CN107977798A - A kind of risk evaluating method of e-commerce product quality - Google Patents
A kind of risk evaluating method of e-commerce product quality Download PDFInfo
- Publication number
- CN107977798A CN107977798A CN201711392410.5A CN201711392410A CN107977798A CN 107977798 A CN107977798 A CN 107977798A CN 201711392410 A CN201711392410 A CN 201711392410A CN 107977798 A CN107977798 A CN 107977798A
- Authority
- CN
- China
- Prior art keywords
- comment
- score
- product
- quality
- risk
- 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
Classifications
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- 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]
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Educational Administration (AREA)
- Theoretical Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention proposes a kind of risk evaluating method of e-commerce product quality, comprises the following steps that：1, comment corpus obtains：Product review specify information is crawled in electric business platform and be saved in database using web crawlers technology；2, Chinese natural language processing：Comment text is pre-processed first, qualitative character word is then extracted from comment data using conditional random field models；3, quality risk evaluation：Merged according to multi-dimensional data, design evaluation fusion function, calculate the final score per a electric business product, the risk class of product is obtained according to scoring.This is just the supervision of quality safety work of optimization e-commerce product, improves supervision quality and e-commerce security creates condition.
Description
Technical field：
The invention belongs to product quality management field, more particularly to a kind of risk evaluating method of e-commerce product quality.
Background technology：
Traditional method for quality control often only focuses on the quality management in production process, and dispatching from the factory for product means quality management
End.With the rise of total quality control, the scope of quality management extend to user's service stage, and enterprise is directed to sending out
Product quality problem during current family use, and these quality problems are fed back into design and producing department, so as to improve
Product quality, improves user experience.At present, corporate boss will collect the product during user's use by after-sale service department
Quality problems.Many large-scale manufacturing enterprises set up after-sale service point in the whole nation, and collecting user by after-sale service point was using
The quality problems run into journey, and these quality problems are fed back into design and producing department, provided for the improvement of product quality
Direction.But due to the limitation of fund, human and material resources etc., the covering of after-sale service point is limited in scope, or even the enterprise having is basic
After-sale service point is not just set up, so traditional collect the product quality during user's use by after-sale service department
Problem can not fully meet the demand of enterprise.
E-commerce refers to be traded activity and phase in a manner of electronic transaction on the networks such as internet, intranet
The activity of service is closed, is the various business activities carried out based on computer network, is the networking of traditional commerce activity.
Although e-commerce development is swift and violent, there is also many problems.One of them is e-commerce security problem.Carrying out electricity
During sub- commercial activity, it can all be related to the storage of substantial amounts of information and transmit, such as the transfer etc. of individual subscriber data, fund,
These behaviors are required for special technology to ensure security.Another major issue is e-commerce product quality.Country
State Administration of Quality Supervision, Inspection and Quarantine pays high attention to e-commerce product quality, and National Electrical commercial affairs product quality wind will be established in the end of the year 2013
Dangerous inspection center, works in concert with e-commerce companies such as Alibaba, Jingdone district, and structure is believed comprising e-commerce product sales volume
Risk Monitoring knowledge base including breath, calling information, evaluation information, company-information etc., is the improvement of e-commerce product quality
Strong support is provided with supervise and examine.
E-commerce product and traditional product are consistent in nature, are online difference lies in traditional product sales platform
Under, and e-commerce product is on line.Consumer by electric business platform, stay indoors can buy with solid shop/brick and mortar store
Product, this kind of product is referred to as e-commerce product.Virtual due to e-commerce, the pursuit that some enterprises can be unilateral is short
Phase economic interests, use inferior materials and turn out substandard goods, adulterate in process of production, produce counterfeit and shoddy goods, but in platform displaying but
It is qualified product.Consumer is difficult that the true and false and quality of identification product whether there is problem on network, therefore is very easy to
These defective products are bought, if can be by the analysis of the public sentiment data to network Shanghai amount and quality testing data, profit
With data mining technology, risk assessment is carried out to e-commerce product quality, it is possible to effectively avoid being triggered by product quality
Various problems.Therefore need quality testing department to take effective Supervision Measures and improve product quality level to supervise enterprise, at the same time
Also the management of e-commerce platform is strengthened.
