CN109766491A - Product search method, device, computer equipment and storage medium - Google Patents
Product search method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN109766491A CN109766491A CN201811546846.XA CN201811546846A CN109766491A CN 109766491 A CN109766491 A CN 109766491A CN 201811546846 A CN201811546846 A CN 201811546846A CN 109766491 A CN109766491 A CN 109766491A
- Authority
- CN
- China
- Prior art keywords
- commodity
- micro
- expression
- matching
- 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 43
- 230000014509 gene expression Effects 0.000 claims abstract description 234
- 230000036651 mood Effects 0.000 claims description 54
- 238000004590 computer program Methods 0.000 claims description 29
- 230000009471 action Effects 0.000 claims description 22
- 238000010195 expression analysis Methods 0.000 claims description 16
- 238000004364 calculation method Methods 0.000 claims description 14
- 239000000284 extract Substances 0.000 claims description 10
- 238000013145 classification model Methods 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 9
- 238000010191 image analysis Methods 0.000 claims description 2
- 239000000047 product Substances 0.000 description 35
- 238000012216 screening Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 9
- 230000001815 facial effect Effects 0.000 description 8
- 238000004458 analytical method Methods 0.000 description 5
- 238000013135 deep learning Methods 0.000 description 5
- 238000013528 artificial neural network Methods 0.000 description 3
- 230000006698 induction Effects 0.000 description 3
- 238000003062 neural network model Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 239000006227 byproduct Substances 0.000 description 2
- 238000003066 decision tree Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 230000013016 learning Effects 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 238000012163 sequencing technique Methods 0.000 description 2
- 238000004804 winding Methods 0.000 description 2
- 206010027940 Mood altered Diseases 0.000 description 1
- 230000003796 beauty Effects 0.000 description 1
- 230000004397 blinking Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 239000013065 commercial product Substances 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000004424 eye movement Effects 0.000 description 1
- 210000004709 eyebrow Anatomy 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
This application involves big data fields, and in particular to a kind of product search method, device, computer equipment and storage medium.The described method includes: receiving commercial articles searching instruction, and commodity keyword is extracted from commercial articles searching instruction；Search the matching commodity with the commodity Keywords matching；Calculate the matching degree of each the matching commodity and the commodity keyword；Obtain micro- expression label of each matching commodity；The matching commodity are ranked up to obtain ranking results according to the matching degree and micro- expression label；Commercial articles searching result is generated according to the ranking results.Its favorite commodity can be recommended to user timely and reasonably using this method, sales volume is promoted, also increase the flowing of access of cell phone software, website or webpage.
Description
Technical field
This application involves field of computer technology, more particularly to a kind of product search method, device, computer equipment and
Storage medium.
Background technique
With the continuous development of Internet technology, the various aspects lived to people bring convenient, more and more people
It is more likely to purchase article on line.
When user carries out commercial articles searching, all kinds of shopping websites, shopping APP generally record data according to the browsing of user
Commercial product recommending is carried out to the commodity searched.But data are recorded by the browsing of user to determine what the hobby of user obtained
Recommendation results be it is more unilateral, the recommendation effect for causing all kinds of shopping websites, shopping APP etc. to push commodity to user is poor.
Summary of the invention
Based on this, it is necessary to which in view of the above technical problems, providing one kind can be the effective Recommendations search result of user
Product search method, device, computer equipment and storage medium.
A kind of product search method, which comprises
Commercial articles searching instruction is received, and extracts commodity keyword from commercial articles searching instruction；
Search the matching commodity with the commodity Keywords matching；
Calculate the matching degree of each the matching commodity and the commodity keyword；
Obtain micro- expression label of each matching commodity；
The matching commodity are ranked up to obtain ranking results according to the matching degree and micro- expression label；
Commercial articles searching result is generated according to the ranking results.
