CN106484802A - A kind of data processing method of the information for auto defect issue and device - Google Patents

A kind of data processing method of the information for auto defect issue and device Download PDF

Info

Publication number
CN106484802A
CN106484802A CN201610842681.5A CN201610842681A CN106484802A CN 106484802 A CN106484802 A CN 106484802A CN 201610842681 A CN201610842681 A CN 201610842681A CN 106484802 A CN106484802 A CN 106484802A
Authority
CN
China
Prior art keywords
information
network
influence
indicator vector
media platform
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
Application number
CN201610842681.5A
Other languages
Chinese (zh)
Inventor
姜肇财
孙宁
宋黎
李会通
段岩峰
费凡
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China National Institute of Standardization
Original Assignee
China National Institute of Standardization
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by China National Institute of Standardization filed Critical China National Institute of Standardization
Priority to CN201610842681.5A priority Critical patent/CN106484802A/en
Publication of CN106484802A publication Critical patent/CN106484802A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90Details of database functions independent of the retrieved data types
    • G06F16/95Retrieval from the web
    • G06F16/958Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90Details of database functions independent of the retrieved data types
    • G06F16/95Retrieval from the web
    • G06F16/951Indexing; Web crawling techniques

Landscapes

  • Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention provides a kind of data processing method of the network influence for auto defect and device,By mapping process is carried out to the key word comprising in input instruction,Obtain corresponding keyword set,Conveniently in different network media platform enterprising row information search,Information is avoided to omit,Afterwards,According to this keyword set,Multiple default network media platforms obtain respective information aggregate respectively,Increased and provide user the information source releasing news for assessment,Each self-corresponding network influence indicator vector set is determined respectively from the information aggregate of multiple network media platforms,And then achieve the evaluation indexes different for different network media platform formulations,Solve the problems, such as that the evaluation index leading to because evaluation index is single is poor with multiple information source matching degrees,Also so that the prejudice of the web influence force value of the auto defect calculating reduces,More truly reflect the size of certain power of influence formed in Internet communication for the class auto defect.

