CN109961345A - Interactive Method of Commodity Recommendation and non-transitory computer-readable medium - Google Patents
Interactive Method of Commodity Recommendation and non-transitory computer-readable medium Download PDFInfo
- Publication number
- CN109961345A CN109961345A CN201711468681.4A CN201711468681A CN109961345A CN 109961345 A CN109961345 A CN 109961345A CN 201711468681 A CN201711468681 A CN 201711468681A CN 109961345 A CN109961345 A CN 109961345A
- Authority
- CN
- China
- Prior art keywords
- list
- commodity
- user
- labels
- label
- 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 26
- 230000002452 interceptive effect Effects 0.000 title claims abstract description 21
- 238000012097 association analysis method Methods 0.000 claims description 8
- 230000000694 effects Effects 0.000 claims description 7
- 239000000463 material Substances 0.000 claims description 4
- 239000000047 product Substances 0.000 description 52
- 238000010586 diagram Methods 0.000 description 8
- 238000004422 calculation algorithm Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 230000007774 longterm Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000001914 filtration Methods 0.000 description 3
- 238000007619 statistical method Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 239000013065 commercial product Substances 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000008450 motivation Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000008929 regeneration Effects 0.000 description 1
- 238000011069 regeneration method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- -1 title Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
- G06F3/0481—Interaction techniques based on graphical user interfaces [GUI] based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance
- G06F3/04817—Interaction techniques based on graphical user interfaces [GUI] based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance using icons
-
- 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
-
- 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]
- G06Q30/0641—Shopping interfaces
- G06Q30/0643—Graphical representation of items or shoppers
Abstract
A kind of interactive mode Method of Commodity Recommendation, step includes: from selection target commodity in multiple commodity；Load corresponds to the merchandise news of end article；Items list is generated according to the relevance between commodity and the user preference corresponding to user, wherein items list has corresponding multiple icons to different commodity；The first list of labels is generated according at least one product features for corresponding to end article and the user preference corresponding to user, wherein the first list of labels has corresponding multiple first labels to different product features；And pass through user interface display of commodity information, items list and the first list of labels.When clicking icon, display corresponds to another user interface for the icon being clicked.When clicking the first label, according to the first tag update items list being clicked.
Description
Technical field
The present invention relates to a kind of interactive Method of Commodity Recommendation and non-transitory computer-readable mediums.
Background technique
In existing shopping website or shopping application program, when the user clicks when interesting commodity, electric business is usual
, consumer related to interesting commodity can be further provided in the display page may interested commercial product recommending.So
And in the prior art, Recommendations are largely only shown to user unilaterally by recommendation function, and can not be reflected in real time
The product features that consumer is taken notice of instantly.Therefore how to provide more preferably recommendation list is that must solve the problems, such as at present.
Summary of the invention
One aspect of the present invention provides a kind of interactive Method of Commodity Recommendation, and step includes: to select from multiple commodity
End article；Load corresponds to the merchandise news of end article；According to the relevance between commodity and correspond at least one
The user preference of user generates items list, and wherein items list has corresponding multiple icons to different commodity；According to correspondence
At least one product features in end article and the user preference corresponding to user generate the first list of labels, wherein first
List of labels has corresponding multiple first labels to different product features；And believed by the first user interface display of commodity
Breath, items list and the first list of labels.When any one for the icon for clicking items list, loading and showing has correspondence
In the second user interface of the merchandise news for the icon being clicked.When either one or two of the first label for clicking the first list of labels
When, according to the first tag update items list being clicked.
Another aspect of the present invention provides a kind of non-transitory computer-readable medium, is stored thereon with executable finger
It enables, when instruction is executed by the processor of electronic device, causing operation performed by electronic device includes: from multiple commodity
Selection target commodity；Load corresponds to the merchandise news of end article；According to the relevance between commodity and correspond at least
The user preference of one user generates items list, and wherein items list has corresponding multiple icons to different commodity；According to
At least one product features corresponding to end article and the user preference corresponding to user generate the first list of labels, wherein
First list of labels has corresponding multiple first labels to different product features；And pass through the first user interface display of commodity
Information, items list and the first list of labels.When click items list icon any one when, load and show have pair
The second user interface of the merchandise news for the icon that Ying Yu is clicked.When either one or two of the first label for clicking the first list of labels
When, according to items list described in the first tag update being clicked.
