CN109389442A - Method of Commodity Recommendation and device, storage medium and electric terminal - Google Patents
Method of Commodity Recommendation and device, storage medium and electric terminal Download PDFInfo
- Publication number
- CN109389442A CN109389442A CN201710659767.9A CN201710659767A CN109389442A CN 109389442 A CN109389442 A CN 109389442A CN 201710659767 A CN201710659767 A CN 201710659767A CN 109389442 A CN109389442 A CN 109389442A
- Authority
- CN
- China
- Prior art keywords
- commodity
- user
- score
- recommended
- degree
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
This disclosure relates to technical field of data processing, and in particular to a kind of Method of Commodity Recommendation, a kind of device for recommending the commodity, a kind of storage medium and a kind of electric terminal.The Method of Commodity Recommendation includes: the user's similarity for calculating user and each user to be recommended;User's similarity result is screened, in order to obtain associated user's set and corresponding associated user's commodity rating matrix and dependent merchandise set;Calculate the commodity degree of correlation in the dependent merchandise set between each commodity;According to user to be recommended described in dependent merchandise set described in associated user's commodity rating matrix and the commodity relatedness computation do not score commodity scoring estimation;Appraisal result according to each commodity is ranked up, and the ranking results for choosing preset quantity are sent to the user to be recommended.The disclosure can effectively promote the accuracy and matching degree of recommendation results, so that hobby and demand that Recommendations are more close to the users effectively promote the accuracy and matching degree of recommendation results.
Description
Technical field
This disclosure relates to technical field of data processing, and in particular to a kind of Method of Commodity Recommendation, a kind of device for recommending the commodity,
A kind of storage medium and a kind of electric terminal.
Background technique
In recent years, lead to user so that number of users and commodity amount sharply increase with the fast development of e-commerce
Often can not the quickly and accurately information required for searching out oneself in vast resources or commodity, that is, there is information overload and ask
Topic.Solving problem of information overload at present, there are mainly three types of methods: air navigation aid, search method and recommended method.Wherein, recommend
Method is a kind of especially extensive method of current application.What is be most widely used in existing proposed algorithm is collaborative filtering
(Collaborative Filtering, CF), the most commonly used two types are respectively: the collaborative filtering based on user is calculated
Method (User CF) and project-based collaborative filtering (Item CF).
But two kinds of above-mentioned algorithms have the defects that certain: 1) collaborative filtering based on user is often simple logical
The similarity that rating matrix calculates user is crossed, there are the lower problems of accuracy.Since rating matrix is usually present Deta sparseness
Problem merely carries out relatedness computation by rating matrix, will cause the relatedness computation inaccuracy between user.In addition,
Due to not considering the attribute of user itself in relatedness computation, so that often there is larger difference in calculated result and truth
It is different.2) project-based collaborative filtering does not often consider the hiding relationship between commodity, leads to the reduction of the commodity degree of correlation.By
In the algorithm above not using arrive commodity domain knowledge, it is believed that be between all commodity items it is independent, incoherent,
It is calculated only by rating matrix, then will affect the true degree of correlation between commodity item, lead to consequently recommended result not
Accurately.
It should be noted that information is only used for reinforcing the reason to the background of the disclosure disclosed in above-mentioned background technology part
Solution, therefore may include the information not constituted to the prior art known to persons of ordinary skill in the art.
Summary of the invention
The disclosure be designed to provide a kind of Method of Commodity Recommendation, a kind of device for recommending the commodity, a kind of storage medium with
And a kind of electric terminal, and then overcome caused by the limitation and defect due to the relevant technologies at least to a certain extent one or
The multiple problems of person.
Other characteristics and advantages of the disclosure will be apparent from by the following detailed description, or partially by the disclosure
Practice and acquistion.
According to the disclosure in a first aspect, providing a kind of Method of Commodity Recommendation, comprising:
Calculate user's similarity of user to be recommended Yu each user;
User's similarity result is screened, in order to obtain associated user's set and corresponding associated user
Commodity rating matrix and dependent merchandise set;
Calculate the commodity degree of correlation in the dependent merchandise set between each commodity;
According to institute in dependent merchandise set described in associated user's commodity rating matrix and the commodity relatedness computation
State user to be recommended do not score commodity scoring estimation to obtain the scoring estimated matrix of dependent merchandise;
Appraisal result according to each commodity is ranked up, choose preset quantity ranking results be sent to it is described wait push away
Recommend user.
It is described to calculate user to be recommended and each use according to user tag information in a kind of exemplary embodiment of the disclosure
User's similarity at family includes:
User's set in one user-commodity rating matrix is obtained, respectively by N number of different label information to each described
User is described:
ui=[xi1 ... xil ... xiN]T
Wherein, xilFor user uiLabel information, 1≤l≤N;
The degree of correlation between any two user are as follows:
Wherein, Ruser(ui,uj) it is user uiWith user ujBetween the degree of correlation, N is positive integer.
In a kind of exemplary embodiment of the disclosure, the user tag information include: essential information, interest commodity,
Access any several combination in history, buying behavior and collection record.
In a kind of exemplary embodiment of the disclosure, the commodity degree of correlation calculated between each commodity includes:
Obtain the commodity classification structural information of each commodity;
The commodity degree of correlation between any two commodity, specific formula are calculated according to the taxonomic structure information are as follows:
Wherein, Rgoods(gi,gj) ∈ [0,1];d(gi) it is commodity giTo the path length of root node, LCA (gi,gj) it is quotient
Product giWith commodity gjPublic ancestors with maximum path.
It is described according to associated user's commodity rating matrix and the quotient in a kind of exemplary embodiment of the disclosure
The do not score scoring estimation of commodity of user to be recommended described in dependent merchandise set described in product relatedness computation includes:
It is greater than the commodity of preset value to the commodity screening product degree of correlation that do not score, described is not commented in order to obtain
Divide do not score dependent merchandise set and the corresponding commodity degree of correlation set that do not score of commodity;
It is calculated based on associated user's commodity rating matrix and the commodity degree of correlation set that do not score described to be recommended
Comprehensive score of the user to the commodity that do not score, specific formula are as follows:
Wherein, s (ui,gj) it is the user to be recommended to the commodity g that do not scorejScoring estimation;Rgoods(gk,gj) it is quotient
Product gkWith commodity gjThe degree of correlation;GsFor the dependent merchandise set.
