CN107870990A - A kind of automobile recommends method and device - Google Patents
A kind of automobile recommends method and device Download PDFInfo
- Publication number
- CN107870990A CN107870990A CN201710967299.1A CN201710967299A CN107870990A CN 107870990 A CN107870990 A CN 107870990A CN 201710967299 A CN201710967299 A CN 201710967299A CN 107870990 A CN107870990 A CN 107870990A
- Authority
- CN
- China
- Prior art keywords
- clustering cluster
- dimension
- vehicle
- dimension data
- dimensional information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- 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
- 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)
- Databases & Information Systems (AREA)
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Engineering & Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the present invention discloses a kind of automobile and recommends method and device, wherein, method includes：Obtaining each each dimension data of vehicle, each dimension data in each automotive vertical class website includes the evaluation score of each dimension；Each dimension data is pre-processed, so that evaluation score is distributed in the range of pre-set interval；Pretreated each dimension data is clustered, obtains the clustering cluster of different automotive types, wherein clustering cluster number is the dimensional information in each dimension data of each vehicle according to acquisition to determine；Obtain the dimensional information that user specifies and the clustering cluster of acquisition is screened according to the dimensional information that user specifies；All vehicles in clustering cluster are ranked up in the clustering cluster of selection, ranking results are showed into user.The embodiment of the present invention can provide the user the recommendation of the automobile product of convenient and efficient.
Description
Technical field
The present embodiments relate to technical field of data processing, and in particular to a kind of automobile recommends method and device.
Background technology
At present, in the scheme for recommending automobile to choose, traditional method is broadly divided into two kinds, and the first is to be based on professional people
The recommendation method of member, is the demand by gathering user, such as price, brand, the information such as vehicle, is then familiar with the special of automobile market
Industry personnel provide several candidate items by personal experience.It is for second the method for user oneself study, is automobile purchase user
Oneself is according to the demand of oneself, the paired observation between different automobile 4s shops, Ran Houxuan on the website of each automotive vertical class
Select and oneself think rational vehicle.
Because the popular understanding to automobile is known little a few years ago, therefore the first recommendation method one based on professional
The method that degree chooses short-list as the acquisition automobile of main flow.But the problem of this method is if found third-party
Professional person, it is expensive.If the purpose for consultant's majority that auto vendor provides is for oneself product of sale.It is another
Individual problem is exactly the characteristics of different professional persons is due to personal like, can cause identical user's request, different professional peoples
Candidate's vehicle that scholar provides is different, can not give the efficient recommended suggestion of user.
For the method for second of user oneself study, although as the fast development of information age, user are new in study
The threshold of domain knowledge become more and more lower, but certain technology barriers, this point are still had between different domain knowledges
More very, automotive field is because the field being related to is numerous in the field of science and engineering, wherein containing substantial amounts of specialized technical knowledge, commonly
Personnel's learning cost without background is higher.Secondly as the limitation on the energy and time of each user, the vehicle of understanding, institute
The data that can learn and the data for going to 4s shops to observe all are limited, therefore that certain data sample is not complete can be present,
The vehicle for causing some high-quality does not enter into short-list, i.e., sample is ignored in the selection made on limited sample data sometimes
High-quality vehicle beyond this.
In consideration of it, how to provide a kind of automobile recommends method and device, to provide the user the automobile product of convenient and efficient
Recommendation turn into the current technical issues that need to address.
The content of the invention
Because existing method has above mentioned problem, the embodiment of the present invention proposes that a kind of automobile recommends method and device.
In a first aspect, the embodiment of the present invention proposes that a kind of automobile recommends method, including：
Each each dimension data of vehicle in each automotive vertical class website is obtained, each dimension data includes commenting for each dimension
Valency fraction；
Each dimension data is pre-processed, so that the evaluation score is distributed in the range of pre-set interval；
Pretreated each dimension data is clustered, obtains the clustering cluster of different automotive types, wherein clustering cluster
Number is the dimensional information in each dimension data of each vehicle according to acquisition to determine；
The dimensional information that user specifies is obtained, and the clustering cluster of acquisition is sieved according to the dimensional information that user specifies
Choosing；
All vehicles in clustering cluster are ranked up in the clustering cluster of selection, ranking results are showed into user.
Alternatively, each dimension data of each vehicle in each automotive vertical class website of acquisition, including：
Each automotive vertical class website is crawled using crawler technology, obtains each vehicle in each automotive vertical class website
Each dimension data.
Alternatively, each dimension of each vehicle, including：Space, power, manipulation, oil consumption, comfortableness, outward appearance, interior trim and
Cost performance.
Alternatively, it is described that each dimension data is pre-processed, so that the evaluation score is distributed in preset areas
Between in the range of, including：
The evaluation score of each dimension in each dimension data of each vehicle obtained from each automotive vertical class website is equal
It is mapped in the range of pre-set interval.
Alternatively, it is described that pretreated each dimension data is clustered, the clustering cluster of different automotive types is obtained, is wrapped
Include：
Using kmeans algorithms, pretreated each dimension data is clustered, obtains the cluster of different automotive types
Cluster.