Detailed description of the invention
Fig. 1 diagrammatically illustrates the system architecture diagram of electronic device according to an embodiment of the present invention；
Fig. 2 diagrammatically illustrates the schematic diagram of user interface according to an embodiment of the present invention；
Fig. 3 A~3B diagrammatically illustrates according to an embodiment of the present invention with items list and product features label column
The schematic diagram of the user interface of table；
Fig. 4 diagrammatically illustrates according to an embodiment of the present invention with items list, product features list of labels and mesh
Mark the schematic diagram of the user interface of customers' feature tag list；
Fig. 5 diagrammatically illustrates the flow chart of interactive Method of Commodity Recommendation according to an embodiment of the present invention.
[description of symbols]
100: system architecture；110: processing unit；
120: storage element；130: socket；
140: display unit；300,400: user interface；
310,410: commodity picture；320,420: merchandise related information；
330,430: the label column corresponding to different trading activities；
340,440: items list；341~344,441~444: commodity picture；
350,450: product features list of labels；
351~354,451~454: the corresponding label to different product features；
460: target customers' feature tag list；
461~463: the corresponding label to different target client's group character；
S501~S507: steps flow chart.
Specific embodiment
To make the objectives, technical solutions, and advantages of the present invention clearer, below in conjunction with specific embodiment, and reference
Attached drawing, the present invention is described in further detail.
It should be noted that interactive Method of Commodity Recommendation of the invention and non-transitory computer-readable medium are suitable for
Other ranges will next provided by be described in detail in clearly describe.It must be appreciated that following detailed description and specific reality
Example is applied, when proposing the illustrative examples in relation to interactive Method of Commodity Recommendation and non-transitory computer-readable medium, only
As description purpose and be not used to limit the scope of the present invention.
Fig. 1 diagrammatically illustrates the system architecture diagram of electronic device according to an embodiment of the invention.System architecture 100 can
It is implemented on such as desktop computer, laptop or portable electronic device (such as smartphone, tablet computer
Deng) etc. electronic device in, and include at least processing unit 110.Processing unit 110 can be implemented in several ways, such as with
Special hardware circuit or common hardware (for example, single processor, multiple processors with parallel processing ability, at figure
Manage device perhaps other processors with operational capability) and when executing program code or software, it is described after providing
Function.System architecture 100 further includes storage element 120, to store required data in implementation procedure, miscellaneous electricity
Sub-file and the instruction etc. for executing method described below, such as various algorithms, user related data, commodity related data
And/or transaction content etc..System architecture 100 may also include socket 130, to receive the browsing row of at least one user
For, click behavior and/or buying behavior etc..Display unit 140 can be display panel (for example, film liquid crystal display panel, organic
Light-emitting-diode panel or other panels with display capabilities), to show character, number, the symbol, towing mouse of input
User interface provided by motion track or application program is marked, to be supplied to user's viewing.System architecture 100 further includes input
Equipment (in figure do not go out aobvious), such as mouse, stylus or keyboard etc., with execute browsing behavior for user, click behavior and/
Or buying behavior etc..
Fig. 2 diagrammatically illustrates the schematic diagram of user interface according to an embodiment of the invention.As shown in Fig. 2, user circle
The display of face 200 represents picture 210~230 of different commodity etc..When user clicks figure by input equipment on the user interface 200
When any one in piece 210~230 etc., processing unit 110 is the correlation that the commodity in relation to being clicked are loaded from storage element 120
Information, and correspond to another user interface for the commodity being clicked in the display of display unit 140.
