CN109447713A - A kind of recommended method and device of knowledge based map - Google Patents
A kind of recommended method and device of knowledge based map Download PDFInfo
- Publication number
- CN109447713A CN109447713A CN201811291004.4A CN201811291004A CN109447713A CN 109447713 A CN109447713 A CN 109447713A CN 201811291004 A CN201811291004 A CN 201811291004A CN 109447713 A CN109447713 A CN 109447713A
- Authority
- CN
- China
- Prior art keywords
- commodity
- user
- commodity set
- based map
- similar
- 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
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000013507 mapping Methods 0.000 claims abstract description 31
- 239000011159 matrix material Substances 0.000 claims abstract description 29
- 239000013598 vector Substances 0.000 claims description 37
- 238000001914 filtration Methods 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 6
- 230000009466 transformation Effects 0.000 claims description 5
- 230000005055 memory storage Effects 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 8
- 239000013065 commercial product Substances 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 239000000047 product Substances 0.000 description 5
- 238000012216 screening Methods 0.000 description 5
- HUTDUHSNJYTCAR-UHFFFAOYSA-N ancymidol Chemical compound C1=CC(OC)=CC=C1C(O)(C=1C=NC=NC=1)C1CC1 HUTDUHSNJYTCAR-UHFFFAOYSA-N 0.000 description 4
- 230000006399 behavior Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000010354 integration Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 229940050561 matrix product Drugs 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
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
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0255—Targeted advertisements based on user history
Landscapes
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
This application discloses the recommended methods and device of a kind of knowledge based map, are related to computer software technical field, for accurately giving user's Recommendations comprehensively.This method comprises: determining the second commodity set according to commodity-user's rating matrix and the first commodity set, wherein, first commodity collection is combined into user's search commercial articles set, for commodity-user's rating matrix for determining user to the fancy grade of commodity, the second commodity collection is combined into commodity set identical and/or similar with the first commodity set scoring;Third commodity set is determined according to the first commodity set and knowledge mapping, wherein knowledge mapping includes multiple commodity and the corresponding relationship of multiple commodity, and third commodity collection is combined into and the semantic similar commodity set of the first commodity set;The second commodity set and third commodity set are merged according to preset ratio, at least one commodity is obtained, recommends user.The embodiment of the present application is applied to realize comprehensive accurate recommendation of commodity.
Description
Technical field
The present invention relates to computer software technical field more particularly to a kind of recommended methods and dress of knowledge based map
It sets.
Background technique
With the deep development of network technology, e-commerce is that the internet business opportunity of representative includes huge market value.
In numerous e-commerce websites, such as Amazon and Taobao, for user recommendation always be promoted product brand value and
The important technology in Win Clients market guarantees, increases the sales volume of commodity while in the hope of improving user experience.
The recommended technology of comparative maturity mainly has content-based recommendation and collaborative filtering recommending etc. at present.Based on content
Recommendation, since its recommendation is limited, interested commodity that cannot be new for user's discovery result in the friendship of user and commodity
The sparsity problem of mutual information, it is clear that be not well positioned to meet user under nowadays multi-source heterogeneous big data environment and recommend to need
It asks.Collaborative filtering based on user, for the user being newly added or commodity, since system does not have its history mutual information, because
This accurately can not be modeled and be recommended, that is, lead to the problem of cold start-up.Therefore these recommended technologies cannot reach better
Recommend purpose.
Summary of the invention
Embodiments herein provides the recommended method and device of a kind of knowledge based map, for realizing the complete of commodity
Face is precisely recommended.
In order to achieve the above objectives, embodiments herein adopts the following technical scheme that
In a first aspect, a kind of recommended method of knowledge based map is provided, this method comprises:
The second commodity set is determined according to commodity-user's rating matrix and the first commodity set, wherein first commodity
Collection is combined into user's search commercial articles set, the commodity-user's rating matrix for determine user to the fancy grade of commodity, it is described
Second commodity collection is combined into commodity set identical and/or similar with the first commodity set scoring;
Third commodity set is determined according to the first commodity set and the knowledge mapping, wherein the knowledge mapping
Including multiple commodity and the corresponding relationship of multiple commodity, the third commodity collection is combined into similar to the first commodity set semanteme
Commodity set;
The second commodity set and the third commodity set are merged according to preset ratio, obtains at least one commodity,
Recommend user.
Second aspect, provides a kind of recommendation apparatus of knowledge based map, which includes:
Determination unit, for determining the second commodity set according to commodity-user's rating matrix and the first commodity set,
In, the first commodity collection is combined into user's search commercial articles set, and the commodity-user's rating matrix is for determining user to commodity
Fancy grade, the second commodity collection is combined into commodity set identical and/or similar with the first commodity set scoring;
The determination unit is also used to determine third commodity collection according to the first commodity set and the knowledge mapping
Close, wherein the knowledge mapping includes multiple commodity and the corresponding relationship of multiple commodity, the third commodity collection be combined into it is described
The semantic similar commodity set of first commodity set;
Recommendation unit is obtained for merging the second commodity set and the third commodity set according to preset ratio
At least one commodity, recommends user.
