CN108831482A - A method of based on speech recognition search electronic component - Google Patents
A method of based on speech recognition search electronic component Download PDFInfo
- Publication number
- CN108831482A CN108831482A CN201810975582.3A CN201810975582A CN108831482A CN 108831482 A CN108831482 A CN 108831482A CN 201810975582 A CN201810975582 A CN 201810975582A CN 108831482 A CN108831482 A CN 108831482A
- Authority
- CN
- China
- Prior art keywords
- search
- user
- electronic component
- mentioned
- speech recognition
- 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
- 238000000034 method Methods 0.000 claims abstract description 30
- 238000006243 chemical reaction Methods 0.000 claims abstract description 7
- 238000004458 analytical method Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 238000007476 Maximum Likelihood Methods 0.000 claims description 2
- 238000007405 data analysis Methods 0.000 claims description 2
- 238000000605 extraction Methods 0.000 claims description 2
- 238000005194 fractionation Methods 0.000 claims description 2
- 239000000047 product Substances 0.000 description 12
- 238000005516 engineering process Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 239000006227 byproduct Substances 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/08—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
- G10L15/08—Speech classification or search
- G10L15/18—Speech classification or search using natural language modelling
- G10L15/183—Speech classification or search using natural language modelling using context dependencies, e.g. language models
Landscapes
- Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Artificial Intelligence (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
A method of based on speech recognition search electronic component, which is characterized in that this approach includes the following steps：Receive the voice messaging of user's input；Text is converted by voice input；Semantics recognition is carried out to the text of conversion；Determine the search need of above-mentioned user, i.e., user-defined search project；It is scanned for by search need module according to above-mentioned search project, obtains the service for meeting above-mentioned search need, and above-mentioned service is supplied to user.A kind of method based on speech recognition search electronic component according to the present invention, using semantics recognition and based on context intelligent decision is carried out by the way of, define correct search-type and strategy, to carry out accurately and rapidly searching for, other related informations can be matched simultaneously, it is supplied to searcher simultaneously, it is convenient and practical, improve the efficiency found and search.
Description
【Technical field】
The present invention relates to a kind of searching method based on network and big data, is searched and is searched especially for electronic component
The platform of rope, the method for passing through speech recognition and electronic component being scanned for.
【Background technique】
Modernization science and technology society, electronic product digital product rapid development, keep updating it is with rapid changepl. never-ending changes and improvements, with digital product
Value volume and range of product geometry number be also presented increasing.To electronic component using also more extensive and diversity, so right
Not only it should be understood that various emerging technologies but also to have to various modern electronic components for the enterprise of electronic manufacture industry
Understood, and in order to which the update of product also needs to update more preferable more good hardware device, such enterprise just need to purchase or
Person customizes different components, in adoption process, the product in face of magnanimity due to respective naming system and specifications and models difference,
Cause retrieval difficult in search process, it is difficult to the problem of Effective selection is with screening.
So search effect is bad, it is difficult to which it is exactly that current way of search exists that it is poor, which to meet user's demand, user experience,
The problem of, specifically it there is problems：If complete device name can not be provided, can not search for；Website data amount
Deficiency, data volume can not cover the electronic component of the overwhelming majority, and data accuracy has differences, the data renewal speed period
It is considerably long；The real-time price comparison service of multiple businessmans can not be provided；Can only input completed device model scan for without
Local field can be supported to retrieve.
【Summary of the invention】
The present invention proposes a kind of only importation field for above situation and can support to search for, and multiple terminals access is supported to search
Cable system is inputted based on voice and knows the method for scanning for electronic component otherwise.
A kind of method based on speech recognition search electronic component of the present invention, which is characterized in that this method includes
Following steps：
Step 1: receiving the voice messaging of user's input by speech reception module；
Step 2: converting text for voice input by conversion module；
Step 3: carrying out semantics recognition by text of the identification module to conversion；
Step 4: according to above-mentioned semantics recognition as a result, in conjunction with above-mentioned user's current search behavior context, determine above-mentioned use
The search need at family, i.e., user-defined search project；
Step 5: scanning for by search need module according to above-mentioned search project, the clothes for meeting above-mentioned search need are obtained
Business, and above-mentioned service is supplied to user.
Wherein custom search demand described in step 4 refers to the search project that user is judged by input content, refer to but
It is not limited to：Product type, product brand, product parameters, product producer.
