CN110443646A - Product competition relational network analysis method and system - Google Patents

Product competition relational network analysis method and system Download PDF

Info

Publication number
CN110443646A
CN110443646A CN201910695212.9A CN201910695212A CN110443646A CN 110443646 A CN110443646 A CN 110443646A CN 201910695212 A CN201910695212 A CN 201910695212A CN 110443646 A CN110443646 A CN 110443646A
Authority
CN
China
Prior art keywords
product
competitive relation
competition
data
sub
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
Application number
CN201910695212.9A
Other languages
Chinese (zh)
Other versions
CN110443646B (en
Inventor
李佳楠
石玉柱
方钊
彭张林
陆效农
裴子瑶
周鹏
刘雨柔
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.)
Hefei Polytechnic University
Original Assignee
Hefei Polytechnic University
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 Hefei Polytechnic University filed Critical Hefei Polytechnic University
Priority to CN201910695212.9A priority Critical patent/CN110443646B/en
Publication of CN110443646A publication Critical patent/CN110443646A/en
Application granted granted Critical
Publication of CN110443646B publication Critical patent/CN110443646B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33—Querying
    • G06F16/3331—Query processing
    • G06F16/334—Query execution
    • G06F16/3344—Query execution using natural language analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/35—Clustering; Classification
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/951—Indexing; Web crawling techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0201—Market modelling; Market analysis; Collecting market data

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • Accounting & Taxation (AREA)
  • Strategic Management (AREA)
  • General Engineering & Computer Science (AREA)
  • Finance (AREA)
  • Development Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Artificial Intelligence (AREA)
  • Computational Linguistics (AREA)
  • Game Theory and Decision Science (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The present invention provides a kind of product competition relational network analysis method and system, is related to technical field of data processing.The present invention is by obtaining the primary products comment data in internet, then primary products comment data is pre-processed, obtain product review data, it is then based on product review data and carries out a series of processing, obtain competition network figure, then by the competitive relation between competition network map analysis product, marketing strategy is formulated.For traditional investigation mode, the primary products comment data in internet that the present invention is based on timeliness is strong, sample size is big formulates marketing strategy, so that the marketing strategy reliability formulated is high.Meanwhile the present invention formulates marketing strategy by the primary products comment data in internet, is formulated for marketing strategy relative to traditional using traditional markets method of investigation and study such as questionnaire, expert interviewing or brainstormings, manpower and financial resources cost is lower.