Fig. 3 A diagrammatically illustrates according to an embodiment of the invention with items list and product features list of labels
User interface schematic diagram.As shown in Figure 3A, the user interface corresponding to the commodity being clicked may include corresponding to be clicked
Icon 310, merchandise related information 320, the label column 330 corresponding to different trading activities, items list 340 and the quotient of commodity
Product feature tag list 350 etc..Merchandise related information 320 may include product name, product features or the correlation for having underlying commodity
Description etc..Wherein, product features can be broken by hyphenation word and retains the processes such as most long word and obtains, and by based on behavior
(Behavior-based modeling) association analysis method (such as Association Rule Mining (AR),
Collaborative Filtering (CF), Co-Ocurrence or Matrix Factorization (MF) etc.) or with
Association analysis method (such as the Content similarity etc.) mistake of (Content-based modeling) based on content
The product features that there is higher relevance with end article are filtered out, and generate product features label whereby.Product features may include
Such as brand, product item title, material, color, size, product efficacy, price, preference group feature etc..Wherein, preference group is special
Sign refers to user characteristics, such as gender, age level, residential area of user group of this commodity of preference etc..Label column 330 can wrap
Buttons such as " directly purchases ", " shopping cart is added " and/or " collecting commodities " are included, so that user executes click behavior or purchase row
For etc., but be not limited thereto.The corresponding picture 341~344 to different commodity is shown in items list 340.Wherein, picture
Different commodity corresponding to 341~344 are that have certain correlation with the commodity being clicked, and produced with reference to the preference of user
It is raw.For example, as shown, the commodity being clicked in the present embodiment are women's shoes, and different moneys are shown in items list 340
The women's shoes of formula.Wherein, processing unit 110 generates the different commodity in items list 340 also according to following formula:
Wherein, rU, i, jIndicate the recommender score of commodity,Indicate the correlation between commodity i and j, andThen indicate
User u estimates the long-term preference of commodity j.After obtaining recommender score, processing unit 110 can be according to the height of recommender score
Commodity in low display of commodity list 340.For example, from left to right to be arranged in the high to low mode of score.
Wherein, when the user clicks any one shown in items list 340 commodity when, processing unit 110 is then according to quilt
The commodity of click load corresponding merchandise news from storage element 120, and show to correspond to by another user interface and be clicked
Commodity information.
Another embodiment according to the present invention, processing unit 110 can also generate according to the following formula in items list 340 not
Same commodity:
Wherein,Indicate the correlation between commodity i and j, fbU, uTagFor user u selection consumer's tag set,
fbU, iTagFor the Commercial goods labels set of user's selection, function F indicates the correlation of commodity j and online user's feedback, PrefU, jFor
User u estimates the preference of commodity j.Wherein, preference estimation includes online preferenceAnd long-term preference
The corresponding product features label 351~354 to different product features is shown in product features list of labels 350.Quotient
Product feature may include goods themselves characteristic (such as brand, material, size etc.) and preference group feature (such as consumption race
Group, consumer's age, consumer's gender etc.).For example, in this embodiment, the feature for the commodity being clicked is consumption year
Age layer is about " 30 years old ", brand is " Schutz ", color is " black " and shoes style is " heel sandals (Heel
sandal)".Wherein, processing unit 110 generates product features label 351~354 also according to following formula:
Wherein, rU, i, tIndicate the recommender score of product features,Indicate the correlation between commodity i and label t, andThen indicate that user u estimates the long-term preference of label t.
Another embodiment according to the present invention, processing unit 110 can also generate product features list of labels according to the following formula
350:
Wherein,Indicate the correlation between commodity i and label t, fbU, uTagFor consumer's tally set of user u selection
It closes, fbU, iTagFor the Commercial goods labels set of user's selection, function F indicates the correlation of label t and online user's feedback, PrefU, t
Estimate for preference of the user u for label t.Wherein, preference estimation includes online preferenceAnd long-term preference
Another embodiment according to the present invention, shown product features label is that can open up in product features list of labels 350
It opens.For example, as shown in Figure 3A, compared to product features label 354, a pair of is additionally shown in product features label 353a
Arrow or other icons, to indicate that this product features label 353a is extensible.Product features label when the user clicks
When 353a, deployable is the subtab list as shown in 353b in Fig. 3 B.Wherein, son shown in subtab list 353b
Label belongs to same type but has different attribute.For example, as shown in Figure 3B, " Black " in subtab list 353b,
The type of " Brown ", " White ", " Pink " etc. are color.In addition, subtab list is according between user and commodity
What mutual-action behavior generated.Wherein, mutual-action behavior includes click record, purchase record and/or browsing record of user etc..Citing comes
It says, processing unit 110 can pass through associated parser (such as AR, Co-Ocurrence or Matrix in advance
Factorization) according to the associated score of the mutual-action behavior of user and the feature calculation every two product features of each commodity,
Then the subtab of high relevance is provided by threshold filtering, thus to generate subtab list 353b.Wherein, subtab arranges
Subtab in table 353b can be also ranked up according to the height of score.