The content of the invention：
In order to quickly and efficiently analyze its existing quality risk from magnanimity, the multi-source heterogeneous information for having underlying commodity,
It is to traditional electronic commerce method for quality control the present invention provides a kind of risk evaluating method of e-commerce product quality
One kind supplement.
The technical solution adopted by the present invention to solve the technical problems such as the description below：
A kind of risk evaluating method of e-commerce product quality, it is characterised in that：This method comprises the following steps：
Step 1：Corpus obtains：Using web crawlers software, formulation crawls rule, crawl and the relevant electric business net of appointed product
Stand and forum on user comment text, be saved in structured form in database；
Step 2：Chinese natural language processing：Data scrubbing operation is carried out to original comment data first, then utilizes Chinese
Comment language material is segmented natural language processing instrument for the first time respectively and part-of-speech tagging, new word identification, comment validity emotion
The pretreatment such as analysis is to obtain the sentiment analysis result of structuring and be saved in database, further, training condition random field
Model, finally extracts qualitative character word using conditional random field models from comment data；
Step 3：Quality risk is evaluated：Business trust comprehensive evaluation form is proposed first, and is gone out and each business based on the template statistics
The credit index of family；Further, valuation functions are built, complete the assessment to electric business product, according to design evaluatio fusion function, meter
The final score per a electric business product is calculated, finally, the risk class of product is obtained according to scoring.
In a kind of risk evaluating method of above-mentioned e-commerce product quality, in the step 1, due to network
Opening and the diversification of network comment, discreteness so that contain substantial amounts of " noise ", including nothing in the comment text of crawl
Effect comment, comment spam and repetition are commented on, these comments all can cause significant impact to follow-up text analyzing, in order to solve
" dirty " text, it is necessary to pre-processed to comment text.According to electric business comment text has short number of words, information is big and main body is clear and definite
The characteristics of, number of words threshold value can be set and determine whether that pleonasm comment removes invalid comment；It can sentence for comment spam
It is disconnected whether to be removed containing certain Chinese number of words；The literal similarity for finally calculating comment text removes repetition comment.
In a kind of risk evaluating method of above-mentioned e-commerce product quality, in the step 2, its feature exists
In：（1）The governing word in dependency analysis result is labeled with the emotion word dictionary of arrangement, it is basic to obtain using word
The structural data of recording unit.（2）The result of sentiment analysis is divided into training set and test set, formulates condition random field feature
Template, using Open-Source Tools bag, is trained the training set for having marked product feature, formation condition random field models, then
Product feature mark is carried out to test set using the model, different weighing factors is then given to inhomogeneous feature.
In a kind of risk evaluating method of above-mentioned e-commerce product quality, in the step 3, evaluation fusion
The calculation formula of function is：
Wherein,Sales Volume of Commodity model obatained score, retail shop's reputation model obatained score and comment text mould are represented respectively
Type obatained score,Weight shared by each factor is represented respectively.
In a kind of risk evaluating method of above-mentioned e-commerce product quality, in the step 3, evaluation fusion
In function algorithm,Calculation formula be：
Historical sales percentage：
Future sales percentage：
Sales Volume of Commodity score：
Wherein,Represent regression function,,,For i-th
Commodity penalty term is the percentage of the i-th issue.
In a kind of risk evaluating method of above-mentioned e-commerce product quality, in the step three, evaluating
In fusion function algorithm,Calculation formula be：
Wherein,For retail shop's score set,Represent that the i-th retail shop's score set and i-th of retail shop are final
Point.Represent j-th of score value of i-th of retail shop.Represent respectively, in each j-th of score set of retail shop
Maximum, average value and minimum value.