Description

Product competition relational network analysis method and system
Technical field
The present invention relates to technical field of data processing, and in particular to a kind of product competition relational network analysis method and is System.
Background technique
Marketing strategy is enterprise using customer need as starting point, rule of thumb obtains the letter of customer demand amount and purchasing power It ceases, the desired value of business circles, in a planned way organizes all operations activity.
It is generally obtained currently on the market using the traditional markets such as questionnaire, expert interviewing or brainstorming method of investigation and study The relativity of attribute and total satisfactory grade between product identifies rival with this, and formulates marketing strategy.
However, time-consuming for tradition investigation, product information is caused to lag, it can with the marketing strategy that the product information of lag is formulated It is low by spending.
Summary of the invention
(1) the technical issues of solving
In view of the deficiencies of the prior art, the present invention provides a kind of product competition relational network analysis method and system, solutions It has determined the low technical problem of marketing strategy reliability of the formulation formulated by traditional investigation mode.
(2) technical solution
In order to achieve the above object, the present invention is achieved by the following technical programs:
The present invention provides a kind of product competition relational network analysis method, and the method is executed by computer, the method The following steps are included:
S1, primary products comment data is obtained, and the primary products comment data is pre-processed, obtained product and comment By data；
S2, product type information is obtained, Entity recognition is named to the product type information, obtain name product, And according to the dependence between name product and the product review data, the name product and the product review are believed Breath data are matched；
S3, based on after matching name product and the product review data acquisition product between competitive relation；
Competitive relation between S4, the price range based on product and the product obtains competition network figure；
S5, based on the competitive relation between the competition network map analysis product.
Preferably, in step sl, the pretreated process are as follows:
To in the primary products comment data each comment text carry out data cleansing, removal null value, repetition values, Machine comment and forbidden character；
Remove stop words；
Word involved in sentence is correctly cut out, then identification mark is carried out to part of speech.
Preferably, the step S3 is specifically included:
Based on after matching name product and the product review data, judge that the comment text in product review data is It is no belong to compare viewpoint sentence, the relatively viewpoint sentence refers to: a comment text is related to carrying out the attributive character of two products The sentence compared；
Based on existing sentiment dictionary and the processing of adverbial word the weight relatively viewpoint sentence, to the emotion of the relatively viewpoint sentence It gives a mark, obtains positive emotion score and negative sense emotion score；
Based on positive emotion score and negative sense emotion score, the competitive relation between product is obtained.
Preferably, the step S4 is specifically included:
S401, classified according to product price section to product；
S402, it is based on competitive relation, carries out the sub- market cluster of product in price range；
S403, ranking in clustering cluster is carried out based on cluster.
Preferably, in step S402, it is based on competitive relation, carries out the specific of the sub- market cluster of product in price range Method are as follows:
Based on competitive relation, competitive relation non-directed graph and competitive relation digraph are constructed；
Based on competitive relation non-directed graph, regard each name product as a sub- market, computing module degree Q value；It will be every One node clustering calculates Δ Q to neighbor node, and Δ Q refers to the difference for carrying out a clustering front and back Q value, selects Δ Q most Big scheme, continuous recurrence, until all Δ Q≤0, end of clustering, generate several sub- markets；The calculating of modularity Q value is public Formula is as follows:
Wherein:
M is total number of edges in competitive relation non-directed graph；
S is sub- market；
es=∑i,j∈sAijIt is 2 times of the sub- total number of edges of market s；AijRefer to two nodes of i, j in same sub- market s, if i, j two There is line between a node, then Aij=1, if without line, A between two nodes of i, jij=0；Again because of Aij=Aji, so final es 2 times of total number of edges existing for indicating inside sub- market s；
ks=∑i∈skiFor the number of edges from a node in sub- market s；
R is strategy parameter, influences sub- market volume.
Preferably, in step S403, the calculation formula for carrying out ranking in clustering cluster based on cluster is as follows:
Wherein:
Rank(ci) it is model c in a kind of productiContention level；
N is the model number for including in a kind of product；
D is adjusting parameter；
M(ci) be and model ciThere is the other products model of competitive relation；
L(cj) it is model cjThe model number of outflow.
The present invention also provides a kind of product competition relational network analysis systems, the system comprises computer, the calculating Machine includes:
At least one storage unit；
At least one processing unit；
Wherein, at least one instruction is stored at least one described storage unit, at least one instruction is by described At least one processing unit is loaded and is executed to perform the steps of
S1, primary products comment data is obtained, and the primary products comment data is pre-processed, obtained product and comment By data；
S2, product type information is obtained, Entity recognition is named to the product type information, obtain name product, And according to the dependence between name product and the product review data, the name product and the product review are believed Breath data are matched；