Wherein, when the user clicks in product features list of labels 350 in one or more labels or subtab list one or
When multiple subtabs, processor 110 can update items list 340 according to the label being clicked/subtab.
It is worth noting that, icon 310, merchandise related information 320 shown in Fig. 3 A, 3B, correspond to different transaction row
For the configuration of label column 330, items list 340 and product features list of labels 350 etc. be only one embodiment of the invention,
Electric business can change according to demand the configuration of display, and be not limited with the present invention.
Fig. 4 diagrammatically illustrate it is according to an embodiment of the invention have items list, product features list of labels and
The schematic diagram of the user interface of target customers' feature tag list.Wherein, icon 410, merchandise related information shown in Fig. 4
420, the content class corresponding to the label column 430 of different trading activities, items list 440 and product features list of labels 450
It is similar to icon 310, merchandise related information 320 shown in Fig. 3 A, 3B, corresponding to the label column 330 of different trading activities, commodity
List 340 and product features list of labels 350, details are not described herein.As shown in figure 4, according to the present invention described in an embodiment
User interface may also include target customers' feature tag list 460.Target customers' feature tag list 460 is mainly found out
The feature of the preference group of the feature and each commodity of each commodity preference group, to generate product pass similar to user characteristics
It is, the similarity relation of user characteristics and product features.For example, in this embodiment, the target visitor for the commodity 410 being clicked
About age level is " 30 years old " to group, occupation is " housewife " or " office female officer " etc..Wherein, processing unit 110 can
The list of target customers' feature tag is obtained according to statistical analysis algorithms or collaborative filtering basic algorithm.Statistical analysis algorithms are
It is bought with statistics commodity in the transaction history and browsing history of target visitor group by same subscriber feature using commodity
Probability.The formula of statistical analysis algorithms is as follows:
Wherein family rob (fbIi| uTag) represent under conditions of user property is uTag, commodity i by the probability of feedback,
Prob(uTag|fbIi) represent commodity i by under regeneration event and user property as uTag probability, Prob (fbIi) be commodity i quilt
The probability of feedback, Prob (uTag) are the probability that user property is uTag.
Wherein, when the user clicks one or more labels in target customers' feature tag list 460 when, processor 110
According to the tag update items list and product features list of labels being clicked.Wherein, items list update mode is to utilize
Formula (2) calculates the r_uij score of candidate J commodity and sorts from high to low according to it, then selects according to the Recommendations number of setting
The top n of sequence is taken to recommend, Lai Gengxin items list.And the update mode of feature tag list is calculated using formula (6)
The r_uit score of candidate T feature tag simultaneously sorts according to it from high to low, then chooses sequence according to the recommendation number of tags of setting
Preceding K recommendation, Lai Gengxin feature tag list.It is worth noting that, in this embodiment, product features label when the user clicks
When label in list, processor 110 is according only to the tag update items list being clicked, and target customers' feature tag arranges
Label in table 460 can't change.
It is worth noting that, icon 410, merchandise related information 420 shown in Fig. 4, corresponding to different trading activities
Label column 430, items list 440, product features list of labels 450 and target customers' feature tag list 460 etc. are matched
Only one embodiment of the invention is set, electric business can change the configuration of display according to demand, and the present invention is not limited thereto.
