CN107481066A - A kind of competing product analysis method and system based on big data - Google Patents
A kind of competing product analysis method and system based on big data Download PDFInfo
- Publication number
- CN107481066A CN107481066A CN201710757129.0A CN201710757129A CN107481066A CN 107481066 A CN107481066 A CN 107481066A CN 201710757129 A CN201710757129 A CN 201710757129A CN 107481066 A CN107481066 A CN 107481066A
- Authority
- CN
- China
- Prior art keywords
- product
- mrow
- msub
- target product
- competing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
Abstract
The present invention relates to competing product analysis technical field, it is proposed that a kind of competing product analysis method and system, this method based on big data include：The internet historical behavior data of each user in sample user group are obtained, internet historical behavior data are analyzed by funnel analytic approach, obtain the like product of target product, like product is the market orientation identical product with target product；The degree of association of each product and target product in like product is obtained respectively；The degree of association corresponding to selection is more than competing product of the product of the first predetermined threshold value as target product；Pair internet historical behavior data closed with the target product and the competing condition are analyzed, generation target product relative to competing product pursuit-evasion strategy.The present invention can efficiently and accurately realize the positioning and analysis of competing product, and providing more efficiently competitive strategy for target product formulates foundation, be inclined to simultaneously also by the concern of user and more effectively launch strategy so as to formulate.
Description
Technical field
The present invention relates to competing product analysis technical field, more particularly to a kind of competing product analysis method based on big data and it is
System.
Background technology
In every profession and trade, for competing product research typically all can pole paid attention to, the analysis of competing product or brand analysis are a lot
Enterprise does one of important means of brand market strategic research in market, and is also enterprise to rival's market management situation
Best investigation and analysis.Each enterprise is required for analysis to improve itself product to capture more markets, therefore the analysis of competing product is city
It is most universal on field, and most important analysis approach.After research and development of products is reached the standard grade, all enterprises or brand are required for competing product point
Analysis, is evaluated existing or potential competing product advantage inferior position.According to this analysis come to itself product carry out more comprehensively,
More professional strategy orientation and products perfection.Competing product analysis is mainly from several dimension comparative analyses：Strategy orientation, profit model,
User group, product function, the experience of product operation performance etc..
Before competing product analysis is done, it is critically important link that selection, which defines competing product,.The current scheme for defining competing product is main
Including：A. using technical specification, price positioning and sales volume etc. as measurement index, close person is taken as competing product.Though this method
One of competing product reference can be so used as, because price is one of an important factor for many user groups select product, technical specification
It is the competition of product function, the profit competition that sales volume is in order at product between enterprise and enterprise considers, but this method is only
It only can only be the weight that related personnel judges these indexs from experience, so as to define competing product, have ignored the real demand of user.
Whether one product selected and core that buy is whether the product meets user's request, and it is true that the demand of user is only product
The core of positive selection.B. contrasted according to keyword search amount of the user to Related product, the searched product often of selection is made
For competing product.This method can only determine the total volumes of searches of user, it is impossible to the user for precisely judging search must be target group, one
It is whole that secondary behavior does not represent the real demand of user.Meanwhile when two kinds of crowds for searching for two product keywords compare
When big overlapping, could judge the two products may competing product each other, but only by keyword search amount can not judge this two
The overlapping cases of kind crowd, therefore at this point, the method for selecting competing product by keyword search amount has very big defect.This
Outside, the number being searched according to product, which defines competing product, can not look for dozen Related product concrete function and characteristic, such as can not specifically analyze
Understand which characteristic most attracts clients.C. market survey is counted accordingly, the aggregate analysis of user's focus.Party's legally constituted authority
Meter is people first, has stronger subjective colo(u)r statistics.And the thing of subjectivity can not by common exchange and
Survey obtains information, and exchange is not deep enough, the not comprehensive enough error that can all bring competing product selection.Although the behavior of questionnaire
Data are more specific, and user's focus is more clear and definite, and investigation result is extensively filling out questionnaire as questionnaire without depth, user
The fixed setting of problem, the answer of the temporary divergent thinking of user, causes result data to lose contact with reality.In addition questionnaire
Investigation is through frequently with the mode that question and answer volume is filled out by user oneself, so the quality of its investigation result usually cannot be guaranteed, being adjusted
The skewness for the person of looking into, respondent group have the phenomenon of Relatively centralized.
After defining competing product, the method for the competing product analysis of in the market mainly includes：The analysis sides such as SWTO, sheet format comparative evaluation
Method.Wherein, SWTO methods, mainly with related personnel with subjective and experience, to point of some detail functions of specific competing product
Analyse and compare, and the analysis meeting in market has very big deviation.Equally it is the analysis part that have ignored user's request.Table statistics
Comparative evaluation analytic approach, mainly analyzed with relevant speciality tradesman with good grounds many years of experience, rather than targeted customer
The real tangible behavior of group, and actually have deviation, the subjectivity carried is stronger, for specific product analysis only on surface.
Funnel analytic approach, this behavior discriminatory analysis, product some link can only be analyzed and gone wrong, it is impossible to accurately find out some ring
Which function of the detail of section is gone wrong, and has significant limitation, and one is not reaching to the contrast of product function characteristic analysis
Individual good purpose.Search engine concern amount method of comparative analysis, because the amount of search key simply macroscopically shows keyword
Search temperature and attention rate, the crowd based on search is most likely not the difference for causing volumes of searches with a collection of crowd, is mistakenly considered
Certain functional characteristic be it is more concerned, bring it is misleading can be very big, moreover, the comparison of this simple volumes of searches, Wu Faming
True function difference between certain product and competing product.
Therefore, how a kind of competing product based on big data that can efficiently and accurately position competing product, analyze competing product point are provided
Formulation of the analysis method for brand competition strategy is significant.
The content of the invention
In view of the above problems, the present invention propose a kind of competing product analysis method and system based on big data, can effectively,
Competing product, and the attention rate between quantified goal product and each details of competing product are positioned exactly, and the height based on attention rate enters
The competing product analysis of row, provides more efficiently competitive strategy for target product and formulates foundation, be inclined to simultaneously also by the concern of user
So as to formulate more effective strategy.
One aspect of the present invention, there is provided a kind of competing product analysis method based on big data, including：
The internet historical behavior data of each user in sample user group are obtained, by funnel analytic approach to the internet
Historical behavior data are analyzed, and obtain the like product of target product, and the like product is to determine with the market of target product
Position identical product；
The degree of association of each product and the target product in the like product is obtained respectively；
The degree of association corresponding to selection is more than competing product of the product of the first predetermined threshold value as target product；
Pair internet historical behavior data closed with the target product and the competing condition are analyzed, and generate the mesh
Mark pursuit-evasion strategy of the product relative to the competing product.
Alternatively, in the acquisition sample user group after the internet historical behavior data of each user, methods described
Also include：
The internet historical behavior data are analyzed by funnel analytic approach, it is determined that the class with the target product
Not different third-party products；
Obtain the degree of association in the third-party product with the target product and be more than the related product of the second predetermined threshold value,
Wherein, first predetermined threshold value is more than second predetermined threshold value；
Pair internet historical behavior data related to the target product and the related product are analyzed, and generate institute
State the cooperation policy of target product and the related product.