In a kind of risk evaluating method of above-mentioned e-commerce product quality, in the step three, evaluating
In fusion function algorithm,Calculation formula be：
Wherein, RQC represents comment quality coefficient, and QRG represents quality level score, and FWG represents Feature Words score, and ETA represents feelings
Feel trend analysis score.
Beneficial effects of the present invention：Magnanimity, multi-source heterogeneous is obtained from electric business platform website using web crawlers instrument
Product uses comment text, by shallow-layer, the Chinese text information processing technology of deep layer so that non-structured data become to tie
The data of structure, and therefrom find the quality problems of product, and then risk assessment is carried out to the various aspects of product quality.This is just
The most key transaction risk factor is determined for aid decision making person, the various problems triggered by product quality is effectively avoided, builds
Risk-prove infrastructure is erected, improves the security of e-commerce transaction.
Brief description of the drawings：
Fig. 1 is the Figure of abstract that the overall flow figure of the present invention is also the present invention.
Fig. 2 is the overall technology route map of the present invention.
The corpus that Fig. 3 is the present invention obtains flow chart.
Fig. 4 is the preconditioning technique route map of the present invention.
Fig. 5 is that it builds sentiment dictionary broad flow diagram.
Fig. 6 is its risk class division design drawing.
Embodiment：
With reference to specific attached drawing, the present invention is further illustrated.
The present invention is to carry out information scratching to large-scale electric business platform by web crawlers instrument, obtains magnanimity, multi-source heterogeneous
Chinese network user comment text, and Chinese natural language processing is carried out to it, establishes complete e-commerce product quality
The overall merit of risk.
A kind of risk evaluating method of e-commerce product quality, including corpus obtain, Chinese natural language processing and
Quality risk evaluates these three steps, as shown in Figure 1.These three steps are described in detail respectively below.
Step 1, corpus obtains：Using web crawlers instrument, some appointed product is gathered from large-scale electric business platform
The relevant information that product uses, and local data base is saved in, then the comment information of preservation is pre-processed, reduces data
In noise, obtain true, reliable, non-structured comment corpus.
It is as shown in Figure 3 to comment on the process that corpus obtains.That formulates web crawlers instrument crawls rule, treats the big of crawl
Type electric business platform carries out data grabber, and the result of crawl is stored into local data base, becomes original comment text；To original
Comment text carries out data prediction, and generation comment corpus, is also stored into database.
Wherein, due to the opening of network and diversification, the discreteness of network comment so that captured from electric business platform
Contain a large amount of noises in network comment text, if directly carrying out text mining to it, acquired results may with it is actual produce compared with
Large deviation.So meeting actual as a result, original comment set need to be filtered and cleaned to obtain, noise is reduced.In advance
Processing includes deleting blank, useless comment, deletes punctuation mark unnecessary in comment, deletes the word of redundancy in comment, deletes
Except comment of the number of words less than 4 words, modification wrong word, simplified Chinese character replaces the complex form of Chinese characters, the comment for deleting redundancy etc..
Step 2, Chinese natural language is handled：Comment language material is carried out for the first time respectively using Chinese natural language handling implement
Participle and part-of-speech tagging, new word identification, optimize the operation such as participle and part-of-speech tagging, syntactic analysis and sentiment analysis, obtains structure
The sentiment analysis result of change is simultaneously saved in database, as shown in Figure 4.
2.1）Participle and part-of-speech tagging
Comment of the client feedback on electric business platform is for the purpose of exchanging and share, and is the unstructured natural language of textual form
Speech, to therefrom excavate valuable information, then needs that it is converted into structural data by participle technique.To commenting on language material
The instrument for carrying out participle use is ICTCLAS, and the instrument of part-of-speech tagging use is carried out to the comment language material after participle and is also
ICTCLAS, in order to improve the precision ratio of product feature extraction, the part-of-speech tagging method of selection can mark out more specific situation
Two level marks.