Alternatively, the dimensional information for obtaining user and specifying, and the dimensional information specified according to user is to being gathered
Class cluster is screened, including：
Obtain the dimensional information that user specifies and determine the demand dimension of user, arranged in the dimensional information that wherein user specifies
The weight of the forward dimensional information of name is more than the weight of the dimensional information to rank behind；
According to the demand dimension of user, using the first formula, the dimension for calculating each clustering cluster of acquisition weights two norms
X；
Dimension is selected to weight the maximum clustering cluster of two norms；
Wherein, first formula is
wiFor the weight of i-th of dimension in this clustering cluster, xiFor mean opinion score of i-th of dimension in this clustering cluster
Value, n are the number of dimensions in this clustering cluster, i=1 ..., n.
Alternatively, it is described that all vehicles in clustering cluster are ranked up in the clustering cluster of selection, including：
Using the second formula, the norm X' of weighting two of each vehicle in selected clustering cluster is calculated；
According to the size of the norm of weighting two of each vehicle in the selected clustering cluster being calculated, in clustering cluster
All vehicles are ranked up；
Wherein, second formula is
w'jFor the weight of j-th of vehicle in selected clustering cluster, x'jFor j-th vehicle in selected clustering cluster
Evaluation score value, m are the quantity of vehicle in selected clustering cluster, j=1 ..., m.
Second aspect, the embodiment of the present invention also propose a kind of automobile recommendation apparatus, including：
Acquisition module, for obtaining each each dimension data of vehicle, each dimension data in each automotive vertical class website
Include the evaluation score of each dimension；
Pretreatment module, for being pre-processed to each dimension data so that the evaluation score be distributed in it is pre-
If in interval range；
Cluster module, for being clustered to pretreated each dimension data, the clustering cluster of different automotive types is obtained,
Wherein clustering cluster number is the dimensional information in each dimension data of each vehicle according to acquisition to determine；
Screening module, the dimensional information specified for obtaining user, and the dimensional information specified according to user is to acquisition
Clustering cluster is screened；
Order module, for being ranked up in the clustering cluster of selection to the information in clustering cluster, ranking results are shown
To user.
The third aspect, the embodiment of the present invention also propose a kind of electronic equipment, including：Processor, memory, bus and storage
On a memory and the computer program that can run on a processor；
Wherein, the processor, memory complete mutual communication by the bus；
Described in the computing device above method is realized during computer program.
Fourth aspect, the embodiment of the present invention provide a kind of non-transient computer readable storage medium storing program for executing, the non-transient calculating
Computer program is stored with machine readable storage medium storing program for executing, the computer program realizes the above method when being executed by processor.
As shown from the above technical solution, the embodiment of the present invention is respectively tieed up by obtaining each vehicle in each automotive vertical class website
Degrees of data, each dimension data include the evaluation score of each dimension；Each dimension data is pre-processed, so that evaluation score is divided equally
Cloth is in the range of pre-set interval；Pretreated each dimension data is clustered, obtains the clustering cluster of different automotive types, its
Middle clustering cluster number is the dimensional information in each dimension data of each vehicle according to acquisition to determine；Obtain what user specified
Dimensional information is simultaneously screened according to the dimensional information that user specifies to the clustering cluster of acquisition；To cluster in the clustering cluster of selection
All vehicles in cluster are ranked up, and ranking results are showed into user, and thereby, it is possible to provide the user the automobile of convenient and efficient
The recommendation of product, existing the drawbacks of needing traditional specialty personage to recommend is overcome, consulting cost is reduced, avoids different
Professional person's opinion carries the problem of certain subjectivity；Eliminate user need to learn by oneself with grasp time of these information into
This, user can with convenient and efficient by obtain oneself interested parties to automobile recommendation list (recommendation of automotive type is sorted
As a result).
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
There is the required accompanying drawing used in technology description to be briefly described, it should be apparent that, drawings in the following description are only this
Some embodiments of invention, for those of ordinary skill in the art, on the premise of not paying creative work, can be with
Other accompanying drawings are obtained according to these figures.
Fig. 1 is the schematic flow sheet that a kind of automobile that one embodiment of the invention provides recommends method；
Fig. 2 is a kind of structural representation for automobile recommendation apparatus that one embodiment of the invention provides；
Fig. 3 is the logic diagram for the electronic equipment that one embodiment of the invention provides.
Embodiment
Below in conjunction with the accompanying drawings, the embodiment of the present invention is further described.Following examples are only used for more
Clearly demonstrate technical scheme, and can not be limited the scope of the invention with this.
Fig. 1 shows that a kind of automobile that one embodiment of the invention provides recommends the schematic flow sheet of method, as shown in figure 1,
The automobile of the present embodiment recommends method, including：
Each dimension data of each vehicle in S101, each automotive vertical class website of acquisition, each dimension data include each dimension
The evaluation score of degree.
In a particular application, each automotive vertical class website can be crawled using crawler technology, obtains each automobile and hang down
Each dimension data of each vehicle in straight class website.
Wherein, each dimension of each vehicle, including：Space, power, manipulation, oil consumption, comfortableness, outward appearance, interior trim and property
Valency ratio etc., such as each dimension data of each vehicle obtained from certain automotive vertical class website include：Space 4.42 is divided, power 4.08
Divide, manipulate 4.45 points, oil consumption 4.22 divides, comfortableness 4.16 is divided, outward appearance 4.54 is divided, interior trim 4.33 divides and cost performance 3.89 is divided.This
Embodiment is not limited each each dimension of vehicle, and each dimension of each vehicle can also be according to actual conditions bag
Include other dimensions related to vehicle.