Alternatively, methods described also includes：
The internet historical behavior data are analyzed by funnel analytic approach, to determine that the target product is corresponding
Potential user group, wherein, the potential user group for concern target product and/or like product customer group.
Alternatively, the degree of association for obtaining each product and the target product in the like product respectively, including：
The use of a certain product A in the like product is paid close attention in the number of users of statistic sampling customer group, sample user group
Family colony and number of users, and concern target product B user group and number of users；
The absolute attention rate of a certain product A in the like product to the target product B is calculated, formula is as follows：
Wherein, FRABRepresent absolute attention rates of a certain product A to B, FUAPay close attention to A user group, FUBRepresent to close
Note B user group.Count represents number of users corresponding to user group；
The user for calculating a certain product A in the like product pays close attention to probability, and formula is as follows：
Wherein, FPAProbability, FU are paid close attention to for product A userallFor the number of users of sample user group；
Probability is paid close attention to according to the definitely attention rate and user, a certain product A in like product is calculated and is produced with the target
Product B correlation index, formula are as follows：
Wherein, RIABFor product A and target product B correlation index；
The product A and the target product B degree of association are determined according to the correlation index.
Alternatively, it is described that the internet historical behavior data are analyzed by funnel analytic approach, obtain target production
The like product of product, in addition to：
According to the like product, corresponding user pays close attention to probability in the potential user group, and the like product is entered
Row product ranking.
Alternatively, the described pair of internet historical behavior data closed with the target product and the competing condition are divided
Analysis, generates pursuit-evasion strategy of the target product relative to the competing product, including：
The internet historical behavior data are analyzed by funnel analytic approach, from the internet historical behavior number
According to the corelation behaviour data of middle search user, the corelation behaviour data are related to the target product and/or like product
And within the unit interval high frequency time simultaneously carry out behavioral data；
User's attentinal contents of the target product and corresponding competing product are determined according to the corelation behaviour data；
The competing product and the target product are obtained in the corresponding correlation index of same user's attentinal contents；
Closed based on the correlation index and the competing product and the target product in the user of same user's attentinal contents
Probability is noted, generates pursuit-evasion strategy of the target product relative to the competing product.
Another aspect of the present invention, there is provided a kind of competing product analysis system based on big data, including：
Data analysis module, for obtaining the internet historical behavior data of each user in sample user group, pass through funnel
Analytic approach is analyzed the internet historical behavior data, obtains the like product of target product, and the like product is
With the market orientation identical product of target product；
Acquisition module, for obtaining the degree of association of each product and the target product in the like product respectively；
Selecting module, it is more than the product of the first predetermined threshold value as the target product for choosing the corresponding degree of association
Competing product；
Competing product analysis module, enter for pair internet historical behavior data closed with the target product and the competing condition
Row analysis, generates pursuit-evasion strategy of the target product relative to the competing product.
Alternatively, the data analysis module, the internet historical behavior data of each user in sample user group is obtained
Afterwards, be additionally operable to analyze the internet historical behavior data by funnel analytic approach, it is determined that with the target product
The different third-party product of classification；
The acquisition module, it is additionally operable to obtain the degree of association in the third-party product with the target product and is more than second
The related product of predetermined threshold value, wherein, first predetermined threshold value is more than second predetermined threshold value；
The competing product analysis module, it is additionally operable to a pair internet history related to the target product and the related product
Behavioral data is analyzed, and generates the cooperation policy of the target product and the related product.
Alternatively, the data analysis module, it is additionally operable to by funnel analytic approach to the internet historical behavior data
Analyzed, to determine potential user group corresponding to the target product, wherein, the potential user group is concern target product
And/or the customer group of like product.
Alternatively, the acquisition module, including：
Statistic unit, pay close attention in the like product in the number of users, sample user group for statistic sampling customer group
A certain product A user group and number of users, and concern target product B user group and number of users；
Computing unit, for calculating the absolute attention rate of a certain product A in the like product to the target product B,
Formula is as follows：
Wherein, FRABRepresent absolute attention rates of a certain product A to B, FUAPay close attention to A user group, FUBRepresent to close
Note B user group.Count represents number of users corresponding to user group；
The computing unit, the user for being additionally operable to calculate a certain product A in the like product pay close attention to probability, and formula is such as
Under：
Wherein, FPAProbability, FU are paid close attention to for product A userallFor the number of users of sample user group；
The computing unit, it is additionally operable to pay close attention to probability according to the definitely attention rate and user, calculates certain in like product
One product A and target product B correlation index, formula are as follows：
Wherein, RIABFor product A and target product B correlation index；
First determining unit, for determining associating for the product A and the target product B according to the correlation index
Degree.
Alternatively, the data analysis module, specifically it is additionally operable to according to the like product in the potential user group
Corresponding user pays close attention to probability, and product ranking is carried out to the like product.
Alternatively, the competing product analysis module, including：
Analytic unit, for being analyzed by funnel analytic approach the internet historical behavior data, from it is described mutually
Network historical behavior data in search for user corelation behaviour data, the corelation behaviour data be with the target product and/
Or the behavioral data that like product is related and high frequency time is carried out simultaneously within the unit interval；
Second determining unit, for determining the user of the target product and corresponding competing product according to the corelation behaviour data
Attentinal contents；
Acquiring unit, refer to for obtaining the competing product with the target product in corresponding associate of same user's attentinal contents
Number；
Generation unit, for being paid close attention to based on the correlation index and the competing product and the target product in same user
The user of content pays close attention to probability, generates pursuit-evasion strategy of the target product relative to the competing product.
Competing product analysis method and system provided in an embodiment of the present invention based on big data, according to each production in like product
The degree of association of product and target product, the competing product selection of target product is realized, competing product can be efficiently and accurately positioned, then pass through
The internet historical behavior data of couple user closed with target product and competing condition are analyzed, and more effectively generate target product
Relative to the pursuit-evasion strategy of competing product, and then provide more efficiently competitive strategy for target product and formulate foundation, simultaneously also by
The concern of user is inclined to more effectively launches strategy so as to formulate.
Described above is only the general introduction of technical solution of the present invention, in order to better understand the technological means of the present invention,
And can be practiced according to the content of specification, and in order to allow above and other objects of the present invention, feature and advantage can
Become apparent, below especially exemplified by the embodiment of the present invention.