Wherein the course of work of the search module is such as in step 5：System is existing to inquiry content（Text）Carry out natural-sounding
Processing analysis（So-called NLP）, big data analysis is carried out in conjunction with active user's search need, and to demand, is associated with the demand big
Data support lower high frequency associations, determine the actual search demand in maximum likelihood, obtain corresponding search data, and provide
To user.
In step 5, keyword treatment process, keyword processing are also applied in carrying out natural-sounding processing analysis
Process is to extract, pre-process to keyword, correcting, and is split.
Wherein keyword extraction is that the information and keyword database of text are converted by comparing, and proposes related keyword
Word；
Keyword pretreatment is to carry out denoising to keyword；
Keyword amendment and fractionation intersect amendment and split keyword when comparing keyword database.
Wherein search need analysis module, for combining current search behavior and inquiry content to determine user's actual need；
In step 5, in the service process that obtains above-mentioned meet demand, it is also necessary to use data acquisition module, which obtains
Modulus block is for obtaining search result corresponding data.
A kind of method based on speech recognition search electronic component according to the present invention, use semantics recognition and
Based on context mode carries out intelligent decision, defines correct search-type and strategy, accurate and rapid to carry out
Search, while other related informations can be matched, while being supplied to searcher, it is convenient and practical, it improves lookup and searches
The efficiency of rope.User job efficiency is provided, purchase cost is reduced, search threshold is reduced, improves searching accuracy, data have more
Real-time.
【Detailed description of the invention】
Fig. 1 is that the present invention is based on the flow charts of the method for speech recognition search electronic component；
【Specific embodiment】
Below in conjunction with the drawings and specific embodiments of the present invention, the present invention is further described in detail.
Embodiment 1：
In a kind of implementation of embodiment, the search need of above-mentioned user is the information that specific component is searched by model.
Step 1: receiving the voice messaging of user's input by speech reception module, i.e., said with voice against microphone
"max232"；Step 2: converting text for voice input by conversion module, text " max232 " is converted into system；
Step 3: carrying out semantics recognition by text of the identification module to conversion, that is, judge that the corresponding text of voice whether there is falsehood,
And based on context, identification judges user's search need representated by the information of the input, and the project required to look up is product
Model is the information that specific component is searched by product type；Then step four fundamental rules are：According to the member of above-mentioned user's typing
Device type scans for, and obtains component model list needed for above-mentioned user, and by the information exhibition of above-mentioned component model
Show to above-mentioned user；At this moment, the service that above-mentioned user selects in the service of offer is obtained, the clothes for completing above-mentioned selection are executed
The subsequent operation of business can be：The component model that above-mentioned user selectes is obtained, shows above-mentioned selected first device to above-mentioned user
The details of part model, and one of following operation or combination are executed according to the selection of above-mentioned user：Check component model data,
It buys, check related component model.
Wherein, the component model of above-mentioned typing can be incomplete component model, and the present embodiment is to above-mentioned first device
The length and form of part model are not construed as limiting, and above-mentioned component model complete name is first device of " max232dr " then above-mentioned typing
Part model then can be " max232 ".
Embodiment 2：
In another implementation of the present embodiment, the search need of above-mentioned user is that specific first device is searched by component parameter
The information of part, voice input " 10uf 10v " are searched, and in this embodiment, step 1 and step 2 are all big with embodiment 1
Cause it is identical, in step 3, based on context combine key definition processing mode, can judge that the search need of user is
The information of specific component is searched by component parameter, therefore search engine can be scanned for according to the demand, obtain with
Component model list needed for above-mentioned user, and the information of above-mentioned component model and price are showed into above-mentioned user, for
User selects.After user selectes component model in the component model list of displaying, search engine can be obtained
The component model of user's selection, search engine can show the details for the component model that the user selectes to user, in this way
User can check the information for the component model that the user selectes, also, search engine can also be according to the user's choice
Execute one of following operation or combination：It checks or buys the price of different suppliers, check same type or Related product.
A kind of method based on speech recognition search electronic component according to the present invention, use semantics recognition and
Based on context mode carries out intelligent decision, defines correct search-type and strategy, accurate and rapid to carry out
Search, while other related informations can be matched, while being supplied to searcher, it is convenient and practical, it improves lookup and searches
The efficiency of rope.
The above is only present pre-ferred embodiments, is not intended to limit the present invention in any form, although
The present invention is disclosed above in the preferred embodiment, and however, it is not intended to limit the invention, any person skilled in the art,
It does not depart within the scope of technical solution of the present invention, when the technology contents using the disclosure above make a little change or are modified to equivalent
The equivalent embodiment of variation, but without departing from the technical solutions of the present invention, technology refers to according to the present invention implements to above
Any simple modification, equivalent change and modification made by example, belong in the range of technical solution of the present invention.