2.2）Sentiment analysis
By analyzing the Chinese network comment text of the homologous isomery of magnanimity, the comment of user feedback is business of the user to purchase
The in-service evaluation of product, usually expresses the viewpoint of oneself with adjective, noun or verb.Sentiment dictionary is the set of emotion word.
In broad terms, refer to comprising the tendentious phrase of emotion or sentence;In the narrow sense, refer to comprising passionate tendentious word
Set.Sentiment dictionary generally comprises two parts, a positive emotion word dictionary and a negative emotion word dictionary.Sentiment dictionary
It is the basic resource of text emotion analysis.Chinese emotion vocabulary ontology library, is divided into 7 basic class by emotion and 21 small
Class, is respectively labeled word emotional category and intensity.These resources have forcefully promoted the research that text emotion is analyzed.
It builds sentiment dictionary main flow, and arrangement generates an emotion word dictionary herein as shown in Figure 5, for judging syntactic analysis
As a result whether the governing word of each word is emotion word in, if the governing word of certain word is emotion word, the emotion of the word is marked
IsOp is denoted as " Y ", conversely, being denoted as " N ".
Step 3, quality risk is evaluated：Using P2P technologies, the credit index of businessman is assessed, in combination with
The businessman's creditworthiness information collected（As customer scores）, propose the numeralization model x for businessman's prestige aspect；Reasonably
Virtual qualification authentication program is built to businessman or directly acquires the authentication information of businessman, businessman is assessed with this and possesses authentication credential
Degree, and propose corresponding numeralization model y.Finally to consider customer's comment, businessman's prestige, businessman's certification letter
The factors such as breath, commodity transaction information, are assigned each factor different weights, it are trained using neutral net here, are started
The weights of data item are set by hand, then weights are trained using monolayer neural networks.The calculating of weights is to e-commerce
The foundation of product risks overall merit has very big practical significance.Valuation functions are finally built, according to design evaluatio fusion function,
The final score per a electric business product is calculated, finally by the definite foundation of composite evaluation function S risk as shown in Figure 6
Overall merit.
The calculation formula of risk assessment fusion function is：
Wherein,Sales Volume of Commodity model obatained score, retail shop's reputation model obatained score and comment text mould are represented respectively
Type obatained score,Weight shared by each factor is represented respectively.
Obtain result after sentiment analysis in above-mentioned steps and randomly select some records becoming training set, residue is recorded as surveying
Examination collection.Manually mark product feature is carried out to training set, conditional random field models is trained using training set, recycles model pair
Test set carries out signature, then deletes choosing, extracts product feature.The field of training set totally 6 row, be respectively morphology, part of speech,
The mark symbol of dependence, governing word, the Judgment by emotion of governing word and the product signature that manually marks, wherein product feature
Number collection is { B, I, L, O, U }, they represent that product feature starts respectively（B）, inside product feature（I）, product feature ending
（L）, non-product feature（O）, single product feature（U）.It is trained, is trained using condition random field Open-Source Tools bag
Model files, feature mark is carried out to test set.And the field of test set totally 7 row, be respectively morphology, part of speech, dependence,
Governing word, the Judgment by emotion of governing word, computer program automatic marking product signature and train model mark
Product signature.
Sales Volume of Commodity can represent the overall shop sales situation of businessman, reflect direct sense organ of the client to shop, into
The structure of this model of row plays the role of businessman's risk assessment important.
Calculation formula be：
Historical sales percentage：
Future sales percentage：
Sales Volume of Commodity score：
Wherein,Represent regression function,,,For i-th
Commodity penalty term is the percentage of the i-th issue.
The model of retail shop's prestigeCalculation formula be：
Wherein,For retail shop's score set,Represent that the i-th retail shop's score set and i-th of retail shop are final
Point.Represent j-th of score value of i-th of retail shop.Represent respectively, j-th of each retail shop
Maximum, average value and minimum value in score set.
In businessman's reputation model, product sales volume model, consumer reviews' model, most important of which is that consumer reviews
Model.