In one of the embodiments, before the reception commercial articles searching instruction, further includes:
When the details page for detecting merchandising is opened, the current face image of user is acquired；
Micro- Expression analysis is carried out to the current face image, obtains presetting micro- table with the current face images match
Feelings；
It described preset micro- expression according to matched and sets micro- expression label；
Obtain active user's mark；
Active user mark, micro- expression label and the merchandising are associated storage.
It is described in one of the embodiments, that micro- Expression analysis is carried out to the current face image, it obtains working as with described
Front face images match presets micro- expression, comprising:
Face feature point is extracted from the current face image；
Face action feature is calculated according to the face feature point；
The face action feature is inputted into micro- expression classification model and obtains each probability value for presetting micro- expression；
Micro- expression is preset with the described of the current face images match according to the calculated probability value is selected.
It is described in one of the embodiments, that micro- Expression analysis is carried out to the current face image, it obtains working as with described
Front face images match presets micro- expression, comprising:
Face feature point is extracted from the current face image；
Face action feature is calculated according to the face feature point；
The face action feature is inputted into micro- expression classification model and obtains each probability value for presetting micro- expression；
Micro- expression is preset with the described of the current face images match according to the calculated probability value is selected.
The matching commodity of the lookup and the commodity Keywords matching in one of the embodiments, comprising:
The commodity to be selected of lookup names and the commodity Keywords matching；
Obtain active user's mark；
User information corresponding with active user mark is searched, and user's portrait mark is calculated according to the user information
Label；
Obtain the corresponding history purchase user data of each commodity to be selected；
User data is bought according to the history and user portrait label screen to the commodity to be selected
To matching commodity.
In one of the embodiments, it is described according to the matching degree and micro- expression label to the matching commodity into
Row sequence obtains before ranking results, further includes:
Micro- expression label of the matching commodity is identified；
When identifying micro- expression label includes detesting label, the corresponding matching commodity are deleted.
The matching according to the matching degree and micro- expression label to lookup in one of the embodiments,
Commodity are ranked up to obtain ranking results, comprising:
Obtain the corresponding expression coefficient of micro- expression label；
Obtain active user's mark；
User information corresponding with active user mark is searched, and user's portrait mark is calculated according to the user information
Label；
Search the corresponding recommendation weight of user's portrait label；
Go out to recommend numerical value according to the matching degree, the expression coefficient and the recommendation weight calculation；
The matching commodity found are ranked up to obtain ranking results according to the recommendation numerical value.
A kind of commercial articles searching device, described device include:
Extraction module is instructed, for receiving commercial articles searching instruction, and extracts commodity key from commercial articles searching instruction
Word；
Commodity searching module, for searching and the matching commodity of the commodity Keywords matching；
Matching degree computing module, for calculating the matching degree of each the matching commodity and the commodity keyword；
Label acquisition module, for obtaining micro- expression label of each matching commodity；
Sorting module, for being ranked up to obtain to the matching commodity according to the matching degree and micro- expression label
Ranking results；
Search result generation module, for generating commercial articles searching result according to the ranking results.
A kind of computer equipment, including memory and processor, the memory are stored with computer program, the processing
The step of device realizes the above method when executing the computer program.
A kind of computer readable storage medium, is stored thereon with computer program, and the computer program is held by processor
The step of above method is realized when row.
Above-mentioned product search method, device, computer equipment and storage medium, according to the matching degree of commodity and micro- expression mark
Label the commodity found are ranked up, and according to ranking results generate commercial articles searching as a result, not only can timely and reasonably to
User recommends its favorite commodity, promotes sales volume, also increases the flowing of access of cell phone software, website or webpage.Moreover, quotient
Product search result is generated for user, improves user's shopping experience.
Detailed description of the invention
Fig. 1 is the application scenario diagram of product search method in one embodiment；
Fig. 2 is the flow diagram of product search method in one embodiment；
Fig. 3 is the flow diagram of product search method in one embodiment；
Fig. 4 is the flow diagram of micro- Expression analysis step in another embodiment；
Fig. 5 is the flow diagram of micro- expression label setting procedure in another embodiment；
Fig. 6 is the flow diagram that commodity finding step is matched in one embodiment；
Fig. 7 is the flow diagram that commodity sequence step is matched in another embodiment；
Fig. 8 is the structural block diagram of commercial articles searching device in one embodiment；
Fig. 9 is the internal structure chart of computer equipment in one embodiment.