Description

A kind of data processing method of the information for auto defect issue and device
Technical field
The present invention relates to internet information spreading field, in particular, be related to a kind of for auto defect issue The data processing method of information and device.
Background technology
Popularization with Internet technology and development, the network media is various, interactive strong etc. excellent due to own propagation means Point, is increasingly becoming one of dissemination of news carrier;And along with Internet user increase and Chinese Automobile Industry ' progress, make Obtain automotive networking media to develop rapidly, consumer can also pass through to complain auto defect on automotive networking media platform, Form right-safeguarding alliance, and then protect the legitimate rights and interests of oneself.
The appraisal procedure of the power of influence that the information issued in Internet communication currently for auto defect user is formed, main If being directed to some network media platform crawl information that user issues thereon by means such as web crawlers, to judge certain The size of the power of influence that certain defect caused by a vehicle of one brand automobile is formed in Internet communication, and then know such The threat degree that the defect that automobile causes is brought to consumer of China person, interest in property, thus protect the rights and interests of consumer;So And, the power of influence that the existing information issued in Internet communication by assessing user is formed reflects auto defect and is formed Impact size method, the information by every time providing, by assessment, the information source that user releases news and user issued adopted Evaluation index is all excessively single, leads to the information gathering that user issues not comprehensive, the evaluation index of formulation and multiple information The matching degree in source is poor, and then makes assessment result carry certain prejudice it is impossible to truly reflect certain class auto defect The size of the power of influence formed in Internet communication.
Content of the invention
In view of this, the invention provides a kind of data processing method of the information for auto defect issue and device, The information gathering solving user's issue is not comprehensive, the evaluation index problem poor with the matching degree of multiple information sources.
For achieving the above object, the present invention provides following technical scheme:
A kind of data processing method of the information for auto defect issue, including:
Receives input instructs, and described input instruction is the key word of the brand, vehicle and the fault type that comprise automobile;
Key word in described input instruction is carried out mapping process, obtains keyword set;
According to described keyword set, obtain the information aggregate of multiple default network media platforms respectively;
Determine each self-corresponding web influence respectively from the information aggregate of each described default network media platform Power indicator vector set;
All described network influence indicator vector set will substitute into default impact force value computing formula, calculate automobile The web influence force value of defect.
Preferably, described obtain the information aggregate of multiple default network media platforms respectively according to described keyword set, Including:
Multiple described default network media platforms are classified, obtains the first kind and preset network media platform and Equations of The Second Kind Default network media platform;
Using described keyword set, preset the information that network media platform is comprised from the described first kind and determine bag Multiple first match information containing key word arbitrary in described keyword set;
Obtain the first edge information related to the first match information each described, generate multiple first information, and will The whole first information generating preset the first information set that network media platform obtains, wherein, institute as from the described first kind State the first information and comprise the first match information and the first edge information related to described first match information;
Using described keyword set, preset the information that network media platform is comprised from described Equations of The Second Kind and determine bag Multiple second match information containing key word arbitrary in described keyword set;
Obtain the second edge information related to the second match information each described, generate multiple second information, and will Whole second information generating preset the second information aggregate that network media platform obtains, wherein, institute as from described Equations of The Second Kind State the second packet and contain the second match information and the second edge information related to described second match information.
Preferably, determine respectively the described information aggregate from each described default network media platform and each correspond to Network influence indicator vector set, including:
Determine first network power of influence index using the whole described first edge information in described first information set Vector set;
Determine the second network influence index using the whole described second edge information in described second information aggregate Vector set.
Preferably, described all described network influence indicator vector set will substitute into default impact force value computing formula, Calculate the web influence force value of auto defect, including:
Described first network power of influence indicator vector set is substituted into the first default impact force value computing formula:
Calculate the first network impact force value of auto defect, wherein, FW is described first network power of influence mark sense Duration set, { FWfansk,FWforwardsk,FWthumbkIt is arbitrary in described first network power of influence indicator vector set FW First network power of influence indicator vector corresponding to the bar first information, Norm () function is Sigmond normalization function, and L is institute State the total quantity of the first information comprising in first network power of influence indicator vector set FW;
Described second network influence indicator vector set is substituted into the second default impact force value computing formula:
Calculate the second web influence force value of auto defect, wherein, FN is described second network influence mark sense Duration set, { FNprk,FNrankkIt is corresponding to any bar second information in described second network influence indicator vector set Second network influence indicator vector, Norm () function is Sigmond normalization function, and M refers to for described second network influence The total quantity of the second information comprising in the vectorial set FN of mark;
The first network of the described auto defect calculating is affected the second network shadow of force value and described auto defect Ring force value to be added, obtain the network influence total value of auto defect.
A kind of data processing equipment of the information for auto defect issue, including:
Receiving unit, for receives input instruction, described input instruction is brand, vehicle and the failure classes comprising automobile The key word of type;
Map unit, for the key word in described input instruction is carried out mapping process, obtains keyword set;
First acquisition unit, for according to described keyword set, obtaining the letter of multiple default network media platforms respectively Breath set;
First determining unit, each for determining respectively from the information aggregate of each described default network media platform Self-corresponding network influence indicator vector set;
First computing unit, for all described network influence indicator vector set substituting into default impact force value calculating Formula, calculates the web influence force value of auto defect.
Preferably, described first acquisition unit includes:
Taxon, for multiple described default network media platforms are classified, obtains the first kind and presets network matchmaker Body platform presets network media platform with Equations of The Second Kind;
Second determining unit, for using described keyword set, presetting network media platform from the described first kind and being wrapped Multiple first match information comprising arbitrary key word in described keyword set are determined in the information containing;
Second acquisition unit, for obtaining the first edge information related to the first match information each described, generates Multiple first information, and using the whole first information generating as first obtaining from the default network media platform of the described first kind Information aggregate, wherein, the described first information comprises the first match information and the first edge related to described first match information Information;
3rd determining unit, for using described keyword set, presetting network media platform from described Equations of The Second Kind and being wrapped Multiple second match information comprising arbitrary key word in described keyword set are determined in the information containing;