Regular score of the emotion word that the present invention uses based on sentiment dictionary, wherein have chosen the part word in sentiment dictionary
Language, and some new cyberspeaks have been it is possible to additionally incorporate, division also has been re-started to the emotional semantic classification of word.In the feelings of the present invention
Feel in word dictionary, the Sentiment orientation of word includes three classes：Commendation, derogatory sense, neutrality, are represented with P, N, M respectively, and P represents emotion and inclines
Be that+5, N represents Sentiment orientation analysis and represents Sentiment orientation as 0, M and analyzes as -5 to analysis, calculated using NB Algorithm.
In fusion function algorithm is evaluated,Calculation formula be：
Wherein, RQC represents comment quality coefficient, and QRG represents quality level score, and FWG represents Feature Words score, and ETA represents feelings
Feel trend analysis score.It is the ith feature of comment data,,,,The length of sentence, sentence are represented respectively
In word number, the average length of sentence, the number of part of speech.The crawl data of electric business platform are represented, the inside is related to
The grade of customer；The data captured from forum are represented, the inside does not have the division of customer's grade.Risk assessment
Algorithm is based on emotion word dictionary and degree adverb dictionary.
The present invention can utilize web crawlers instrument capture on large-scale electric business platform with the relevant user comment of appointed product
Text, and a series of processing are carried out to it, reasonable and exercisable Risk Assessment Index System is established, and then to product quality
Various aspects carry out risk assessment.Using the method for the present invention, e-commerce product supervision of quality safety work can be optimized, carried
High supervision quality, sound assurance is provided for e-commerce security.
Claims (9)
- A kind of 1. risk evaluating method of e-commerce product quality, it is characterised in that：Step 1：Corpus obtainsUsing web crawlers software, formulation crawls rule, crawl and the use in the relevant electric business website of appointed product and forum Family comment text, is saved in database with structured form；Step 2：Chinese natural language processingData scrubbing operation is carried out to original comment data first, then using Chinese natural language handling implement to comments Material is segmented for the first time respectively and part-of-speech tagging, new word identification, the pretreatment of comment validity sentiment analysis etc. are to obtain structuring Sentiment analysis result and be saved in database, further, training condition random field models, finally utilize condition random field mould Type extracts qualitative character word from comment data；Step 3：Quality risk is evaluatedBusiness trust comprehensive evaluation form is proposed first, and goes out the credit index with each businessman based on the template statistics；Further, Valuation functions are built, complete the assessment to electric business product, according to design evaluatio fusion function, are calculated per a electric business product Final score, finally, the risk class of product is obtained according to scoring.
- A kind of 2. risk evaluating method of e-commerce product quality as claimed in claim 1, it is characterised in that：In step 1 In, crawler technology is by the http protocol in webpage, and the regular expression made, for gathering electric business website, certain is special Determine the comment information in comment on commodity area.
- A kind of 3. risk evaluating method of e-commerce product quality as claimed in claim 1, it is characterised in that：In step 2 In,（1）Mainly comment text data default value, text are repeated for cleaning to text data and the pre- place of comment number of words limitation Reason；（2）Product feature term clustering and its definition sentiment analysis of weight are segmented to text data.
- A kind of 4. risk evaluating method of e-commerce product quality as claimed in claim 3, it is characterised in that：（1）With whole The emotion word dictionary of reason is labeled the governing word in dependency analysis result, obtains using word as master record unit Structural data；（2）The result of sentiment analysis is divided into training set and test set, formulates condition random field feature templates, is utilized Open-Source Tools bag, is trained the training set for having marked product feature, and formation condition random field models, recycle the model Product feature mark is carried out to test set, different weighing factors is given to inhomogeneous feature.
- A kind of 5. risk evaluating method of e-commerce product quality as claimed in claim 1, it is characterised in that：In step 3 In, the calculation formula for evaluating fusion function is：Wherein,Sales Volume of Commodity model obatained score, retail shop's reputation model obatained score and comment text mould are represented respectively Type obatained score,Weight shared by each factor is represented respectively.
