention also provides the interactive voice intelligent automation search method of industrial supply chain data, packet
Include following steps:
S1, audio user is captured by voice interaction module;
If S2, successfully capturing audio, step S3 is continued to execute;If it is unsuccessful to capture audio, return step
S1;
S3, AVS server calls Alexa speech recognition interface;
If S4, calling the success of Alexa speech recognition interface, step S5 is continued to execute;If calling Alexa voice
Identify that interface is unsuccessful, then return step S3;
Speech recognition is called Alexa Skill Kit to carry out semantic point by S5, Alexa speech recognition interface after text
Analysis, each sentence are corresponding with an operational order, and incoming text will be mapped to corresponding consulting sentence according to its meaning
Operational order, and instruction is returned into finally, carrying out corresponding operating to database according to instruction and being presented to the user result.
The speech recognition of Alexa platform uses the methods of deep learning and acoustic model, can accurately identify that the voice of user is defeated
Enter, there is powerful identification energy ability.By needing to understand semanteme after speech recognition, the voice meaning of user is analyzed
It is intended to.Alexa platform has basic semantic understanding such as: inquiry somewhere weather, but for the data of electronic product this
Block does not support semantic understanding, it is therefore desirable to have for the intent information in terms of electronic product data.Based on electronic product
Data, statistics of attributes for data it is possible that intention, for each intent definition one realization method, that is, skill
Can, technical ability is first triggered when needing to carry out semantic analysis, error result is then returned if being not present or failing and prompts user
Voice is re-entered, technical ability is called if technical ability triggers successfully and is returned the result.
Intention design in S5 is specifically included:
According to the attribute of product table in database and attribute value design idea, the user extracted in voice content is intended to, root
According to the corresponding intention function of calling is intended to, the intention is divided into two classes according to intention type:
(1) accurate to be intended to retrieval: building range of search set L < l1,l2...ln> is produced wherein containing about electromechanicsWherein, attribute liFeature be ci< ci1,ci2,...,cim>.When the semanteme of voice is that retrieval belongs to
Property liFeature cij, at this moment to be accurately intended to retrieve, operated according to the corresponding database retrieval of operation is intended to.
(2) fuzzy intention is retrieved: after carrying out semantic analysis to voice, as the attribute l for containing only Organic Electricity product in semantemei
When feature corresponding without attribute, using the corresponding characteristic set of the attribute as prompt information inform user, allow user therefrom
Selection is one or more to which precise search is intended to, and finally obtains one and is accurately intended to, at this time i.e. executable accurate intention inspection
Suo Fangfa.
For the technical ability function for being intended to design identification intention, wherein technical ability function is not only needed to be realized with code and also be needed
It is configured in Alexa Skill Service platform.There are certain similitudes for the sentence of the intention of usual user, therefore
According to the sentence pattern structure of similitude design idea therein.Using attribute as retrieval object, item of the feature of attribute as retrieval
General intention sentence pattern can be obtained in part:
{ object } of { commodity }<for, it is to have, empty>{ feature }<what, which, empty>
Wherein, " commodity " ∈ { the electronic product collection of all models }, " object " ∈ { property set of electronic product } are " special
Sign " ∈ { property set of electronic product }.The sentence of retrieval can be generated according to the sentence pattern and database is retrieved, thus
Obtain result.
It for the retrieval sentence of Special complex, needs targetedly to design, such as " prediction user will buy certain money
Product probability of transaction is how many " this intention be then unsatisfactory for it is above-mentioned it is general be intended to sentence pattern, need special realization.
The limitation that technical solution of the present invention is not limited to the above specific embodiments, it is all according to the technique and scheme of the present invention
The technology deformation made, falls within the scope of protection of the present invention.
Claims (2)
1. the interactive voice intelligent automation searching system of industrial supply chain data characterized by comprising
One voice interaction module, makes an addition in webpage, for capturing audio user;
One database, interacts with webpage, for storing the data of product;
One AVS server, interacts with webpage, the speech recognition interface comprising Alexa, for receiving user's sound of capture
It frequently is and by speech recognition text;
One ASK server, interacts with AVS server, includes AlexaSkillKit, for being text by speech recognition
After recall AlexaSkillKit, in ASK, each sentence is corresponding with an operational order, and incoming text will be according to it
Meaning is mapped to the operational order of corresponding consulting sentence, and instruction is returned, finally, being carried out according to instruction to database corresponding
It operates and is presented to the user result.