S3, based on after matching name product and the product review data acquisition product between competitive relation；
Competitive relation between S4, the price range based on product and the product obtains competition network figure；
S5, based on the competitive relation between the competition network map analysis product.
(3) beneficial effect
The present invention provides a kind of product competition relational network analysis method and systems.Compared with prior art, have with It is lower the utility model has the advantages that
Then the present invention carries out primary products comment data pre- by obtaining the primary products comment data in internet Processing, obtains product review data, is then based on product review data and carries out a series of processing, obtains competition network figure, so Afterwards by the competitive relation between competition network map analysis product, marketing strategy is formulated.For traditional investigation mode, this Primary products comment data in the internet that invention is strong based on timeliness, sample size is big formulates marketing strategy, so that formulating Marketing strategy reliability it is high.Meanwhile the present invention formulates marketing strategy by the primary products comment data in internet, relatively It is formulated for marketing strategy in traditional using traditional markets method of investigation and study such as questionnaire, expert interviewing or brainstormings, people Power and financial resources cost are lower.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with It obtains other drawings based on these drawings.
Fig. 1 is a kind of block diagram of product competition relational network analysis method of the embodiment of the present invention；
Fig. 2 is competitive relation non-directed graph；
Fig. 3 is competitive relation digraph.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, to the technology in the embodiment of the present invention Scheme is clearly and completely described, it is clear that and described embodiments are some of the embodiments of the present invention, rather than whole Embodiment.Based on the embodiments of the present invention, those of ordinary skill in the art are obtained without creative efforts The every other embodiment obtained, shall fall within the protection scope of the present invention.
The embodiment of the present application solves by providing a kind of product competition relational network analysis method and system and passes through tradition The low problem of marketing strategy reliability of formulation formulated of investigation mode, realize and obtain product review data in time, and made with this Determine the marketing strategy that timeliness is strong, reliability is high.
Technical solution in the embodiment of the present application is in order to solve the above technical problems, general thought is as follows:
The embodiment of the present invention is by obtaining the primary products comment data in internet, then to primary products comment data It is pre-processed, obtains product review data, be then based on product review data and carry out a series of processing, obtain competition network Figure formulates marketing strategy then by the competitive relation between competition network map analysis product, and the embodiment of the present invention is based on timeliness By force, the primary products comment data in the big internet of sample size formulates marketing strategy, so that the marketing strategy formulated is reliable Degree is high.
In order to better understand the above technical scheme, in conjunction with appended figures and specific embodiments to upper Technical solution is stated to be described in detail.
The embodiment of the invention provides a kind of product competition relational network analysis methods, as shown in Figure 1, this method is by calculating Machine executes, method includes the following steps:
S1, primary products comment data is obtained, and the primary products comment data is pre-processed, obtained product and comment By data；
S2, product type information is obtained, Entity recognition is named to the product type information, obtain name product, And according to the dependence between name product and the product review data, the name product and the product review are believed Breath data are matched；
S3, based on after matching name product and the product review data acquisition product between competitive relation；
Competitive relation between S4, the price range based on product and the product obtains competition network figure；
S5, based on the competitive relation between the competition network map analysis product.
The embodiment of the present invention is by obtaining the primary products comment data in internet, then to primary products comment data It is pre-processed, obtains product review data, be then based on product review data and carry out a series of processing, obtain competition network Figure formulates marketing strategy then by the competitive relation between competition network map analysis product, comes relative to traditional investigation mode It says, the primary products comment data in the internet that the embodiment of the present invention is strong based on timeliness, sample size is big formulates marketing plan Slightly, so that the marketing strategy reliability formulated is high.Meanwhile the embodiment of the present invention passes through the primary products comment data in internet Marketing strategy is formulated, utilizes the traditional markets method of investigation and study systems such as questionnaire, expert interviewing or brainstorming relative to traditional Determine for marketing strategy, manpower and financial resources cost is lower.
Each step is described in detail below.
It should be noted that in the present embodiment by taking automobile this kind of product as an example.
S1, primary products comment data is obtained, and the primary products comment data is pre-processed, obtained product and comment By data.Specifically:
S101, the primary products comment data about automobile on internet is acquired by octopus collector.Specifically Collection process are as follows: first need that essential information is arranged first, to design collection rule and identify different collection rules.It is arranged again and adopts Collect process, acquisition option, to reduce data acquisition time, during avoiding data from taking due to it is counter climb mechanism and cause it is unnecessary Trouble.Finally export acquisition data are stored in database.
S102, the primary products comment data in database is pre-processed, obtains product review data.Detailed process Are as follows: data cleansing, removal null value, repetition values, machine comment and forbidden character are carried out to primary products comment data first.Then Remove stop words, such as the word of " ", " ", " so " without practical significance.Word segmentation processing is finally carried out, will first be related in sentence And word correctly cut out, then identification mark is carried out to part of speech, obtains product review data.
S2, product type information is obtained, Entity recognition is named to the product type information, obtain name product, And according to the dependence between name product and the product review data, the name product and the product review are believed Breath data are matched.Specifically:
S201, all product type information are crawled in related web site all products is obtained by further data processing The name product of model.
S202, the name entity that these products are identified in product review data, it should be noted that if product review Include implicit entity in data, then it is identified using BosonNLP.Then and according to syntax dependence, name is produced Product and comment data are matched.
S3, based on after matching name product and the product review data acquisition product between competitive relation.Specifically:
In the comment text of product review data, it is related to the sentence quilt being compared to the attributive character of certain two product Referred to as compare viewpoint sentence, such as: the appearance ratio B product of A product is more preferable.It is handled according to existing sentiment dictionary and adverbial word weight, The emotion for comparing viewpoint sentence is given a mark, obtains positive emotion score and negative sense emotion score respectively.Each viewpoint sentence is reflected Be mapped to tuple t={ p1, p2, pScore, nScore }, meaning are as follows: occur product p2 in the comment of product p1, pScore be by The enthusiasm score that polarity classifier determines, nScore is the passivity score determined by polarity classifier.
Competitive relation between S4, the price range based on product and the product obtains competition network figure.Specifically:
S401, classified according to product price section to product.Detailed process are as follows: under every class product, due to identical Product is bigger a possibility that there are competitive relations in price range, therefore, is classified first according to product price section.
S402, it is based on competitive relation, carries out the sub- market cluster of product in price range.Specifically:
S4021, it is based on competitive relation, constructs competitive relation non-directed graph and competitive relation digraph.
In the specific implementation process, if occurring 2 products in the comment of 1 product, defining the two, there are competitive relation, In In product node, even a undirected line segment indicates competitive relation, referred to as competitive relation non-directed graph, as shown in Figure 2.
On the basis of competitive relation non-directed graph, competitive relation digraph is constructed, as shown in figure 3, working asWhen, the pointing direction of comment is that p2 is directed toward p1；WhenWhen, the pointing direction of comment is that p1 is directed toward p2.Fig. 3 isThe case where.
S4022, it is based on competitive relation non-directed graph, regards each name product as a sub- market, calculates in this case Modularity Q value；By each node clustering to neighbor node, Δ Q is calculated, Δ Q refers to Q value before and after clustering of progress Difference, such as: when initial, by each name product regard a sub- market as, calculate Q1Then value randomly chooses one Node gathers on its neighbor node, obtains Q21, then another node is changed, movement just now is repeated, Q is obtained22, selection difference Node simultaneously computes repeatedly Q2n, finding makes Q2n-Q1Maximum scheme, the i.e. maximum scheme of Δ Q, continuous recurrence, until all Δ Q≤ 0, end of clustering generates several sub- markets；The calculation formula of modularity Q value is as follows:
Wherein:
M is total number of edges in competitive relation non-directed graph；
S is sub- market；
es=∑i,j∈sAijIt is 2 times of the sub- total number of edges of market s；AijRefer to two nodes of i, j in same sub- market s, if i, j two There is line between a node, then Aij=1, if without line, A between two nodes of i, jij=0；Again because of Aij=Aji, so final es 2 times of total number of edges existing for indicating inside sub- market s；
ks=∑i∈skiFor the number of edges from a node in sub- market s, (degree is equal to from the side of a node Number)；
R is strategy parameter, influences sub- market volume, in the specific implementation process, first rule of thumb sets a parameter r, After obtaining final cluster, is tested according to the requirement under different application scene, according to inspection result adjusting parameter r, obtained more Excellent cluster result.
Specific calculating process is as follows:
Input: the undirected competitive relation and strategy parameter r of name product in price range；
Step: 1. each name product regards one kind as, calculates current Q value
2. each node clustering to neighbor node is calculated Δ Q, selection makes the maximum cluster operation of Δ Q；
3. repeating 2., until Δ Q≤0 of any cluster operation
Output: the clustering cluster in price range.