In a kind of exemplary embodiment of the disclosure, estimate calculating the scoring for completing the commodity that do not score to obtain
After the scoring estimated matrix of dependent merchandise, the Method of Commodity Recommendation further include:
The user to be recommended is calculated to institute according to the scoring estimated matrix of user's similarity and the dependent merchandise
State the comprehensive score of each commodity in dependent merchandise set, specific formula are as follows:
Wherein,For the user u to be recommendediTo commodity gjComprehensive score;s(uk,gj) it is user ukWait push away to quotient
Product gjScoring;For the user u to be recommendediTo the mean value of each commodity scoring.
According to the second aspect of the disclosure, a kind of device for recommending the commodity is provided, comprising:
User's similarity processing module, for calculating user phase of the user to be recommended with each user according to user tag information
Like degree;
User's screening module, for being screened to user's similarity result with obtain associated user set and it is right
The associated user's commodity rating matrix and dependent merchandise set answered;
Commodity degree of correlation processing module, for calculating the commodity degree of correlation in the dependent merchandise set between each commodity;
Score estimation module, for according to described in associated user's commodity rating matrix and the commodity relatedness computation
User to be recommended described in dependent merchandise set do not score commodity scoring estimation to obtain the scoring estimated matrix of dependent merchandise;
Recommendation process module chooses the sequence of preset quantity for being ranked up according to the appraisal result of each commodity
As a result recommend to the user to be recommended.
In a kind of exemplary embodiment of the disclosure, the device for recommending the commodity further include:
Comprehensive score module, for it is described do not score commodity screening the product degree of correlation be greater than preset value the commodity with
Obtain do not score dependent merchandise set and the corresponding commodity degree of correlation set that do not score of the commodity that do not score;
And it is calculated based on associated user's commodity rating matrix and the commodity degree of correlation set that do not score described wait push away
User is recommended to the comprehensive score of the commodity that do not score.
According to the third aspect of the disclosure, a kind of storage medium is provided, is stored thereon with computer program, described program quilt
Processor realizes above-mentioned Method of Commodity Recommendation when executing.
According to the fourth aspect of the disclosure, a kind of electric terminal is provided, comprising:
Processor;And
Memory, for storing the executable instruction of the processor;
Wherein, the processor is configured to execute following operation via the executable instruction is executed:
User's similarity of user to be recommended Yu each user are calculated using user tag information;
User's similarity result is screened, in order to obtain associated user's set and corresponding associated user
Commodity rating matrix and dependent merchandise set;
Calculate the commodity degree of correlation in the dependent merchandise set between each commodity;
According to institute in dependent merchandise set described in associated user's commodity rating matrix and the commodity relatedness computation
State user to be recommended do not score commodity scoring estimation to obtain the scoring estimated matrix of dependent merchandise;
Appraisal result according to each commodity is ranked up, choose preset quantity ranking results be sent to it is described wait push away
Recommend user.
In Method of Commodity Recommendation provided by a kind of embodiment of the disclosure, calculate first user to be recommended and each user it
Between user's similarity and user is screened according to user's similarity, then corresponded to after calculating sifting in dependent merchandise set
The degree of correlation between each commodity finally combines user's similarity and the commodity degree of correlation to score commodity, and to appraisal result
It is ranked up, the ranking results for choosing preset quantity is recommended to user.Pass through, while related using user's similarity and product
Degree scores to product, fully considers the relevance between the attribute and product of user itself, guarantees the accurate of recommendation results
Property and matching degree so that the hobby be more close to the users of commodity and demand recommended effectively promoted recommendation results accuracy and
With degree.
It should be understood that above general description and following detailed description be only it is exemplary and explanatory, not
The disclosure can be limited.
Detailed description of the invention
The drawings herein are incorporated into the specification and forms part of this specification, and shows the implementation for meeting the disclosure
Example, and together with specification for explaining the principles of this disclosure.It should be evident that the accompanying drawings in the following description is only the disclosure
Some embodiments for those of ordinary skill in the art without creative efforts, can also basis
These attached drawings obtain other attached drawings.
Fig. 1 schematically shows a kind of Method of Commodity Recommendation schematic diagram in disclosure exemplary embodiment;
Fig. 2 schematically shows a kind of user's similarity calculating method schematic diagram in disclosure exemplary embodiment;
Fig. 3 schematically shows a kind of product similarity calculating method schematic diagram in disclosure exemplary embodiment;
Fig. 4 schematically shows a kind of commodity classification structural schematic diagram in disclosure exemplary embodiment;
Fig. 5 schematically shows another Method of Commodity Recommendation schematic diagram in disclosure exemplary embodiment;
Fig. 6 schematically shows a kind of composition schematic diagram of the device for recommending the commodity in disclosure exemplary embodiment;
Fig. 7 schematically shows a kind of another schematic diagram of the device for recommending the commodity in disclosure exemplary embodiment;
Fig. 8 schematically shows a kind of another schematic diagram of the device for recommending the commodity in disclosure exemplary embodiment.
Specific embodiment
Example embodiment is described more fully with reference to the drawings.However, example embodiment can be with a variety of shapes
Formula is implemented, and is not understood as limited to example set forth herein;On the contrary, thesing embodiments are provided so that the disclosure will more
Fully and completely, and by the design of example embodiment comprehensively it is communicated to those skilled in the art.Described feature, knot
Structure or characteristic can be incorporated in any suitable manner in one or more embodiments.
In addition, attached drawing is only the schematic illustrations of the disclosure, it is not necessarily drawn to scale.Identical attached drawing mark in figure
Note indicates same or similar part, thus will omit repetition thereof.Some block diagrams shown in the drawings are function
Energy entity, not necessarily must be corresponding with physically or logically independent entity.These function can be realized using software form
Energy entity, or these functional entitys are realized in one or more hardware modules or integrated circuit, or at heterogeneous networks and/or place
These functional entitys are realized in reason device device and/or microcontroller device.