The third aspect, provides a kind of computer readable storage medium for storing one or more programs, it is one or
Multiple programs include instruction, described instruction make when executed by a computer the computer execute as described in relation to the first aspect based on
The recommended method of knowledge mapping.
Fourth aspect provides a kind of computer program product comprising instruction, when described instruction is run on computers
When, so that computer executes the recommended method of knowledge based map as described in relation to the first aspect.
5th aspect, provides a kind of recommendation apparatus of knowledge based map, comprising: processor and memory, memory are used
In storage program, processor calls the program of memory storage, to execute knowledge based map described in above-mentioned first aspect
Recommended method.
The recommended method and device for the knowledge based map that embodiments herein provides, according to commodity-user's scoring square
Battle array carries out the commodity arest neighbors for coordinating to be obtained by filtration, and is obtained with the semantic similar commodity of user demand, together according to knowledge mapping
When adjust commodity arest neighbors required for user and the integration percentage with the semantic similar commodity of user demand, obtain recommending use
The commodity at family, so that realizing more comprehensively, more is accurately the purpose of user's Recommendations.
Detailed description of the invention
Fig. 1 is a kind of recommender system structural schematic diagram for knowledge based map that embodiments herein provides;
Fig. 2 is a kind of recommended method flow diagram one for knowledge based map that embodiments herein provides;
Fig. 3 is a kind of recommended method flow diagram two for knowledge based map that embodiments herein provides;
Fig. 4 is a kind of recommended method flow diagram three for knowledge based map that embodiments herein provides;
Fig. 5 is a kind of recommended method flow diagram four for knowledge based map that embodiments herein provides;
Fig. 6 is a kind of commodity vector and the corresponding relation vector schematic diagram of commodity vector that embodiments herein provides;
Fig. 7 is a kind of recommendation apparatus structural schematic diagram one for knowledge based map that embodiments herein provides;
Fig. 8 is a kind of recommendation apparatus structural schematic diagram two for knowledge based map that embodiments herein provides.
Specific embodiment
The recommended method and device of knowledge based map provided by the embodiments of the present application, according to commodity-user's rating matrix
With the determining similar commodity set that scores with user's search commercial articles set of user's search commercial articles set, and according to knowledge mapping and use
The determining commodity set similar with user's search commercial articles set semanteme of family search commercial articles set, will comment with user's search commercial articles set
Commodity set as split-phase and semantic similar commodity set proportionally merge, to obtain recommending the commodity of user.
Fig. 1 is the general frame figure of the recommender system of knowledge based map provided by the embodiments of the present application.Institute referring to Fig.1
Show, general frame includes: subscriber information module 100, merchandise news module 200 and personalized recommendation module 300.
Subscriber information module 100 includes user behavior information excavating unit and user information database:
Wherein, user behavior information excavating refers to that webpage Web server passes through Web digging technology to user because browsing net
Page, the journal file checking the behaviors such as commodity and commodity purchasing and generating carry out Web usage mining task, to obtain user
The information such as feature, interest, these information may include that commodity number of clicks, page residence time and the page enter frequency etc..Letter
Breath data are stored into user information database after screening, arranging the pretreatment such as classification;
User information database mainly stores user basic information, user's our station access record information and user individual feature letter
Cease these three types of information.Wherein, user basic information includes name, gender, age, occupation, address of user etc., and user's our station is visited
Ask that record information includes goods browse record, commodity purchasing record, page access number etc., user individual characteristic information includes
The interested product name of user, merchandise classification, user's evaluation etc..These information carry out commercial product recommending for recommender system and provide
Data are supported and foundation.
Merchandise news module 200 includes commodity information database and commodity information management unit:
Wherein, commodity information database mainly stores the essential information of commodity, and commodity essential information includes merchandise classification, trade name
Title, price, shelf-life, production time, packaging time, pageview etc., these information are used according to by commercial product recommending system
Or display, it is that recommender system is able to the premise to play a role and guarantee;
The major function and task of commodity information management unit be realize the access of information of goods information data, screening, processing and
Transmitting etc., the access and processing of all data internally may be implemented in commodity information management, as the addition of new commodity data, data are repaired
Change, format conversion etc., the transmitting and display of data externally may be implemented, such as the generation of knowledge mapping and commercial product recommending list, aobvious
Show.
Personalized recommendation module 300 includes user requirements analysis unit and collaborative filtering unit:
The major function of user requirements analysis is that the behavior for collecting user, feature letter are tracked by the relevant technologies and method
Breath, purchaser record etc. analyze hobby, the purchase intention etc. of user on this basis.Recommender system provided by the embodiments of the present application
Different electric business commercial product recommending lists can be generated according to different user, recommender system obtains the feature of user from user information database
Information and commodity purchasing record, analyze user demand with this;
Collaborative filtering unit includes the proposed algorithm of the collaborative filtering based on user and commodity, which belongs to recommender system
Core, which carries out commercial product recommending according to the similitude between user and the similitude between commodity.