Fig. 5 diagrammatically illustrates the flow chart of interactive Method of Commodity Recommendation according to an embodiment of the invention.In step
S501, selection target commodity during user's multiple commodity 210~230 shown from user interface 200 are equal.In step S502,
Processing unit 110 corresponds to the relevant information of end article from the load of storage element 120.In step S503,110 basis of processor
Product features corresponding to end article and the user preference corresponding to user generate items list.In step S504, processing
User preference of the device 110 according to the product features for corresponding to end article and corresponding to user generates product features label column
Table.In step S505, processor 110 is also according to the product features for corresponding to end article and corresponding to the user preference of user
Generate the list of target customers' feature tag.Then, obtain merchandise news, items list, product features list of labels and
After target customers' feature tag list, S506 is entered step, processing unit 110 is by user interface on display unit 140
Display of commodity information, items list, product features list of labels and target customers' feature tag list.Finally, in step
S507, user is operated on a user interface by input equipment, so that processing unit 110 is held according to the clicking operation of user
The corresponding operation of row.For example, when corresponding to the picture of commodity in items list when the user clicks, processor 110 is loaded simultaneously
Display corresponds to another user interface of the merchandise news for the commodity being clicked.Alternatively, product features label column when the user clicks
When table, processor 110 is according to the tag update items list being clicked.And target customers' feature tag when the user clicks
When list, processor 110 is according to the tag update items list and product features list of labels being clicked.
Wherein, method of the invention or specific modality or part thereof can also exist in the form of program code.Program generation
Code may include in tangible media, as floppy disk, disc, hard disk or any other machine-readable are (such as computer-readable
Take) storage medium, or be not limited to the computer program product of external form, wherein when program code is by machine, such as computer
When load and execution, this machine becomes to participate in the device of the invention.Program code can also be by some transmission media, such as
Electric wire or cable, optical fiber or any transmission form are transmitted, wherein when program code is by electronic equipment, such as computer
When receiving, load and executing, this electronic equipment becomes to participate in the device of the invention.Implement when in general service processing unit
When, program code combination processing unit provides operation and is similar to the unique apparatus for applying particular logic circuit.
In conclusion an embodiment proposes according to the present invention interactive Method of Commodity Recommendation and non-instantaneous computer can
Medium is read, by special according to the product features, the user preference corresponding to user and/or target customers that correspond to end article
Sign etc. generates different lists, and can correspond to the feedback of label according to consumer, learns the commodity that consumer is taken notice of instantly
Feature, in time to update shown items list.In this way, consumer can efficiently find end article, and can
Increase the consumer motivation of consumer.
Particular embodiments described above has carried out further in detail the purpose of the present invention, technical scheme and beneficial effects
Describe in detail bright, it should be understood that the above is only a specific embodiment of the present invention, is not intended to restrict the invention, it is all
Within the spirit and principles in the present invention, any modification, equivalent substitution, improvement and etc. done should be included in protection of the invention
Within the scope of.
Claims (22)
1. a kind of interactive mode Method of Commodity Recommendation, comprising:
From selection target commodity in multiple commodity；
Load corresponds to the merchandise news of the end article；
Items list is generated according to the relevance between the commodity and the user preference corresponding at least one user, wherein
The items list has corresponding multiple icons to different commodity；
According at least one product features for corresponding to the end article and corresponding to the user preference of the user
The first list of labels is generated, wherein first list of labels has corresponding multiple first marks to the different product features
Label；And
The merchandise news, the items list and first list of labels are shown by the first user interface；
Wherein, when any one for the icon for clicking the items list, loading and showing has corresponding to described by point
The second user interface of the merchandise news of the icon hit；And
Wherein, when any one for first label for clicking first list of labels, according to first be clicked
Items list described in tag update.
2. interactive mode Method of Commodity Recommendation according to claim 1, further includes:
The second list of labels is generated according to the preference consumer characteristic for corresponding to the end article, wherein second label column
Table has corresponding multiple second labels to different target client's group character.
3. interactive mode Method of Commodity Recommendation according to claim 2, wherein when either one or two of described second label of click
When, according to items list described in second tag update being clicked and first list of labels.
4. interactive mode Method of Commodity Recommendation according to claim 1, wherein first list of labels, which also has, to be corresponded to
At least one first deployable label of the product features loads when clicking the first deployable label and shows
One subtab list.
5. interactive mode Method of Commodity Recommendation according to claim 4, further includes:
Every two commodity are calculated according to the historical record for corresponding to the user by the association analysis method based on behavior
The score of feature；And
The product features are screened to generate the first subtab list by threshold value according to the score.
6. interactive mode Method of Commodity Recommendation according to claim 4, wherein the first subtab list, which has, belongs to phase
Multiple first subtabs of same type but different attribute.
7. interactive mode Method of Commodity Recommendation according to claim 4, wherein when either one or two of described first subtab of click
When, the items list is updated according to first subtab being clicked.