A kind of Method of Commodity Recommendation is provided firstly in this example embodiment, can be applied to e-commerce website.It pushes away
The method of recommending can be in the indefinite situation of user demand, and the historical behavior data by analyzing user establish user model, into
And corresponding information is recommended according to the interest of user and demand.In this way, user is facilitated quickly to obtain the letter of needs
Breath improves the effective rate of utilization of information while saving the time of information sifting.With reference to shown in Fig. 1, above-mentioned commodity
Recommended method may comprise steps of:
S1 calculates user's similarity of user to be recommended Yu each user;
S2 screens user's similarity result, in order to obtain associated user's set and corresponding correlation
User's commodity rating matrix and dependent merchandise set;
S3 calculates the commodity degree of correlation in the dependent merchandise set between each commodity;
S4, according in dependent merchandise set described in associated user's commodity rating matrix and the commodity relatedness computation
The user to be recommended do not score commodity scoring estimation to obtain the scoring estimated matrix of dependent merchandise;
S5, the appraisal result according to each commodity are ranked up, choose preset quantity ranking results be sent to it is described
User to be recommended.
In Method of Commodity Recommendation provided by this example embodiment, by related using user's similarity and product simultaneously
Degree scores to product, fully considers the relevance between the attribute and product of user itself, guarantees the accurate of recommendation results
Property and matching degree so that the commodity hobby and demand be more close to the users recommended.
In the following, it is more detailed that accompanying drawings and embodiments will be combined to carry out each step of the method in this example embodiment
Explanation.
Step S1 calculates user u to be recommendediWith user's similarity of each user.
In this example embodiment, refering to what is shown in Fig. 2, can specifically include following steps when calculating user's similarity:
Step S11 obtains user's set U in one user-commodity rating matrix.
Step S12 is respectively described each user by N number of different label information,
ui=[xi1 ... xil ... xiN]T (1)
Wherein, xilFor user uiLabel information, 1≤l≤N;
Step S13 calculates the degree of correlation between any two user, specific formula are as follows:
Wherein, Ruser(ui,uj) it is user uiWith user ujBetween the degree of correlation, N is positive integer.
User u to be recommendediIt can be indicated with user's similarity of user's set U are as follows:
Ruser(ui, U) and=[Ruser(ui,u1) ... Ruser(ui,uj) ... Ruser(ui,uM)] (3)
In above-mentioned formula (2), the degree of correlation between cosine formula calculating user, R can useuser(ui,uj) meter
It is bigger to calculate result, then illustrates user uiWith user ujBetween similarity it is higher.
It, can be with when calculating the degree of correlation between user two-by-two by being more fully described using label information to user
The similitude between user is compared, judged and scored from multiple dimensions, and then promotes user's similarity calculation result
Accuracy and reliability.Meanwhile it can effectively avoid user's similarity calculation as caused by Sparse in rating matrix
Inaccuracy.
In other examples of the disclosure, above-mentioned user tag information be can include but is not limited to: essential information, interest
The label datas such as commodity, access history, buying behavior and collection record, the user tag information can be appoints among the above
It anticipates several combinations.Wherein, the essential information may include: gender, age, work, hobby and ownership place etc.
Information.Above-mentioned interest commodity can be class I goods, such as sports apparatus, kitchen tools etc., be also possible to a commodity, such as:
Basketball, dish-washing machine etc..
Step S2 screens user's similarity result, in order to obtain associated user set and it is corresponding
Associated user's commodity rating matrix and dependent merchandise set.
It, can be according to user's similarity after calculating the degree of correlation for completing above-mentioned user to be recommended and each user
Preset value τuserEach user is screened, R is worked asuser(ui,uj)≥τuserWhen, i.e., as user ujWith user u to be recommendediBetween
User's similarity is greater than preset value, then by user ujIt is included into associated user's set Ui.Meanwhile according to associated user's set UiIt can
To obtain corresponding associated user's set UiAssociated user-commodity rating matrix SiAnd corresponding dependent merchandise set Gs。
Step S3 calculates the dependent merchandise set GsCommodity degree of correlation R between interior each commodityg。
In this example embodiment, calculating the commodity degree of correlation be can specifically include:
Step S31 obtains the commodity classification structural information of each commodity.
Step S32 calculates the commodity degree of correlation between any two commodity, specific formula according to the taxonomic structure information
Are as follows:
Wherein, Rgoods(gi,gj) ∈ [0,1];Work as gi=gjWhen, Rgoods(gi,gj)=1.d(gi) it is commodity giTo root node
Path length, LCA (gi,gj) it is commodity giWith commodity gjPublic ancestors with maximum path.
For electric business website, the classification relation of commodity is that comparison is fixed whithin a period of time, at this time can will be each
Commodity are come out by downtree type representation.Refering to what is shown in Fig. 4, being corresponding in turn to the first-level class of commodity, secondary classification, three in figure
Grade classification etc. divides category information, and lowermost layer (leaf layer) identifies merchandise news.By calculating each commodity using the classification relation of commodity
Between the degree of correlation, fully consider the relationship between each commodity fields and commodity and commodity, effectively improve commodity correlation
The accuracy of degree.
Step S4, according to associated user's commodity rating matrix SiAnd the commodity degree of correlation RgCalculate the related quotient
Product set GsDescribed in user to be recommended do not score commodity scoring estimation to obtain the scoring estimated matrix S of dependent merchandise2。
Based on above content, in this example embodiment, above-mentioned step S4 be can specifically include:
Step S41 screens dependent merchandise set GsIn with do not score commodity gjThe commodity degree of correlation be greater than preset value quotient
Product, in order to obtain and the commodity g that do not scorejThe higher dependent merchandise set G that do not score of the commodity degree of correlationsj, and obtain and correspond to
The commodity degree of correlation set R that do not scoregoods(gj,Gsj), wherein the dependent merchandise set that do not score GsjAnd the commodity phase that do not score
Guan Du set RgoodsIt can respectively indicate are as follows:
Gsj=[g1 ... gi ... gk] (5)
Rgoods(gj,Gsj)=[Rgoods(gj,g1) ... Rgoods(gj,gi) ... Rgoods(gj,gk)] (6)
Based on associated user's commodity rating matrix SiAnd the above-mentioned commodity degree of correlation set R that do not scoregoods(gj,
Gsj), calculate the user u to be recommendediScoring estimation to the commodity that do not score, specific formula are as follows:
Wherein, s (ui,gj) it is the user to be recommended to the commodity g that do not scorejScoring estimation;s(ui,gj) be it is described to
Recommended user is to commodity gkScoring estimation;Rgoods(gk,gj) it is commodity gkWith commodity gjThe degree of correlation;GsFor the dependent merchandise
Set.