3rd acquiring unit, for obtaining the second edge information related to the second match information each described, generates Multiple second information, and using whole second information generating as second obtaining from the default network media platform of described Equations of The Second Kind Information aggregate, wherein, described second packet contains the second match information and the second edge related to described second match information Information.
Preferably, described first determining unit includes:
4th determining unit, for determining using the whole described first edge information in described first information set One network influence indicator vector set;
5th determining unit, for determining using the whole described second edge information in described second information aggregate Two network influence indicator vector set.
Preferably, described first computing unit includes:
Second computing unit, for substituting into the first default impact force value by described first network power of influence indicator vector set Computing formula:
Calculate the first network impact force value of auto defect, wherein, FW is described first network power of influence mark sense Duration set, { FWfansk,FWforwardsk,FWthumbkIt is arbitrary in described first network power of influence indicator vector set FW First network power of influence indicator vector corresponding to the bar first information, Norm () function is Sigmond normalization function, and L is institute State the total quantity of the first information comprising in first network power of influence indicator vector set FW;
3rd computing unit, for substituting into the second default impact force value by described second network influence indicator vector set Computing formula:
Calculate the second web influence force value of auto defect, wherein, FN is described second network influence mark sense Duration set, { FNprk,FNrankkIt is corresponding to any bar second information in described second network influence indicator vector set Second network influence indicator vector, Norm () function is Sigmond normalization function, and M refers to for described second network influence The total quantity of the second information comprising in the vectorial set FN of mark;
4th computing unit, for affecting force value and described automobile by the first network of the described auto defect calculating Second web influence force value of defect is added, and obtains the network influence total value of auto defect.
Understand via above-mentioned technical scheme, compared with prior art, the invention provides one kind is sent out for auto defect The data processing method of the information of cloth and device, by containing brand, vehicle and the failure classes of automobile in input instruction The key word of type carries out mapping process, obtains corresponding keyword set, conveniently in the different enterprising row informations of network media platform Search, expands the acquisition range that user releases news, it is to avoid information is omitted, afterwards, according to described keyword set, multiple Obtain respective information aggregate respectively on default network media platform, increased and provide the information that user releases news for assessment Source, determines each self-corresponding network influence indicator vector set from the information aggregate of multiple network media platforms respectively, And then achieve automatic gathering, the analytical calculation completing user is released news in the case of being not required to manually participate in, drawing can The network influence evaluation index quantifying, has reached the purpose formulating different evaluation indexes for different network media platforms, Solve the problems, such as that the evaluation index leading to because evaluation index is single is poor with multiple information source matching degrees, reduce meter simultaneously The prejudice of the web influence force value of the auto defect drawing is so as to more can truly reflect that certain class auto defect exists The size of the power of influence formed in Internet communication.
Brief description
In order to be illustrated more clearly that the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing Have technology description in required use accompanying drawing be briefly described it should be apparent that, drawings in the following description be only this Inventive embodiment, for those of ordinary skill in the art, on the premise of not paying creative work, can also basis The accompanying drawing providing obtains other accompanying drawings.
Fig. 1 is a kind of method of the data processing method of information for auto defect issue provided in an embodiment of the present invention Flow chart;
Fig. 2 is the side of another data processing method of information for auto defect issue provided in an embodiment of the present invention Method flow chart;
Fig. 3 is a kind of structure of the data processing equipment of information for auto defect issue provided in an embodiment of the present invention Schematic diagram;
Fig. 4 is the knot of another data processing equipment of information for auto defect issue provided in an embodiment of the present invention Structure schematic diagram.
Specific embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete Site preparation description is it is clear that described embodiment is only a part of embodiment of the present invention, rather than whole embodiments.It is based on Embodiment in the present invention, it is every other that those of ordinary skill in the art are obtained under the premise of not making creative work Embodiment, broadly falls into the scope of protection of the invention.
The embodiment of the invention discloses a kind of data processing method of the information for auto defect issue, refer to accompanying drawing 1, methods described specifically includes following steps:
S101:Receives input instructs, and described input instruction is the key of the brand, vehicle and the fault type that comprise automobile Word;
Specifically, in order to pass through on network the information searching issued of user exactly to being related to certain a automobile The information of a certain fault, can limit this target information to be searched, and this target information can be including but not limited to vapour The key word of the brand of car, vehicle and fault type;After receiving the input instruction of user, can be quickly from this input The key word of brand, vehicle and the fault type of this automobile to be searched is analyzed in instruction, and between key word Connected mode this programme does not limit, and can be connected by mathematical symbol, such as "+", " * " etc.;Word description can also be passed through To connect, such as " and ", "AND" etc.;Can also be connected by " space ".Therefore, the form of expression of the input instruction receiving can With such as " Audi's+A6+ burn oil ", and then obtain that this input instruction wants to know by parsing is with regard to " Audi's A6 vehicle " The size of the power of influence caused in current network public opinion of defect of " burn oil " existing.
S102:Key word in described input instruction is carried out mapping process, obtains keyword set;
Specifically, fully comprehensive in order to ensure key word, can be using mapping function to contained pass in input instruction Keyword carries out mapping process, and then obtains more vocabulary describing the same defects of same automobile, lacks as this vehicle is a certain Sunken keyword set, to obtain more information with regard to a certain defect of this vehicle from the information that the network user is issued. For example, " burn oil " this defect key word can be mapped as by the defect of " burn oil " that exist for " Audi's A6 vehicle " The vocabulary such as " burn oil ", " machine oil burning ", expand hunting zone.Wherein, the mapping data being adopted can be amassed according to history The tired record being associated with auto defect description is drawn.
S103:According to described keyword set, obtain the information aggregate of multiple default network media platforms respectively;
Specifically, using the keyword set obtaining, the information that user is issued from multiple default network media platforms In, search the information of the arbitrary key word comprising in this keyword set, and will be final from each default network media platform The multiple information obtaining as the information aggregate of this default network media platform so that follow-up to the letter in each information aggregate Breath is analyzed processing.Wherein, default network media platform is the predetermined multiple network matchmakers being related to automobile industry out Body platform, the number of default network media platform with real-time update, and then can extend information source at any time, increases Information Number Amount.
The mode this programme obtaining information aggregate from multiple default network media platforms does not limit, and can pass through canonical Coupling, the URL url using each default network media platform grabs the data content wanted.
S104:Determine each self-corresponding network respectively from the information aggregate of each described default network media platform Power of influence indicator vector set;