- A kind of 6. risk evaluating method of e-commerce product quality as claimed in claim 5, it is characterised in that：In step 3 In, evaluate in fusion function algorithm,Calculation formula be：Historical sales percentage：Future sales percentage：Sales Volume of Commodity score：Wherein,Represent regression function,,,For i-th Commodity penalty term is the percentage of the i-th issue.
- A kind of 7. risk evaluating method of e-commerce product quality as claimed in claim 5, it is characterised in that：Melt in evaluation Close in function algorithm,Calculation formula be：Wherein,For retail shop's score set,Represent i-th retail shop's score set and i-th of retail shop's final score；Represent j-th of score value of i-th of retail shop；Represent respectively, j-th of each retail shop Divide maximum, average value and the minimum value in set.
- 8. in a kind of risk evaluating method of e-commerce product quality as claimed in claim 5, it is characterised in that：Evaluating In fusion function algorithm,Calculation formula be：Wherein, RQC represents comment quality coefficient, and QRG represents quality level score, and FWG represents Feature Words score, and ETA represents feelings Feel trend analysis score.
- A kind of 9. risk evaluating method of e-commerce product quality as claimed in claim 1, it is characterised in that：The matter Amount risk assessment is that the risk class of e-commerce product quality is marked off according to evaluation fusion function total score.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711392410.5A CN107977798B (en) | 2017-12-21 | 2017-12-21 | Risk assessment method for quality of electronic commerce product |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711392410.5A CN107977798B (en) | 2017-12-21 | 2017-12-21 | Risk assessment method for quality of electronic commerce product |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107977798A true CN107977798A (en) | 2018-05-01 |
| CN107977798B CN107977798B (en) | 2023-09-12 |
Family
ID=62007090
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711392410.5A Active CN107977798B (en) | 2017-12-21 | 2017-12-21 | Risk assessment method for quality of electronic commerce product |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107977798B (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108648022A (en) * | 2018-05-10 | 2018-10-12 | 广州腾骋飞贸易有限公司 | A kind of commodity defect estimation method based on big data |
| CN109254959A (en) * | 2018-08-17 | 2019-01-22 | 广东技术师范学院 | A kind of data evaluation method, apparatus, terminal device and readable storage medium storing program for executing |
| CN109308567A (en) * | 2018-08-14 | 2019-02-05 | 广州广之旅国际旅行社股份有限公司 | A kind of full dimension service evaluation system of travelling products and method |
| CN109408808A (en) * | 2018-09-12 | 2019-03-01 | 中国传媒大学 | A kind of appraisal procedure and assessment system of artistic works |
| CN109460508A (en) * | 2018-10-10 | 2019-03-12 | 浙江大学 | A kind of efficient comment spam groups of users detection method |
| CN109472462A (en) * | 2018-10-18 | 2019-03-15 | 中山大学 | A kind of project risk ranking method and device based on the fusion of multi-model storehouse |
| CN110738056A (en) * | 2018-07-03 | 2020-01-31 | 百度在线网络技术（北京）有限公司 | Method and apparatus for generating information |
| CN110942259A (en) * | 2019-12-10 | 2020-03-31 | 北方工业大学 | Community gas equipment risk assessment method and device |
| CN111523322A (en) * | 2020-04-25 | 2020-08-11 | 中信银行股份有限公司 | Requirement document quality evaluation model training method and requirement document quality evaluation method |
| CN111612340A (en) * | 2020-05-21 | 2020-09-01 | 中国标准化研究院 | Network commodity inspection sampling method based on big data |
| WO2020177463A1 (en) * | 2019-03-04 | 2020-09-10 | 拉扎斯网络科技（上海）有限公司 | Information processing method and apparatus, storage medium, and electronic device |