S403, ranking in clustering cluster is carried out based on cluster.In the specific implementation process, it is calculated and is produced by PageRank algorithm Ranking of the product in competitive relation, illustrates by taking automobile as an example below:
More multi-product has the product of competitive relation to have stronger competitiveness in competition network；There is strong competitiveness by more Product has the product of competitive relation also to have stronger competitiveness.
Wherein:
CarRank(ci) it is vehicle ciContention level；
N is vehicle number；
D is adjusting parameter；
M(ci) be and vehicle ciThere is the vehicle of competitive relation；
L(cj) it is vehicle cjThe vehicle number of outflow is obtained by the digraph of building competition network figure, in simple terms, is exactly Refer to: from vehicle cjNode set out, the side for being directed toward other nodes is a total of several, is exactly vehicle cjThe vehicle number of outflow.
S5, based on the competitive relation between the competition network map analysis product.In the specific implementation process, it is calculated by cluster It can be concluded that under a certain price range, each product competition relationship is stronger to segment market method, and can be with according to PageRank algorithm The competitiveness rank of the middle various products that segment market is obtained, so as to obtain the competition gap edge between each product.Pass through For competitive relation digraph it can be concluded that in competition, whether a certain product has and has how many competitive advantage, is tied according to analysis Fruit formulates marketing strategy.
The present invention also provides a kind of systems of product competition relational network analysis, the system comprises computer, the meter Calculation machine includes:
At least one storage unit；
At least one processing unit；
Wherein, at least one instruction is stored at least one described storage unit, at least one instruction is by described At least one processing unit is loaded and is executed to perform the steps of
S1, primary products comment data is obtained, and the primary products comment data is pre-processed, obtained product and comment By data；
S2, product type information is obtained, Entity recognition is named to the product type information, obtain name product, And according to the dependence between name product and the product review data, the name product and the product review are believed Breath data are matched；
S3, based on after matching name product and the product review data acquisition product between competitive relation；
Competitive relation between S4, the price range based on product and the product obtains competition network figure；
S5, based on the competitive relation between the competition network map analysis product.
In conclusion compared with prior art, have it is following the utility model has the advantages that
1, then the present invention carries out primary products comment data by obtaining the primary products comment data in internet Pretreatment, obtains product review data, is then based on product review data and carries out a series of processing, obtains competition network figure, Then by the competitive relation between competition network map analysis product, marketing strategy is formulated.For traditional investigation mode, The primary products comment data in internet that the present invention is based on timeliness is strong, sample size is big formulates marketing strategy, so that system Fixed marketing strategy reliability is high.
2, the present invention formulates marketing strategy by the primary products comment data in internet, utilizes tune relative to traditional It interrogates the traditional markets method of investigation and study such as volume, expert interviewing or brainstorming to formulate for marketing strategy, manpower and financial resources cost is more It is low.
3, the embodiment of the present invention is by the competitive advantage relationship between combining sentiment analysis and PageRank algorithm to analyze product, The accuracy of analysis result is improved, so that it is high according to the marketing strategy reliability formulated for analyzing result with this.
It should be noted that through the above description of the embodiments, those skilled in the art can be understood that It can be realized by means of software and necessary general hardware platform to each embodiment.Based on this understanding, above-mentioned skill Substantially the part that contributes to existing technology can be embodied in the form of software products art scheme in other words, the calculating Machine software product may be stored in a computer readable storage medium, such as ROM/RAM, magnetic disk, CD, including some instructions are used So that computer equipment (can be personal computer, server or the network equipment etc.) execute each embodiment or Method described in certain parts of person's embodiment.
Herein, relational terms such as first and second and the like be used merely to by an entity or operation with it is another One entity or operation distinguish, and without necessarily requiring or implying between these entities or operation, there are any this reality Relationship or sequence.Moreover, the terms "include", "comprise" or its any other variant are intended to the packet of nonexcludability Contain, so that the process, method, article or equipment for including a series of elements not only includes those elements, but also including Other elements that are not explicitly listed, or further include for elements inherent to such a process, method, article, or device. In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including the element Process, method, article or equipment in there is also other identical elements.
The above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although with reference to the foregoing embodiments Invention is explained in detail, those skilled in the art should understand that: it still can be to aforementioned each implementation Technical solution documented by example is modified or equivalent replacement of some of the technical features；And these modification or Replacement, the spirit and scope for technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution.