The application implements the recommender system of offer by coordinating filter algorithm and user requirements analysis and commodity being combined to believe
Breath manages to carry out the screening and filtering of commodity, is finally completed the personalized recommendation of commodity.
Recommender system provided by the embodiments of the present application, when the platform of user's first passage recommender system buys commodity,
Proposed algorithm according to user has purchased commodity to generate commercial product recommending list, when user uses the recommender system next time, system
Foreground can call the merchandise news in commodity information database and according to spatial order display of commodity map from top to bottom, and will be upper
The Recommendations once generated for the user preferentially show that the neighbouring commodity or sub- commodity of these commodity are also preferentially shown
It shows and, so that user can be appreciated that and last different items list, see with also can be convenient and purchased commodity with oneself
Relevant some commodity, this enhances whole recommendation effect to a certain extent.
Optionally, recommender system provided by the embodiments of the present application can be applied to electric business platform.
The building process of the recommender system based on knowledge mapping is described in detail using detailed embodiment below.
Embodiment 1,
The embodiment of the present application provides a kind of recommended method of knowledge based map, and referring to fig. 2, this method can be with
Including S101-S103:
S101, the second commodity set is determined according to commodity-user's rating matrix and the first commodity set.
Wherein, the first commodity collection is combined into user's search commercial articles set, and commodity-user's rating matrix is for determining user to quotient
The fancy grade of product, the second commodity collection are combined into the first commodity set the similar commodity set that scores.
Specifically, utilizing commodity-by the essential information and hobby commodity set of the available user of above-mentioned recommender system
User's rating matrix calculate electric business platform in commodity and the first commodity set in commodity between similitude, can be generated with
The similar commodity of first commodity set-commodity similar set, and neighbour's selection is carried out to this commodity-commodity similitude set,
By neighbour's selection screening is ranked up to the article that user selected respectively, and then determines the second commodity set.
Optionally, referring to fig. 3, before S101, this method can also include S201-S202:
S201, multiple user's score informations and the corresponding commodity set of multiple user's score informations are obtained.
After user buys commodity by electric business platform, it can score the fancy grade of purchased item, therefore
Pass through the score information of the corresponding multiple users of the available commodity of the server of electric business platform.
S202, commodity-use is constructed according to multiple user's score informations and the corresponding commodity set of multiple user's score informations
Family rating matrix.
Illustratively, it is equipped with m user U=(U1, U2..., Um), n commodity I=(I1, I2..., In), this m user
It is all scored respectively this n commodity I, wherein when user does not give a mark to some commodity, system can default the user
Be preset value to the scorings of the commodity, which can be 0 or 1, or other values, according to the score information of user and
The corresponding commodity set of score information can construct commodity-user's rating matrix R of a m × nmn。
Wherein,RijFor user UiTo commodity IjComment
Point, and the scoring represents user UiTo article IjFancy grade.
Optionally, referring to fig. 4, S101 may include S301:
S301, collaborative filtering is carried out to the first commodity set according to commodity-user's rating matrix, it is multiple with first to obtain
The scoring of commodity set is identical and/or close commodity, multiple commodity identical and/or close with the first commodity set scoring are the second quotient
Product set.
Specifically, utilizing collaborative filtering and commodity-user's rating matrix RmnCalculate the commodity in electric business platform and the
The weight similitude of commodity in one commodity set, the similitude set of an available commodity-commodity as shown in Table 1,
Neighbour's selection is carried out to this similitude set, neighbour's selection is that the article selected user is ranked up screening respectively,
Identical and/similar commodity the set that can will score is sorted out to get to the second commodity set.
1 commodity of table-commodity similitude set
In the similitude set of table 1, aijThe similitude between the commodity of serial number i and the commodity of serial number j, the i-th row
The set constituted is defined as neighbour's set of serial number j commodity.
Optionally, the similitude between commodity can for certain user to article i with the scoring of article j identical and/or phase
Closely, or two commodity are closely located in knowledge mapping, and the embodiment of the present application does not limit.
S102, third commodity set is determined according to the first commodity set and knowledge mapping.
Wherein, knowledge mapping includes multiple commodity and the corresponding relationship of multiple commodity, and third commodity collection is combined into and the first quotient
The semantic similar commodity set of product set.
First commodity set and knowledge mapping are corresponded, a commodity is obtained and correspond to table, it is the which, which corresponds to table,
One commodity set commodity set corresponding with the commodity of knowledge mapping indicates that algorithm obtains commodity and corresponds in table using knowledge mapping
The semantic information of commodity corresponds to Semantic Similarity in table between commodity by calculating the commodity, available with the first commodity
The semantic similar commodity set of set, i.e. third commodity set.