Specific embodiment
It is with reference to the accompanying drawings and embodiments, right in order to which the objects, technical solutions and advantages of the application are more clearly understood
The application is further elaborated.It should be appreciated that specific embodiment described herein is only used to explain the application, not
For limiting the application.
Product search method provided by the present application can be applied in application environment as shown in Figure 1.Wherein, terminal 102
It is communicated by network with server 104.Wherein, terminal 102 can be, but not limited to be various personal computers, notebook electricity
Brain, smart phone, tablet computer and portable intelligent device, server 104 can use independent server either multiple clothes
The server cluster of business device composition is realized.Terminal 102 receives the commodity such as the product name of commodity to be retrieved of user's input and closes
Keyword, when user's confirmation needs to scan for, terminal 102 generates commercial articles searching instruction；Terminal 102 can refer to commercial articles searching
Order is sent to server 104；After server 104 receives commercial articles searching instruction, to extract user defeated from commercial articles searching instruction
The commodity keyword entered；Server 104 searches the matching commodity with commodity Keywords matching again；Server 104 calculates matching quotient
The matching degree of product and commodity keyword；Server 104 obtains micro- expression label of matching commodity；Server 104 can according to
Matching commodity are ranked up to obtain ranking results with degree and micro- expression label；Server 104 can be generated according to ranking results
Commercial articles searching result.
In one embodiment, as shown in Fig. 2, providing a kind of product search method, it is applied in Fig. 1 in this way
It is illustrated for server 104, comprising the following steps:
Step 202, commercial articles searching instruction is received, and extracts commodity keyword from commercial articles searching instruction.
Commercial articles searching instruction is used to indicate the commodity of the commodity Keywords matching of search and user's input, inputs containing user
The commodity keyword such as the product name of commodity to be retrieved.Commodity keyword can be the title of commodity to be retrieved, commodity classification
And/or corresponding brand name etc..For example, commodity keyword can be " mobile phone " etc..
Server 104 can receive the commercial articles searching instruction that terminal 102 is sent, and extract from commercial articles searching instruction
Commodity keyword.
Step 204, the matching commodity with the commodity Keywords matching are searched.
Server 104 can search the matching commodity with commodity Keywords matching according to pre-defined rule.Matching commodity can be with
It is title and the completely the same merchandising of commodity keyword, is also possible to the merchandising in title comprising commodity keyword,
Being also possible to title and commodity keyword has partial words or the consistent merchandising of phrase.Pre-defined rule may is that when commodity close
When keyword includes by product name, then determine that corresponding merchandising is the matching commodity to match with commodity keyword；It is predetermined
Rule is also possible to: when commodity keyword is with the partial words of product name or consistent phrase, then determining corresponding merchandising
For the matching commodity to match with commodity keyword.
Step 206, the matching degree of each the matching commodity and the commodity keyword is calculated.
Server 104 obtains matching commodity and commodity by calculating the title of matching commodity with the matching degree of commodity keyword
The matching degree of keyword.It can be previously set when product name and commodity keyword are completely the same, matching degree is the first numerical value；
When commodity keyword includes by product name, matching degree is second value；When commodity keyword and product name have partial words
Or phrase it is consistent when, matching degree is third value, and the first numerical value > second value > third value.Calculation can also be previously set
Method calculates the character match rate of commodity keyword and product name, and using character match rate as matching commodity and commodity keyword
Matching degree.
Step 208, micro- expression label of each matching commodity is obtained.