S102, each dimension data is pre-processed, so that the evaluation score is distributed in pre-set interval scope
It is interior.
In a particular application, can will be each in each dimension data of each vehicle obtained from each automotive vertical class website
The evaluation score of dimension is both mapped in the range of pre-set interval.For example, the pre-set interval may range from 0-5.
S103, pretreated each dimension data is clustered, obtain the clustering cluster of different automotive types, wherein clustering
Cluster number is the dimensional information in each dimension data of each vehicle according to acquisition to determine.
In a particular application, the present embodiment can utilize kmeans algorithms, and pretreated each dimension data is gathered
Class, obtain the clustering cluster of different automotive types.Certainly, the present embodiment can also utilize other clustering algorithms to pretreated each
Dimension data is clustered, and obtains the clustering cluster of different automotive types, and the present embodiment is not limited.
It is understood that Kmeans algorithms are the very typical clustering algorithms based on distance, using distance as similar
The evaluation index of property, that is, think that the distance of two objects is nearer, its similarity is bigger.The algorithm thinks that cluster is by apart from close
Object composition, therefore using obtaining compact and independent cluster as final goal.
How many it should be noted that in this step, dimensional information in each dimension data of each vehicle of acquisition, can obtain
Obtain the clustering cluster of how many individual automotive types.
It is understood that clustering algorithm, although not needing label information, needs as a kind of unsupervised learning algorithm
Determine the convergent hyper parameter of clustering algorithm (clustering cluster number is exactly a kind of).By using cluster number of dimensions in the present embodiment
Method estimate clustering cluster number, avoid and artificially estimate due to caused uncertainty of lacking experience, while in certain journey
Meet certain natural law on degree, each automobile has the aspect being good at, and the similar vehicle of dimension is easier to cluster to together.
S104, the dimensional information that user specifies is obtained, and the clustering cluster of acquisition is entered according to the dimensional information that user specifies
Row screening.
In a particular application, the step S104 can include：Obtain the dimensional information that user specifies and determine user's
(weight of dimensional information in the top is more than the dimension letter to rank behind to demand dimension in the dimensional information that wherein user specifies
The weight of breath)；According to the demand dimension of user, using the first formula, the dimension for calculating each clustering cluster of acquisition weights two models
Number X；Dimension is selected to weight the maximum clustering cluster of two norms；
Wherein, first formula is
wiFor the weight of i-th of dimension in this clustering cluster, xiFor mean opinion score of i-th of dimension in this clustering cluster
Value, n are the number of dimensions in this clustering cluster, i=1 ..., n.
It is understood that the demand dimension of user can be understood as preference type (such as cost performance, outward appearance, interior of user
Decorations etc.), this step be really according to the demand dimension of user carry out various dimensions screening (such as may a certain user compare emphasis
Power and interior trim), determine the clustering cluster of which automotive type and the matching degree highest of user's request information.
It is understood that the present embodiment by weight two norms method come determine the vehicle in which clustering cluster be
The cluster to behave oneself best under user's request, while attention rate difference of the user to different dimensions is considered, it will be more to be also exactly
Individual dimensional information, it is mapped to and one-dimensional is compared selection.
S105, all vehicles in clustering cluster are ranked up in the clustering cluster of selection, ranking results are showed into use
Family.
In the step S105, the second formula can be utilized, calculates the weighting of each vehicle in selected clustering cluster
Two norm X'；According to the size of the norm of weighting two of each vehicle in the selected clustering cluster being calculated, in clustering cluster
All vehicles be ranked up；
Wherein, second formula is
w'jFor the weight of j-th of vehicle in selected clustering cluster, x'jFor j-th vehicle in selected clustering cluster
Evaluation score value, m are the quantity of vehicle in selected clustering cluster, j=1 ..., m.
It is understood that the method using two norms of weighting, it may be determined that paid close attention to inside same clustering cluster in user
Dimensional information under each vehicle recommendation sequence, it is exactly the recommendation purchase car team for meeting user's request that the ranking results are actual
Table.
The present embodiment can utilize the method for weighting two norms twice, be once that specifically which cluster is to meet use in selection
Family dimensional information interested.Another time is after it have selected cluster, solves how to arrange different vehicles inside cluster
The problem of sequence.Compared with prior art, the present embodiment is all taken into account the value of all dimensions based on the method for cluster, Ran Houchong
Point considers the dimension of user's concern, and this method meets the increasingly harsher purchasing standard of current user.
The automobile of the present embodiment recommends method, by obtaining each each dimension data of vehicle in each automotive vertical class website,
Each dimension data includes the evaluation score of each dimension；Each dimension data is pre-processed so that evaluation score be distributed in it is pre-
If in interval range；Pretreated each dimension data is clustered, obtains the clustering cluster of different automotive types, wherein clustering
Cluster number is the dimensional information in each dimension data of each vehicle according to acquisition to determine；Obtain the dimension letter that user specifies
Cease and the clustering cluster of acquisition is screened according to the dimensional information that user specifies；To in clustering cluster in the clustering cluster of selection
All vehicles are ranked up, ranking results are showed into user, and thereby, it is possible to provide the user the automobile product of convenient and efficient
Recommend, overcome existing the drawbacks of needing traditional specialty personage to recommend, reduce consulting cost, avoid different professional peoples
Scholar's opinion carries the problem of certain subjectivity；Eliminating user needs to learn by oneself and grasp the time cost of these information, user
Can with convenient and efficient by obtain oneself interested parties to automobile recommendation list (the recommendation ranking results of automotive type).