Claims (7)

1. a kind of product competition relational network analysis method, which is characterized in that the method is executed by computer, the method packet Include following steps:
S1, primary products comment data is obtained, and the primary products comment data is pre-processed, obtain product review number According to；
S2, product type information is obtained, Entity recognition is named to the product type information, obtain name product, and root According to the dependence between name product and the product review data, by the name product and the product review information number According to being matched；
S3, based on after matching name product and the product review data acquisition product between competitive relation；
Competitive relation between S4, the price range based on product and the product obtains competition network figure；
S5, based on the competitive relation between the competition network map analysis product.
2. product competition relational network analysis method as described in claim 1, which is characterized in that in step sl, described pre- The process of processing are as follows:
Data cleansing is carried out to each comment text in the primary products comment data, removes null value, repetition values, machine Comment and forbidden character；
Remove stop words；
Word involved in sentence is correctly cut out, then identification mark is carried out to part of speech.
3. product competition relational network analysis method as described in claim 1, which is characterized in that the step S3 is specifically wrapped It includes:
Based on after matching name product and the product review data, judge whether the comment text in product review data belongs to In comparing viewpoint sentence, the relatively viewpoint sentence refers to: a comment text is related to being compared the attributive character of two products Sentence；
Based on existing sentiment dictionary and the processing of adverbial word the weight relatively viewpoint sentence, the emotion of the relatively viewpoint sentence is carried out Marking, obtains positive emotion score and negative sense emotion score；
Based on positive emotion score and negative sense emotion score, the competitive relation between product is obtained.
4. product competition relational network analysis method as claimed in claim 3, which is characterized in that the step S4 is specifically wrapped It includes:
S401, classified according to product price section to product；
S402, it is based on competitive relation, carries out the sub- market cluster of product in price range；
S403, ranking in clustering cluster is carried out based on cluster.
5. product competition relational network analysis method as claimed in claim 4, which is characterized in that in step S402, be based on Competitive relation carries out the sub- market cluster of product in price range method particularly includes:
Based on competitive relation, competitive relation non-directed graph and competitive relation digraph are constructed；
Based on competitive relation non-directed graph, regard each name product as a sub- market, computing module degree Q value；By each Node clustering calculates Δ Q to neighbor node, and Δ Q refers to the difference for carrying out a clustering front and back Q value, selects Δ Q maximum Scheme, continuous recurrence, until all Δ Q≤0, end of clustering, generate several sub- markets；The calculation formula of modularity Q value is such as Under:
Wherein:
M is total number of edges in competitive relation non-directed graph；
S is sub- market；
es=∑i,j∈sAijIt is 2 times of the sub- total number of edges of market s；AijRefer to two nodes of i, j in same sub- market s, if i, j two sections There is line between point, then Aij=1, if without line, A between two nodes of i, jij=0；Again because of Aij=Aji, so final esIt indicates 2 times of total number of edges existing for inside sub- market s；
ks=∑i∈skiFor the number of edges from a node in sub- market s；
R is strategy parameter, influences sub- market volume.
6. product competition relational network analysis method as claimed in claim 5, which is characterized in that described in step S403 The calculation formula for carrying out ranking in clustering cluster based on cluster is as follows:
Wherein:
Rank(ci) it is model c in a kind of productiContention level；
N is the model number for including in a kind of product；
D is adjusting parameter；
M(ci) be and model ciThere is the other products model of competitive relation；
L(cj) it is model cjThe model number of outflow.
7. a kind of product competition relational network analysis system, which is characterized in that the system comprises computer, the computer packet It includes:
At least one storage unit；
At least one processing unit；
Wherein, be stored at least one instruction at least one described storage unit, at least one instruction by it is described at least One processing unit is loaded and is executed to perform the steps of
S1, primary products comment data is obtained, and the primary products comment data is pre-processed, obtain product review number According to；
S2, product type information is obtained, Entity recognition is named to the product type information, obtain name product, and root According to the dependence between name product and the product review data, by the name product and the product review information number According to being matched；
S3, based on after matching name product and the product review data acquisition product between competitive relation；
Competitive relation between S4, the price range based on product and the product obtains competition network figure；
S5, based on the competitive relation between the competition network map analysis product.
CN201910695212.9A 2019-07-30 2019-07-30 Product competition relation network analysis method and system Active CN110443646B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910695212.9A CN110443646B (en) 2019-07-30 2019-07-30 Product competition relation network analysis method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910695212.9A CN110443646B (en) 2019-07-30 2019-07-30 Product competition relation network analysis method and system