8. interactive mode Method of Commodity Recommendation according to claim 1, further includes:
By the association analysis method based on behavior or the association analysis method based on content filter out with it is described
End article has the product features of the relevance to generate first label.
9. interactive mode Method of Commodity Recommendation according to claim 1, further includes:
The user preference is updated according to the click behavior and/or buying behavior of the user.
10. it is according to claim 1 interactive mode Method of Commodity Recommendation, wherein product features include brand, product item title,
Material, size, commodity effect, price and/or preference group feature.
11. interactive mode Method of Commodity Recommendation according to claim 10, wherein preference group feature includes user's
Gender, age level and/or residential area.
12. a kind of non-transitory computer-readable medium, is stored thereon with executable instruction, when described instruction passes through electronic device
When processor executes, the operation performed by above-mentioned electronic device is caused to include:
From selection target commodity in multiple commodity；
Load corresponds to the merchandise news of above-mentioned end article；
Items list is generated according to the relevance between the commodity and the user preference corresponding at least one user, wherein
The items list has corresponding multiple icons to different commodity；
According at least one product features for corresponding to the end article and corresponding to the user preference of the user
The first list of labels is generated, wherein first list of labels has corresponding multiple first marks to the different product features
Label；And
The merchandise news, the items list and first list of labels are shown by the first user interface；
Wherein, when any one for the icon for clicking the items list, loading and showing has corresponding to described by point
The second user interface of the merchandise news of the icon hit；And
Wherein, when any one for first label for clicking first list of labels, according to first be clicked
Items list described in tag update.
13. non-transitory computer-readable medium according to claim 12, wherein cause performed by the electronic device
Operation further include:
The second list of labels is generated according to the preference consumer characteristic for corresponding to the end article, wherein second label column
Table has corresponding multiple second labels to different target client's group character.
14. non-transitory computer-readable medium according to claim 13, wherein when any for clicking second label
When a, according to items list described in second tag update being clicked and first list of labels.
15. non-transitory computer-readable medium according to claim 12, wherein first list of labels also has pair
The deployable label of at least one of product features first described in Ying Yu is loaded and is shown when clicking the first deployable label
Show the first subtab list.
16. non-transitory computer-readable medium according to claim 15, wherein cause performed by the electronic device
Operation further include:
Every two commodity are calculated according to the historical record for corresponding to the user by the association analysis method based on behavior
The score of feature；And
Above-mentioned product features are screened to generate the first subtab list by threshold value according to the score.
17. non-transitory computer-readable medium according to claim 15, wherein the first subtab list, which has, to be belonged to
In same type but multiple first subtabs of different attribute.
18. non-transitory computer-readable medium according to claim 15, wherein as times for clicking first subtab
At one, the items list is updated according to first subtab being clicked.
19. non-transitory computer-readable medium according to claim 12, wherein cause performed by the electronic device
Operation further include:
By the association analysis method based on behavior or the association analysis method based on content filter out with it is described
End article has the product features of the relevance to generate first label.
20. non-transitory computer-readable medium according to claim 12, wherein cause performed by the electronic device
Operation further include:
The user preference is updated according to the click behavior and/or buying behavior of the user.
21. non-transitory computer-readable medium according to claim 12, wherein product features include brand, product key name
Title, material, size, commodity effect, price and/or preference group feature.