Fig. 2 shows a kind of structural representation for automobile recommendation apparatus that one embodiment of the invention provides, as shown in Fig. 2
The automobile recommendation apparatus of the present embodiment, including：Acquisition module 21, pretreatment module 22, cluster module 23, screening module 24 and row
Sequence module 25；Wherein：
The acquisition module 21, for obtaining each each dimension data of vehicle in each automotive vertical class website, each dimension
Degrees of data includes the evaluation score of each dimension；
The pretreatment module 22, for being pre-processed to each dimension data, so that the evaluation score is divided equally
Cloth is in the range of pre-set interval；
The cluster module 23, for being clustered to pretreated each dimension data, obtain different automotive types
Clustering cluster, wherein clustering cluster number are the dimensional informations in each dimension data of each vehicle according to acquisition to determine；
The screening module 24, the dimensional information specified for obtaining user, and the dimensional information pair specified according to user
The clustering cluster of acquisition is screened；
The order module 25, for being ranked up in the clustering cluster of selection to the information in clustering cluster, sequence is tied
Fruit shows user.
Specifically, the acquisition module 21 obtains each each dimension data of vehicle in each automotive vertical class website, described each
Dimension data includes the evaluation score of each dimension；The pretreatment module 22 pre-processes to each dimension data, so that
The evaluation score is distributed in the range of pre-set interval；The cluster module 23 gathers to pretreated each dimension data
Class, the clustering cluster of different automotive types is obtained, wherein clustering cluster number is in each dimension data of each vehicle according to acquisition
Dimensional information determines；The screening module 24 obtains the dimensional information that user specifies, and the dimension specified according to user is believed
Cease and the clustering cluster of acquisition is screened；The order module 25 is arranged the information in clustering cluster in the clustering cluster of selection
Sequence, ranking results are showed into user.
In a particular application, the acquisition module 21 can be climbed using crawler technology to each automotive vertical class website
Take, obtain each each dimension data of vehicle in each automotive vertical class website.
Wherein, each dimension of each vehicle, including：Space, power, manipulation, oil consumption, comfortableness, outward appearance, interior trim and property
Valency ratio etc., the present embodiment is not limited, and each each dimension of vehicle can also include other according to actual conditions
The dimension related to vehicle.
In a particular application, each vehicle that the pretreatment module 22 will can obtain from each automotive vertical class website
The evaluation score of each dimension in each dimension data is both mapped in the range of pre-set interval.
In a particular application, the cluster module 23 can utilize kmeans algorithms, to pretreated each dimension data
Clustered, obtain the clustering cluster of different automotive types.Certainly, the cluster module 23 can utilize other clustering algorithms to pre-
Each dimension data after processing is clustered, and obtains the clustering cluster of different automotive types, and the present embodiment is not limited.
It should be noted that in the cluster module 23, how many dimension letter in each dimension data of each vehicle of acquisition
Breath, the clustering cluster of how many individual automotive types can be obtained.
It is understood that clustering algorithm, although not needing label information, needs as a kind of unsupervised learning algorithm
Determine the convergent hyper parameter of clustering algorithm (clustering cluster number is exactly a kind of).By using cluster number of dimensions in the present embodiment
Method estimate clustering cluster number, avoid and artificially estimate due to caused uncertainty of lacking experience, while in certain journey
Meet certain natural law on degree, each automobile has the aspect being good at, and the similar vehicle of dimension is easier to cluster to together.
In a particular application, the screening module 24, can be specifically used for
Obtain the dimensional information that user specifies and determine that the demand dimension of user (is arranged in the dimensional information that wherein user specifies
The weight of the forward dimensional information of name is more than the weight of the dimensional information to rank behind)；According to the demand dimension of user, is utilized
One formula, the dimension for calculating each clustering cluster of acquisition weight two norm X；Dimension is selected to weight the maximum clustering cluster of two norms；
Wherein, first formula is
wiFor the weight of i-th of dimension in this clustering cluster, xiFor mean opinion score of i-th of dimension in this clustering cluster
Value, n are the number of dimensions in this clustering cluster, i=1 ..., n.
It is understood that the demand dimension of user can be understood as preference type (such as cost performance, outward appearance, interior of user
Decorations etc.), the screening module 24 be really the screenings of various dimensions is carried out according to the demand dimension of user (such as may a certain user
Compare and focus on power and interior trim), determine the clustering cluster of which automotive type and the matching degree highest of user's request information.
It is understood that the screening module 24 determines the car in which clustering cluster by weighting the method for two norms
Type is the cluster to behave oneself best under user's request, while considers attention rate difference of the user to different dimensions, and being also exactly can
One-dimensional selection is compared by multiple dimensional informations, to be mapped to.