Publications (2)

Publication Number Publication Date
CN110443646A true CN110443646A (en) 2019-11-12
CN110443646B CN110443646B (en) 2022-04-19

Family

ID=68432237

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910695212.9A Active CN110443646B (en) 2019-07-30 2019-07-30 Product competition relation network analysis method and system

Country Status (1)

Country Link
CN (1) CN110443646B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113420122A (en) * 2021-06-24 2021-09-21 平安科技（深圳）有限公司 Method, device and equipment for analyzing text and storage medium

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140074844A1 (en) * 2012-09-09 2014-03-13 Oracle International Corporation Method and system for implementing semantic analysis of internal social network content
CN108388660A (en) * 2018-03-08 2018-08-10 中国计量大学 A kind of improved electric business product pain spot analysis method
CN109684531A (en) * 2018-12-20 2019-04-26 郑州轻工业学院 The method and apparatus that a kind of pair of user's evaluation carries out sentiment analysis

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140074844A1 (en) * 2012-09-09 2014-03-13 Oracle International Corporation Method and system for implementing semantic analysis of internal social network content
CN108388660A (en) * 2018-03-08 2018-08-10 中国计量大学 A kind of improved electric business product pain spot analysis method
CN109684531A (en) * 2018-12-20 2019-04-26 郑州轻工业学院 The method and apparatus that a kind of pair of user's evaluation carries out sentiment analysis

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113420122A (en) * 2021-06-24 2021-09-21 平安科技（深圳）有限公司 Method, device and equipment for analyzing text and storage medium
CN113420122B (en) * 2021-06-24 2024-06-04 平安科技（深圳）有限公司 Method, device, equipment and storage medium for analyzing text

Also Published As

Publication number Publication date
CN110443646B (en) 2022-04-19

Similar Documents

Publication Publication Date Title
US10095782B2 (en) Summarization of short comments
CN103218436B (en) A kind of Similar Problems search method and device that merges class of subscriber label
Shen et al. A pricing model for big personal data
CN108665159A (en) A kind of methods of risk assessment, device, terminal device and storage medium
US20160357845A1 (en) Method and Apparatus for Classifying Object Based on Social Networking Service, and Storage Medium
CN104462327B (en) Calculating, search processing method and the device of statement similarity
CN108573041A (en) Probability matrix based on weighting trusting relationship decomposes recommendation method
CN105787662A (en) Mobile application software performance prediction method based on attributes
CN112214614A (en) Method and system for mining risk propagation path based on knowledge graph
CN106991577A (en) A kind of method and device for determining targeted customer
CN106897359A (en) Internet information is collected and correlating method
CN114612251A (en) Risk assessment method, device, equipment and storage medium
CN106557954A (en) The method and device of customer service marketing
CN105808541A (en) Information matching processing method and apparatus
Li et al. TODQA: Efficient task-oriented data quality assessment
CN103218419B (en) Web tab clustering method and system
CN103353865A (en) Barter electronic trading commodity recommendation method based on position
Volk et al. Ask the Right Questions: Requirements Engineering for the Execution of Big Data Projects.
CN104572915A (en) User event relevance calculation method based on content environment enhancement
CN108509588B (en) Lawyer evaluation method and recommendation method based on big data
CN110443646A (en) Product competition relational network analysis method and system
CN113988638A (en) Method and device for measuring and calculating strength of general association relationship, electronic equipment and medium
CN104778205A (en) Heterogeneous information network-based mobile application ordering and clustering method
EP4116884A2 (en) Method and apparatus for training tag recommendation model, and method and apparatus for obtaining tag
CN111382265B (en) Searching method, device, equipment and medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant