CN107526782A - Demand supply matching process based on natural language analysis - Google Patents
Demand supply matching process based on natural language analysis Download PDFInfo
- Publication number
- CN107526782A CN107526782A CN201710622701.2A CN201710622701A CN107526782A CN 107526782 A CN107526782 A CN 107526782A CN 201710622701 A CN201710622701 A CN 201710622701A CN 107526782 A CN107526782 A CN 107526782A
- Authority
- CN
- China
- Prior art keywords
- information
- natural language
- language analysis
- production unit
- user
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
-
- 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
- G06F16/951—Indexing; Web crawling techniques
-
- 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
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0605—Supply or demand aggregation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention provides a kind of electric business customer satisfaction evaluation method based on natural language analysis, comprises the following steps:(1)User's message information in target web is obtained by reptile instrument;(2)Clean user's message information;(3)The single frequency and repetition frequency degree of vocabulary in user's message information valid data are obtained, forms product demand keyword set;(4)According to the type of keyword and frequency value, product demand information is obtained;(5)Obtain each production unit information;(5)Production unit information is matched with product demand information and sends corresponding product demand information to production unit.Beneficial effect of the present invention is:Natural language analysis is carried out so as to extract the product demand information in market by information of leaving a message the user on network, corresponding production unit is sent to, so as to greatly improve resource matched degree, brings huge economic benefit and social benefit;Method is quickly direct, result of calculation good reliability.
Description
Technical field
The present invention relates to natural language processing field, in particular to a kind of demand-supply based on natural language analysis
Method of completing the square.
Background technology
User's message information on network contains affluent resources, and user is can extract out to product by natural language analysis
Demand information, if it is possible to these information analyses are arranged and are sent to production unit, it will create huge social value.But
Do not have effective method in the prior art.
The content of the invention
The goal of the invention of the present invention is in view of the above-mentioned problems existing in the prior art, there is provided a kind of based on natural language point
The electric business customer satisfaction evaluation method of analysis.
Foregoing invention purpose is realized by following scheme:
Demand based on natural language analysis-supply matching process, comprises the following steps:(1)Target is obtained by reptile instrument
User's message information in webpage;(2)Clean user's message information;(3)Obtain vocabulary in user's message information valid data
Single frequency and repetition frequency degree, form product demand keyword set;(4)According to the type of keyword and frequency value, produced
Product demand information;(5)Obtain each production unit information;(5)Production unit information is matched with product demand information and to
Production unit sends corresponding product demand information.
Further, production unit information includes geographical position, production capacity and degrees of comparison information.
Further, target web includes electric business platform, forum, user message information of the same IP in multiple Homepage Publishings
It is considered as same demand information.
Further, cleaning step includes(2-1):Waste advertisements are removed according to lists of keywords.
Further, cleaning step includes(2-2):Remove the unconventional data with website information in comment data.
Further, cleaning step includes(2-3):Remove and repeat comment data.
Beneficial effect of the present invention is:Natural language analysis is carried out so as to extract by information of leaving a message the user on network
Go out the product demand information in market, be sent to corresponding production unit, so as to greatly improve resource matched degree, bring huge warp
Benefit of helping and social benefit;Method is quickly direct, result of calculation good reliability.
Embodiment
Below in conjunction with specific embodiment, the invention will be further described.
Demand based on natural language analysis-supply matching process, comprises the following steps:(1)Obtained by reptile instrument
User's message information in target web;(2)Clean user's message information;(3)Obtain word in user's message information valid data
The single frequency and repetition frequency degree of remittance, form product demand keyword set;(4)According to the type of keyword and frequency value, obtain
To product demand information;(5)Obtain each production unit information;(5)Production unit information is matched with product demand information
And send corresponding product demand information to production unit.
Production unit information includes geographical position, production capacity and degrees of comparison information.Target web includes electric business platform, opinion
Altar, same IP are considered as same demand information in user's message information of multiple Homepage Publishings.Cleaning step includes(2-1):According to
Lists of keywords removes waste advertisements.Cleaning step includes(2-2):Remove the unconventional number with website information in comment data
According to.Cleaning step includes(2-3):Remove and repeat comment data.
Although the present invention is described by reference to preferred embodiment, those of ordinary skill in the art should
Work as understanding, the description of above-described embodiment can be not limited to, in the range of claims, can make each in form and details
Kind change.
Claims (6)
1. the demand based on natural language analysis-supply matching process, it is characterised in that comprise the following steps:(1)Pass through reptile
Instrument obtains user's message information in target web;(2)Clean user's message information;(3)It is effective to obtain user's message information
The single frequency and repetition frequency degree of vocabulary in data, form product demand keyword set;(4)According to the type and frequency of keyword
Angle value, obtain product demand information;(5)Obtain each production unit information;(5)Production unit information and product demand information are entered
Row matching simultaneously sends corresponding product demand information to production unit.