In a particular application, in the order module 25, the second formula can be utilized, is calculated in selected clustering cluster
The norm X' of weighting two of each vehicle；According in the selected clustering cluster being calculated the norm of weighting two of each vehicle it is big
It is small, all vehicles in clustering cluster are ranked up；
Wherein, second formula is
w'jFor the weight of j-th of vehicle in selected clustering cluster, x'jFor j-th vehicle in selected clustering cluster
Evaluation score value, m are the quantity of vehicle in selected clustering cluster, j=1 ..., m.
It is understood that the method using two norms of weighting, it may be determined that paid close attention to inside same clustering cluster in user
Dimensional information under each vehicle recommendation sequence, it is exactly the recommendation purchase car team for meeting user's request that the ranking results are actual
Table.
The present embodiment can utilize the method for weighting two norms twice, be once that specifically which cluster is to meet use in selection
Family dimensional information interested.Another time is after it have selected cluster, solves how to arrange different vehicles inside cluster
The problem of sequence.Compared with prior art, the present embodiment is all taken into account the value of all dimensions based on the method for cluster, Ran Houchong
Point considers the dimension of user's concern, and this method meets the increasingly harsher purchasing standard of current user.
The automobile recommendation apparatus of the present embodiment, can provide the user the recommendation of the automobile product of convenient and efficient, overcome
Existing the drawbacks of needing traditional specialty personage to recommend, consulting cost is reduced, different professional person's opinions is avoided and carries
The problem of certain subjectivity；Eliminating user needs to learn by oneself and grasp the time cost of these information, and user can be with convenient height
Effect by obtain oneself interested parties to automobile recommendation list (the recommendation ranking results of automotive type).
The automobile recommendation apparatus of the present embodiment, it can be used for the technical scheme for performing preceding method embodiment, it realizes former
Reason is similar with technique effect, and here is omitted.
Fig. 3 shows the entity structure schematic diagram of a kind of electronic equipment provided in an embodiment of the present invention, as shown in figure 3, should
Electronic equipment can include：Processor 11, memory 12, bus 13 and it is stored on memory 12 and can be transported on processor 11
Capable computer program；
Wherein, the processor 11, memory 12 complete mutual communication by the bus 13；
The processor 11 realizes the method that above-mentioned each method embodiment is provided when performing the computer program, such as
Including：Obtaining each each dimension data of vehicle, each dimension data in each automotive vertical class website includes the evaluation of each dimension
Fraction；Each dimension data is pre-processed, so that the evaluation score is distributed in the range of pre-set interval；To pre- place
Each dimension data after reason is clustered, and obtains the clustering cluster of different automotive types, and wherein clustering cluster number is according to acquisition
Dimensional information in each each dimension data of vehicle determines；The dimensional information that user specifies is obtained, and is specified according to user
Dimensional information the clustering cluster of acquisition is screened；All vehicles in clustering cluster are arranged in the clustering cluster of selection
Sequence, ranking results are showed into user.
The embodiment of the present invention provides a kind of non-transient computer readable storage medium storing program for executing, is stored thereon with computer program, should
Realize the method that above-mentioned each method embodiment is provided when computer program is executed by processor, such as including：Obtain each automobile
Each dimension data of each vehicle, each dimension data include the evaluation score of each dimension in vertical class website；To each dimension
Degrees of data is pre-processed, so that the evaluation score is distributed in the range of pre-set interval；To pretreated each number of dimensions
According to being clustered, the clustering cluster of different automotive types is obtained, wherein clustering cluster number is each dimension of each vehicle according to acquisition
Dimensional information in data determines；The dimensional information that user specifies is obtained, and the dimensional information specified according to user is to obtaining
The clustering cluster obtained is screened；All vehicles in clustering cluster are ranked up in the clustering cluster of selection, by ranking results exhibition
Show to user.
It should be understood by those skilled in the art that, embodiments herein can be provided as method, apparatus or computer program
Product.Therefore, the application can use the reality in terms of complete hardware embodiment, complete software embodiment or combination software and hardware
Apply the form of example.Moreover, the application can use the computer for wherein including computer usable program code in one or more
The computer program production that usable storage medium is implemented on (including but is not limited to magnetic disk storage, CD-ROM, optical memory etc.)
The form of product.
The application be with reference to according to the method, apparatus of the embodiment of the present application and the flow chart of computer program product and/or
Block diagram describes.It should be understood that can by each flow in computer program instructions implementation process figure and/or block diagram and/or
Square frame and the flow in flow chart and/or block diagram and/or the combination of square frame.These computer program instructions can be provided to arrive
All-purpose computer, special-purpose computer, the processor of Embedded Processor or other programmable data processing devices are to produce one
Machine so that produced by the instruction of computer or the computing device of other programmable data processing devices and flowed for realizing
The device/system for the function of being specified in one flow of journey figure or multiple flows and/or one square frame of block diagram or multiple square frames.
These computer program instructions, which may be alternatively stored in, can guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works so that the instruction being stored in the computer-readable memory, which produces, to be included referring to
Make the manufacture of device, the command device realize in one flow of flow chart or multiple flows and/or one square frame of block diagram or
The function of being specified in multiple square frames.
These computer program instructions can be also loaded into computer or other programmable data processing devices so that counted
Series of operation steps is performed on calculation machine or other programmable devices to produce computer implemented processing, so as in computer or
The instruction performed on other programmable devices is provided for realizing in one flow of flow chart or multiple flows and/or block diagram one
The step of function of being specified in individual square frame or multiple square frames.