Calculating user u to be recommendediTo the commodity g that do not scorejScoring when, calculate related quotient first with above-mentioned step S3
Product set GsIn each commodity and do not score commodity gjThe commodity degree of correlation, and pass through the commodity degree of correlation preset value that is arranged in advance
It is screened, the dependent merchandise set G that do not score is added in the commodity that the commodity degree of correlation is greater than preset valuesj, while obtaining corresponding
The commodity degree of correlation set that do not score Rgoods(gj,Gsj).Estimate in the grading for obtaining the commodity that do not score by above-mentioned formula (7)
Afterwards, user to be recommended is obtained to dependent merchandise set GsComplete scoring estimated matrix S2。
Step S5, the appraisal result according to each commodity are ranked up, and the ranking results for choosing preset quantity are sent to
The user to be recommended.
In the scoring estimation and complete scoring estimated matrix S for obtaining the commodity that do not score respectively2It afterwards, can be according to each commodity
Scoring commodity are ranked up from high to low;Then a certain number of higher commodity of sequence can be chosen by preset rules,
And recommend the user to be recommended.
Based on above content, in other examples of the disclosure, in order to further optimize recommendation results, with reference to Fig. 5 institute
Show, above-mentioned Method of Commodity Recommendation can also include: after the completion of the step S4
Step S5, according to user's similarity Ruser(ui, U) and the dependent merchandise scoring estimated matrix S2It calculates
Comprehensive score of the user to be recommended to each commodity in the dependent merchandise set, specific formula are as follows:
Wherein,For the user u to be recommendediTo commodity gjComprehensive score;s(uk,gj) it is user ukTo commodity gj
Scoring;For the user ukTo the mean value of the commodity scoring each in the user-commodity rating matrix;It is described
User u to be recommendediTo the mean value of the commodity scoring each in user-commodity rating matrix.
In other disclosed exemplary embodiments, in order to mitigate the burden of server and promote the accurate of checkout result
It spends, in above-mentioned formula (8)It may be the user ukTo the dependent merchandise set GsIn each commodity scoring it is equal
Value,It can be the user u to be recommendediTo the dependent merchandise set GsIn each commodity scoring mean value.
Step S6, the appraisal result according to each commodity are ranked up, and the ranking results for choosing preset quantity are sent to
The user to be recommended.
In this example, the mean value and corresponding user's similarity to be scored by introducing user all commodity is realized and is added
Power calculates user u to be recommendediTo the comprehensive score of commodity, the reliability and accuracy to score commodity is further promoted.
The Method of Commodity Recommendation that the disclosure provides, the label information by introducing user in calculating process calculate user's phase
Like degree, effectively avoids user's relatedness computation as caused by Sparse in rating matrix inaccurate, ensure that calculated result
Accuracy and reliability, effectively improve customer relationship analysis accuracy.Meanwhile passing through the classification relation using commodity
The degree of correlation between commodity is calculated, the relationship between commodity and commodity has been fully considered, compared to original using each commodity as one
The calculation of a noncontinuous item, calculated result can more accurately indicate the relationship between commodity, and improve calculated result has
Effect property.
When carrying out Products Show, by being scored simultaneously using user's similarity and the product degree of correlation product, fill
Divide the relevance between the attribute and product that consider user itself, guarantee the accuracy of consequently recommended result, so that the quotient recommended
The hobby and demand that product are more close to the users, and then efficient personalized service is provided for user.
It should be noted that above-mentioned attached drawing is only showing for processing included by method according to an exemplary embodiment of the present invention
Meaning property explanation, rather than limit purpose.It can be readily appreciated that it is above-mentioned it is shown in the drawings processing do not indicate or limit these processing when
Between sequence.In addition, be also easy to understand, these processing, which can be, for example either synchronously or asynchronously to be executed in multiple modules.
Further, refering to what is shown in Fig. 6, also providing the device for recommending the commodity 6 in this exemplary embodiment, comprising: user
At similarity processing module 61, user's screening module 62, commodity degree of correlation processing module 63, scoring estimation module 64 and recommendation
Manage module 65.Wherein:
User's similarity processing module 61 can be used for calculating user to be recommended and each use according to user tag information
User's similarity at family.
User's screening module 62 can be used for screening to obtain associated user user's similarity result
Set and corresponding associated user's commodity rating matrix and dependent merchandise set.
The commodity degree of correlation processing module 63 can be used for calculating the quotient in the dependent merchandise set between each commodity
The product degree of correlation;
The scoring estimation module 64 can be used for related according to associated user's commodity rating matrix and the commodity
Degree calculate user to be recommended described in the dependent merchandise set do not score commodity scoring estimation to obtain commenting for dependent merchandise
Divide estimated matrix;
The recommendation process module 65 can be used for being ranked up according to the appraisal result of each commodity, choose present count
The ranking results of amount are recommended to the user to be recommended.
It on the basis of the above, is further optimization recommendation results, in the present example embodiment, above-mentioned quotient
Product recommendation apparatus 6 can also include:
Comprehensive score module, for it is described do not score commodity screening the product degree of correlation be greater than preset value the commodity with
Obtain do not score dependent merchandise set and the corresponding commodity degree of correlation set that do not score of the commodity that do not score;And based on institute
It states associated user's commodity rating matrix and the commodity degree of correlation set that do not score calculates the user to be recommended and do not comment described
Divide the comprehensive score of commodity.
The detail of each module carries out in corresponding Method of Commodity Recommendation in the above-mentioned device for recommending the commodity
Detailed description, therefore details are not described herein again.
It should be noted that although being referred to several modules or list for acting the equipment executed in the above detailed description
Member, but this division is not enforceable.In fact, according to embodiment of the present disclosure, it is above-described two or more
Module or the feature and function of unit can embody in a module or unit.Conversely, an above-described mould
The feature and function of block or unit can be to be embodied by multiple modules or unit with further division.
In an exemplary embodiment of the disclosure, a kind of electronic equipment that can be realized the above method is additionally provided.