Brief description of the drawings
By reading the detailed description of hereafter preferred embodiment, it is various other the advantages of and benefit it is common for this area
Technical staff will be clear understanding.Accompanying drawing is only used for showing the purpose of preferred embodiment, and is not considered as to the present invention
Limitation.And in whole accompanying drawing, identical part is denoted by the same reference numerals.In the accompanying drawings：
Fig. 1 is a kind of flow chart of competing product analysis method based on big data of the embodiment of the present invention；
Fig. 2 be the embodiment of the present invention a kind of competing product analysis method based on big data in step S12 subdivision flow chart；
Fig. 3 be the embodiment of the present invention a kind of competing product analysis method based on big data in step S14 subdivision flow chart；
Fig. 4 is the schematic diagram of the funnel screening rule of links in funnel analytic approach in the embodiment of the present invention；
Fig. 5 is a kind of structural representation of competing product analysis system based on big data of the embodiment of the present invention；
Fig. 6 shows for the internal structure of acquisition module in a kind of competing product analysis system based on big data of the embodiment of the present invention
It is intended to；
Fig. 7 be the embodiment of the present invention a kind of competing product analysis system based on big data in competing product analysis module internal junction
Structure schematic diagram.
Embodiment
The exemplary embodiment of the disclosure is more fully described below with reference to accompanying drawings.Although the disclosure is shown in accompanying drawing
Exemplary embodiment, it being understood, however, that may be realized in various forms the disclosure without should be by embodiments set forth here
Limited.On the contrary, these embodiments are provided to facilitate a more thoroughly understanding of the present invention, and can be by the scope of the present disclosure
Completely it is communicated to those skilled in the art.
Those skilled in the art of the present technique are appreciated that unless expressly stated, singulative " one " used herein, " one
It is individual ", " described " and "the" may also comprise plural form.It is to be further understood that what is used in the specification of the present invention arranges
Diction " comprising " refer to the feature, integer, step, operation, element and/or component be present, but it is not excluded that in the presence of or addition
One or more other features, integer, step, operation, element, component and/or their groups.
Those skilled in the art of the present technique are appreciated that unless otherwise defined, all terms used herein (including technology art
Language and scientific terminology), there is the general understanding identical meaning with the those of ordinary skill in art of the present invention.Should also
Understand, those terms defined in such as general dictionary, it should be understood that have with the context of prior art
The consistent meaning of meaning, and unless by specific definitions, otherwise will not be explained with the implication of idealization or overly formal.
In order to solve technical problem present in prior art, the embodiment of the present invention proposes a kind of competing product based on big data
Analysis method and system, realization efficiently and accurately positions competing product, the competing product of analysis, and then the formulation for brand competition strategy provides
Important directive significance.
Fig. 1 diagrammatically illustrates the flow chart of the competing product analysis method based on big data of one embodiment of the invention.Ginseng
According to Fig. 1, the competing product analysis method based on big data of the embodiment of the present invention specifically includes following steps：
S11, the internet historical behavior data for obtaining each user in sample user group, by funnel analytic approach to described mutual
Networking historical behavior data are analyzed, and obtain the like product of target product, and the like product is the city with target product
Field positioning identical product.
Wherein, in internet historical behavior packet group containing sample user each user it is various on the internet search for, browse,
The data such as concern, comment, these behaviors generally occur in internets such as major search engine, product related web site, forum, APP
On platform.In a specific example, the funnel screening rule of links from top to bottom configures as follows in funnel analytic approach：
The associative key of a certain product was searched in the top of funnel in a search engine by user first, with from magnanimity big data
In filter out target product, the Related product of target product and each product related content search, browse, pay close attention to, commenting on
Data；Then it is that user pays close attention to the product in the Domestic News class content of the vertical class platform of Related product, the product in phase successively
Close the atlas class content of the vertical class platform of product, the product evaluates and tests class content, the production in the use of the vertical class platform of Related product
Product contrast class content and the price scope for the i.e. product of consuming capacity being used in the product of the vertical class platform of Related product, most
Post analysis obtain the like product of target product.
S12, the degree of association for obtaining each product and the target product in the like product respectively.
The degree of association corresponding to S13, selection is more than competing product of the product of the first predetermined threshold value as the target product.
S14, pair internet historical behavior data closed with the target product and the competing condition are analyzed, and generate institute
State pursuit-evasion strategy of the target product relative to the competing product.
Competing product analysis method provided in an embodiment of the present invention based on big data, according to each product and mesh in like product
Mark product the degree of association, realize target product competing product selection, can efficiently and accurately position competing product, then by pair and mesh
The internet historical behavior data of user that mark product and competing condition close are analyzed, it is more effective generate target product relative to
The pursuit-evasion strategy of competing product, and then provide more efficiently competitive strategy for target product and formulate foundation, simultaneously also by user's
Concern tendency more effectively launches strategy so as to formulate.
In embodiments of the present invention, it is described acquisition sample user group in each user internet historical behavior data it
Afterwards, methods described is further comprising the steps of：
The internet historical behavior data are analyzed by funnel analytic approach, it is determined that the class with the target product
Not different third-party products；
Obtain the degree of association in the third-party product with the target product and be more than the related product of the second predetermined threshold value,
Wherein, first predetermined threshold value is more than second predetermined threshold value；
Pair internet historical behavior data related to the target product and the related product are analyzed, and generate institute
State the cooperation policy of target product and the related product.
In actual applications, when the internet historical behavior data of each user in sample user group are analyzed, remove
Obtain outside the like product of target product, can also be inhomogeneous third-party product.When inhomogeneous third-party product
In some products corresponding with target product crowd when paying close attention to message area there is a big chunk registration, illustrate two
Crowd's attention rate registration of person's product is very high, has the very high degree of association, then can be pair related to target product, related product
Internet historical behavior data analyzed, set objectives product and the effective cooperation policy of related product, realizes cooperation altogether
Win.
Wherein, obtain in sample user group after the internet historical behavior data of each user, methods described also includes：It is logical
Cross funnel analytic approach to analyze the internet historical behavior data, to determine targeted customer corresponding to the target product
Group, wherein, the potential user group is the customer group of concern target product and/or like product.Further, funnel is being passed through
Analytic approach is analyzed the internet historical behavior data, when obtaining the like product of target product, concrete implementation side
Formula is that corresponding user pays close attention to probability in the potential user group according to the like product, and probability is paid close attention to according to the user
Model sequencing is carried out to the like product, and then the maximum product of the degree of association corresponding to choosing from model sequencing is as target
The competing product of product.
The embodiment of the present invention is analyzed the internet historical behavior data by funnel analytic approach, with described in determination
Potential user group corresponding to target product.The potential user group can be regarded as the actual customer or potential consumption of target product
Person.The competing product pair of the product are defined by concern behavioural analysis of the consumer (actual customer or potential consumer) to product
As, while by concern behavior of the consumer to product correlation function and content, in terms of analyzing target product and competing product function
Difference.The embodiment of the present invention uses funnel thoughtcast, by the corelation behaviour data to consumer on certain product, carries out layer
Layer is recursively analyzed, so that it is determined that the competing product of the correspondence of the product.Simultaneously according to the search associative key of this ripple target group
Functional characteristic accounting analysis.Wherein, corelation behaviour data generally these packets contain consumer on the internet to product
And product related content search, the data such as browse, pay close attention to, commenting on, these behaviors generally occur in major search engine, product
On the internet platforms such as related web site, forum, APP.