Optionally, referring to fig. 5, S102 may include S301-S303:
S301, the first commodity set and knowledge mapping are corresponded, with obtain in the first commodity set multiple commodity and
The corresponding relationship of multiple commodity.
First commodity set and knowledge mapping are corresponded, an available commodity correspond to table, and then can be from knowing
Know and obtains the commodity in map and correspond to set of relationship in table between commodity.
S302, multiple commodity are converted to multiple commodity vectors, and is more by the corresponding transformation of multiple commodity vectors
A relation vector.
Knowledge mapping includes multiple triples, and the node on each triple both sides is commodity, and the side between node is between commodity
Relationship, each commodity can be converted to a commodity vector, the corresponding transformation of commodity vector be relation vector.
Illustratively, referring to fig. 6, in Fig. 6,Indicate the head vector an of commodity,Indicate the tails of the commodity to
Amount,Indicate the corresponding relation vector of commodity vector, wherein
S303, multiple commodity vectors and the corresponding relation vector of multiple commodity vectors are subjected to semanteme according to cosine similarity
Similar calculating, it is multiple similar with the first commodity set semanteme to obtain multiple commodity similar with the first commodity set semanteme
Commodity third commodity set.
The semantic similarity that two commodity vectors are calculated according to cosine similarity, when the cosine similar value of two vectors more connects
When being bordering on 1, the semantic similarity of two vectors is higher.It is possible thereby to calculate above-mentioned commodity correspond in table with the first commodity set
The high commodity set of semantic similarity, i.e. third commodity set.
Optionally, cosine similarity calculation formula can be with are as follows:Wherein,For commodity vectorWith commodity vectorCosine similarity.
S103, the second commodity set and third commodity set are merged according to preset ratio, obtains at least one commodity, recommended
To user.
By the commodity set obtained according to commodity-user's rating matrix and the commodity set obtained according to knowledge mapping, press
It is replaced according to certain integration percentage, at least one commodity may finally be obtained, and result is recommended into user;It can also take
Obtained commodity set is recommended user by two commodity intersection of sets collection or union.
Optionally, after obtaining recommending the commodity of user, recommender system can be sent out the commodity of recommendation by server
It is sent to the terminal device of user, which can be PC, or mobile device, the embodiment of the present application is not
It limits.
Recommended method provided by the embodiments of the present application carries out the quotient for coordinating to be obtained by filtration according to commodity-user's rating matrix
Product arest neighbors, and obtained according to knowledge mapping with the semantic similar commodity of user demand, while adjusting commodity required for user
Arest neighbors and integration percentage with the semantic similar commodity of user demand, obtain the commodity for recommending user, are solving to recommend system
It can be accurately more comprehensively, more user's Recommendations while system cold start-up.
Embodiment 2,
The embodiment of the present application provides a kind of recommendation apparatus of knowledge based map, referring to fig. 7, the recommendation apparatus
400 include:
Determination unit 401, for determining the second commodity set according to commodity-user's rating matrix and the first commodity set,
Wherein, the first commodity collection is combined into user's search commercial articles set, and commodity-user's rating matrix is for determining user to the hobby of commodity
Degree, the second commodity collection are combined into commodity set identical and/or similar with the first commodity set scoring.
Determination unit 401 is also used to determine third commodity set according to the first commodity set and knowledge mapping, wherein know
Knowing map includes multiple commodity and the corresponding relationship of multiple commodity, and third commodity collection is combined into similar with the first commodity set semanteme
Commodity set.
Recommendation unit 402 obtains at least one for merging the second commodity set and third commodity set according to preset ratio
A commodity, recommend user.
Optionally, referring to fig. 8, which can also include:
Acquiring unit 501, for obtaining multiple user's score informations and the corresponding commodity set of multiple user's score informations.
Construction unit 502, for according to multiple user's score informations and the corresponding commodity set of multiple user's score informations
Construct commodity-user's rating matrix.
Optionally, determination unit 401 can be specifically used for: according to commodity-user's rating matrix to the first commodity set into
Row collaborative filtering, it is multiple to be commented with the first commodity set to obtain multiple commodity identical and/or close with the first commodity set scoring
Split-phase is together and/or close commodity are the second commodity set.
Optionally, determination unit 401 can also be specifically used for: the first commodity set and knowledge mapping corresponded, with
Obtain multiple commodity and the corresponding relationship of multiple commodity;Convert multiple commodity vectors for multiple commodity, and by multiple commodity to
Measuring corresponding transformation is multiple relation vectors;By multiple commodity vectors and the corresponding relation vector of multiple commodity vectors according to
Cosine similarity carries out semantic similar calculating, to obtain multiple commodity set similar with the first commodity set semanteme, Duo Geyu
The semantic similar commodity collection of first commodity set is combined into third commodity set.
The embodiment of the present application provides a kind of computer readable storage medium for storing one or more programs, it is one or
Multiple programs include instruction, and described instruction makes the computer execute the side as described in Fig. 2-Fig. 5 when executed by a computer
Method.