2. the demand based on natural language analysis-supply matching process according to claim 1, it is characterised in that:Production
Unit information includes geographical position, production capacity and degrees of comparison information.
3. the demand based on natural language analysis-supply matching process according to claim 1, it is characterised in that:Target
Webpage includes electric business platform, forum, and same IP is considered as same demand information in user's message information of multiple Homepage Publishings.
4. the demand based on natural language analysis-supply matching process according to claim 1, it is characterised in that cleaning step
Suddenly include(2-1):Waste advertisements are removed according to lists of keywords.
5. the demand based on natural language analysis-supply matching process according to claim 1, it is characterised in that cleaning step
Suddenly include(2-2):Remove the unconventional data with website information in comment data.
6. the demand based on natural language analysis-supply matching process according to claim 1, it is characterised in that cleaning step
Suddenly include(2-3):Remove and repeat comment data.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710622701.2A CN107526782A (en) | 2017-07-27 | 2017-07-27 | Demand supply matching process based on natural language analysis |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710622701.2A CN107526782A (en) | 2017-07-27 | 2017-07-27 | Demand supply matching process based on natural language analysis |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107526782A true CN107526782A (en) | 2017-12-29 |
Family
ID=60680168
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710622701.2A Pending CN107526782A (en) | 2017-07-27 | 2017-07-27 | Demand supply matching process based on natural language analysis |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107526782A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109242640A (en) * | 2018-09-27 | 2019-01-18 | 唐山市奎星电商供应链管理有限责任公司 | Electric business supply system and method |
CN109255026A (en) * | 2018-08-23 | 2019-01-22 | 云南师范大学 | A method of it is analyzed based on Co-word analysis and the learning demand of clustering |
CN113379398A (en) * | 2021-08-13 | 2021-09-10 | 北京明略软件系统有限公司 | Project requirement generation method and device, electronic equipment and storage medium |
-
2017
- 2017-07-27 CN CN201710622701.2A patent/CN107526782A/en active Pending
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109255026A (en) * | 2018-08-23 | 2019-01-22 | 云南师范大学 | A method of it is analyzed based on Co-word analysis and the learning demand of clustering |
CN109255026B (en) * | 2018-08-23 | 2021-06-25 | 云南师范大学 | Learning demand analysis method based on common word analysis and cluster analysis |
CN109242640A (en) * | 2018-09-27 | 2019-01-18 | 唐山市奎星电商供应链管理有限责任公司 | Electric business supply system and method |
CN113379398A (en) * | 2021-08-13 | 2021-09-10 | 北京明略软件系统有限公司 | Project requirement generation method and device, electronic equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11100466B2 (en) | Social media profiling for one or more authors using one or more social media platforms | |
CN104317959B (en) | Data digging method based on social platform and device | |
CN105247507B (en) | Method, system and storage medium for the influence power score for determining brand | |
CN103886047B (en) | Towards the online recommendation method of distribution of stream data | |
Jiang et al. | Spotting suspicious behaviors in multimodal data: A general metric and algorithms | |
CN104394118A (en) | User identity identification method and system | |
TW201717071A (en) | Recommendation method and device | |
CN107526782A (en) | Demand supply matching process based on natural language analysis | |
CN107122481B (en) | Real-time online prediction method for news popularity | |
CN103778214A (en) | Commodity property clustering method based on user comments | |
CN104751354B (en) | A kind of advertisement crowd screening technique | |
CN104917739A (en) | False account identification method and device | |
CN102298650B (en) | Distributed recommendation method of massive digital information | |
CN103942298B (en) | Recommendation method and system based on linear regression | |
US20170078415A1 (en) | Identifying Users' Identity Through Tracking Common Activity | |
CN107590691B (en) | Information publishing method and device, storage medium and terminal | |
Siddiqui et al. | Bots and Gender Profiling on Twitter. | |
Jalali et al. | Social network sampling using spanning trees | |
CN104268230A (en) | Method for detecting objective points of Chinese micro-blogs based on heterogeneous graph random walk | |
CN105978729B (en) | A kind of cellphone information supplying system and method based on user's internet log and position | |
US9489428B2 (en) | Search ranking method and system for community users | |
CN105824942A (en) | Item recommendation method and system based on collaborative filtering algorithm | |
CN102479193A (en) | Method and equipment for match search popularization based on match bid coefficient | |
CN105701224A (en) | Security information customized service system based on big data | |
Dansana et al. | An approach to analyse and forecast social media data using machine learning and data analysis |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20171229 |