In the present embodiment, as shown in Fig. 2 the determination of the degree of association can specifically be realized by following steps in step S12：
A certain product A in the like product is paid close attention in S121, the number of users of statistic sampling customer group, sample user group
User group and number of users, and concern target product B user group and number of users；
S122, the absolute attention rate of a certain product A in the like product to the target product B is calculated, formula is as follows：
Wherein, FRABRepresent absolute attention rates of a certain product A to B, FUAPay close attention to A user group, FUBRepresent to close
Note B user group.Count represents number of users corresponding to user group；
S123, the user's concern probability for calculating a certain product A in the like product, formula are as follows：
Wherein, FPAProbability, FU are paid close attention to for product A userallFor the number of users of sample user group；
S124, probability paid close attention to according to definitely attention rate and the user, calculate a certain product A and the mesh in like product
Product B correlation index is marked, formula is as follows：
Wherein, RIABFor product A and target product B correlation index；
S125, the degree of association for determining according to the correlation index product A and the target product B.
Wherein, visually specific service conditions is defined in detail A and B classification, can also be needed according to customer analysis direct
Set.In actual applications, when A and B in market orientation it is consistent, then it is assumed that A and B forms competitive relation, when A and B is in market
Upper positioning is inconsistent, even in different industries, then it is assumed that they are towards identical user crowd.Selected by such competing product
And analysis method, then it can accurately confirm competing product, or even the corresponding feature of crowd can be found out, so as to develop to enterprise marketing
Formulation Information base important in providing.
In the present embodiment, as shown in figure 3, the interconnection pair closed with the target product and the competing condition in step S14
Net historical behavior data are analyzed, and pursuit-evasion strategy of the target product relative to the competing product are generated, especially by following
Step is realized：
S141, by funnel analytic approach the internet historical behavior data are analyzed, from the internet history
The corelation behaviour data of user are searched in behavioral data, the corelation behaviour data are and the target product and/or similar production
Behavioral data that condition closes and that high frequency time is carried out simultaneously within the unit interval；
S142, determine the target product according to the corelation behaviour data and correspond to user's attentinal contents of competing product；
S143, the competing product and the target product are obtained in the corresponding correlation index of same user's attentinal contents；
S144, based on the correlation index and the competing product and the target product same user's attentinal contents use
Probability is paid close attention at family, generates pursuit-evasion strategy of the target product relative to the competing product.
Wherein, include attack, onrelevant in pursuit-evasion strategy of the target product relative to the competing product, defend and strive for
Etc. specific strategy.In a specific embodiment, if competing product and target product are in the corresponding association of same user's attentinal contents
Index is higher than predetermined threshold value, then proves that competing product and target product turn into competing product in terms of this user's attentinal contents, then further
According to competing product and target product the specific pursuit-evasion strategy of determine the probability is paid close attention in the user of same user's attentinal contents.It is if for example, competing
Product are paid close attention to probability in the user of a certain user's attentinal contents and paid close attention to generally higher than user of the target product in same user's attentinal contents
Rate, then this aspect formulates offensive strategy to target product needs again；If competing product are general in user's concern of a certain user's attentinal contents
Rate pays close attention to probability less than user of the target product in same user's attentinal contents, then target product needs again this aspect to formulate anti-
Keep strategy.
The embodiment of the present invention is selected by effective competing product, and according to user's attentinal contents, establishes corresponding product class
Do not contrast, by the concern association analysis to target product and competing product, in terms of different product concerns, user presents difference
Concern tendency, with reference to abilities such as attack, defences, can obtain target product needs to improve, adjust and strengthen competitiveness
Aspect, while it can also be seen that competing product are waited to supplement, in terms of chance to be improved, provided for target product more efficiently competing
Policy development foundation is striven, is inclined to simultaneously also by the concern of user and more effectively launches strategy so as to formulate.
Below by taking the competing product analysis of certain vehicle as an example, technical solution of the present invention is carried out explanation is explained in detail：
First, the funnel screening rule of links in funnel analytic approach is defined, referring to Fig. 4, Fig. 4 is the embodiment of the present invention
The schematic diagram of the funnel screening rule of links, is from top to bottom followed successively by middle funnel analytic approach：
User searched for the associative key of the vehicle in a search engine；
User pays close attention to Domestic News class content of the vehicle in automotive vertical class platform；
User pays close attention to picture category content of the vehicle in automotive vertical class platform；
User pays close attention to the vehicle and evaluates and tests class content in the test ride of automotive vertical class platform；
User pays close attention to the vehicle and contrasts class content in the vehicle of automotive vertical class platform；
The consuming capacity (meeting vehicle price scope) of user.
The information above user related internet behavior information that high frequency time is carried out simultaneously within the unit interval can all be carried out accordingly
Monitoring and obtain corresponding data, so as to by Data Integration draw the high product ranking of degree of focusing particularly on, selected target
Competing product corresponding to product.Further, it is also possible to it is analyzed in conjunction with investigational data under line, more accurately to select phase
The competing product answered, so as to carry out competing product analysis.
Further, the present embodiment using the analysis methodology of attacking and defending figure effectively divide target product and competing product
Analysis.Complicated network data, the diverse nature of competing product, customer demand change unpredictably, allow brand and enterprise to the market demand with
And user's request is increasingly difficult to arrange and analyzed.State attacking and defending diagram technology is a kind of effective scheme that analysis is modeled to it,
Be present numerous limitations in traditional attacking and defending figure thinking analysis, such as the limitation of data acquisition, the uncertainty of competing product selection, make
Obtain in practical application if analysis personnel lack experience, then can be difficult to reflect the details ratio between real market demand and competing product
Compared with.
The embodiment of the present invention, selected by effective competing product, and establish corresponding product category contrast, by target
The concern association analysis of brand and competing product brand, in terms of different product concerns, user presents different concern tendencies, knot
The abilities such as attack, defence are closed, can obtain target brand needs to improve, adjust and strengthen the aspect of competitiveness, while
It can be seen that competing product brand is waited to supplement, in terms of chance to be improved, more efficiently competitive strategy system is provided for target brand
Determine foundation, be inclined to simultaneously also by the concern of user and more effectively launch strategy so as to formulate.It is as follows, in a specific embodiment
In, illustrated by taking the competing product analysis of automobile brand as an example, precondition is that both market orientations are consistent：
Wherein, using vehicle A as target product, vehicle B is specific as shown in table 1 as the competing product analyzed：
The vehicle A of table 1 and vehicle B attacking and defending map analysis
Percentage in table 1 is that the user of corresponding crowd pays close attention to probability, and by comparative analysis, we may determine that product
Market situation, if to improve or increase marketing ideas.It is higher to pay close attention to probability, it might even be possible to one as brand advertising marketing
Individual attraction.In the attacking and defending map analysis, it can be seen that both are the same market of positioning, and user crowd's particular association index is with intersection
Registration is higher and bigger, then just maximum as the possibility of competing product.In this specific embodiment, attacking and defending map analysis establish based on
In automobile market research.Intelligible, technical solution of the present invention can also expand to other brand market researchs.Both if
Not same positioning, in the case that the degree of association is very big, the model also has very big Research Significance.Based on this, it is known that both
In face of market, crowd has very big general character, the corresponding cooperation that can be necessary, realizes the strategy of win-win cooperation.It can be seen that this hair
The analysis of the competing product based on big data that bright embodiment provides has very big directive significance to product.