It should be noted that herein, such as first and second or the like relational terms are used merely to a reality
Body or operation make a distinction with another entity or operation, and not necessarily require or imply and deposited between these entities or operation
In any this actual relation or order.Moreover, term " comprising ", "comprising" or its any other variant are intended to
Nonexcludability includes, so that process, method, article or equipment including a series of elements not only will including those
Element, but also the other element including being not expressly set out, or it is this process, method, article or equipment also to include
Intrinsic key element.In the absence of more restrictions, the key element limited by sentence "including a ...", it is not excluded that
Other identical element also be present in process, method, article or equipment including the key element.Term " on ", " under " etc. refers to
The orientation or position relationship shown is based on orientation shown in the drawings or position relationship, is for only for ease of the description present invention and simplifies
Description, rather than the device or element of instruction or hint meaning must have specific orientation, with specific azimuth configuration and behaviour
Make, therefore be not considered as limiting the invention.Unless otherwise clearly defined and limited, term " installation ", " connected ",
" connection " should be interpreted broadly, for example, it may be being fixedly connected or being detachably connected, or be integrally connected；Can be
Mechanically connect or electrically connect；Can be joined directly together, can also be indirectly connected by intermediary, can be two
The connection of element internal.For the ordinary skill in the art, above-mentioned term can be understood at this as the case may be
Concrete meaning in invention.
In the specification of the present invention, numerous specific details are set forth.Although it is understood that embodiments of the invention can
To be put into practice in the case of these no details.In some instances, known method, structure and skill is not been shown in detail
Art, so as not to obscure the understanding of this description.Similarly, it will be appreciated that disclose in order to simplify the present invention and helps to understand respectively
One or more of individual inventive aspect, in the description to the exemplary embodiment of the present invention above, each spy of the invention
Sign is grouped together into single embodiment, figure or descriptions thereof sometimes.However, should not be by the method solution of the disclosure
Release and be intended in reflection is following：I.e. the present invention for required protection requirement is than the feature that is expressly recited in each claim more
More features.More precisely, as the following claims reflect, inventive aspect is to be less than single reality disclosed above
Apply all features of example.Therefore, it then follows thus claims of embodiment are expressly incorporated in the embodiment,
Wherein each claim is in itself as separate embodiments of the invention.It should be noted that in the case where not conflicting, this
The feature in embodiment and embodiment in application can be mutually combined.The invention is not limited in any single aspect,
Any single embodiment is not limited to, is also not limited to any combination and/or the displacement of these aspects and/or embodiment.And
And can be used alone the present invention each aspect and/or embodiment or with other one or more aspects and/or its implementation
Example is used in combination.
Finally it should be noted that：Various embodiments above is merely illustrative of the technical solution of the present invention, rather than its limitations；To the greatest extent
The present invention is described in detail with reference to foregoing embodiments for pipe, it will be understood by those within the art that：Its according to
The technical scheme described in foregoing embodiments can so be modified, either which part or all technical characteristic are entered
Row equivalent substitution；And these modifications or replacement, the essence of appropriate technical solution is departed from various embodiments of the present invention technology
The scope of scheme, it all should cover among the claim of the present invention and the scope of specification.
Claims (10)
1. a kind of automobile recommends method, it is characterised in that including：
Each each dimension data of vehicle in each automotive vertical class website is obtained, each dimension data includes the evaluation point of each dimension
Number；
Each dimension data is pre-processed, so that the evaluation score is distributed in the range of pre-set interval；
Pretreated each dimension data is clustered, obtains the clustering cluster of different automotive types, wherein clustering cluster number is
Dimensional information in each dimension data of each vehicle of acquisition determines；
The dimensional information that user specifies is obtained, and the clustering cluster of acquisition is screened according to the dimensional information that user specifies；
All vehicles in clustering cluster are ranked up in the clustering cluster of selection, ranking results are showed into user.
2. according to the method for claim 1, it is characterised in that each vehicle is each in each automotive vertical class website of acquisition
Dimension data, including：
Each automotive vertical class website is crawled using crawler technology, each vehicle in each automotive vertical class website is obtained and respectively ties up
Degrees of data.
3. according to the method for claim 1, it is characterised in that each dimension of each vehicle, including：Space, power, behaviour
Control, oil consumption, comfortableness, outward appearance, interior trim and cost performance.
4. according to the method for claim 1, it is characterised in that it is described that each dimension data is pre-processed, so that
The evaluation score is distributed in the range of pre-set interval, including：
The evaluation score of each dimension in each dimension data of each vehicle obtained from each automotive vertical class website is mapped
To in the range of pre-set interval.
5. according to the method for claim 1, it is characterised in that it is described that pretreated each dimension data is clustered,
The clustering cluster of different automotive types is obtained, including：
Using kmeans algorithms, pretreated each dimension data is clustered, obtains the clustering cluster of different automotive types.