Person of ordinary skill in the field it is understood that various aspects of the invention can be implemented as system, method or
Program product.Therefore, various aspects of the invention can be embodied in the following forms, it may be assumed that complete hardware embodiment, complete
The embodiment combined in terms of full Software Implementation (including firmware, microcode etc.) or hardware and software, can unite here
Referred to as circuit, " module " or " system ".
The electronic equipment 600 of this embodiment according to the present invention is described referring to Fig. 7.The electronics that Fig. 7 is shown
Equipment 600 is only an example, should not function to the embodiment of the present invention and use scope bring any restrictions.
As shown in fig. 7, electronic equipment 600 is showed in the form of universal computing device.The component of electronic equipment 600 can wrap
It includes but is not limited to: at least one above-mentioned processing unit 610, at least one above-mentioned storage unit 620, the different system components of connection
The bus 630 of (including storage unit 620 and processing unit 610), display unit 640.
Wherein, the storage unit is stored with program code, and said program code can be held by the processing unit 610
Row, so that various according to the present invention described in the execution of the processing unit 610 above-mentioned " illustrative methods " part of this specification
The step of illustrative embodiments.For example, the processing unit 610 can execute S1 as shown in Figure 1: calculating use to be recommended
User's similarity at family and each user;S2: screening user's similarity result, in order to obtain associated user's set
And corresponding associated user's commodity rating matrix and dependent merchandise set;S3: each commodity in the dependent merchandise set are calculated
Between the commodity degree of correlation;S4: according to correlation described in associated user's commodity rating matrix and the commodity relatedness computation
User to be recommended described in commodity set do not score commodity scoring estimation to obtain the scoring estimated matrix of dependent merchandise;S5:
Appraisal result according to each commodity is ranked up, and the ranking results for choosing preset quantity are sent to the user to be recommended.
Storage unit 620 may include the readable medium of volatile memory cell form, such as Random Access Storage Unit
(RAM) 6201 and/or cache memory unit 6202, it can further include read-only memory unit (ROM) 6203.
Storage unit 620 can also include program/utility with one group of (at least one) program module 6205
6204, such program module 6205 includes but is not limited to: operating system, one or more application program, other program moulds
It may include the realization of network environment in block and program data, each of these examples or certain combination.
Bus 630 can be to indicate one of a few class bus structures or a variety of, including storage unit bus or storage
Cell controller, peripheral bus, graphics acceleration port, processing unit use any bus structures in a variety of bus structures
Local bus.
Electronic equipment 600 can also be with one or more external equipments 700 (such as keyboard, sensing equipment, bluetooth equipment
Deng) communication, can also be enabled a user to one or more equipment interact with the electronic equipment 600 communicate, and/or with make
Any equipment (such as the router, modulation /demodulation that the electronic equipment 600 can be communicated with one or more of the other calculating equipment
Device etc.) communication.This communication can be carried out by input/output (I/O) interface 650.Also, electronic equipment 600 can be with
By network adapter 660 and one or more network (such as local area network (LAN), wide area network (WAN) and/or public network,
Such as internet) communication.As shown, network adapter 660 is communicated by bus 630 with other modules of electronic equipment 600.
It should be understood that although not shown in the drawings, other hardware and/or software module can not used in conjunction with electronic equipment 600, including but not
Be limited to: microcode, device driver, redundant processing unit, external disk drive array, RAID system, tape drive and
Data backup storage system etc..
Through the above description of the embodiments, those skilled in the art is it can be readily appreciated that example described herein is implemented
Mode can also be realized by software realization in such a way that software is in conjunction with necessary hardware.Therefore, according to the disclosure
The technical solution of embodiment can be embodied in the form of software products, which can store non-volatile at one
Property storage medium (can be CD-ROM, USB flash disk, mobile hard disk etc.) in or network on, including some instructions are so that a calculating
Equipment (can be personal computer, server, terminal installation or network equipment etc.) is executed according to disclosure embodiment
Method.
In an exemplary embodiment of the disclosure, a kind of computer readable storage medium is additionally provided, energy is stored thereon with
Enough realize the program product of this specification above method.In some possible embodiments, various aspects of the invention may be used also
In the form of being embodied as a kind of program product comprising program code, when described program product is run on the terminal device, institute
Program code is stated for executing the terminal device described in above-mentioned " illustrative methods " part of this specification according to this hair
The step of bright various illustrative embodiments.
Refering to what is shown in Fig. 8, describing the program product for realizing the above method of embodiment according to the present invention
800, can using portable compact disc read only memory (CD-ROM) and including program code, and can in terminal device,
Such as it is run on PC.However, program product of the invention is without being limited thereto, in this document, readable storage medium storing program for executing can be with
To be any include or the tangible medium of storage program, the program can be commanded execution system, device or device use or
It is in connection.
Described program product can be using any combination of one or more readable mediums.Readable medium can be readable letter
Number medium or readable storage medium storing program for executing.Readable storage medium storing program for executing for example can be but be not limited to electricity, magnetic, optical, electromagnetic, infrared ray or
System, device or the device of semiconductor, or any above combination.The more specific example of readable storage medium storing program for executing is (non exhaustive
List) include: electrical connection with one or more conducting wires, portable disc, hard disk, random access memory (RAM), read-only
Memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read only memory
(CD-ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.
Computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal,
In carry readable program code.The data-signal of this propagation can take various forms, including but not limited to electromagnetic signal,
Optical signal or above-mentioned any appropriate combination.Readable signal medium can also be any readable Jie other than readable storage medium storing program for executing
Matter, the readable medium can send, propagate or transmit for by instruction execution system, device or device use or and its
The program of combined use.
The program code for including on readable medium can transmit with any suitable medium, including but not limited to wirelessly, have
Line, optical cable, RF etc. or above-mentioned any appropriate combination.
The program for executing operation of the present invention can be write with any combination of one or more programming languages
Code, described program design language include object oriented program language-Java, C++ etc., further include conventional
Procedural programming language-such as " C " language or similar programming language.Program code can be fully in user
It calculates and executes in equipment, partly executes on a user device, being executed as an independent software package, partially in user's calculating
Upper side point is executed on a remote computing or is executed in remote computing device or server completely.It is being related to far
Journey calculates in the situation of equipment, and remote computing device can pass through the network of any kind, including local area network (LAN) or wide area network
(WAN), it is connected to user calculating equipment, or, it may be connected to external computing device (such as utilize ISP
To be connected by internet).