The embodiment of the present invention, it is according to internet big data background interest, with tradition by the competing product of big data analytic definition
Data are compared, and data source is wider.Tradition is simple competing product website, is investigated under line, counts platform, their side for defining competing product
Method opinion is not accurate enough crowd, and the embodiment of the present invention is progressive formula crawl user's search behavior data and constantly rejected,
It is accurate target group so as to finally arrive the crowd of search.It is thinner to analyze competing product and product, or even also enters other brand products
Go analysis and reference, can be as the selection of cooperative development object.Attacking and defending figure is based between each details of the competing product of product
Attention rate height is compared analysis, faces market so as to draw, how product, which is made, is correspondingly improved.
Competing product analysis method provided in an embodiment of the present invention based on big data, selected by effective competing product, Yi Jijian
Vertical corresponding product category contrast, by the concern association analysis to target brand and competing product brand, pays close attention in different products
Aspect, user present different concern tendencies, and with reference to abilities such as attack, defences, can obtain target brand needs to change
Kind, adjustment and the aspect for strengthening competitiveness, while be mesh it can also be seen that competing product brand is waited to supplement, in terms of chance to be improved
Mark brand provides more efficiently competitive strategy and formulates foundation, is inclined to simultaneously also by the concern of user more effective so as to formulate
Dispensing strategy.
For embodiment of the method, in order to be briefly described, therefore it is all expressed as to a series of combination of actions, but this area
Technical staff should know that the embodiment of the present invention is not limited by described sequence of movement, because implementing according to the present invention
Example, some steps can use other orders or carry out simultaneously.Secondly, those skilled in the art should also know, specification
Described in embodiment belong to preferred embodiment, necessary to the involved action not necessarily embodiment of the present invention.
Fig. 5 diagrammatically illustrates the structural representation of the competing product analysis system based on big data of one embodiment of the invention
Figure.Reference picture 5, the competing product analysis system based on big data of the embodiment of the present invention specifically include data analysis module 501, obtained
Module 502, selecting module 503 and competing product analysis module 504, wherein, data analysis module 501, for obtaining sample user
The internet historical behavior data are divided by the internet historical behavior data of each user by funnel analytic approach in group
Analysis, obtains the like product of target product, and the like product is the market orientation identical product with target product；Obtain mould
Block 502, for obtaining the degree of association of each product and the target product in the like product respectively；Selecting module 503, use
It is more than competing product of the product of the first predetermined threshold value as the target product in the degree of association corresponding to selection；Competing product analysis module
504, analyzed for pair internet historical behavior data closed with the target product and the competing condition, generate the mesh
Mark pursuit-evasion strategy of the product relative to the competing product.
In an alternate embodiment of the present invention where, the data analysis module 501, respectively used in sample user group is obtained
After the internet historical behavior data at family, it is additionally operable to divide the internet historical behavior data by funnel analytic approach
Analysis, it is determined that the third-party product different from the classification of the target product；
The acquisition module 502, the degree of association for being additionally operable to obtain in the third-party product with the target product are more than
The related product of second predetermined threshold value, wherein, first predetermined threshold value is more than second predetermined threshold value；
The competing product analysis module 504, it is additionally operable to a pair internet related to the target product and the related product
Historical behavior data are analyzed, and generate the cooperation policy of the target product and the related product.
In the embodiment of the present invention, the data analysis module 501, it is additionally operable to go through the internet by funnel analytic approach
History behavioral data is analyzed, to determine potential user group corresponding to the target product, wherein, the potential user group is pass
Note the customer group of target product and/or like product.
Specifically, as shown in fig. 6, the acquisition module 502, further comprises statistic unit 5021, computing unit 5022
With the first determining unit 5023, wherein：
Statistic unit 5021, the similar production is paid close attention in the number of users, sample user group for statistic sampling customer group
A certain product A user group and number of users in product, and concern target product B user group and number of users；
Computing unit 5022, for calculating absolute concerns of a certain product A to the target product B in the like product
Degree, formula are as follows：
Wherein, FRABRepresent absolute attention rates of a certain product A to B, FUAPay close attention to A user group, FUBRepresent to close
Note B user group.Count represents number of users corresponding to user group；
The computing unit 5022, the user for being additionally operable to calculate a certain product A in the like product pay close attention to probability, formula
It is as follows：
Wherein, FPAProbability, FU are paid close attention to for product A userallFor the number of users of sample user group；
The computing unit 5022, it is additionally operable to pay close attention to probability according to the definitely attention rate and user, calculates like product
In a certain product A and the target product B correlation index, formula is as follows：
Wherein, RIABFor product A and target product B correlation index；
First determining unit 5023, for determining the product A and the target product B pass according to the correlation index
Connection degree.
In the embodiment of the present invention, the data analysis module 501, specifically for according to the like product in the target
Corresponding user pays close attention to probability in customer group, and product ranking is carried out to the like product.
In the embodiment of the present invention, as shown in fig. 7, the competing product analysis module 504, further comprise analytic unit 5041,
Second determining unit 5042, acquiring unit 5043 and generation unit 5044, wherein：
Analytic unit 5041, for being analyzed by funnel analytic approach the internet historical behavior data, from institute
The corelation behaviour data that user is searched in internet historical behavior data are stated, the corelation behaviour data are and the target product
And/or the behavioral data that like product is related and high frequency time is carried out simultaneously within the unit interval；
Second determining unit 5042, for determining the target product according to the corelation behaviour data and corresponding to competing product
User's attentinal contents；
Acquiring unit 5043, closed for obtaining the competing product and the target product same user's attentinal contents are corresponding
Join index；
Generation unit 5044, for based on the correlation index and the competing product and the target product in same user
The user of attentinal contents pays close attention to probability, generates pursuit-evasion strategy of the target product relative to the competing product.
For system embodiment, because it is substantially similar to embodiment of the method, so description is fairly simple, it is related
Part illustrates referring to the part of embodiment of the method.
In addition, the embodiment of the present invention additionally provides a kind of computer-readable recording medium, computer program is stored thereon with,
The program realizes the step in above-mentioned each competing product analysis method embodiment based on big data when being executed by processor.
In addition, another embodiment of the present invention additionally provides a kind of electronic equipment, the electronic equipment includes：Housing, processing
Device, memory, circuit board and power circuit, wherein, the circuit board is placed in the interior volume that the housing surrounds, the place
Reason device and the memory are arranged on the circuit board；The power circuit, for each circuit for the electronic equipment
Or device power supply；The memory is used to store executable program code；The processor is deposited by reading in the memory
The executable program code of storage runs program corresponding with executable program code, for performing following steps：Acquisition is adopted
The internet historical behavior data of each user in sample customer group, internet historical behavior data are divided by funnel analytic approach
Analysis, obtains the like product of target product, and like product is the market orientation identical product with target product；Obtain respectively same
The degree of association of each product and target product in class product；The maximum product of the degree of association corresponding to selection is as the competing of target product
Product；Pair internet historical behavior data closed with target product and competing condition are analyzed, and generation target product is relative to competing product
Pursuit-evasion strategy.