Micro- expression label is micro- expression of the face-image according to historical viewings user when browsing to merchandising
What analysis generated.Server 104 obtains micro- table when user browses merchandising by carrying out micro- Expression analysis to face-image
Feelings information, and according to micro- expression label of micro- expression information setting merchandising.Each merchandising can be with only one micro- table
Feelings label can also have multiple micro- expression labels.Micro- expression label, which can have, to be liked label, sad label, detests label, is surprised
Label etc..Server 104 successively obtains the corresponding micro- expression label of each matching commodity.
Step 210, the matching commodity are ranked up according to the matching degree and micro- expression label and are sorted
As a result.
Server 104 comprehensively considers matching degree and micro- expression label and is ranked up to obtain ranking results to matching commodity.
Such as expression coefficient can be set to each micro- expression label in advance, server 104 obtains the corresponding expression of each micro- expression label
Coefficient, then the product value of matching degree Yu expression coefficient is calculated, from big to small according to the product value of matching degree and expression coefficient then
Matching commodity are ranked up to obtain ranking results.
Step 212, commercial articles searching result is generated according to the ranking results.
Server 104 can generate commercial articles searching as a result, commercial articles searching result is then sent to end according to ranking results
End 102, terminal 102 shows commercial articles searching result.Ranking results can also be transmitted directly to terminal by server 104
102, terminal 102 can generate commercial articles searching result according to ranking results.
In above-mentioned product search method, the commodity found are arranged according to the matching degree of commodity and micro- expression label
Sequence, and commercial articles searching is generated as a result, not only its favorite commodity can be recommended to user timely and reasonably according to ranking results, it mentions
Sales volume is risen, the flowing of access of cell phone software, website or webpage is also increased.Moreover, commercial articles searching is the result is that according to history quotient
Product browse what big data was generated for user, can obtain more preferably recommendation effect, improve user's shopping experience.
In one embodiment, as shown in figure 3, method is further comprising the steps of before receiving commercial articles searching instruction:
Step 302, when the details page for detecting merchandising is opened, the current face image of user is acquired.
Details page is used to introduce the commodity details of merchandising.The details page of the detection merchandising of terminal 102
Whether it is turned on, when terminal 102 detects the details page unlatching of merchandising, terminal 102 acquires the current face of user
Image.Current face image is the user's face image of the terminal shooting in user's operation terminal, and user's face image can be with
It is one to multiple.When user's face image is only one, which is exactly current face image；Work as user's face
When image is multiple, can set wherein a certain user's face image can also set a few use as current face image
Family face-image is current face image.
Step 304, micro- Expression analysis is carried out to the current face image, obtained and the current face images match
Preset micro- expression.
Specifically, terminal 102 directly can carry out micro- Expression analysis to current face image, can also be by current face figure
As being uploaded to server 104, micro- Expression analysis is carried out by server 104.The neural network mould that terminal 102 can be completed by building
Type or 3D faceform extract characteristics of image from current face image, then analyze characteristics of image, and search
The preset micro- expression to match with characteristics of image, and then the probability value of each micro- expression is obtained, it is determined according to probability value pre-
If micro- expression.Micro- expression screening quantity can be previously set in terminal, will arrange by presetting in micro- expression after the sequence of probability value size
Micro- expression of presetting in forefront screens, and the quantity filtered out is consistent with micro- expression sieve access amount, for example, can be by micro- expression
Sieve access amount is set as 5 etc..Micro- expression probability value screening threshold value can also be previously set in terminal, and probability value is greater than micro- expression
Micro- expression of presetting of probability value screening threshold value screens, such as micro- expression probability value screening threshold value can be 50%.
For example, when the characteristics of image that terminal 102 is extracted from current face image has " ceiling ", " narrowing one's eyes ", " mouth
Angle raises up ", " dew tooth ", by image characteristic analysis obtain " narrowing one's eyes ", " corners of the mouth raises up ", " dew tooth " with it is preset
Micro- expression matching, and the probability value of each micro- expression is respectively 40%, 80% and 10%.Micro- expression probability value screens threshold value
50%.It therefore, is " corners of the mouth raises up " with micro- expression of presetting of current face images match, and the probability value for presetting micro- expression is
80%.