Claims (9)
1. a kind of method based on speech recognition search electronic component, which is characterized in that this approach includes the following steps：
Step 1: receiving the voice messaging of user's input by speech reception module；
Step 2: converting text for voice input by conversion module；
Step 3: carrying out semantics recognition by text of the identification module to conversion；
Step 4: according to above-mentioned semantics recognition as a result, in conjunction with above-mentioned user's current search behavior context, determine above-mentioned use
The search need at family, i.e., user-defined search project；
Step 5: scanning for by search need module according to above-mentioned search project, the clothes for meeting above-mentioned search need are obtained
Business, and above-mentioned service is supplied to user.
2. the method according to claim 1 based on speech recognition search electronic component, which is characterized in that wherein step 4
Described in custom search demand refer to the search project that user is judged by input content, refer to but be not limited to：Product type,
Product brand, product parameters, product producer.
3. the method according to claim 1 based on speech recognition search electronic component, which is characterized in that wherein step 5
In the search module the course of work such as：System is existing to inquiry content（Text）Carry out natural-sounding processing analysis（So-called NLP）,
Big data analysis is carried out in conjunction with active user's search need, and to demand, demand high frequency under big data support is associated with and is associated with
, it determines the actual search demand in maximum likelihood, obtains corresponding search data, and be supplied to user.
4. the method according to claim 1 based on speech recognition search electronic component, which is characterized in that in step 5
In, also apply keyword treatment process in carrying out natural-sounding processing analysis, keyword treatment process be to keyword into
Row is extracted, pretreatment, is corrected, and is split.
5. the method according to claim 4 based on speech recognition search electronic component, which is characterized in that wherein keyword
Extraction is that the information and keyword database of text are converted by comparing, and proposes associative key.
6. the method according to claim 4 based on speech recognition search electronic component, which is characterized in that keyword is located in advance
Reason is to carry out denoising to keyword.
7. the method according to claim 4 based on speech recognition search electronic component, which is characterized in that keyword amendment
And fractionation intersects amendment and splits keyword when comparing keyword database.
8. the method according to claim 1 based on speech recognition search electronic component, which is characterized in that wherein search needs
Analysis module is sought, for combining current search behavior and inquiry content to determine user's actual need, that is, determines the letter that user provides
Type is ceased, and judges to belong to product item to be searched.
9. the method according to claim 1 based on speech recognition search electronic component, which is characterized in that in step 5
In, in the service process that obtains above-mentioned meet demand, it is also necessary to use data acquisition module, the data acquisition module is for obtaining
Take search result corresponding data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810975582.3A CN108831482A (en) | 2018-08-24 | 2018-08-24 | A method of based on speech recognition search electronic component |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810975582.3A CN108831482A (en) | 2018-08-24 | 2018-08-24 | A method of based on speech recognition search electronic component |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108831482A true CN108831482A (en) | 2018-11-16 |
Family
ID=64151510
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810975582.3A Pending CN108831482A (en) | 2018-08-24 | 2018-08-24 | A method of based on speech recognition search electronic component |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108831482A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109815379A (en) * | 2018-12-28 | 2019-05-28 | 深圳市世强元件网络有限公司 | A kind of intelligent search recommended method, storage medium and terminal for content |
| CN111291088A (en) * | 2020-01-17 | 2020-06-16 | 安徽机器猫电子商务股份有限公司 | Intelligent part number searching method based on subordination relation |
| CN112579629A (en) * | 2020-12-10 | 2021-03-30 | 青岛檬豆网络科技有限公司 | Method for helping purchasers of electronic component enterprises to accurately find products |
| CN114201662A (en) * | 2021-12-03 | 2022-03-18 | 上海电气智慧城市信息科技有限公司 | A data middle-end operating system and using method thereof |