The electronic equipment can be the computing devices such as desktop PC, notebook, palm PC and cloud server.
The computer equipment may include, but be not limited only to, processor, memory.It will be understood by those skilled in the art that the present invention is real
The example of the only computer equipment provided in example is applied, does not form the restriction to computer equipment, can be included than diagram
More or less parts, some parts or different parts are either combined, such as the computer equipment can also include
Input-output equipment, network access equipment, bus etc..
Competing product analysis method and system provided in an embodiment of the present invention based on big data, according to each production in like product
The degree of association of product and target product, the competing product selection of target product is realized, competing product can be efficiently and accurately positioned, then pass through
The internet historical behavior data of couple user closed with target product and competing condition are analyzed, and more effectively generate target product
Relative to the pursuit-evasion strategy of competing product, and then provide more efficiently competitive strategy for target product and formulate foundation, simultaneously also by
The concern of user is inclined to more effectively launches strategy so as to formulate.
Device embodiment described above is only schematical, wherein the unit illustrated as separating component can
To be or may not be physically separate, it can be as the part that unit is shown or may not be physics list
Member, you can with positioned at a place, or can also be distributed on multiple NEs.It can be selected according to the actual needs
In some or all of module realize the purpose of this embodiment scheme.Those of ordinary skill in the art are not paying creativeness
Work in the case of, you can to understand and implement.
Through the above description of the embodiments, those skilled in the art can be understood that each embodiment can
Realized by the mode of software plus required general hardware platform, naturally it is also possible to pass through hardware.Based on such understanding, on
The part that technical scheme substantially in other words contributes to prior art is stated to embody in the form of software product, should
Computer software product can store in a computer-readable storage medium, such as ROM/RAM, magnetic disc, CD, including some fingers
Make to cause a computer equipment (can be personal computer, server, or network equipment etc.) to perform each implementation
Method described in some parts of example or embodiment.
In addition, it will be appreciated by those of skill in the art that although some embodiments in this include institute in other embodiments
Including some features rather than further feature, but the combination of the feature of different embodiments means to be in the scope of the present invention
Within and form different embodiments.For example, in the following claims, embodiment claimed it is any it
One mode can use in any combination.
Finally it should be noted that：The above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although
The present invention is described in detail with reference to the foregoing embodiments, it will be understood by those within the art that：It still may be used
To be modified to the technical scheme described in foregoing embodiments, or equivalent substitution is carried out to which part technical characteristic；
And these modification or replace, do not make appropriate technical solution essence depart from various embodiments of the present invention technical scheme spirit and
Scope.
Claims (10)
- A kind of 1. competing product analysis method based on big data, it is characterised in that including:The internet historical behavior data of each user in sample user group are obtained, by funnel analytic approach to the internet history Behavioral data is analyzed, and obtains the like product of target product, and the like product is the market orientation phase with target product Same product；The degree of association of each product and the target product in the like product is obtained respectively；The degree of association corresponding to selection is more than competing product of the product of the first predetermined threshold value as the target product；Pair internet historical behavior data closed with the target product and the competing condition are analyzed, and generate the target production Pursuit-evasion strategy of the condition for the competing product.
- 2. according to the method for claim 1, it is characterised in that the internet of each user in the acquisition sample user group After historical behavior data, methods described also includes：The internet historical behavior data are analyzed by funnel analytic approach, it is determined that with the classification of the target product not Same third-party product；Obtain the degree of association in the third-party product with the target product and be more than the related product of the second predetermined threshold value, its In, first predetermined threshold value is more than second predetermined threshold value；Pair internet historical behavior data related to the target product and the related product are analyzed, and generate the mesh Mark the cooperation policy of product and the related product.
- 3. according to the method for claim 1, it is characterised in that methods described also includes：The internet historical behavior data are analyzed by funnel analytic approach, to determine mesh corresponding to the target product Customer group is marked, wherein, the potential user group is the customer group of concern target product and/or like product.
- 4. according to the method for claim 3, it is characterised in that it is described obtain respectively in the like product each product with The degree of association of the target product, including：The customer group of a certain product A in the like product is paid close attention in the number of users of statistic sampling customer group, sample user group Body and number of users, and concern target product B user group and number of users；The absolute attention rate of a certain product A in the like product to the target product B is calculated, formula is as follows：<mrow> <msub> <mi>FR</mi> <mrow> <mi>A</mi> <mi>B</mi> </mrow> </msub> <mo>=</mo> <mfrac> <mrow> <mi>C</mi> <mi>o</mi> <mi>u</mi> <mi>n</mi> <mi>t</mi> <mrow> <mo>(</mo> <msub> <mi>FU</mi> <mi>A</mi> </msub> <mo>&cap;</mo> <msub> <mi>FU</mi> <mi>B</mi> </msub> <mo>)</mo> </mrow> </mrow> <mrow> <mi>C</mi> <mi>o</mi> <mi>u</mi> <mi>n</mi> <mi>t</mi> <mrow> <mo>(</mo> <msub> <mi>FU</mi> <mi>B</mi> </msub> <mo>)</mo> </mrow> </mrow> </mfrac> </mrow>Wherein, FRABRepresent absolute attention rates of a certain product A to B, FUAPay close attention to A user group, FUBPay close attention to B's User group.Count represents number of users corresponding to user group；The user for calculating a certain product A in the like product pays close attention to probability, and formula is as follows：<mrow> <msub> <mi>FP</mi> <mi>A</mi> </msub> <mo>=</mo> <mfrac> <mrow> <mi>C</mi> <mi>o</mi> <mi>u</mi> <mi>n</mi> <mi>t</mi> <mrow> <mo>(</mo> <msub> <mi>FU</mi> <mi>A</mi> </msub> <mo>)</mo> </mrow> </mrow> <mrow> <msub> <mi>FU</mi> <mrow> <mi>a</mi> <mi>l</mi> <mi>l</mi> </mrow> </msub> </mrow> </mfrac> </mrow>Wherein, FPAProbability, FU are paid close attention to for product A userallFor the number of users of sample user group；Probability is paid close attention to according to the definitely attention rate and user, calculates a certain product A and target product B in like product Correlation index, formula are as follows：<mrow> <msub> <mi>RI</mi> <mrow> <mi>A</mi> <mi>B</mi> </mrow> </msub> <mo>=</mo> <mfrac> <mrow> <msub> <mi>FR</mi> <mrow> <mi>A</mi> <mi>B</mi> </mrow> </msub> </mrow> <mrow> <msub> <mi>FP</mi> <mi>A</mi> </msub> </mrow> </mfrac> </mrow>Wherein, RIABFor product A and target product B correlation index；The product A and the target product B degree of association are determined according to the correlation index.