Specifically, determine network shadow corresponding with this information aggregate according to the information included in each information aggregate Ring power indicator vector set, be used as assessing the caused power of influence size in current network public opinion of a certain defect of this vehicle Principal element.Wherein, the set of network influence indicator vector is to issue with reference to user on multiple default network media platforms The extensiveness and intensiveness that information is propagated, formulate out more can truly reflect a certain defect of automotive type in network Formed in propagating influence indicator vector set, and for each information aggregate formulate network influence mark sense Duration set can preset the respective feature of network media platform and the web influence to user according to the difference obtaining information aggregate Power size and different, and then single evaluation index can be compared, sensitive reflect some high-quality user profile, and can so that The result that assessment obtains more has practical value.
S105:All described network influence indicator vector set will substitute into default impact force value computing formula, calculate Go out the web influence force value of auto defect;
Specifically, the degree of correlation of network media platform and automobile industry is all preset by consideration, and different default The information quality of the information aggregate acquired in network media platform, sets out default impact force value computing formula so that will be many After individual described network influence indicator vector set substitutes into, the result obtaining more can really reflect certain class auto defect The size of the power of influence formed in Internet communication.
In the disclosed data processing method of information issued for auto defect of the embodiment of the present invention, by input is referred to The key word containing brand, vehicle and the fault type of automobile in order carries out mapping process, obtains corresponding keyword set, Conveniently in different network media platform enterprising row information search, expand the acquisition range that user releases news, it is to avoid information Omit, afterwards, according to described keyword set, multiple default network media platforms obtain respective information aggregate respectively, Increased and provide user the information source releasing news for assessment, determine respectively from the information aggregate of multiple network media platforms Go out each self-corresponding network influence indicator vector set, and then achieve and formulate difference for different network media platforms and comment Estimate index, solve the problems, such as that the evaluation index leading to because evaluation index is single is poor with multiple information source matching degrees, also make The prejudice obtaining the web influence force value of auto defect finally calculating reduces, and more truly reflects certain class lacking of automobile It is trapped in the size of the power of influence formed in Internet communication.
On the basis of embodiment corresponding to Fig. 1, the embodiment of the invention discloses another is directed to what auto defect was issued The data processing method of information, refers to accompanying drawing 2, methods described specifically includes following steps:
S201:Receives input instructs, and described input instruction is the key of the brand, vehicle and the fault type that comprise automobile Word.
S202:Key word in described input instruction is carried out mapping process, obtains keyword set.
S203:Multiple described default network media platforms are classified, obtain the first kind preset network media platform with Equations of The Second Kind presets network media platform, and executes S204a and S204b simultaneously;
Specifically, in order that the assessment result of the web influence force value of auto defect obtaining more really reflects this The size of power of influence formed in Internet communication for the auto defect, need consider network today formed in be related to garage The characteristic that the network media platform of industry is each provided with, such as interactivity, instantaneity, magnanimity, sharing, personalization, socialization, Any one or more combination such as randomness, and default overall network media platform is carried out point according to respective characteristic Class, and then obtain the default network media platform of the first kind and the default network media platform of Equations of The Second Kind, to be subsequently respectively directed to this Two classes are preset network media platform and are carried out being directed to the assessment of the web influence force value of auto defect accordingly.
To further explain how in conjunction with example accurately default multiple network media platforms to be classified.For 90 pre-set network media platforms, by interactivity that this 90 network media platforms are each had, instantaneity And randomness is analyzed, draw belong in this 90 network media platforms network media platform of microblogging one class compared to For other kinds of network media platform, possess higher interactivity and instantaneity, as the institute of registration in this microblog Have user can share at any time, acquisition information, do not limited by other factors such as time, places;And the network matchmaker of microblogging one class Body platform, as a kind of platform shared and exchange, is more focused on the randomness that content presents, is facilitated user by a period of time Finding, what is heard, felt and other users are presented to by microblog.Therefore using the network media platform belonging to microblogging one class as One class presets network media platform;And the more close class network media platform of characteristic that other are had, the such as family of automobile, Phoenix automobile etc. presets network media platform as Equations of The Second Kind.
S204a:Using described keyword set, preset the information that network media platform is comprised really from the described first kind Make multiple first match information comprising arbitrary key word in described keyword set, and execute S205;
Specifically, using the keyword set obtaining, whole preset from what the first kind preset that network media platform comprised In network media platform, match the information that the whole users comprising arbitrary key word in this keyword set issue respectively, and Each information that coupling is obtained, as first match information, is preserved.For example in the network belonging to microblogging one class Carry out matching inquiry using whole key words that keyword set is comprised, if find comprising any one key in media platform The information word of word, then preserve this information word, as the basic data information of further evaluation analysis.
S204b:Using described keyword set, preset the information that network media platform is comprised really from described Equations of The Second Kind Make multiple second match information comprising arbitrary key word in described keyword set, and execute S206;
Specifically, using the keyword set obtaining, whole preset from what Equations of The Second Kind preset that network media platform comprised In network media platform, match the information that the whole users comprising arbitrary key word in this keyword set issue respectively, and Each information that coupling is obtained, as second match information, is preserved.For example in family this network matchmaker of automobile Carry out matching inquiry using whole key words that keyword set is comprised, if find comprising any one key word in body platform Article content, then this article content is preserved, as further evaluation analysis basic data information;
Secondly, on the different default network media platform of two classes, enter the coupling of row information respectively using keyword set During inquiry, the keyword set this programme being used does not limit, and can be to enter row information using identical keyword set Matching inquiry or be respectively directed to this two class preset network media platform characteristic, using different keyword set Enter the matching inquiry of row information.
S205:Obtain the first edge information related to the first match information each described, generate multiple first information, And the whole first information generating are preset, as from the described first kind, the first information set that network media platform obtains, its In, the described first information comprises the first match information and the first edge information related to described first match information, and executes S207;
Specifically, the property difference each being had due to the different default network media platform of two classes is larger, therefore in order to carry The verity of the assessment result of web influence force value of high auto defect, needs to preset network media platform institute for from this two class In the whole match information determined, extract respectively and can reflect auto defect formed in the propagation of this network media platform Power of influence size.That is, presetting, for the first kind, whole first coupling letters that network media platform is mated out Breath, extracts its first edge information respectively from each first match information again, and by this first match information with its One marginal information, as a first information, is preserved.In Tengxun's microblogging, 402 first coupling letters have for example been matched Breath, then extract the forwarding total number related to this information from each first match information, put and praise total number, this first coupling The first edge information such as vermicelli total number of persons of information publisher, and by relative for the first match information first edge information Set as a first information of acquisition from Tengxun's microblogging, and using get 402 first information as micro- from Tengxun The first information set of acquisition in rich, for being estimated analysis offer base for subsequently presetting network media platform for the first kind Plinth analytical data.