In addition, above-mentioned attached drawing is only the schematic theory of processing included by method according to an exemplary embodiment of the present invention
It is bright, rather than limit purpose.It can be readily appreciated that the time that above-mentioned processing shown in the drawings did not indicated or limited these processing is suitable
Sequence.In addition, be also easy to understand, these processing, which can be, for example either synchronously or asynchronously to be executed in multiple modules.
Those skilled in the art after considering the specification and implementing the invention disclosed here, will readily occur to its of the disclosure
His embodiment.This application is intended to cover any variations, uses, or adaptations of the disclosure, these modifications, purposes or
Adaptive change follow the general principles of this disclosure and including the undocumented common knowledge in the art of the disclosure or
Conventional techniques.The description and examples are only to be considered as illustrative, and the true scope and spirit of the disclosure are by claim
It points out.
It should be understood that the present disclosure is not limited to the precise structures that have been described above and shown in the drawings, and
And various modifications and changes may be made without departing from the scope thereof.The scope of the present disclosure is only limited by the attached claims.
Claims (10)
1. a kind of Method of Commodity Recommendation characterized by comprising
Calculate user's similarity of user to be recommended Yu each user;
User's similarity result is screened, in order to obtain associated user's set and corresponding associated user's commodity
Rating matrix and dependent merchandise set;
Calculate the commodity degree of correlation in the dependent merchandise set between each commodity;
According to described in dependent merchandise set described in associated user's commodity rating matrix and the commodity relatedness computation to
Recommended user do not score commodity scoring estimation, and obtain dependent merchandise scoring estimated matrix;
Appraisal result according to each commodity is ranked up, and the ranking results for choosing preset quantity are sent to the use to be recommended
Family.
2. Method of Commodity Recommendation according to claim 1, which is characterized in that described to calculate user to be recommended and each user's
User's similarity includes:
User's set in one user-commodity rating matrix is obtained, respectively by N number of different label information to each user
It is described:
ui=[xi1 ... xil ... xiN]T
Wherein, xilFor user uiLabel information, 1≤l≤N;
The degree of correlation between any two user are as follows:
Wherein, Ruser(ui,uj) it is user uiWith user ujBetween the degree of correlation, N is positive integer.
3. Method of Commodity Recommendation according to claim 1 or 2, which is characterized in that the user tag information includes: basic
Any several combination in information, interest commodity, access history, buying behavior and collection record.
4. Method of Commodity Recommendation according to claim 1, which is characterized in that the commodity calculated between each commodity are related
Degree includes:
Obtain the commodity classification structural information of each commodity;
The commodity degree of correlation between any two commodity, specific formula are calculated according to the taxonomic structure information are as follows:
Wherein, Rgoods(gi,gj) ∈ [0,1];d(gi) it is commodity giTo the path length of root node, LCA (gi,gj) it is commodity gi
With commodity gjPublic ancestors with maximum path.
5. Method of Commodity Recommendation according to claim 4, which is characterized in that described to score according to associated user's commodity
User to be recommended described in dependent merchandise set described in matrix and the commodity relatedness computation does not score the scoring estimations of commodity
Include:
It is greater than the commodity of preset value, to the commodity screening product degree of correlation that do not score in order to obtain the quotient that do not score
Do not score dependent merchandise set and the corresponding commodity degree of correlation set that do not score of product;
The user to be recommended is calculated based on associated user's commodity rating matrix and the commodity degree of correlation set that do not score
Scoring estimation to the commodity that do not score, specific formula are as follows:
Wherein, s (ui,gj) it is the user to be recommended to the commodity g that do not scorejScoring estimation;Rgoods(gk,gj) it is commodity gkWith
Commodity gjThe degree of correlation;GsFor the dependent merchandise set.
6. Method of Commodity Recommendation according to claim 5, which is characterized in that complete commenting for the commodity that do not score calculating
After dividing scoring estimated matrix of the estimation to obtain dependent merchandise, the Method of Commodity Recommendation further include:
The user to be recommended is calculated to the phase according to the scoring estimated matrix of user's similarity and the dependent merchandise
The comprehensive score of each commodity, specific formula in underlying commodity set are as follows:
Wherein,For the user u to be recommendediTo commodity gjComprehensive score;s(uk,gj) it is user ukWait push away to commodity gj
Scoring;For the user u to be recommendediTo the mean value of each commodity scoring.
7. a kind of device for recommending the commodity characterized by comprising
User's similarity processing module, it is similar to the user of each user for calculating user to be recommended according to user tag information
Degree;
User's screening module, for being screened to user's similarity result with obtain associated user set and it is corresponding
Associated user's commodity rating matrix and dependent merchandise set;
Commodity degree of correlation processing module, for calculating the commodity degree of correlation in the dependent merchandise set between each commodity;
Score estimation module, for according to correlation described in associated user's commodity rating matrix and the commodity relatedness computation
User to be recommended described in commodity set do not score commodity scoring estimation to obtain the scoring estimated matrix of dependent merchandise;
Recommendation process module chooses the ranking results of preset quantity for being ranked up according to the appraisal result of each commodity
Recommend to the user to be recommended.
8. the device for recommending the commodity according to claim 7, which is characterized in that further include:
Comprehensive score module, for being greater than the commodity of preset value to the commodity screening product degree of correlation that do not score to obtain
Do not score dependent merchandise set and the corresponding commodity degree of correlation set that do not score of the commodity that do not score;
And the use to be recommended is calculated based on associated user's commodity rating matrix and the commodity degree of correlation set that do not score
Comprehensive score of the family to the commodity that do not score.
9. a kind of storage medium is stored thereon with computer program, realizes when described program is executed by processor and wanted according to right
Method of Commodity Recommendation described in asking any one of 1 to 6.