- 5. according to the method for claim 3, it is characterised in that it is described by funnel analytic approach to the internet history row Analyzed for data, obtain the like product of target product, in addition to：According to the like product, corresponding user pays close attention to probability in the potential user group, and the like product is produced Product ranking.
- 6. according to the method described in claim any one of 1-5, it is characterised in that described pair with the target product and described competing The internet historical behavior data that condition closes are analyzed, and generate pursuit-evasion strategy of the target product relative to the competing product, Including：The internet historical behavior data are analyzed by funnel analytic approach, from the internet historical behavior data Search for user corelation behaviour data, the corelation behaviour data be to the target product and/or like product it is related and The behavioral data that high frequency time is carried out simultaneously within the unit interval；User's attentinal contents of the target product and corresponding competing product are determined according to the corelation behaviour data；The competing product and the target product are obtained in the corresponding correlation index of same user's attentinal contents；It is general in user's concern of same user's attentinal contents based on the correlation index and the competing product and the target product Rate, generate pursuit-evasion strategy of the target product relative to the competing product.
- A kind of 7. competing product analysis system based on big data, it is characterised in that including：Data analysis module, for obtaining the internet historical behavior data of each user in sample user group, analyzed by funnel Method is analyzed the internet historical behavior data, obtains the like product of target product, and the like product is and mesh Mark the market orientation identical product of product；Acquisition module, for obtaining the degree of association of each product and the target product in the like product respectively；Selecting module, it is more than the product of the first predetermined threshold value as the competing of the target product for choosing the corresponding degree of association Product；Competing product analysis module, divide for pair internet historical behavior data closed with the target product and the competing condition Analysis, generates pursuit-evasion strategy of the target product relative to the competing product.
- 8. system according to claim 7, it is characterised in that the data analysis module, in sample user group is obtained After the internet historical behavior data of each user, it is additionally operable to enter the internet historical behavior data by funnel analytic approach Row analysis, it is determined that the third-party product different from the classification of the target product；The acquisition module, it is additionally operable to obtain default more than second with the degree of association of the target product in the third-party product The related product of threshold value, wherein, first predetermined threshold value is more than second predetermined threshold value；The competing product analysis module, it is additionally operable to a pair internet historical behavior related to the target product and the related product Data are analyzed, and generate the cooperation policy of the target product and the related product.
- 9. system according to claim 7, it is characterised in that the data analysis module, be additionally operable to analyze by funnel Method is analyzed the internet historical behavior data, to determine potential user group corresponding to the target product, wherein, institute State customer group of the potential user group for concern target product and/or like product.
- 10. system according to claim 7, it is characterised in that the acquisition module, including：Statistic unit, pay close attention in the number of users, sample user group for statistic sampling customer group a certain in the like product Product A user group and number of users, and concern target product B user group and number of users；Computing unit, for calculating in the like product a certain product A to the absolute attention rate of the target product B, formula It is as follows：<mrow> <msub> <mi>FR</mi> <mrow> <mi>A</mi> <mi>B</mi> </mrow> </msub> <mo>=</mo> <mfrac> <mrow> <mi>C</mi> <mi>o</mi> <mi>u</mi> <mi>n</mi> <mi>t</mi> <mrow> <mo>(</mo> <msub> <mi>FU</mi> <mi>A</mi> </msub> <mo>&cap;</mo> <msub> <mi>FU</mi> <mi>B</mi> </msub> <mo>)</mo> </mrow> </mrow> <mrow> <mi>C</mi> <mi>o</mi> <mi>u</mi> <mi>n</mi> <mi>t</mi> <mrow> <mo>(</mo> <msub> <mi>FU</mi> <mi>B</mi> </msub> <mo>)</mo> </mrow> </mrow> </mfrac> </mrow>Wherein, FRABRepresent absolute attention rates of a certain product A to B, FUAPay close attention to A user group, FUBPay close attention to B's User group.Count represents number of users corresponding to user group；The computing unit, the user for being additionally operable to calculate a certain product A in the like product pay close attention to probability, and formula is as follows：<mrow> <msub> <mi>FP</mi> <mi>A</mi> </msub> <mo>=</mo> <mfrac> <mrow> <mi>C</mi> <mi>o</mi> <mi>u</mi> <mi>n</mi> <mi>t</mi> <mrow> <mo>(</mo> <msub> <mi>FU</mi> <mi>A</mi> </msub> <mo>)</mo> </mrow> </mrow> <mrow> <msub> <mi>FU</mi> <mrow> <mi>a</mi> <mi>l</mi> <mi>l</mi> </mrow> </msub> </mrow> </mfrac> </mrow>Wherein, FPAProbability, FU are paid close attention to for product A userallFor the number of users of sample user group；The computing unit, it is additionally operable to pay close attention to probability according to the definitely attention rate and user, calculates a certain production in like product Product A and target product B correlation index, formula are as follows：<mrow> <msub> <mi>RI</mi> <mrow> <mi>A</mi> <mi>B</mi> </mrow> </msub> <mo>=</mo> <mfrac> <mrow> <msub> <mi>FR</mi> <mrow> <mi>A</mi> <mi>B</mi> </mrow> </msub> </mrow> <mrow> <msub> <mi>FP</mi> <mi>A</mi> </msub> </mrow> </mfrac> </mrow>Wherein, RIABFor product A and target product B correlation index；First determining unit, for determining the product A and the target product B degree of association according to the correlation index.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710757129.0A CN107481066A (en) | 2017-08-29 | 2017-08-29 | A kind of competing product analysis method and system based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710757129.0A CN107481066A (en) | 2017-08-29 | 2017-08-29 | A kind of competing product analysis method and system based on big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107481066A true CN107481066A (en) | 2017-12-15 |
Family
ID=60603940
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710757129.0A Pending CN107481066A (en) | 2017-08-29 | 2017-08-29 | A kind of competing product analysis method and system based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107481066A (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109408695A (en) * | 2018-09-27 | 2019-03-01 | 苏州创旅天下信息技术有限公司 | Competing product data grab method and system |
| CN109993553A (en) * | 2017-12-30 | 2019-07-09 | 中国移动通信集团山西有限公司 | Data analysing method, device, equipment and medium based on reverse funnel |
| CN110443290A (en) * | 2019-07-23 | 2019-11-12 | 广东数鼎科技有限公司 | A kind of product competition relationship quantization generation method and device based on big data |