S206:Obtain the second edge information related to the second match information each described, generate multiple second information, And whole second information generating are preset, as from described Equations of The Second Kind, the second information aggregate that network media platform obtains, its In, described second packet contains the second match information and the second edge information related to described second match information, and executes S208.
Specifically, the property difference each being had due to the different default network media platform of two classes is larger, therefore in order to carry The verity of the assessment result of web influence force value of high auto defect, needs to preset network media platform institute for from this two class In the whole match information determined, extract respectively and can reflect auto defect formed in the propagation of this network media platform Power of influence size.That is, presetting, for Equations of The Second Kind, whole second coupling letters that network media platform is mated out Breath, extracts its second edge information respectively from each second match information again, and by this second match information with its Two marginal informations, as second information, are preserved.For example match in this network media platform of phoenix automobile 325 the second match information, then extract the publication medium source related to this information, this letter from each second match information Breath assumes the second edge information such as PR value in Google for the webpage, information issuing time, and will be associated therewith for the second match information Second edge information set as acquisition from phoenix automobile second information, and by get 325 second Information as the second information aggregate obtaining from phoenix automobile, for entering for being subsequently directed to the default network media platform of Equations of The Second Kind Row analysis and assessment provide fundamental analysiss data.
S207:Determine first network power of influence using the whole described first edge information in described first information set Indicator vector set, and execute S209;
Specifically, in order to prevent the evaluation index formulated poor with information source matching degree, and assessment result is led to exist relatively Big prejudice, the special Information Communication range of default network media platform different according to two classes of the embodiment of the present invention and depth Degree, makes the evaluation index of the power of influence size that can at utmost reflect auto defect formed in Internet communication.Pin Network media platform is preset to the first kind, the first network power of influence indicator vector formulated is to preset network according to this first kind Whole first edge information in the first information set that media platform gets and determine.Still enter taking Tengxun's microblogging as a example One step illustrates how to determine first network power of influence indicator vector set, for the first information collection getting from Tengxun's microblogging Close, extract whole first edge information of its correlation again from each first information of this first information set, then will The forwarding total number related to this information extracting from each first edge information, point praise total number, this first coupling The vermicelli total number of persons of information publisher is as a first network power of influence indicator vector, and is extracting whole first edges After information, obtain first network power of influence indicator vector set, so that subsequent calculations auto defect presets network matchmaker in the first kind Web influence force value produced by body platform.
S208:Determine the second network influence using the whole described second edge information in described second information aggregate Indicator vector set, and execute S2010;
Specifically, in order to prevent the evaluation index formulated poor with information source matching degree, and assessment result is led to exist relatively Big prejudice, the special Information Communication range of default network media platform different according to two classes of the embodiment of the present invention and depth Degree, makes the evaluation index of the power of influence size that can at utmost reflect auto defect formed in Internet communication.Pin Network media platform is preset to Equations of The Second Kind, the second network influence indicator vector formulated is to preset network according to this Equations of The Second Kind Whole second edge information in the second information aggregate that media platform gets and determine.Still enter taking phoenix automobile as a example One step illustrates how to determine the second network influence indicator vector set, for the second information collection getting from phoenix automobile Close, extract whole second edge information of its correlation again from each second information of this second information aggregate, and from This information extracted in each second edge information assumes PR value in Google for the webpage;Afterwards, according to phoenix automobile this Current the second match information sum issued of one network media platform accounts for the weight all releasing news, calculate phoenix automobile this One network media platform and the ident value of automobile industry dependency, this ident value can be represented using 0-10, and the number of ident value Value bigger then it represents that this network media platform of phoenix automobile is bigger with the dependency of automobile industry.Finally, by each second This information extracted in marginal information assumes PR value in Google for the webpage with calculated ident value as one second Network influence indicator vector, and after having extracted whole second edge information, obtain the second network influence indicator vector Set, so that subsequent calculations auto defect presets web influence force value produced by network media platform in Equations of The Second Kind.
S209:Described first network power of influence indicator vector set is substituted into the first default impact force value computing formula:
Calculate the first network impact force value of auto defect, wherein, FW is described first network power of influence mark sense Duration set, { FWfansk,FWforwardsk,FWthumbkIt is arbitrary in described first network power of influence indicator vector set FW First network power of influence indicator vector corresponding to the bar first information, Norm () function is Sigmond normalization function, and L is institute State the total quantity of the first information comprising in first network power of influence indicator vector set FW;And execute S2011;
Specifically, the specific formula for calculation of Norm () function is:
Wherein, the FWfans that t is comprised by first network power of influence indicator vectork,FWforwardsk,FWthumbkIn Any one.
S2010:Described second network influence indicator vector set is substituted into the second default impact force value computing formula:
Calculate the second web influence force value of auto defect, wherein, FN is described second network influence mark sense Duration set, { FNprk,FNrankkIt is corresponding to any bar second information in described second network influence indicator vector set Second network influence indicator vector, Norm () function is Sigmond normalization function, and M refers to for described second network influence The total quantity of the second information comprising in the vectorial set FN of mark;And execute S2011;
Specifically, the specific formula for calculation of Norm () function is:
Wherein, the FNpr that t is comprised by first network power of influence indicator vectork,FNrankkIn any one.
S2011:The first network of the described auto defect calculating is affected the second of force value and described auto defect Web influence force value is added, and obtains the network influence total value of auto defect.
In the disclosed data processing method of information issued for auto defect of the embodiment of the present invention, pre- by the first kind If network media platform presets network media platform with Equations of The Second Kind, get respectively in first information set and the second information aggregate Each self-contained first edge information and second edge information, then divide according to whole first edge information and second edge information Do not determine that the first kind presets network media platform and Equations of The Second Kind presets the first network power of influence mark sense of network media platform Duration set and the second network influence indicator vector set, and then achieve and formulate difference for different network media platform and comment Estimate index, solve the problems, such as that the evaluation index leading to because evaluation index is single is poor with multiple information source matching degrees, afterwards, Calculate auto defect according to first network power of influence indicator vector set and the second network influence indicator vector set again First network affects the second web influence force value of force value and auto defect, and then is added the network influence obtaining auto defect Total value, reduces the prejudice of the web influence force value of auto defect, more truly reflects certain class auto defect in network The size of the power of influence formed in propagation.