22. non-transitory computer-readable medium according to claim 21, wherein preference group feature includes user
Gender, age level and/or residential area.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| TW106145265 | 2017-12-22 | ||
| TW106145265A TWI665630B (en) | 2017-12-22 | 2017-12-22 | Interactive product recommendation method and non-transitory computer-readable medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109961345A true CN109961345A (en) | 2019-07-02 |
Family
ID=67022933
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711468681.4A Pending CN109961345A (en) | 2017-12-22 | 2017-12-28 | Interactive Method of Commodity Recommendation and non-transitory computer-readable medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN109961345A (en) |
| TW (1) | TWI665630B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110889747A (en) * | 2019-12-02 | 2020-03-17 | 腾讯科技（深圳）有限公司 | Commodity recommendation method, commodity recommendation device, commodity recommendation system, computer equipment and storage medium |
| CN111144971A (en) * | 2019-11-28 | 2020-05-12 | 上海宝尊电子商务有限公司 | Left-side expanded screening bullet frame type commodity selector interactive design |
| CN111738802A (en) * | 2020-06-30 | 2020-10-02 | 广东奥园奥买家电子商务有限公司 | Introduction method, device and equipment of E-commerce commodities |
| CN112036988A (en) * | 2020-09-24 | 2020-12-04 | 上海风秩科技有限公司 | Label generation method and device, storage medium and electronic equipment |
| CN112749322A (en) * | 2019-10-31 | 2021-05-04 | 阿里巴巴集团控股有限公司 | Commodity object information recommendation method and device and electronic equipment |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102591972A (en) * | 2011-12-31 | 2012-07-18 | 北京百度网讯科技有限公司 | Method and device for providing goods search results |
| CN105469263A (en) * | 2014-09-24 | 2016-04-06 | 阿里巴巴集团控股有限公司 | Commodity recommendation method and device |
| CN106485562A (en) * | 2015-09-01 | 2017-03-08 | 苏宁云商集团股份有限公司 | A kind of commodity information recommendation method based on user's history behavior and system |
| CN106600372A (en) * | 2016-12-12 | 2017-04-26 | 武汉烽火信息集成技术有限公司 | Commodity recommending method and system based on user behaviors |
| CN106708821A (en) * | 2015-07-21 | 2017-05-24 | 广州市本真网络科技有限公司 | User personalized shopping behavior-based commodity recommendation method |
| CN107154109A (en) * | 2017-06-02 | 2017-09-12 | 深圳正品创想科技有限公司 | A kind of commodity rendering method, device and self-service cabinet |
| CN107274242A (en) * | 2016-04-08 | 2017-10-20 | 上海旭薇物联网科技有限公司 | A kind of Method of Commodity Recommendation based on association analysis algorithm |
| CN107392718A (en) * | 2017-07-26 | 2017-11-24 | 四川长虹电器股份有限公司 | Method of Commodity Recommendation |
| CN107464162A (en) * | 2017-07-28 | 2017-12-12 | 腾讯科技（深圳）有限公司 | Commodity association method, apparatus and computer-readable recording medium |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7672865B2 (en) * | 2005-10-21 | 2010-03-02 | Fair Isaac Corporation | Method and apparatus for retail data mining using pair-wise co-occurrence consistency |
| US20070174085A1 (en) * | 2006-01-26 | 2007-07-26 | Koo Charles C | System and method for ordered recommendation of healthcare or personal care products |
| KR20160013266A (en) * | 2011-04-11 | 2016-02-03 | 인텔 코포레이션 | Personalized advertisement selection system and method |
| US9020835B2 (en) * | 2012-07-13 | 2015-04-28 | Facebook, Inc. | Search-powered connection targeting |
| TWI554957B (en) * | 2013-11-25 | 2016-10-21 | 雅虎股份有限公司 | The recommendation of promotion discount combo based on selected items |
| CN105446972B (en) * | 2014-06-17 | 2022-06-10 | 阿里巴巴集团控股有限公司 | Searching method, device and system based on and fused with user relationship data |
| CN106408365B (en) * | 2016-08-24 | 2019-10-11 | 北京无线体育俱乐部有限公司 | Content recommendation method and device |
-
2017
- 2017-12-22 TW TW106145265A patent/TWI665630B/en active
- 2017-12-28 CN CN201711468681.4A patent/CN109961345A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102591972A (en) * | 2011-12-31 | 2012-07-18 | 北京百度网讯科技有限公司 | Method and device for providing goods search results |
| CN105469263A (en) * | 2014-09-24 | 2016-04-06 | 阿里巴巴集团控股有限公司 | Commodity recommendation method and device |
| CN106708821A (en) * | 2015-07-21 | 2017-05-24 | 广州市本真网络科技有限公司 | User personalized shopping behavior-based commodity recommendation method |