| CN110544140A (en) * | 2018-05-29 | 2019-12-06 | 北京京东尚科信息技术有限公司 | method and device for processing browsing data |
| CN110659924A (en) * | 2018-06-29 | 2020-01-07 | 北京奇虎科技有限公司 | Product competition relationship visual analysis method, device and equipment |
| CN110675205A (en) * | 2018-07-03 | 2020-01-10 | 百度在线网络技术（北京）有限公司 | Application-based competitive product analysis method and device and storage medium |
| CN112598405A (en) * | 2021-02-20 | 2021-04-02 | 汇正(广州)企业管理咨询有限公司 | Business project data management method and system based on big data |
| CN112651781A (en) * | 2020-12-29 | 2021-04-13 | 车主邦（北京）科技有限公司 | Method and device for analyzing competitive products |
| CN113743721A (en) * | 2021-07-29 | 2021-12-03 | 深圳市东信时代信息技术有限公司 | Marketing strategy generation method and device, computer equipment and storage medium |
| CN113761332A (en) * | 2020-11-10 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | Data processing method, device, equipment and computer readable storage medium |
| CN116758576A (en) * | 2023-08-21 | 2023-09-15 | 苏州极易科技股份有限公司 | Marketing information identification method, device, equipment and medium based on machine learning |
| CN117094752A (en) * | 2023-10-13 | 2023-11-21 | 广州市零脉信息科技有限公司 | Product sales intention group analysis system |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150242863A1 (en) * | 2012-07-19 | 2015-08-27 | Nikon Corporation | Electronic apparatus and method |
| CN103077220B (en) * | 2012-12-29 | 2016-06-29 | 中国科学院深圳先进技术研究院 | A kind of personalized recommendation method based on the customer group degree of association and system |
-
2017
- 2017-08-29 CN CN201710757129.0A patent/CN107481066A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150242863A1 (en) * | 2012-07-19 | 2015-08-27 | Nikon Corporation | Electronic apparatus and method |
| CN103077220B (en) * | 2012-12-29 | 2016-06-29 | 中国科学院深圳先进技术研究院 | A kind of personalized recommendation method based on the customer group degree of association and system |
Non-Patent Citations (2)
| Title |
|---|
| 姜浩: "消费者视角下的跨国公司品牌联合研究—以汽车行业为例", 《经济与管理科学辑》 * |
| 王贵苏: "消解与重构：大数据时代的品牌营销变革", 《经济与管理科学辑》 * |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109993553A (en) * | 2017-12-30 | 2019-07-09 | 中国移动通信集团山西有限公司 | Data analysing method, device, equipment and medium based on reverse funnel |
| CN109993553B (en) * | 2017-12-30 | 2021-09-03 | 中国移动通信集团山西有限公司 | Data analysis method, device, equipment and medium based on reverse funnel |
| CN110544140A (en) * | 2018-05-29 | 2019-12-06 | 北京京东尚科信息技术有限公司 | method and device for processing browsing data |
| CN110659924A (en) * | 2018-06-29 | 2020-01-07 | 北京奇虎科技有限公司 | Product competition relationship visual analysis method, device and equipment |
| CN110659924B (en) * | 2018-06-29 | 2023-09-01 | 北京奇虎科技有限公司 | Visual analysis method, device and equipment for product competition relationship |
| CN110675205A (en) * | 2018-07-03 | 2020-01-10 | 百度在线网络技术（北京）有限公司 | Application-based competitive product analysis method and device and storage medium |
| CN110675205B (en) * | 2018-07-03 | 2022-11-29 | 百度在线网络技术（北京）有限公司 | Application-based competitive product analysis method and device and storage medium |
| CN109408695A (en) * | 2018-09-27 | 2019-03-01 | 苏州创旅天下信息技术有限公司 | Competing product data grab method and system |
| CN110443290A (en) * | 2019-07-23 | 2019-11-12 | 广东数鼎科技有限公司 | A kind of product competition relationship quantization generation method and device based on big data |
| CN113761332A (en) * | 2020-11-10 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | Data processing method, device, equipment and computer readable storage medium |
| CN112651781A (en) * | 2020-12-29 | 2021-04-13 | 车主邦（北京）科技有限公司 | Method and device for analyzing competitive products |
| CN112598405B (en) * | 2021-02-20 | 2021-11-05 | 苏州天合启信科技有限公司 | Business project data management method and system based on big data |
| CN112598405A (en) * | 2021-02-20 | 2021-04-02 | 汇正(广州)企业管理咨询有限公司 | Business project data management method and system based on big data |
| CN113743721A (en) * | 2021-07-29 | 2021-12-03 | 深圳市东信时代信息技术有限公司 | Marketing strategy generation method and device, computer equipment and storage medium |
| CN116758576A (en) * | 2023-08-21 | 2023-09-15 | 苏州极易科技股份有限公司 | Marketing information identification method, device, equipment and medium based on machine learning |
| CN116758576B (en) * | 2023-08-21 | 2023-11-21 | 苏州极易科技股份有限公司 | Marketing information identification method, device, equipment and medium based on machine learning |
| CN117094752A (en) * | 2023-10-13 | 2023-11-21 | 广州市零脉信息科技有限公司 | Product sales intention group analysis system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107481066A (en) | A kind of competing product analysis method and system based on big data | |
| US20210329094A1 (en) | Discovering signature of electronic social networks | |
| Ruchansky et al. | Csi: A hybrid deep model for fake news detection | |
| US11734566B2 (en) | Systems and processes for bias removal in a predictive performance model | |
| Gil et al. | Towards content trust of web resources | |
| Tsytsarau et al. | Dynamics of news events and social media reaction | |
| Johansson et al. | Comparison of methods for handling missing covariate data | |
| US20080195609A1 (en) | Method and System for Generating a Population Representative of a Set of Users of a Communication Network | |
| CN109167816A (en) | Information-pushing method, device, equipment and storage medium | |
| Jansen et al. | Measuring user interactions with websites: A comparison of two industry standard analytics approaches using data of 86 websites | |
| Dey et al. | Sample complexity for winner prediction in elections | |
| Saleem et al. | Personalized decision-strategy based web service selection using a learning-to-rank algorithm | |
| CN111079009A (en) | User interest detection method and system for government map service | |
| Bansal et al. | Trust evaluation of websites: a comprehensive study | |
| CN110309411A (en) | A kind of resource recommendation method and device | |
| CN116701772A (en) | Data recommendation method and device, computer readable storage medium and electronic equipment | |
| Johansson et al. | Assessment of enterprise information security-estimating the credibility of the results | |
| O’brien | Beyond reliable: Challenging and deciding expert admissibility in US civil courts | |
| Khadangi et al. | Presenting novel application-based centrality measures for finding important users based on their activities and social behavior | |
| Anderson et al. | Using Copulas to Model and Simulate Two‐dimensional Warranty Data | |
| CN110210978A (en) | Determine the method, apparatus, equipment and storage medium of fund factor validity | |
| Sijtsma et al. | Nonparametric statistical methods | |
| Vranić et al. | Sustainability of Stack Exchange Q&A communities: the role of trust | |
| Šitum | Analysis of algorithms for determining trust among friends on social networks | |
| KR100469822B1 (en) | Method for managing on-line knowledge community and system for enabling the method |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20180109 Address after: 100027 Fuhua building, No. 8, Chaoyangmen North Street, Dongcheng District, Beijing, Dongcheng District, F 17-C Applicant after: Liu Geng Address before: 100027 Fuhua building, No. 8, Chaoyangmen North Street, Dongcheng District, Beijing, Dongcheng District, F 17-C Applicant before: EPPs Shengguo (Beijing) intelligent Polytron Technologies Inc |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171215 |