Embodiments herein provides a kind of computer program product comprising instruction, when instruction is run on computers
When, so that computer executes the recommended method of the knowledge based map as described in Fig. 2-Fig. 5.
Embodiments herein provides a kind of recommendation apparatus of knowledge based map, comprising: processor and memory, storage
Device is for storing program, and processor calls the program of memory storage, to execute the knowledge based map as described in Fig. 2-Fig. 5
Recommended method.
By the recommendation apparatus of knowledge based map in an embodiment of the present invention, computer readable storage medium, calculating
Machine program product can be applied to the above method, therefore, can be obtained technical effect see also above method embodiment,
Details are not described herein for the embodiment of the present invention.
It should be noted that above-mentioned each unit can be the processor individually set up, also can integrate controller certain
It is realized in one processor, in addition it is also possible to be stored in the form of program code in the memory of controller, by controller
Some processor calls and executes the function of the above each unit.Processor described here can be a central processing unit
(Central Processing Unit, CPU) or specific integrated circuit (Application Specific
Integrated Circuit, ASIC), or be arranged to implement one or more integrated circuits of the embodiment of the present application.
It should be understood that magnitude of the sequence numbers of the above procedures are not meant to execute suitable in the various embodiments of the application
Sequence it is successive, the execution of each process sequence should be determined by its function and internal logic, the implementation without coping with the embodiment of the present application
Process constitutes any restriction.
Those of ordinary skill in the art may be aware that list described in conjunction with the examples disclosed in the embodiments of the present disclosure
Member and algorithm steps can be realized with the combination of electronic hardware or computer software and electronic hardware.These functions are actually
It is implemented in hardware or software, the specific application and design constraint depending on technical solution.Professional technician
Each specific application can be used different methods to achieve the described function, but this realization is it is not considered that exceed
Scope of the present application.
It is apparent to those skilled in the art that for convenience and simplicity of description, the system of foregoing description,
The specific work process of device and unit, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
In several embodiments provided herein, it should be understood that disclosed system, apparatus and method, it can be with
It realizes by another way.For example, apparatus embodiments described above are merely indicative, for example, the unit
It divides, only a kind of logical function partition, there may be another division manner in actual implementation, such as multiple units or components
It can be combined or can be integrated into another system, or some features can be ignored or not executed.Another point, it is shown or
The mutual coupling, direct-coupling or communication connection discussed can be through some interfaces, the indirect coupling of equipment or unit
It closes or communicates to connect, can be electrical property, mechanical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
It, can also be in addition, each functional unit in each embodiment of the application can integrate in one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.
In the above-described embodiments, can come wholly or partly by software, hardware, firmware or any combination thereof real
It is existing.When being realized using software program, can entirely or partly realize in the form of a computer program product.The computer
Program product includes one or more computer instructions.On computers load and execute computer program instructions when, all or
It partly generates according to process or function described in the embodiment of the present application.The computer can be general purpose computer, dedicated meter
Calculation machine, computer network or other programmable devices.The computer instruction can store in computer readable storage medium
In, or from a computer readable storage medium to the transmission of another computer readable storage medium, for example, the computer
Instruction can pass through wired (such as coaxial cable, optical fiber, number from a web-site, computer, server or data center
Word user line (Digital Subscriber Line, DSL)) or wireless (such as infrared, wireless, microwave etc.) mode to another
A web-site, computer, server or data center are transmitted.The computer readable storage medium can be computer
Any usable medium that can be accessed either includes the numbers such as one or more server, data centers that medium can be used to integrate
According to storage equipment.The usable medium can be magnetic medium (for example, floppy disk, hard disk, tape), optical medium (for example, DVD),
Or semiconductor medium (such as solid state hard disk (Solid State Disk, SSD)) etc..
The above, the only specific embodiment of the application, but the protection scope of the application is not limited thereto, it is any
Those familiar with the art within the technical scope of the present application, can easily think of the change or the replacement, and should all contain
Lid is within the scope of protection of this application.Therefore, the protection scope of the application should be based on the protection scope of the described claims.
Claims (11)
1. a kind of recommended method of knowledge based map, which is characterized in that the described method includes:
The second commodity set is determined according to commodity-user's rating matrix and the first commodity set, wherein the first commodity set
For user's search commercial articles set, the commodity-user's rating matrix for determine user to the fancy grade of commodity, described second
Commodity collection is combined into commodity set identical and/or similar with the first commodity set scoring;
Third commodity set is determined according to the first commodity set and the knowledge mapping, wherein the knowledge mapping includes
Multiple commodity and the corresponding relationship of multiple commodity, the third commodity collection are combined into and the semantic similar quotient of the first commodity set
Product set;
The second commodity set and the third commodity set are merged according to preset ratio, obtains at least one commodity, is recommended
To user.