Step 306, it described preset micro- expression according to matched and sets micro- expression label.
Terminal 102 can set micro- expression label according to micro- expression and corresponding probability value is preset.Micro- expression label can
To be set by the user or terminal default setting, may include like label, sad label, detest label, surprised label etc. it is micro-
Expression label.Terminal can preset the micro- expression label of micro- expression judgement according to probability value is maximum, also available each default
Mood score value of micro- expression under each micro- expression label calculates each micro- expression according to the probability value and mood score value for presetting micro- expression
The corresponding mood score of label, and then according to micro- expression label of mood score judgement merchandising.
Step 308, active user's mark is obtained.
Active user's mark is the mark of active user for identification, can be account, cell-phone number, the identity of active user
Card number etc..Terminal 102 obtains active user's mark.
Step 310, active user mark, micro- expression label and the merchandising are associated storage.
Terminal 102 identifies active user, micro- expression label and merchandising are associated storage, so as to be directed to user into
Row personalized recommendation.
In above-mentioned product search method, by acquiring and identifying that user is current when browsing the details page of merchandising
Face-image, and obtain presetting micro- expression, then basis presets micro- expression label of micro- expression judgement merchandising, and then will work as
Preceding user identifier, micro- expression label and merchandising are associated storage, thus for user construct individuation data library, for use
When family scans for recommending, recommendation results are more in line with the expection of user, and then improve user's shopping experience.
In one embodiment, as shown in figure 4, carrying out micro- Expression analysis to the current face image, obtain with it is described
Current face images match presets micro- expression, specifically includes the following steps:
Step 402, face feature point is extracted from the current face image.
Face feature point is the characteristic point of face and face mask, such as the characteristic coordinates of eyes, mouth, nose, eyebrow.
Before carrying out facial feature extraction, server/terminal can be pre-processed current face image, obtain meeting criterion of identification
Current face image.Specifically, server/terminal can pass through preparatory trained 3D faceform or deep learning mind
Face feature point extraction is carried out to current face image through network.
Step 404, face action feature is calculated according to the face feature point.
Server/terminal can be passed through again based on the face feature point extracted preparatory trained 3D faceform or
Deep learning neural network model extracts face action feature from current face image, each face that can also will be extracted
Characteristic point inputs corresponding face action feature calculation model after being classified, obtain corresponding facial motion characteristic, for example, will belong to
The available face action feature about eye of eye movement model is inputted in the face feature point of eye, feature of such as blinking narrows eye
Feature, feature of staring etc..3D faceform, deep learning neural network model, face action feature calculation model all pass through
The training of multiple facial image deep learnings is obtained in advance.The facial image that facial image can be user is also possible to masses
Facial image.
Step 406, the face action feature is inputted into micro- expression classification model and obtains each probability value for presetting micro- expression.
Server/terminal can be according to 3D faceform or deep learning neural network model or face action feature
Computation model calculates the value of each face action feature, and face action feature and value are inputted trained micro- table in advance
In mutual affection class model, the various probability values for presetting micro- expression are obtained, at this point, the sum of all values for presetting micro- expression are 1.Micro- table
Mutual affection class model can be a variety of for classifying using SVM classifier, deep neural network learning model, Decision-Tree Classifier Model etc.
Model, micro- expression classification model is by advance obtaining the training of the face action features of multiple facial images.
Step 408, it is preset according to selected described with the current face images match of the calculated probability value micro-
Expression.
Micro- expression screening quantity can be previously set in terminal, will come by presetting in micro- expression after the sequence of probability value size
Micro- expression of presetting in forefront screens, and the quantity filtered out is consistent with micro- expression sieve access amount, for example, micro- expression can be sieved
Access amount is set as 5 etc..The matching screening process for presetting micro- expression can carry out in the terminal, can also will be current by terminal
Face-image is sent in server and carries out, and the micro- expression of presetting filtered out is returned to terminal by server.