6. according to the method for claim 1, it is characterised in that it is described to obtain the dimensional information specified of user, and according to
The dimensional information that family is specified is screened to the clustering cluster of acquisition, including：
Obtain the dimensional information that user specifies and determine the demand dimension of user, ranking is leaned in the dimensional information that wherein user specifies
The weight of preceding dimensional information is more than the weight of the dimensional information to rank behind；
According to the demand dimension of user, using the first formula, the dimension for calculating each clustering cluster of acquisition weights two norm X；
Dimension is selected to weight the maximum clustering cluster of two norms；
Wherein, first formula is
<mrow>
<mi>X</mi>
<mo>=</mo>
<msqrt>
<mrow>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>n</mi>
</munderover>
<msub>
<mi>w</mi>
<mi>i</mi>
</msub>
<msubsup>
<mi>x</mi>
<mi>i</mi>
<mn>2</mn>
</msubsup>
</mrow>
</msqrt>
</mrow>
wiFor the weight of i-th of dimension in this clustering cluster, xiThe mean opinion score value for being i-th of dimension in this clustering cluster, n
For the number of dimensions in this clustering cluster, i=1 ..., n.
7. according to the method for claim 1, it is characterised in that it is described in the clustering cluster of selection to all in clustering cluster
Vehicle is ranked up, including：
Using the second formula, the norm X' of weighting two of each vehicle in selected clustering cluster is calculated；
According to the size of the norm of weighting two of each vehicle in the selected clustering cluster being calculated, to all in clustering cluster
Vehicle is ranked up；
Wherein, second formula is
<mrow>
<msup>
<mi>X</mi>
<mo>&prime;</mo>
</msup>
<mo>=</mo>
<msqrt>
<mrow>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>j</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>m</mi>
</munderover>
<msub>
<msup>
<mi>w</mi>
<mo>&prime;</mo>
</msup>
<mi>j</mi>
</msub>
<msubsup>
<msup>
<mi>x</mi>
<mo>&prime;</mo>
</msup>
<mi>j</mi>
<mn>2</mn>
</msubsup>
</mrow>
</msqrt>
</mrow>
w'jFor the weight of j-th of vehicle in selected clustering cluster, x'jFor the evaluation of j-th of vehicle in selected clustering cluster
Fractional value, m are the quantity of vehicle in selected clustering cluster, j=1 ..., m.
A kind of 8. automobile recommendation apparatus, it is characterised in that including：
Acquisition module, include for obtaining each each dimension data of vehicle, each dimension data in each automotive vertical class website
The evaluation score of each dimension；
Pretreatment module, for being pre-processed to each dimension data, so that the evaluation score is distributed in preset areas
Between in the range of；
Cluster module, for being clustered to pretreated each dimension data, the clustering cluster of different automotive types is obtained, wherein
Clustering cluster number is the dimensional information in each dimension data of each vehicle according to acquisition to determine；
Screening module, the dimensional information specified for obtaining user, and the cluster according to the dimensional information that user specifies to acquisition
Cluster is screened；
Order module, for being ranked up in the clustering cluster of selection to the information in clustering cluster, ranking results are showed into use
Family.
9. a kind of electronic equipment, it is characterised in that including：Processor, memory, bus and storage on a memory and can located
The computer program run on reason device；
Wherein, the processor, memory complete mutual communication by the bus；
The method as any one of claim 1-7 is realized described in the computing device during computer program.
10. a kind of non-transient computer readable storage medium storing program for executing, it is characterised in that on the non-transient computer readable storage medium storing program for executing
Computer program is stored with, the side as any one of claim 1-7 is realized when the computer program is executed by processor
Method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710967299.1A CN107870990B (en) | 2017-10-17 | 2017-10-17 | Automobile recommendation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710967299.1A CN107870990B (en) | 2017-10-17 | 2017-10-17 | Automobile recommendation method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107870990A true CN107870990A (en) | 2018-04-03 |
| CN107870990B CN107870990B (en) | 2020-05-19 |
Family
ID=61753171
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710967299.1A Active CN107870990B (en) | 2017-10-17 | 2017-10-17 | Automobile recommendation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107870990B (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109389178A (en) * | 2018-10-26 | 2019-02-26 | 深圳市元征科技股份有限公司 | A kind of maintenance factory's ranking method, system and electronic equipment and storage medium |
| CN109408562A (en) * | 2018-11-07 | 2019-03-01 | 广东工业大学 | A kind of grouping recommended method and its device based on client characteristics |
| CN109447719A (en) * | 2018-12-17 | 2019-03-08 | 厦门美柚信息科技有限公司 | Targeted promotion commodity automatic determination method, device, medium and electronic equipment |
| CN110442762A (en) * | 2019-08-08 | 2019-11-12 | 厦门久凌创新科技有限公司 | Big data processing method based on cloud platform big data |
| CN110599297A (en) * | 2019-08-26 | 2019-12-20 | 浙江大搜车软件技术有限公司 | Vehicle type recommendation method and device, computer equipment and storage medium |
| CN110990692A (en) * | 2019-11-13 | 2020-04-10 | 上海易点时空网络有限公司 | Data processing method and device based on portrait analysis |
| CN111861680A (en) * | 2020-08-06 | 2020-10-30 | 南京三百云信息科技有限公司 | Configuration-based vehicle type determination method and device and electronic terminal |