10. a kind of electric terminal characterized by comprising
Processor;And
Memory, for storing the executable instruction of the processor;
Wherein, the processor is configured to execute following operation via the executable instruction is executed:
Calculate user's similarity of user to be recommended Yu each user;
User's similarity result is screened, in order to obtain associated user's set and corresponding associated user's commodity
Rating matrix and dependent merchandise set;
Calculate the commodity degree of correlation in the dependent merchandise set between each commodity;
According to described in dependent merchandise set described in associated user's commodity rating matrix and the commodity relatedness computation to
Recommended user do not score commodity scoring estimation, and obtain dependent merchandise scoring estimated matrix;
Appraisal result according to each commodity is ranked up, and the ranking results for choosing preset quantity are sent to the use to be recommended
Family.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710659767.9A CN109389442A (en) | 2017-08-04 | 2017-08-04 | Method of Commodity Recommendation and device, storage medium and electric terminal |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710659767.9A CN109389442A (en) | 2017-08-04 | 2017-08-04 | Method of Commodity Recommendation and device, storage medium and electric terminal |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109389442A true CN109389442A (en) | 2019-02-26 |
Family
ID=65413272
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710659767.9A Pending CN109389442A (en) | 2017-08-04 | 2017-08-04 | Method of Commodity Recommendation and device, storage medium and electric terminal |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109389442A (en) |
Cited By (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109948059A (en) * | 2019-03-28 | 2019-06-28 | 北京字节跳动网络技术有限公司 | Recommended method, device, equipment and the storage medium of content |
CN110046965A (en) * | 2019-04-18 | 2019-07-23 | 北京百度网讯科技有限公司 | Information recommendation method, device, equipment and medium |
CN110633418A (en) * | 2019-09-20 | 2019-12-31 | 曹严清 | Commodity recommendation method and device |
CN110689383A (en) * | 2019-10-12 | 2020-01-14 | 腾讯科技(深圳)有限公司 | Information pushing method and device, server and storage medium |
CN110807691A (en) * | 2019-10-31 | 2020-02-18 | 深圳市云积分科技有限公司 | Cross-commodity-class commodity recommendation method and device |
CN111056210A (en) * | 2020-01-16 | 2020-04-24 | 北京旷视机器人技术有限公司 | Material box position adjusting method and device, storage system, medium and electronic equipment |
CN111353862A (en) * | 2020-03-30 | 2020-06-30 | 贝壳技术有限公司 | Commodity recommendation method and device, electronic equipment and storage medium |
CN111626804A (en) * | 2019-02-28 | 2020-09-04 | 北京京东尚科信息技术有限公司 | Commodity recommendation method and device, electronic equipment and computer readable medium |
CN111754300A (en) * | 2020-06-22 | 2020-10-09 | 深圳市分期乐网络科技有限公司 | Commodity recommendation method, commodity recommendation device, commodity recommendation equipment and storage medium |
CN112016582A (en) * | 2019-05-31 | 2020-12-01 | 口口相传(北京)网络技术有限公司 | Dish recommending method and device |
CN112435102A (en) * | 2020-12-15 | 2021-03-02 | 中国联合网络通信集团有限公司 | Commodity similarity calculation method and device, and commodity recommendation method and system |
WO2021093399A1 (en) * | 2019-11-15 | 2021-05-20 | 北京沃东天骏信息技术有限公司 | Method and apparatus for sharing information |
CN113077319A (en) * | 2021-04-19 | 2021-07-06 | 北京沃东天骏信息技术有限公司 | Dynamic recommendation method and device for micro detail page |
CN113127750A (en) * | 2021-05-19 | 2021-07-16 | 同盾科技有限公司 | Information list generation method and device, storage medium and electronic equipment |
CN113379482A (en) * | 2021-05-28 | 2021-09-10 | 车智互联(北京)科技有限公司 | Item recommendation method, computing device and storage medium |
CN113763065A (en) * | 2020-06-17 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | Method, device, equipment and computer readable medium for recommending commodities |
CN113836310A (en) * | 2021-08-04 | 2021-12-24 | 欧冶工业品股份有限公司 | Knowledge graph driven industrial product supply chain management method and system |
CN117994010A (en) * | 2024-04-07 | 2024-05-07 | 深圳市正东兴通讯设备有限公司 | Intelligent screen information recommendation method based on big data |
CN117994010B (en) * | 2024-04-07 | 2024-07-12 | 深圳市正东兴通讯设备有限公司 | Intelligent screen information recommendation method based on big data |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8032526B2 (en) * | 2008-04-10 | 2011-10-04 | Ntt Docomo, Inc. | Recommendation information generation apparatus and recommendation information generation method |
CN103500228A (en) * | 2013-10-23 | 2014-01-08 | 苏州大学 | Similarity measuring method improved through collaborative filtering recommendation algorithm |
CN105512919A (en) * | 2016-02-23 | 2016-04-20 | 无锡中科富农物联科技有限公司 | Algorithm for collaboratively filtering agricultural materials on basis of time and region granularity |
CN106326322A (en) * | 2015-09-07 | 2017-01-11 | 北京智谷睿拓技术服务有限公司 | Recommendation method and device |
CN106779825A (en) * | 2016-12-02 | 2017-05-31 | 乐视控股(北京)有限公司 | A kind of item recommendation method, device and electronic equipment |
-
2017
- 2017-08-04 CN CN201710659767.9A patent/CN109389442A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8032526B2 (en) * | 2008-04-10 | 2011-10-04 | Ntt Docomo, Inc. | Recommendation information generation apparatus and recommendation information generation method |
CN103500228A (en) * | 2013-10-23 | 2014-01-08 | 苏州大学 | Similarity measuring method improved through collaborative filtering recommendation algorithm |
CN106326322A (en) * | 2015-09-07 | 2017-01-11 | 北京智谷睿拓技术服务有限公司 | Recommendation method and device |
CN105512919A (en) * | 2016-02-23 | 2016-04-20 | 无锡中科富农物联科技有限公司 | Algorithm for collaboratively filtering agricultural materials on basis of time and region granularity |
CN106779825A (en) * | 2016-12-02 | 2017-05-31 | 乐视控股(北京)有限公司 | A kind of item recommendation method, device and electronic equipment |
Non-Patent Citations (2)
Title |
---|