2. the recommended method of knowledge based map according to claim 1, which is characterized in that described according to commodity-use
Before family rating matrix and the first commodity set determine the second commodity set, the method also includes:
Obtain multiple user's score informations and the corresponding commodity set of the multiple user's score information;
The commodity-are constructed according to the multiple user's score information and the corresponding commodity set of the multiple user's score information
User's rating matrix.
3. the recommended method of knowledge based map according to claim 1, which is characterized in that described according to the commodity-
User's rating matrix and the first commodity set determine the second commodity set, comprising:
According to the commodity-user's rating matrix to the first commodity set carry out collaborative filtering, with obtain it is multiple with it is described
The scoring of first commodity set is identical and/or close commodity, the multiple identical and/or close as the first commodity set scoring
Commodity are the second commodity set.
4. the recommended method of knowledge based map according to claim 1, which is characterized in that according to the first commodity collection
It closes and the knowledge mapping determines third commodity set, comprising:
The first commodity set and the knowledge mapping are corresponded, it is corresponding to obtain multiple commodity and the multiple commodity
Relationship;
Multiple commodity vectors are converted by the multiple commodity, and are multiple by the corresponding transformation of the multiple commodity vector
Relation vector;
The multiple commodity vector and the corresponding relation vector of the multiple commodity vector are subjected to semanteme according to cosine similarity
Similar calculating, to obtain multiple commodity set similar with the first commodity set semanteme, the multiple and first quotient
The semantic similar commodity collection of product set is combined into the third commodity set.
5. a kind of recommendation apparatus of knowledge based map, which is characterized in that the recommendation apparatus includes:
Determination unit, for determining the second commodity set according to commodity-user's rating matrix and the first commodity set, wherein institute
It states the first commodity collection and is combined into user's search commercial articles set, the commodity-user's rating matrix is for determining happiness of the user to commodity
Good degree, the second commodity collection are combined into commodity set identical and/or similar with the first commodity set scoring;
The determination unit is also used to determine third commodity set according to the first commodity set and the knowledge mapping,
In, the knowledge mapping includes multiple commodity and the corresponding relationship of multiple commodity, and the third commodity collection is combined into and described first
The semantic similar commodity set of commodity set;
Recommendation unit obtains at least for merging the second commodity set and the third commodity set according to preset ratio
One commodity, recommends user.
6. the recommendation apparatus of knowledge based map according to claim 5, which is characterized in that the recommendation apparatus also wraps
It includes:
Acquiring unit, for obtaining multiple user's score informations and the corresponding commodity set of the multiple user's score information;
Construction unit, for according to the multiple user's score information and the corresponding commodity set of the multiple user's score information
Construct the commodity-user's rating matrix.
7. the recommendation apparatus of knowledge based map according to claim 5, which is characterized in that the determination unit is specifically used
In:
According to the commodity-user's rating matrix to the first commodity set carry out collaborative filtering, with obtain it is multiple with it is described
The scoring of first commodity set is identical and/or close commodity, the multiple same or similar quotient that scores with the first commodity set
Product are the second commodity set.
8. the recommendation apparatus of knowledge based map according to claim 5, which is characterized in that the determination unit is specifically used
In:
The first commodity set and the knowledge mapping are corresponded, it is corresponding to obtain multiple commodity and the multiple commodity
Relationship;
Multiple commodity vectors are converted by the multiple commodity, and are multiple by the corresponding transformation of the multiple commodity vector
Relation vector;
The multiple commodity vector and the corresponding relation vector of the multiple commodity vector are subjected to semanteme according to cosine similarity
Similar calculating, to obtain multiple commodity set similar with the first commodity set semanteme, the multiple and first quotient
The semantic similar commodity collection of product set is combined into the third commodity set.
9. a kind of computer readable storage medium for storing one or more programs, which is characterized in that one or more of journeys
Sequence includes instruction, and it is according to any one of claims 1-4 that described instruction when executed by a computer executes the computer
The recommended method of knowledge based map.
10. a kind of computer program product comprising instruction, which is characterized in that when described instruction is run on computers, make
Obtain the recommended method that the computer executes knowledge based map according to any one of claims 1-4.