In one embodiment, as shown in figure 5, according to it is matched it is described preset micro- expression and set micro- expression label, have
Following steps:
Step 502, the mood score value preset under the corresponding each mood mode of micro- expression is obtained.
Specifically, mood mode can be by user setting or terminal default setting, such as may include liking, being sad, detesting
Dislike, is surprised etc..Different micro- expressions and the correlation between each mood mode are different, so mood score value is also different, for example,
Micro- expression " corners of the mouth raises up " with like, it is sad, detest, the corresponding mood score value of the moods mode such as surprised be respectively 7,0,0 and
1；Micro- expression " looks is winding " with like, it is sad, detest, the corresponding mood score value of the moods mode such as surprised is respectively 8,0,0, with
And 3.
Step 504, each mood mode pair is calculated according to the probability value for presetting micro- expression and the mood score value
The mood score answered.
Terminal is superimposed after each mood score value for presetting micro- expression under each mood mode is multiplied with probability value respectively, is obtained
Mood score.For example, micro- expression of presetting that terminal obtains includes that looks is winding, laughs heartily, exudes tenderness and love, optimistic open-minded, happiness
Smiling face opens 5 kinds, and corresponding probability value is respectively 25%, 10%, 8%, 15% and 12%, presets micro- expression for 5 kinds and likes mode
Under mood score value be respectively 8,10,6,6 and 9, then like the mood under mode to be scored at 25%*8+10%*10+8%*6+
15%*6+12%*9=5.46.
Step 506, each mood score input label computation model is obtained into micro- expression label.
After terminal calculates the mood score under be in a bad mood mode, it will be obtained in each mood score input label computation model
To micro- expression label.Label computation model can use SVM classifier, deep neural network learning model, decision tree classification mould
A variety of models for classification such as type, micro- expression classification model pass through in advance to multiple micro- expression labels and the training of mood score
It obtains.
In above-mentioned product search method, it will preset that micro- expression is corresponding with micro- expression label, obtained mood numerical value can be with
The current state for more accurately embodying user reduces the judgement fault of micro- expression label.
In another embodiment, as shown in fig. 6, searching the matching commodity with the commodity Keywords matching, specifically have
Following steps:
Step 602, the commodity to be selected of lookup names and the commodity Keywords matching.
Server 104 can be title and quotient according to the matched commodity to be selected of commodity keyword lookup names, commodity to be selected
The completely the same merchandising of product keyword is also possible to the merchandising in title comprising commodity keyword, is also possible to name
Claim have partial words or the consistent merchandising of phrase with commodity keyword.For example, when commodity keyword and product name have to
, it is specified that corresponding merchandising is the matching commodity to match with commodity keyword when few a part of word or consistent phrase.
Step 604, active user's mark is obtained.
Server 104 can obtain active user's mark of active user from terminal.Server can also be useful from carrying
Active user's mark is extracted in the commercial articles searching instruction of family mark.
Step 606, user information corresponding with active user mark is searched, and is calculated and is used according to the user information
Family portrait label.
Server 104 searches user information corresponding with active user's mark, and user information may include user's gender, year
The information such as age, hobby, income level, history purchaser record.Server carries out portrait analysis according to user's information and obtains
User's portrait label of user.User draw a portrait label can be by big data induction and conclusion go out, for example, it may be Bai Fu
Beauty, scientific and technological intelligent, makeups intelligent, health intelligent, Gao Fushuai, explorer etc..Different user portrait label can match difference
User information.Same user information can match multiple users' portrait labels.
Step 608, it obtains the corresponding history of each commodity to be selected and buys user data.
Server 104 obtains the corresponding history purchase user data of each commodity to be selected, and history purchase user data can be used
In know history buy crowd, and determine history purchase user common point.History purchase user data may include purchase pin
Sell historical user's label etc. of the history purchase user of commodity.
Step 610, according to the history buy user data and the user draw a portrait label to the commodity to be selected into
Row screening obtains matching commodity.