| CN106485562A (en) * | 2015-09-01 | 2017-03-08 | 苏宁云商集团股份有限公司 | A kind of commodity information recommendation method based on user's history behavior and system |
| CN107274242A (en) * | 2016-04-08 | 2017-10-20 | 上海旭薇物联网科技有限公司 | A kind of Method of Commodity Recommendation based on association analysis algorithm |
| CN106600372A (en) * | 2016-12-12 | 2017-04-26 | 武汉烽火信息集成技术有限公司 | Commodity recommending method and system based on user behaviors |
| CN107154109A (en) * | 2017-06-02 | 2017-09-12 | 深圳正品创想科技有限公司 | A kind of commodity rendering method, device and self-service cabinet |
| CN107392718A (en) * | 2017-07-26 | 2017-11-24 | 四川长虹电器股份有限公司 | Method of Commodity Recommendation |
| CN107464162A (en) * | 2017-07-28 | 2017-12-12 | 腾讯科技（深圳）有限公司 | Commodity association method, apparatus and computer-readable recording medium |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112749322A (en) * | 2019-10-31 | 2021-05-04 | 阿里巴巴集团控股有限公司 | Commodity object information recommendation method and device and electronic equipment |
| CN111144971A (en) * | 2019-11-28 | 2020-05-12 | 上海宝尊电子商务有限公司 | Left-side expanded screening bullet frame type commodity selector interactive design |
| CN110889747A (en) * | 2019-12-02 | 2020-03-17 | 腾讯科技（深圳）有限公司 | Commodity recommendation method, commodity recommendation device, commodity recommendation system, computer equipment and storage medium |
| CN110889747B (en) * | 2019-12-02 | 2023-05-09 | 腾讯科技（深圳）有限公司 | Commodity recommendation method, device, system, computer equipment and storage medium |
| CN111738802A (en) * | 2020-06-30 | 2020-10-02 | 广东奥园奥买家电子商务有限公司 | Introduction method, device and equipment of E-commerce commodities |
| CN112036988A (en) * | 2020-09-24 | 2020-12-04 | 上海风秩科技有限公司 | Label generation method and device, storage medium and electronic equipment |
| CN112036988B (en) * | 2020-09-24 | 2023-04-07 | 上海风秩科技有限公司 | Label generation method and device, storage medium and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| TW201928838A (en) | 2019-07-16 |
| TWI665630B (en) | 2019-07-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109961345A (en) | Interactive Method of Commodity Recommendation and non-transitory computer-readable medium | |
| US11080314B2 (en) | Dynamic search suggestion and category specific completion | |
| US10922737B2 (en) | Interactive product recommendation method and non-transitory computer-readable medium | |
| US8560398B1 (en) | Method and system for providing item recommendations | |
| US7979462B2 (en) | Head-to-head comparisons | |
| US20190156395A1 (en) | System and Method for Analyzing and Searching for Features Associated with Objects | |
| US20130091013A1 (en) | Presenting Targeted Social Advertisements | |
| US11204785B1 (en) | Parameterized user interface for capturing user feedback | |
| US9633392B2 (en) | Integrated finding experience systems and methods | |
| US9817846B1 (en) | Content selection algorithms | |
| US20180240158A1 (en) | Computer implemented system and method for customer profiling using micro-conversions via machine learning | |
| US9594540B1 (en) | Techniques for providing item information by expanding item facets | |
| US11636313B2 (en) | Recommendation system based on neural network models to improve efficiencies in interacting with e-commerce platforms | |
| US9799065B1 (en) | Associating items based at least in part on physical location information | |
| US10417687B1 (en) | Generating modified query to identify similar items in a data store | |
| US11062371B1 (en) | Determine product relevance | |
| KR20100044394A (en) | Method and server for searching commodity | |
| US20130054501A1 (en) | Optimizing selection and ordering of items displayed | |
| US11972468B2 (en) | Decision organizer | |
| US9652792B1 (en) | Dynamically generating resource tracking codes | |
| Balyan et al. | Using Product Meta Information for Bias Removal in E-Commerce Grid Search. | |
| Gill et al. | Leveraging meta-information of products to eliminate bias in an e-commerce grid search | |
| Sinha et al. | Improving marketing interactions by mining sequences | |
| WO2021076810A1 (en) | Graphical user interface with correlated and uncorrelated constituents | |
| CN114021000A (en) | Commodity recommendation method and device, storage medium and electronic equipment |
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 |