11. a kind of recommendation apparatus of knowledge based map characterized by comprising processor and memory, memory is for depositing
Program is stored up, processor calls the program of memory storage, to execute knowledge based map according to any one of claims 1-4
Recommended method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811291004.4A CN109447713A (en) | 2018-10-31 | 2018-10-31 | A kind of recommended method and device of knowledge based map |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811291004.4A CN109447713A (en) | 2018-10-31 | 2018-10-31 | A kind of recommended method and device of knowledge based map |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109447713A true CN109447713A (en) | 2019-03-08 |
Family
ID=65550491
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811291004.4A Pending CN109447713A (en) | 2018-10-31 | 2018-10-31 | A kind of recommended method and device of knowledge based map |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109447713A (en) |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110060121A (en) * | 2019-03-14 | 2019-07-26 | 五邑大学 | Method of Commodity Recommendation, device and storage medium based on feature ordering |
CN110110222A (en) * | 2019-04-12 | 2019-08-09 | 保定市大为计算机软件开发有限公司 | A kind of target object determines method, apparatus and computer storage medium |
CN110222127A (en) * | 2019-06-06 | 2019-09-10 | 中国电子科技集团公司第二十八研究所 | The converging information method, apparatus and equipment of knowledge based map |
CN110765273A (en) * | 2019-09-17 | 2020-02-07 | 北京三快在线科技有限公司 | Recommended document generation method and device, electronic equipment and readable storage medium |
CN111985994A (en) * | 2020-08-06 | 2020-11-24 | 上海博泰悦臻电子设备制造有限公司 | Commodity recommendation method and related equipment |
CN112036987A (en) * | 2020-09-11 | 2020-12-04 | 杭州海康威视数字技术股份有限公司 | Method and device for determining recommended commodities |
CN112102029A (en) * | 2020-08-20 | 2020-12-18 | 浙江大学 | Knowledge graph-based long-tail recommendation calculation method |
CN112561581A (en) * | 2020-12-14 | 2021-03-26 | 珠海格力电器股份有限公司 | Recommendation method and device, electronic equipment and storage medium |
CN112612973A (en) * | 2020-12-31 | 2021-04-06 | 重庆邮电大学 | Personalized intelligent clothing matching recommendation method combining knowledge graph |
CN112785372A (en) * | 2021-01-11 | 2021-05-11 | 北京欧拉认知智能科技有限公司 | Intelligent recommendation method based on semantic relation |
CN112800207A (en) * | 2021-01-13 | 2021-05-14 | 桂林电子科技大学 | Commodity information recommendation method and device and storage medium |
CN112989176A (en) * | 2019-12-12 | 2021-06-18 | 国网电子商务有限公司 | Information recommendation method and device |
CN113360784A (en) * | 2021-06-22 | 2021-09-07 | 北京邮电大学 | Collaborative filtering algorithm for knowledge graph optimization recommended by equipment operation and maintenance scheme |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103412948A (en) * | 2013-08-27 | 2013-11-27 | 北京交通大学 | Cluster-based collaborative filtering commodity recommendation method and system |
CN103559622A (en) * | 2013-07-31 | 2014-02-05 | 焦点科技股份有限公司 | Characteristic-based collaborative filtering recommendation method |
WO2016191959A1 (en) * | 2015-05-29 | 2016-12-08 | 深圳市汇游智慧旅游网络有限公司 | Time-varying collaborative filtering recommendation method |
CN107273490A (en) * | 2017-06-14 | 2017-10-20 | 北京工业大学 | A kind of combination mistake topic recommendation method of knowledge based collection of illustrative plates |
CN107729444A (en) * | 2017-09-30 | 2018-02-23 | 桂林电子科技大学 | Recommend method in a kind of personalized tourist attractions of knowledge based collection of illustrative plates |
US10102559B1 (en) * | 2014-09-30 | 2018-10-16 | Amazon Technologies, Inc. | Diversification of recommendations |
US20180308100A1 (en) * | 2017-04-19 | 2018-10-25 | Risto Haukioja | System and method of client recognition for service provider transactions |
-
2018
- 2018-10-31 CN CN201811291004.4A patent/CN109447713A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103559622A (en) * | 2013-07-31 | 2014-02-05 | 焦点科技股份有限公司 | Characteristic-based collaborative filtering recommendation method |
CN103412948A (en) * | 2013-08-27 | 2013-11-27 | 北京交通大学 | Cluster-based collaborative filtering commodity recommendation method and system |
US10102559B1 (en) * | 2014-09-30 | 2018-10-16 | Amazon Technologies, Inc. | Diversification of recommendations |
WO2016191959A1 (en) * | 2015-05-29 | 2016-12-08 | 深圳市汇游智慧旅游网络有限公司 | Time-varying collaborative filtering recommendation method |
US20180308100A1 (en) * | 2017-04-19 | 2018-10-25 | Risto Haukioja | System and method of client recognition for service provider transactions |
CN107273490A (en) * | 2017-06-14 | 2017-10-20 | 北京工业大学 | A kind of combination mistake topic recommendation method of knowledge based collection of illustrative plates |
CN107729444A (en) * | 2017-09-30 | 2018-02-23 | 桂林电子科技大学 | Recommend method in a kind of personalized tourist attractions of knowledge based collection of illustrative plates |
Non-Patent Citations (1)
Title |
---|
HUAGONG_ADU: "基于物品的协同过滤推荐算法---读Item-Based Collaborative Filtering Recommendation Algorithms", 《CSDN》 * |