| CN111861507A (en) * | 2020-06-30 | 2020-10-30 | 成都数之联科技有限公司 | Identification method and system for analyzing risks of online catering stores in real time |
| CN112801384A (en) * | 2021-02-03 | 2021-05-14 | 湖北民族大学 | Commodity quality evaluation and prediction method, system, medium and equipment |
| CN113793169A (en) * | 2021-08-12 | 2021-12-14 | 惠州Tcl云创科技有限公司 | User comment data processing method, device, equipment and storage medium |
| CN115081890A (en) * | 2022-06-27 | 2022-09-20 | 湖北中烟工业有限责任公司 | Cigarette formula module quality monitoring system, method and related components |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104462333A (en) * | 2014-12-03 | 2015-03-25 | 上海耀肖电子商务有限公司 | Shopping search recommending and alarming method and system |
| US20150363840A1 (en) * | 2014-06-13 | 2015-12-17 | Mastercard International Incorporated | Systems and Methods for Recommending Merchants to Consumers |
| CN105844424A (en) * | 2016-05-30 | 2016-08-10 | 中国计量学院 | Product quality problem discovery and risk assessment method based on network comments |
| CN107133214A (en) * | 2017-05-05 | 2017-09-05 | 中国计量大学 | A kind of product demand preference profiles based on comment information are excavated and its method for evaluating quality |
-
2017
- 2017-12-21 CN CN201711392410.5A patent/CN107977798B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150363840A1 (en) * | 2014-06-13 | 2015-12-17 | Mastercard International Incorporated | Systems and Methods for Recommending Merchants to Consumers |
| CN104462333A (en) * | 2014-12-03 | 2015-03-25 | 上海耀肖电子商务有限公司 | Shopping search recommending and alarming method and system |
| CN105844424A (en) * | 2016-05-30 | 2016-08-10 | 中国计量学院 | Product quality problem discovery and risk assessment method based on network comments |
| CN107133214A (en) * | 2017-05-05 | 2017-09-05 | 中国计量大学 | A kind of product demand preference profiles based on comment information are excavated and its method for evaluating quality |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108648022A (en) * | 2018-05-10 | 2018-10-12 | 广州腾骋飞贸易有限公司 | A kind of commodity defect estimation method based on big data |
| CN110738056A (en) * | 2018-07-03 | 2020-01-31 | 百度在线网络技术（北京）有限公司 | Method and apparatus for generating information |
| CN110738056B (en) * | 2018-07-03 | 2023-12-19 | 百度在线网络技术（北京）有限公司 | Method and device for generating information |
| CN109308567A (en) * | 2018-08-14 | 2019-02-05 | 广州广之旅国际旅行社股份有限公司 | A kind of full dimension service evaluation system of travelling products and method |
| CN109254959A (en) * | 2018-08-17 | 2019-01-22 | 广东技术师范学院 | A kind of data evaluation method, apparatus, terminal device and readable storage medium storing program for executing |
| CN109254959B (en) * | 2018-08-17 | 2022-04-08 | 广东技术师范大学 | Data evaluation method and device, terminal equipment and readable storage medium |
| CN109408808A (en) * | 2018-09-12 | 2019-03-01 | 中国传媒大学 | A kind of appraisal procedure and assessment system of artistic works |
| CN109408808B (en) * | 2018-09-12 | 2023-08-22 | 中国传媒大学 | Evaluation method and evaluation system for literature works |
| CN109460508B (en) * | 2018-10-10 | 2021-10-15 | 浙江大学 | Efficient spam comment user group detection method |
| CN109460508A (en) * | 2018-10-10 | 2019-03-12 | 浙江大学 | A kind of efficient comment spam groups of users detection method |
| CN109472462A (en) * | 2018-10-18 | 2019-03-15 | 中山大学 | A kind of project risk ranking method and device based on the fusion of multi-model storehouse |
| CN109472462B (en) * | 2018-10-18 | 2022-02-01 | 中山大学 | Project risk rating method and device based on multi-model stack fusion |
| WO2020177463A1 (en) * | 2019-03-04 | 2020-09-10 | 拉扎斯网络科技（上海）有限公司 | Information processing method and apparatus, storage medium, and electronic device |
| CN110942259A (en) * | 2019-12-10 | 2020-03-31 | 北方工业大学 | Community gas equipment risk assessment method and device |