2. the interactive voice intelligent automation search method of industry supply chain data as described in claim 1, which is characterized in that
The following steps are included:
S1, audio user is captured by voice interaction module;
If S2, successfully capturing audio, step S3 is continued to execute;If it is unsuccessful to capture audio, return step S1;
S3, AVS server calls Alexa speech recognition interface;
If S4, calling the success of Alexa speech recognition interface, step S5 is continued to execute;If Alexa speech recognition is called to connect
Mouth is unsuccessful, then return step S3;
AlexaSkillKit progress semantic analysis is called in speech recognition by S5, Alexa speech recognition interface after text, each
Sentence is all corresponding with an operational order, and incoming text refers to the operation for being mapped to corresponding consulting sentence according to its meaning
It enables, and instruction is returned, finally, carrying out corresponding operating to database according to instruction and being presented to the user result.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811235989.9A CN109460454A (en) | 2018-10-22 | 2018-10-22 | The interactive voice intelligent automation searching system and method for industrial supply chain data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811235989.9A CN109460454A (en) | 2018-10-22 | 2018-10-22 | The interactive voice intelligent automation searching system and method for industrial supply chain data |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109460454A true CN109460454A (en) | 2019-03-12 |
Family
ID=65608221
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811235989.9A Pending CN109460454A (en) | 2018-10-22 | 2018-10-22 | The interactive voice intelligent automation searching system and method for industrial supply chain data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109460454A (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101655876A (en) * | 2009-09-17 | 2010-02-24 | 广东国笔科技股份有限公司 | Intelligent searching system and intelligent searching method based on semantic analysis |
CN102332032A (en) * | 2011-10-20 | 2012-01-25 | 博宇金属股份有限公司 | Webpage-based metal material retrieval system and method |
CN106528770A (en) * | 2016-11-07 | 2017-03-22 | 大连工业大学 | CAD semantic model search method based on design intent |
CN106657239A (en) * | 2016-10-18 | 2017-05-10 | 江西博瑞彤芸科技有限公司 | Information interaction method and system |
CN108427746A (en) * | 2018-03-09 | 2018-08-21 | 江苏丹毛纺织股份有限公司 | A kind of production management intelligent speech interactive system and method |
-
2018
- 2018-10-22 CN CN201811235989.9A patent/CN109460454A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101655876A (en) * | 2009-09-17 | 2010-02-24 | 广东国笔科技股份有限公司 | Intelligent searching system and intelligent searching method based on semantic analysis |
CN102332032A (en) * | 2011-10-20 | 2012-01-25 | 博宇金属股份有限公司 | Webpage-based metal material retrieval system and method |
CN106657239A (en) * | 2016-10-18 | 2017-05-10 | 江西博瑞彤芸科技有限公司 | Information interaction method and system |
CN106528770A (en) * | 2016-11-07 | 2017-03-22 | 大连工业大学 | CAD semantic model search method based on design intent |
CN108427746A (en) * | 2018-03-09 | 2018-08-21 | 江苏丹毛纺织股份有限公司 | A kind of production management intelligent speech interactive system and method |
Non-Patent Citations (2)
Title |
---|
STEVEN GUAMÁN 等: "Device Control System for a Smart Home using Voice Commands: A Practical Case", 《《ICIME 2018》》 * |
戴鄂: "全球人工智能大战前夜 看亚马逊未兆之谋", 《创新世界周刊》 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
KR102288249B1 (en) | Information processing method, terminal, and computer storage medium | |
CN107153965A (en) | A kind of intelligent customer service solution of multiple terminals | |
WO2017151400A1 (en) | Interpreting and resolving conditional natural language queries | |
CN111368548A (en) | Semantic recognition method and device, electronic equipment and computer-readable storage medium | |
JP2017505964A (en) | Automatic task classification based on machine learning | |
CN114840671A (en) | Dialogue generation method, model training method, device, equipment and medium | |
CN113051362A (en) | Data query method and device and server | |
CN109766451A (en) | A kind of cloud computing platform and its scheduling, data analysing method | |
CN111368145A (en) | Knowledge graph creating method and system and terminal equipment | |
CN114186108A (en) | Multimode man-machine interaction system oriented to electric power material service scene | |
CN114817478A (en) | Text-based question and answer method and device, computer equipment and storage medium | |
CN110750626B (en) | Scene-based task-driven multi-turn dialogue method and system | |
CN113726942A (en) | Intelligent telephone answering method, system, medium and electronic terminal | |
CN111538817A (en) | Man-machine interaction method and device | |
CN117520498A (en) | Virtual digital human interaction processing method, system, terminal, equipment and medium | |
US20220327147A1 (en) | Method for updating information of point of interest, electronic device and storage medium | |
CN110597765A (en) | Large retail call center heterogeneous data source data processing method and device | |
CN115688758A (en) | Statement intention identification method and device and storage medium | |
CN109460454A (en) | The interactive voice intelligent automation searching system and method for industrial supply chain data | |
CN112133306B (en) | Response method and device based on express delivery user and computer equipment | |
CN114637831A (en) | Data query method based on semantic analysis and related equipment thereof | |
CN114297229A (en) | Data query method and device, electronic equipment and storage medium | |
CN113962213A (en) | Multi-turn dialog generation method, terminal and computer readable storage medium | |
CN113722584A (en) | Task pushing method and device and storage medium | |
CN114138943A (en) | Dialog message generation method and device, electronic 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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190312 |