Cited By (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110060121A (en) * | 2019-03-14 | 2019-07-26 | 五邑大学 | Method of Commodity Recommendation, device and storage medium based on feature ordering |
CN110110222B (en) * | 2019-04-12 | 2021-03-16 | 保定市大为计算机软件开发有限公司 | Target object determination method and device and computer storage medium |
CN110110222A (en) * | 2019-04-12 | 2019-08-09 | 保定市大为计算机软件开发有限公司 | A kind of target object determines method, apparatus and computer storage medium |
CN110222127A (en) * | 2019-06-06 | 2019-09-10 | 中国电子科技集团公司第二十八研究所 | The converging information method, apparatus and equipment of knowledge based map |
CN110765273A (en) * | 2019-09-17 | 2020-02-07 | 北京三快在线科技有限公司 | Recommended document generation method and device, electronic equipment and readable storage medium |
CN110765273B (en) * | 2019-09-17 | 2020-12-18 | 北京三快在线科技有限公司 | Recommended document generation method and device, electronic equipment and readable storage medium |
CN112989176A (en) * | 2019-12-12 | 2021-06-18 | 国网电子商务有限公司 | Information recommendation method and device |
CN111985994A (en) * | 2020-08-06 | 2020-11-24 | 上海博泰悦臻电子设备制造有限公司 | Commodity recommendation method and related equipment |
CN112102029A (en) * | 2020-08-20 | 2020-12-18 | 浙江大学 | Knowledge graph-based long-tail recommendation calculation method |
CN112036987A (en) * | 2020-09-11 | 2020-12-04 | 杭州海康威视数字技术股份有限公司 | Method and device for determining recommended commodities |
CN112036987B (en) * | 2020-09-11 | 2024-04-02 | 杭州海康威视数字技术股份有限公司 | Method and device for determining recommended commodity |
CN112561581A (en) * | 2020-12-14 | 2021-03-26 | 珠海格力电器股份有限公司 | Recommendation method and device, electronic equipment and storage medium |
CN112612973A (en) * | 2020-12-31 | 2021-04-06 | 重庆邮电大学 | Personalized intelligent clothing matching recommendation method combining knowledge graph |
CN112612973B (en) * | 2020-12-31 | 2022-03-22 | 重庆邮电大学 | Personalized intelligent clothing matching recommendation method combining knowledge graph |
CN112785372A (en) * | 2021-01-11 | 2021-05-11 | 北京欧拉认知智能科技有限公司 | Intelligent recommendation method based on semantic relation |
CN112785372B (en) * | 2021-01-11 | 2023-09-12 | 北京欧拉认知智能科技有限公司 | Intelligent recommendation method based on semantic relation |
CN112800207A (en) * | 2021-01-13 | 2021-05-14 | 桂林电子科技大学 | Commodity information recommendation method and device and storage medium |
CN113360784A (en) * | 2021-06-22 | 2021-09-07 | 北京邮电大学 | Collaborative filtering algorithm for knowledge graph optimization recommended by equipment operation and maintenance scheme |
CN113360784B (en) * | 2021-06-22 | 2023-09-19 | 北京邮电大学 | Collaborative filtering algorithm for knowledge graph optimization of equipment operation and maintenance scheme recommendation |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109447713A (en) | A kind of recommended method and device of knowledge based map | |
JP6356744B2 (en) | Method and system for displaying cross-website information | |
US8504436B2 (en) | Systems and methods for generating a manufacturer tier product rollup | |
US10095771B1 (en) | Clustering and recommending items based upon keyword analysis | |
US10304116B2 (en) | System and method for targeting content based on filter activity | |
US10423999B1 (en) | Performing personalized category-based product sorting | |
US20120005044A1 (en) | System And Method To Provide A Table Of Products Based On Ranked User Specified Product Attributes | |
CN106708821A (en) | User personalized shopping behavior-based commodity recommendation method | |
CN110580649B (en) | Method and device for determining commodity potential value | |
CN110335123B (en) | Commodity recommendation method, system, computer readable medium and device based on social e-commerce platform | |
CN106326318B (en) | Searching method and device | |
JP6976207B2 (en) | Information processing equipment, information processing methods, and programs | |
US20160196593A1 (en) | System and method for tracking filter activity and monitoring trends associated with said activity | |
KR101707660B1 (en) | An e-commerce system based on interest category using related keywords | |
US20170046768A1 (en) | Hybrid recommendation system for recommending product advertisements | |
Małecki et al. | The classification of internet shop customers based on the cluster analysis and graph cellular automata | |
CN107103490B (en) | Data processing method, network server and terminal | |
US10169798B2 (en) | Automatic selection of featured product groups within a product search engine | |
KR20140132033A (en) | System and method for products recommendation service, and apparatus applied to the same | |
WO2013096749A2 (en) | System and method for generating user recommendations | |
CN110827044A (en) | Method and device for extracting user interest mode | |
CN112488854A (en) | Service manager personalized recommendation method and related equipment | |
Somya et al. | A novel approach to collect and analyze market customer behavior data on online shop | |
KR102619084B1 (en) | Method for recommending products and service server using the same | |
Kailer et al. | An empirical study on the usage of social media in german b2c-online stores |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190308 |
|
RJ01 | Rejection of invention patent application after publication |