Server 104 can buy user data to history and analyze, and server calculates each historical user's label and going through
History buys probability of occurrence in the label of user, and is carried out from big to small to all historical user's labels according to the size of probability of occurrence
Sequence chooses predetermined quantity and comes general portrait label of the historical user's label of preamble as history purchase user, general picture
As label be it is all purchase merchandisings history buy user's common label that may be present, be by big data induction and conclusion
Out.Server calculates the similarity of general portrait label and user's portrait label, and from big to small according to the size of similarity
Commodity to be selected are ranked up, are then matching quotient by the commodity to be selected stood out screening according to the commodity amount that can be shown
Product.When user draws a portrait label there are multiple users, server calculates the phase of each user's portrait label and general portrait label
Like degree, and therefrom chooses and draw a portrait label as sort by with the maximum user of general portrait label similarity.
In above-mentioned product search method, the user information for analyzing user determines user's portrait label, and is purchased according to history
It buys user data and determines target customers, and draw a portrait label for target customers' setting general-purpose, then drawn a portrait label by user
It determines whether commodity to be selected meet the hobby of user with general portrait label, to be preferably that user recommends, improves and use
The usage experience at family.
In one embodiment, the matching commodity are ranked up according to the matching degree and micro- expression label
To before ranking results, method is further comprising the steps of: identifying to micro- expression label of the matching commodity；Work as knowledge
Not Chu micro- expression label include when detesting label, deleting corresponding matching commodity.
When user browses same matching commodity under different conditions, micro- expression label that terminal 102 identifies may be different
It causes, thus same matching commodity can have multiple micro- expression labels, micro- expression label can include detest label simultaneously, sad
Label likes label etc..Terminal 102 obtains all corresponding micro- expression labels of matching commodity for finding, and to finding
Micro- expression label of matching commodity carries out recognition and verification one by one, when terminal 102 identifies that micro- expression label includes detesting label,
Terminal deletes corresponding matching commodity according to label is detested, and then terminal is further according to the matching degree and micro- expression label pair
The matching commodity are ranked up to obtain ranking results.
In above-mentioned product search method, the matching commodity of user's detest are actively deleted, user is avoided to browse to detest
Commodity are matched, the usage experience of user is improved.
In one embodiment, as shown in fig. 7, according to the matching degree and micro- expression label to described in lookup
It is ranked up to obtain ranking results with commodity, comprising the following steps:
Step 702, the corresponding expression coefficient of micro- expression label is obtained.
Different micro- expression labels all corresponds to different expression coefficients, such as likes what the expression coefficient of label can be set
Numerical value is relatively high, and it is relatively low to detest the numerical value that the expression coefficient of label can be set.Expression coefficient can be by user setting or end
Hold self-setting.Expression coefficient is for embodying the possible situation when user is in corresponding micro- expression label.Terminal 102 obtains
The corresponding expression coefficient of micro- expression label.
Step 704, active user's mark is obtained.
Terminal 102 obtains active user's mark of user.Active user's mark can be inputted by user or terminal is direct
Read the active user's mark being previously stored.
Step 706, user information corresponding with active user mark is searched, and is calculated and is used according to the user information
Family portrait label.
Terminal 102 searches user information corresponding with active user's mark, and user information may include user's gender, year
The information such as age, hobby, income level, history purchaser record.Terminal carries out portrait analysis according to user's information and is used
User's portrait label at family.User draw a portrait label can be by big data induction and conclusion go out, be also possible to user according to right
The understanding of itself and set, for example, it may be Bai Fumei, scientific and technological intelligent, makeups intelligent, health intelligent, Gao Fushuai, explorer
Etc..Different user portrait label can match different user informations.Same user information can match multiple user's portraits
Label.
Step 708, the corresponding recommendation weight of user's portrait label is searched.
It is set in advance by terminal for recommending weight, is that matching degree and expression coefficient are respectively shared when calculating recommendation numerical value
Ratio.Terminal 102 searches each user and draws a portrait the corresponding recommendation weight of label, determines matching degree and expression coefficient in calculating
Weight.