叶剑宇 等: "基于路径搜索的相似度计算的协同过滤推荐方法", 《贵州大学学报(自然科学版)》 * |
杨家慧 等: "基于巴氏系数和Jaccard系数的协同过滤算法", 《计算机应用》 * |
Cited By (26)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111626804A (en) * | 2019-02-28 | 2020-09-04 | 北京京东尚科信息技术有限公司 | Commodity recommendation method and device, electronic equipment and computer readable medium |
CN109948059A (en) * | 2019-03-28 | 2019-06-28 | 北京字节跳动网络技术有限公司 | Recommended method, device, equipment and the storage medium of content |
CN110046965A (en) * | 2019-04-18 | 2019-07-23 | 北京百度网讯科技有限公司 | Information recommendation method, device, equipment and medium |
CN112016582A (en) * | 2019-05-31 | 2020-12-01 | 口口相传(北京)网络技术有限公司 | Dish recommending method and device |
CN112016582B (en) * | 2019-05-31 | 2023-11-24 | 口口相传(北京)网络技术有限公司 | Dish recommending method and device |
CN110633418A (en) * | 2019-09-20 | 2019-12-31 | 曹严清 | Commodity recommendation method and device |
CN110689383A (en) * | 2019-10-12 | 2020-01-14 | 腾讯科技(深圳)有限公司 | Information pushing method and device, server and storage medium |
CN110689383B (en) * | 2019-10-12 | 2023-08-22 | 腾讯科技(深圳)有限公司 | Information pushing method, device, server and storage medium |
CN110807691A (en) * | 2019-10-31 | 2020-02-18 | 深圳市云积分科技有限公司 | Cross-commodity-class commodity recommendation method and device |
CN110807691B (en) * | 2019-10-31 | 2022-03-04 | 深圳市云积分科技有限公司 | Cross-commodity-class commodity recommendation method and device |
WO2021093399A1 (en) * | 2019-11-15 | 2021-05-20 | 北京沃东天骏信息技术有限公司 | Method and apparatus for sharing information |
CN111056210A (en) * | 2020-01-16 | 2020-04-24 | 北京旷视机器人技术有限公司 | Material box position adjusting method and device, storage system, medium and electronic equipment |
CN111056210B (en) * | 2020-01-16 | 2022-05-06 | 北京旷视机器人技术有限公司 | Material box position adjusting method and device, storage system, medium and electronic equipment |
CN111353862A (en) * | 2020-03-30 | 2020-06-30 | 贝壳技术有限公司 | Commodity recommendation method and device, electronic equipment and storage medium |
CN113763065A (en) * | 2020-06-17 | 2021-12-07 | 北京沃东天骏信息技术有限公司 | Method, device, equipment and computer readable medium for recommending commodities |
CN111754300A (en) * | 2020-06-22 | 2020-10-09 | 深圳市分期乐网络科技有限公司 | Commodity recommendation method, commodity recommendation device, commodity recommendation equipment and storage medium |
CN112435102A (en) * | 2020-12-15 | 2021-03-02 | 中国联合网络通信集团有限公司 | Commodity similarity calculation method and device, and commodity recommendation method and system |
CN113077319A (en) * | 2021-04-19 | 2021-07-06 | 北京沃东天骏信息技术有限公司 | Dynamic recommendation method and device for micro detail page |
CN113127750A (en) * | 2021-05-19 | 2021-07-16 | 同盾科技有限公司 | Information list generation method and device, storage medium and electronic equipment |
CN113127750B (en) * | 2021-05-19 | 2024-04-02 | 同盾科技有限公司 | Information list generation method and device, storage medium and electronic equipment |
CN113379482A (en) * | 2021-05-28 | 2021-09-10 | 车智互联(北京)科技有限公司 | Item recommendation method, computing device and storage medium |
CN113379482B (en) * | 2021-05-28 | 2023-12-01 | 车智互联(北京)科技有限公司 | Article recommendation method, computing device and storage medium |
CN113836310A (en) * | 2021-08-04 | 2021-12-24 | 欧冶工业品股份有限公司 | Knowledge graph driven industrial product supply chain management method and system |
CN113836310B (en) * | 2021-08-04 | 2022-11-29 | 欧冶工业品股份有限公司 | Knowledge graph driven industrial product supply chain management method and system |
CN117994010A (en) * | 2024-04-07 | 2024-05-07 | 深圳市正东兴通讯设备有限公司 | Intelligent screen information recommendation method based on big data |
CN117994010B (en) * | 2024-04-07 | 2024-07-12 | 深圳市正东兴通讯设备有限公司 | Intelligent screen information recommendation method based on big data |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109389442A (en) | Method of Commodity Recommendation and device, storage medium and electric terminal | |
CN104123332B (en) | The display methods and device of search result | |
US11049149B2 (en) | Determination of targeted food recommendation | |
CN103164463B (en) | Method and device for recommending labels | |
CN110046965A (en) | Information recommendation method, device, equipment and medium | |
CA2944652C (en) | Inference model for traveler classification | |
US20170193853A1 (en) | Generative group-based meal planning system and method | |
US9230277B2 (en) | Presentation of product recommendations based on social informatics | |
US20120290509A1 (en) | Training Statistical Dialog Managers in Spoken Dialog Systems With Web Data | |
CN110110205A (en) | Recommendation information generation method and device | |
CN109242044A (en) | Training method, device, storage medium and the electronic equipment of vehicle and goods matching model | |
CN109493101A (en) | Target brand message determines method, apparatus, electronic equipment and storage medium | |
CN112612957A (en) | Interest point recommendation method, interest point recommendation model training method and device | |
CN109359247A (en) | Content delivery method and storage medium, computer equipment | |
US20150040018A1 (en) | Rating and review interface | |
WO2012158571A2 (en) | Training statistical dialog managers in spoken dialog systems with web data | |
CN112182360A (en) | Personalized recommender with limited data availability | |
US10332161B2 (en) | Retrieving reviews based on user profile information | |
US11061943B2 (en) | Constructing, evaluating, and improving a search string for retrieving images indicating item use | |
CN109543107A (en) | Data processing method, medium, device and calculating equipment | |
CN110059172B (en) | Method and device for recommending answers based on natural language understanding | |
US11475485B2 (en) | Automated curation of digital information and user interface for same | |
US20170004511A1 (en) | Identifying Drivers for a Metric-of-Interest | |
US10521751B2 (en) | Using customer profiling and analytics to understand, rank, score, and visualize best practices | |
US11138273B2 (en) | Onboarding services |
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: 20190226 |
|
RJ01 | Rejection of invention patent application after publication |