| CN112668815A (en) * | 2019-09-30 | 2021-04-16 | 北京国双科技有限公司 | Automobile data processing method and device |
| CN114579859A (en) * | 2022-03-04 | 2022-06-03 | 北京永泰万德信息工程技术有限公司 | Vehicle personalized configuration method and system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100299190A1 (en) * | 2009-05-20 | 2010-11-25 | Tim Pratt | Automotive market place system |
| US20140114796A1 (en) * | 2012-10-19 | 2014-04-24 | Barnesandnoble.Com Llc | Techniques for generating content recommendations |
| CN103778214A (en) * | 2014-01-16 | 2014-05-07 | 北京理工大学 | Commodity property clustering method based on user comments |
| CN105681910A (en) * | 2015-12-29 | 2016-06-15 | 海信集团有限公司 | Video recommending method and device based on multiple users |
-
2017
- 2017-10-17 CN CN201710967299.1A patent/CN107870990B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100299190A1 (en) * | 2009-05-20 | 2010-11-25 | Tim Pratt | Automotive market place system |
| US20140114796A1 (en) * | 2012-10-19 | 2014-04-24 | Barnesandnoble.Com Llc | Techniques for generating content recommendations |
| CN103778214A (en) * | 2014-01-16 | 2014-05-07 | 北京理工大学 | Commodity property clustering method based on user comments |
| CN105681910A (en) * | 2015-12-29 | 2016-06-15 | 海信集团有限公司 | Video recommending method and device based on multiple users |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109389178A (en) * | 2018-10-26 | 2019-02-26 | 深圳市元征科技股份有限公司 | A kind of maintenance factory's ranking method, system and electronic equipment and storage medium |
| CN109408562A (en) * | 2018-11-07 | 2019-03-01 | 广东工业大学 | A kind of grouping recommended method and its device based on client characteristics |
| CN109447719A (en) * | 2018-12-17 | 2019-03-08 | 厦门美柚信息科技有限公司 | Targeted promotion commodity automatic determination method, device, medium and electronic equipment |
| CN110442762A (en) * | 2019-08-08 | 2019-11-12 | 厦门久凌创新科技有限公司 | Big data processing method based on cloud platform big data |
| CN110442762B (en) * | 2019-08-08 | 2022-02-08 | 厦门久凌创新科技有限公司 | Big data processing method based on cloud platform big data |
| CN110599297A (en) * | 2019-08-26 | 2019-12-20 | 浙江大搜车软件技术有限公司 | Vehicle type recommendation method and device, computer equipment and storage medium |
| CN110599297B (en) * | 2019-08-26 | 2022-06-03 | 浙江大搜车软件技术有限公司 | Vehicle type recommendation method and device, computer equipment and storage medium |
| CN112668815A (en) * | 2019-09-30 | 2021-04-16 | 北京国双科技有限公司 | Automobile data processing method and device |
| CN110990692A (en) * | 2019-11-13 | 2020-04-10 | 上海易点时空网络有限公司 | Data processing method and device based on portrait analysis |
| CN111861680A (en) * | 2020-08-06 | 2020-10-30 | 南京三百云信息科技有限公司 | Configuration-based vehicle type determination method and device and electronic terminal |
| CN111861680B (en) * | 2020-08-06 | 2024-03-29 | 南京三百云信息科技有限公司 | Configuration-based vehicle type determining method and device and electronic terminal |
| CN114579859A (en) * | 2022-03-04 | 2022-06-03 | 北京永泰万德信息工程技术有限公司 | Vehicle personalized configuration method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107870990B (en) | 2020-05-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107870990A (en) | A kind of automobile recommends method and device | |
| US10963942B1 (en) | Systems, methods, and devices for generating recommendations of unique items | |
| CN103353872B (en) | A kind of teaching resource personalized recommendation method based on neutral net | |
| CA2655196C (en) | System and method for generating a display of tags | |
| US6012051A (en) | Consumer profiling system with analytic decision processor | |
| CN105868847A (en) | Shopping behavior prediction method and device | |
| CN103377190B (en) | Trading platform based supplier information searching method and device | |
| CN109522556A (en) | A kind of intension recognizing method and device | |
| Li et al. | A posterior preference articulation approach to Kansei engineering system for product form design | |
| CN103970850B (en) | Site information recommends method and system | |
| CN106327227A (en) | Information recommendation system and information recommendation method | |
| CN111428147A (en) | Social recommendation method of heterogeneous graph volume network combining social and interest information | |
| US10007946B1 (en) | Systems, methods, and devices for measuring similarity of and generating recommendations for unique items | |
| CN109447713A (en) | A kind of recommended method and device of knowledge based map | |
| WO1998035297A9 (en) | Consumer profiling system with analytic decision processor | |
| CN109711925A (en) | Cross-domain recommending data processing method, cross-domain recommender system with multiple auxiliary domains | |
| CN109740072B (en) | Hotel ordering method and system based on POI under OTA platform | |
| CN103426102A (en) | Commodity feature recommending method based on body classification | |
| CN109300018A (en) | A kind of Vehicular intelligent recommended method, device, equipment and storage medium | |
| CN109670161A (en) | Commodity similarity calculating method and device, storage medium, electronic equipment | |
| CN108648058A (en) | Model sequencing method and device, electronic equipment, storage medium | |
| CN108256970A (en) | A kind of method that Products Show is carried out based on shopping need | |
| CN110335123A (en) | Method of Commodity Recommendation, system, computer-readable medium and device based on social electric business platform | |
| CN109376219A (en) | Matching process, device, electronic equipment and the storage medium of text attributes field | |
| US20200051153A1 (en) | Comparative ranking system |
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 |