The embodiment of the invention discloses a kind of data processing equipment of the information for auto defect issue, refer to accompanying drawing 3, described device includes:
Receiving unit 301, for receives input instruction, described input instruction is brand, vehicle and the event comprising automobile The key word of barrier type;
Map unit 302, for the key word in described input instruction is carried out mapping process, obtains keyword set;
First acquisition unit 303, for according to described keyword set, obtaining multiple default network media platforms respectively Information aggregate;
First determining unit 304, for determining respectively from the information aggregate of each described default network media platform Go out each self-corresponding network influence indicator vector set;
First computing unit 305, for all described network influence indicator vector set substituting into default impact force value Computing formula, calculates the web influence force value of auto defect.
In the disclosed data processing equipment of information issued for auto defect of the embodiment of the present invention, by map unit The key word containing brand, vehicle and the fault type of automobile in input instruction is carried out mapping process by 302, obtains and corresponds to Keyword set, conveniently in different network media platform enterprising row information search, expands the collection model that user releases news Enclose, it is to avoid information is omitted, and afterwards, according to described keyword set, first acquisition unit 303 is in multiple default network media platforms Upper obtain respective information aggregate respectively, increased and provide the information source that releases news of user, the first determining unit for assessment 304 determine each self-corresponding network influence indicator vector set from the information aggregate of multiple network media platforms respectively, And then achieve and formulate different evaluation indexes for different network media platform, solve and lead to because evaluation index is single The evaluation index problem poor with multiple information source matching degrees, also reduces the lacking of automobile that the first computing unit 305 calculates The prejudice of sunken web influence force value is so as to more truly reflect certain class auto defect formed in Internet communication The size of power of influence.
The work process of modules provided in an embodiment of the present invention, refer to the method flow diagram corresponding to accompanying drawing 1, tool Body running process repeats no more.
Present embodiment discloses another is directed to the data processing equipment of the information that auto defect is issued, refer to accompanying drawing 4, Described device includes:
Receiving unit 301, map unit 302, first acquisition unit 303, the first determining unit 304, the first computing unit 305;
Wherein, described first acquisition unit 303 includes:
Taxon 3031, for multiple described default network media platforms are classified, obtains the first kind and presets net Network media platform presets network media platform with Equations of The Second Kind;
Second determining unit 3032, for using described keyword set, presetting network media platform from the described first kind Multiple first match information comprising arbitrary key word in described keyword set are determined in the information being comprised;
Second acquisition unit 3033, for obtaining the first edge information related to the first match information each described, Generate multiple first information, and the whole first information generating are preset what network media platform obtained as from the described first kind First information set, wherein, the described first information comprises the first match information and related to described first match information first Marginal information;
3rd determining unit 3034, for using described keyword set, presetting network media platform from described Equations of The Second Kind Multiple second match information comprising arbitrary key word in described keyword set are determined in the information being comprised;
3rd acquiring unit 3035, for obtaining the second edge information related to the second match information each described, Generate multiple second information, and whole second information generating are preset what network media platform obtained as from described Equations of The Second Kind Second information aggregate, wherein, described second packet contains the second match information and related to described second match information second Marginal information.
Described first determining unit 304 includes:
4th determining unit 3041, for being determined using the whole described first edge information in described first information set Go out first network power of influence indicator vector set;
5th determining unit 3042, for being determined using the whole described second edge information in described second information aggregate Go out the second network influence indicator vector set.
Described first computing unit 305 includes:
Second computing unit 3051, for substituting into the first default impact by described first network power of influence indicator vector set Force value computing formula:
Calculate the first network impact force value of auto defect, wherein, FW is described first network power of influence mark sense Duration set, { FWfansk,FWforwardsk,FWthumbkIt is arbitrary in described first network power of influence indicator vector set FW First network power of influence indicator vector corresponding to the bar first information, Norm () function is Sigmond normalization function, and L is institute State the total quantity of the first information comprising in first network power of influence indicator vector set FW;
3rd computing unit 3052, for substituting into the second default impact by described second network influence indicator vector set Force value computing formula:
Calculate the second web influence force value of auto defect, wherein, FN is described second network influence mark sense Duration set, { FNprk,FNrankkIt is corresponding to any bar second information in described second network influence indicator vector set Second network influence indicator vector, Norm () function is Sigmond normalization function, and M refers to for described second network influence The total quantity of the second information comprising in the vectorial set FN of mark;
4th computing unit 3053, for by the first network of the described auto defect calculating impact force value with described Second web influence force value of auto defect is added, and obtains the network influence total value of auto defect.
In the disclosed data processing equipment of information issued for auto defect of the embodiment of the present invention, obtain by second Unit 3033 and the 3rd determining unit 3034 get first information set and the second information collection, more respectively according to first information collection Close and each self-contained whole first edge information of the second information collection and second edge information, by the 4th determining unit 3041 and the Five determining units 3042 determine that the first kind presets network media platform and Equations of The Second Kind presets the first of network media platform respectively Network influence indicator vector set and the second network influence indicator vector set, and then achieve for different network matchmakers Different evaluation indexes formulated by body platform, solve the evaluation index leading to because evaluation index is single and multiple information source matching degrees Poor problem, afterwards, the second computing unit 3051 and the 3rd computing unit 3052 are according to first network power of influence indicator vector The first network that set and the second network influence indicator vector set calculate auto defect affects force value and auto defect Second web influence force value, and then the network influence total value obtaining auto defect is added by the 4th computing unit 3053, reduce The prejudice of the web influence force value of auto defect, more truly reflects certain class auto defect institute's shape in Internet communication The size of the power of influence becoming.
The work process of modules provided in an embodiment of the present invention, refer to the method flow diagram corresponding to accompanying drawing 2, tool Body running process repeats no more.
Described above to the disclosed embodiments, makes professional and technical personnel in the field be capable of or uses the present invention. Multiple modifications to these embodiments will be apparent from for those skilled in the art, as defined herein General Principle can be realized without departing from the spirit or scope of the present invention in other embodiments.Therefore, the present invention It is not intended to be limited to the embodiments shown herein, and be to fit to and principles disclosed herein and features of novelty phase one The scope the widest causing.