| CN114912002A (en) * | 2022-05-30 | 2022-08-16 | 深圳市云采网络科技有限公司 | Electronic component searching method and device, electronic equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1573928A (en) * | 2003-05-29 | 2005-02-02 | 微软公司 | Semantic object synchronous understanding implemented with speech application language tags |
| US20090306981A1 (en) * | 2008-04-23 | 2009-12-10 | Mark Cromack | Systems and methods for conversation enhancement |
| US20100161446A1 (en) * | 2008-12-19 | 2010-06-24 | At&T Intellectual Property I, L.P. | System and method for wireless ordering using speech recognition |
| CN104599184A (en) * | 2014-12-09 | 2015-05-06 | 北京奇虎科技有限公司 | Stock information pushing system |
| CN104794218A (en) * | 2015-04-28 | 2015-07-22 | 百度在线网络技术（北京）有限公司 | Voice searching method and device |
| CN107408156A (en) * | 2015-03-09 | 2017-11-28 | 皇家飞利浦有限公司 | For carrying out semantic search and the system and method for extracting related notion from clinical document |
-
2018
- 2018-08-24 CN CN201810975582.3A patent/CN108831482A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1573928A (en) * | 2003-05-29 | 2005-02-02 | 微软公司 | Semantic object synchronous understanding implemented with speech application language tags |
| US20090306981A1 (en) * | 2008-04-23 | 2009-12-10 | Mark Cromack | Systems and methods for conversation enhancement |
| US20100161446A1 (en) * | 2008-12-19 | 2010-06-24 | At&T Intellectual Property I, L.P. | System and method for wireless ordering using speech recognition |
| CN104599184A (en) * | 2014-12-09 | 2015-05-06 | 北京奇虎科技有限公司 | Stock information pushing system |
| CN107408156A (en) * | 2015-03-09 | 2017-11-28 | 皇家飞利浦有限公司 | For carrying out semantic search and the system and method for extracting related notion from clinical document |
| CN104794218A (en) * | 2015-04-28 | 2015-07-22 | 百度在线网络技术（北京）有限公司 | Voice searching method and device |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109815379A (en) * | 2018-12-28 | 2019-05-28 | 深圳市世强元件网络有限公司 | A kind of intelligent search recommended method, storage medium and terminal for content |
| CN111291088A (en) * | 2020-01-17 | 2020-06-16 | 安徽机器猫电子商务股份有限公司 | Intelligent part number searching method based on subordination relation |
| CN112579629A (en) * | 2020-12-10 | 2021-03-30 | 青岛檬豆网络科技有限公司 | Method for helping purchasers of electronic component enterprises to accurately find products |
| CN114201662A (en) * | 2021-12-03 | 2022-03-18 | 上海电气智慧城市信息科技有限公司 | A data middle-end operating system and using method thereof |
| CN114912002A (en) * | 2022-05-30 | 2022-08-16 | 深圳市云采网络科技有限公司 | Electronic component searching method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108831482A (en) | A method of based on speech recognition search electronic component | |
| CN109063221B (en) | Query intention identification method and device based on mixed strategy | |
| CN110138980B (en) | Intelligent outbound method, device, storage medium and server | |
| CN110147437A (en) | A kind of searching method and device of knowledge based map | |
| CN102866990A (en) | Thematic conversation method and device | |
| CN109815952A (en) | Brand name recognition methods, computer installation and computer readable storage medium | |
| CN103198067B (en) | A kind of service search method and system | |
| US20070043562A1 (en) | Email capture system for a voice recognition speech application | |
| CN109933645A (en) | Information query method, device, computer equipment and storage medium | |
| CN101149758A (en) | Searching system and searching method | |
| CN105744057A (en) | Intelligent voice dialogue interaction method and intelligent voice dialogue interaction device | |
| CN111666425B (en) | Automobile accessory searching method based on semantic knowledge | |
| CN115375380B (en) | Service data processing method and processing device based on attribute classification | |
| CN109408799A (en) | Semantic decision-making technique and system | |
| CN110413708B (en) | Data analysis system oriented to business terms | |
| CN110347786A (en) | A kind of tuning method and system of semantic model | |
| Noy et al. | What do we need for ontology integration on the semantic web, position statement | |
| CN116415180A (en) | Automatic data classification and classification method and device based on identification | |
| CN106339105A (en) | Method and device for identifying phonetic information | |
| CN112163075B (en) | Information recommendation method and device, computer equipment and storage medium | |
| CN116595149A (en) | Man-machine dialogue generation method, device, equipment and storage medium | |
| CN116757855A (en) | Intelligent insurance service method, device, equipment and storage medium | |
| CN104243501A (en) | Filtering and intercepting method for junk mail | |
| CN116701667A (en) | Keyword extraction method, system, equipment and storage medium | |
| CN115934923A (en) | E-commerce reply method and system based on big data |
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: 20181116 |