| CN111523322A (en) * | 2020-04-25 | 2020-08-11 | 中信银行股份有限公司 | Requirement document quality evaluation model training method and requirement document quality evaluation method |
| WO2021232856A1 (en) * | 2020-05-21 | 2021-11-25 | 中国标准化研究院 | Big data-based online sales commodity sampling and testing method |
| CN111612340A (en) * | 2020-05-21 | 2020-09-01 | 中国标准化研究院 | Network commodity inspection sampling method based on big data |
| CN111612340B (en) * | 2020-05-21 | 2023-10-17 | 中国标准化研究院 | Big data-based network sales commodity inspection sampling method |
| CN111861507A (en) * | 2020-06-30 | 2020-10-30 | 成都数之联科技有限公司 | Identification method and system for analyzing risks of online catering stores in real time |
| CN111861507B (en) * | 2020-06-30 | 2023-10-24 | 成都数之联科技股份有限公司 | Identification method and system for real-time analysis of risks of network restaurant shops |
| CN112801384A (en) * | 2021-02-03 | 2021-05-14 | 湖北民族大学 | Commodity quality evaluation and prediction method, system, medium and equipment |
| CN113793169A (en) * | 2021-08-12 | 2021-12-14 | 惠州Tcl云创科技有限公司 | User comment data processing method, device, equipment and storage medium |
| CN115081890A (en) * | 2022-06-27 | 2022-09-20 | 湖北中烟工业有限责任公司 | Cigarette formula module quality monitoring system, method and related components |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107977798B (en) | 2023-09-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107977798A (en) | A kind of risk evaluating method of e-commerce product quality | |
| US20210272040A1 (en) | Systems and methods for language and speech processing with artificial intelligence | |
| KR101741509B1 (en) | Device and method for analyzing corporate reputation by data mining of news, recording medium for performing the method | |
| Alsubari et al. | [Retracted] Development of Integrated Neural Network Model for Identification of Fake Reviews in E‐Commerce Using Multidomain Datasets | |
| CN102831234B (en) | Personalized news recommendation device and method based on news content and theme feature | |
| CN105512687A (en) | Emotion classification model training and textual emotion polarity analysis method and system | |
| CN110442728A (en) | Sentiment dictionary construction method based on word2vec automobile product field | |
| CN103886501B (en) | Post-loan risk early warning system based on semantic sentiment analysis | |
| CN109345272A (en) | One kind is based on the markovian shop credit risk forecast method of improvement | |
| Banić et al. | Using big data and sentiment analysis in product evaluation | |
| Radovanović et al. | Review spam detection using machine learning | |
| Ishfaq et al. | Identifying the influential bloggers: a modular approach based on sentiment analysis | |
| Almagrabi et al. | A survey of quality prediction of product reviews | |
| Yao et al. | Online deception detection refueled by real world data collection | |
| Alksher et al. | A review of methods for mining idea from text | |
| Al Marouf et al. | Looking behind the mask: A framework for detecting character assassination via troll comments on social media using psycholinguistic tools | |
| Vukanti et al. | Business Analytics: A case-study approach using LDA topic modelling | |
| Chandrakala et al. | Identifying the label of crisis related tweets using deep neural networks for aiding emergency planning | |
| Purohit et al. | Product review opinion based on sentiment analysis | |
| Ben Khalifa et al. | Multiple criteria fake reviews detection using belief function theory | |
| Dinesh et al. | Product Reviews on Opinion Mining using NLP Techniques | |
| Tang et al. | Emotion analysis platform on chinese microblog | |
| Sharma et al. | Score prediction model for sentiment classification using machine learning algorithms | |
| Chandurkar et al. | Sentiment analysis: A review and comparative analysis on colleges | |
| Sing et al. | Judgemental Analysis of Data and Prediction Using Ann |
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 |