Claims (8)

1. a kind of data processing method of the information for auto defect issue is it is characterised in that methods described includes:
Receives input instructs, and described input instruction is the key word of the brand, vehicle and the fault type that comprise automobile;
Key word in described input instruction is carried out mapping process, obtains keyword set;
According to described keyword set, obtain the information aggregate of multiple default network media platforms respectively;
Determine that each self-corresponding network influence refers to respectively from the information aggregate of each described default network media platform Mark vector set;
All described network influence indicator vector set will substitute into default impact force value computing formula, calculate auto defect Web influence force value.
2. method according to claim 1 it is characterised in that described according to described keyword set, obtain multiple respectively The information aggregate of default network media platform, including:
Multiple described default network media platforms are classified, obtains the default network media platform of the first kind and preset with Equations of The Second Kind Network media platform;
Using described keyword set, determine from the information that the default network media platform of the described first kind is comprised and comprise institute State multiple first match information of arbitrary key word in keyword set;
Obtain the first edge information related to the first match information each described, generate multiple first information, and will generate Whole first information preset, as from the described first kind, the first information set that network media platform obtains, wherein, described the One packet contains the first match information and the first edge information related to described first match information;
Using described keyword set, determine from the information that the default network media platform of described Equations of The Second Kind is comprised and comprise institute State multiple second match information of arbitrary key word in keyword set;
Obtain the second edge information related to the second match information each described, generate multiple second information, and will generate Whole second information preset, as from described Equations of The Second Kind, the second information aggregate that network media platform obtains, wherein, described the Two packets contain the second match information and the second edge information related to described second match information.
3. method according to claim 2 is it is characterised in that the described letter from each described default network media platform Each self-corresponding network influence indicator vector set is determined respectively in breath set, including:
Determine first network power of influence indicator vector using the whole described first edge information in described first information set Set;
Determine the second network influence indicator vector using the whole described second edge information in described second information aggregate Set.
4. method according to claim 3 is it is characterised in that described will all described network influence indicator vector set Substitute into default impact force value computing formula, calculate the web influence force value of auto defect, including:
Described first network power of influence indicator vector set is substituted into the first default impact force value computing formula:
I ( F W ) = Σ k = 1 L ( 0.54 * N o r m ( FWfans k ) + 0.322 * N o r m ( FWforwards k ) + 0.138 * N o r m ( FWthumb k ) )
Calculate the first network impact force value of auto defect, wherein, FW is described first network power of influence mark sense quantity set Close, { FWfansk,FWforwardsk,FWthumbkFor any bar in described first network power of influence indicator vector set FW the First network power of influence indicator vector corresponding to one information, Norm () function is Sigmond normalization function, and L is described the The total quantity of the first information comprising in one network influence indicator vector set FW;
Described second network influence indicator vector set is substituted into the second default impact force value computing formula:
I ( F N ) = Σ k = 1 M ( 0.54 * N o r m ( FNpr k ) + 0.46 * N o r m ( FNrank k ) )
Calculate the second web influence force value of auto defect, wherein, FN is described second network influence mark sense quantity set Close, { FNprk,FNrankkBe in described second network influence indicator vector set corresponding to any bar second information second Network influence indicator vector, Norm () function is Sigmond normalization function, and M is described second network influence mark sense The total quantity of the second information comprising in duration set FN;
The first network of the described auto defect calculating is affected the second network influence of force value and described auto defect Value is added, and obtains the network influence total value of auto defect.
5. a kind of data processing equipment of the information for auto defect issue is it is characterised in that include:
Receiving unit, for receives input instruction, described input instruction is brand, vehicle and the fault type comprising automobile Key word;
Map unit, for the key word in described input instruction is carried out mapping process, obtains keyword set;
First acquisition unit, for according to described keyword set, obtaining the information collection of multiple default network media platforms respectively Close;
First determining unit is each right for determining respectively from the information aggregate of each described default network media platform The network influence indicator vector set answered;
First computing unit, for all described network influence indicator vector set substituting into default impact force value calculating public affairs Formula, calculates the web influence force value of auto defect.
6. device according to claim 5 is it is characterised in that described first acquisition unit includes:
Taxon, for multiple described default network media platforms are classified, obtains the default network media of the first kind and puts down Platform presets network media platform with Equations of The Second Kind;
Second determining unit, for using described keyword set, presetting what network media platform was comprised from the described first kind Multiple first match information comprising arbitrary key word in described keyword set are determined in information;
Second acquisition unit, for obtaining the first edge information related to the first match information each described, generates multiple The first information, and the whole first information generating are preset, as from the described first kind, the first information that network media platform obtains Set, wherein, the described first information comprises the first match information and the first edge information related to described first match information;
3rd determining unit, for using described keyword set, presetting what network media platform was comprised from described Equations of The Second Kind Multiple second match information comprising arbitrary key word in described keyword set are determined in information;
3rd acquiring unit, for obtaining the second edge information related to the second match information each described, generates multiple Second information, and whole second information generating are preset, as from described Equations of The Second Kind, the second information that network media platform obtains Set, wherein, described second packet contains the second match information and the second edge information related to described second match information.
7. device according to claim 6 is it is characterised in that described first determining unit includes:
4th determining unit, for determining the first net using the whole described first edge information in described first information set Network power of influence indicator vector set;
5th determining unit, for determining the second net using the whole described second edge information in described second information aggregate Network power of influence indicator vector set.
8. device according to claim 7 is it is characterised in that described first computing unit includes:
Second computing unit, calculates for described first network power of influence indicator vector set is substituted into the first default impact force value Formula:
I ( F W ) = Σ k = 1 L ( 0.54 * N o r m ( FWfans k ) + 0.322 * N o r m ( FWforwards k ) + 0.138 * N o r m ( FWthumb k ) )
Calculate the first network impact force value of auto defect, wherein, FW is described first network power of influence mark sense quantity set Close, { FWfansk,FWforwardsk,FWthumbkFor any bar in described first network power of influence indicator vector set FW the First network power of influence indicator vector corresponding to one information, Norm () function is Sigmond normalization function, and L is described the The total quantity of the first information comprising in one network influence indicator vector set FW;
3rd computing unit, calculates for described second network influence indicator vector set is substituted into the second default impact force value Formula:
I ( F N ) = Σ k = 1 M ( 0.54 * N o r m ( FNpr k ) + 0.46 * N o r m ( FNrank k ) )
Calculate the second web influence force value of auto defect, wherein, FN is described second network influence mark sense quantity set Close, { FNprk,FNrankkBe in described second network influence indicator vector set corresponding to any bar second information second Network influence indicator vector, Norm () function is Sigmond normalization function, and M is described second network influence mark sense The total quantity of the second information comprising in duration set FN;
4th computing unit, for affecting force value and described auto defect by the first network of the described auto defect calculating Second web influence force value be added, obtain the network influence total value of auto defect.
CN201610842681.5A 2016-09-22 2016-09-22 A kind of data processing method of the information for auto defect issue and device Pending CN106484802A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610842681.5A CN106484802A (en) 2016-09-22 2016-09-22 A kind of data processing method of the information for auto defect issue and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610842681.5A CN106484802A (en) 2016-09-22 2016-09-22 A kind of data processing method of the information for auto defect issue and device

Publications (1)

Publication Number Publication Date
CN106484802A true CN106484802A (en) 2017-03-08

Family

ID=58267759

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610842681.5A Pending CN106484802A (en) 2016-09-22 2016-09-22 A kind of data processing method of the information for auto defect issue and device

Country Status (1)

Country Link
CN (1) CN106484802A (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108765178A (en) * 2018-04-23 2018-11-06 华侨大学 The appraisal procedure of the transmission on Internet influence power of toy defect event
CN113259150A (en) * 2021-03-30 2021-08-13 联想(北京)有限公司 Data processing method, system and storage medium
CN113435866A (en) * 2021-08-25 2021-09-24 北京新河科技有限公司 Data processing system and method
CN113763024A (en) * 2021-03-19 2021-12-07 北京沃东天骏信息技术有限公司 Article attribute mining method, apparatus and storage medium

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103218375A (en) * 2012-01-20 2013-07-24 北京四维图新科技股份有限公司 POI (Point of Interest) information supplementing method and device
CN104317881A (en) * 2014-04-11 2015-01-28 北京理工大学 Method for reordering microblogs on basis of authorities of users' topics
CN104960523A (en) * 2015-06-25 2015-10-07 奇瑞汽车股份有限公司 Intelligent lane changing assisting system for intelligent vehicle and control method thereof
CN105247507A (en) * 2013-05-31 2016-01-13 惠普发展公司,有限责任合伙企业 Influence score of a brand

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103218375A (en) * 2012-01-20 2013-07-24 北京四维图新科技股份有限公司 POI (Point of Interest) information supplementing method and device
CN105247507A (en) * 2013-05-31 2016-01-13 惠普发展公司,有限责任合伙企业 Influence score of a brand
CN104317881A (en) * 2014-04-11 2015-01-28 北京理工大学 Method for reordering microblogs on basis of authorities of users' topics
CN104960523A (en) * 2015-06-25 2015-10-07 奇瑞汽车股份有限公司 Intelligent lane changing assisting system for intelligent vehicle and control method thereof

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
姜肇财 等: "我国汽车召回领域媒体信息传播影响力分析研究", 《标准科学》 *
宋沛军: "《网络营销理论与实务》", 30 September 2010, 西安电子科技大学出版社 *
方一: "网络舆情监测指标体系的设计与实证研究", 《中国优秀硕士学位论文全文数据库信息科技辑》 *

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108765178A (en) * 2018-04-23 2018-11-06 华侨大学 The appraisal procedure of the transmission on Internet influence power of toy defect event
CN113763024A (en) * 2021-03-19 2021-12-07 北京沃东天骏信息技术有限公司 Article attribute mining method, apparatus and storage medium
CN113259150A (en) * 2021-03-30 2021-08-13 联想(北京)有限公司 Data processing method, system and storage medium
CN113435866A (en) * 2021-08-25 2021-09-24 北京新河科技有限公司 Data processing system and method

Similar Documents

Publication Publication Date Title
CN106484802A (en) A kind of data processing method of the information for auto defect issue and device
Wang et al. Using humans as sensors: an estimation-theoretic perspective
JP6211605B2 (en) Ranking search results based on click-through rate
Falahrastegar et al. Tracking personal identifiers across the web
CN107515915B (en) User identification association method based on user behavior data
CN103605715B (en) Data Integration treating method and apparatus for multiple data sources
CN104424231B (en) The processing method and processing device of multidimensional data
CN106096040B (en) Organization web ownership place method of discrimination and its device based on search engine
CN103426191B (en) A kind of picture mask method and system
CN105975852A (en) Method and system for detecting sample relevance based on label propagation
CN107766470B (en) Intelligent statistical method, intelligent statistical display method and device for data sharing
KR20180088655A (en) A method for detecting web tracking services
CN104615627A (en) Event public sentiment information extracting method and system based on micro-blog platform
CN104301323B (en) Balanced third-party application personalized service and the method for user privacy information safety
CN111224923A (en) Detection method, device and system for counterfeit websites
CN102654861A (en) Method and system for calculating webpage extraction accuracy
CN105515859B (en) The method and system of community's detection are carried out to symbolic network based on similarity of paths
CN110110179A (en) House market heating power ground drawing generating method, device, equipment and storage medium
CN103729458B (en) Method and device for distinguishing webpage requests
Brügger 8. Using the web to examine the evolution of the abortion debate in Australia, 2005–2015
CN105912875A (en) Anonymous no-correlation detection method and epidemic situation monitoring method and device
CN103605735B (en) website data analysis method and device
CN106777015A (en) A kind of data analysing method based on accessible detecting system
CN104317903B (en) The recognition methods of the chapters and sections integrality of chapters and sections formula text and device
CN102957721B (en) Device and method for classifying users based on identification information

Legal Events

Date Code Title Description
C06 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: 20170308