Step 710, go out to recommend numerical value according to the matching degree, the expression coefficient and the recommendation weight calculation.
Terminal 102 is matched according to weight of the recommendation weight to the matching degree and expression coefficient recommended in numerical computational formulas
It sets, then substitutes into recommend to calculate in numerical computational formulas by the numerical value of matching degree and expression coefficient and recommend numerical value.
Step 712, the matching commodity found are ranked up to obtain ranking results according to the recommendation numerical value.
Terminal 102 according to recommend numerical value size it is descending to the matching commodity found be ranked up, and will matching
Sequence after commodity sequence is as ranking results.
In above-mentioned product search method, user's portrait label is determined according to user information, and according to user's portrait label
The expression coefficient of matching degree and micro- expression label is configured, the demand of user is comprehensively considered, is searched timely and reasonably for user
Rope simultaneously recommends its favorite commodity, improves user's shopping experience.
It should be understood that although each step in the flow chart of Fig. 2-7 is successively shown according to the instruction of arrow,
These steps are not that the inevitable sequence according to arrow instruction successively executes.Unless expressly stating otherwise herein, these steps
Execution there is no stringent sequences to limit, these steps can execute in other order.Moreover, at least one in Fig. 2-7
Part steps may include that perhaps these sub-steps of multiple stages or stage are not necessarily in synchronization to multiple sub-steps
Completion is executed, but can be executed at different times, the execution sequence in these sub-steps or stage is also not necessarily successively
It carries out, but can be at least part of the sub-step or stage of other steps or other steps in turn or alternately
It executes.
In one embodiment, as shown in figure 8, providing a kind of commercial articles searching device, comprising: instruction extraction module 802,
Commodity searching module 804, matching degree computing module 806, label acquisition module 808, sorting module 810 and search result generate mould
Block 812, in which:
Extraction module 802 is instructed, for receiving commercial articles searching instruction, and commodity is extracted from commercial articles searching instruction and closes
Keyword.
Commodity searching module 804, for searching and the matching commodity of the commodity Keywords matching.
Matching degree computing module 806, for calculating the matching degree of each the matching commodity and the commodity keyword.
Label acquisition module 808, for obtaining micro- expression label of each matching commodity.
Sorting module 810, for being ranked up according to the matching degree and micro- expression label to the matching commodity
Obtain ranking results.
Search result generation module 812, for generating commercial articles searching result according to the ranking results.
In one embodiment, device further includes image capture module, micro- Expression analysis module, micro- expression label setting mould
Block, user identifier obtain module and memory module, in which:
Image capture module, for acquiring the current face of user when the details page for detecting merchandising is opened
Image.
Micro- Expression analysis module obtains working as front with described for carrying out micro- Expression analysis to the current face image
Portion's images match presets micro- expression.
Micro- expression label setting module, for described presetting micro- expression according to matched and setting micro- expression label.
User identifier obtains module, for obtaining active user's mark.
Memory module, for active user mark, micro- expression label to be associated with the merchandising
Storage.
In another embodiment, micro- Expression analysis module includes feature point extraction unit, feature calculation unit, probability value meter
Calculate unit and micro- expression selection unit, in which:
Feature point extraction unit, for extracting face feature point from the current face image.
Feature calculation unit, for face action feature to be calculated according to the face feature point.
Probability value computing unit obtains each presetting micro- table for the face action feature to be inputted micro- expression classification model
The probability value of feelings.
Micro- expression selection unit, for being selected and the current face images match according to the calculated probability value
It is described to preset micro- expression.
In one embodiment, micro- expression label setting module includes mood score value acquiring unit, mood score calculating list
Member and label acquiring unit, in which:
Mood score value acquiring unit, for obtaining the mood score value preset under the corresponding each mood mode of micro- expression；
Mood score calculation unit, for calculating each institute according to the probability value for presetting micro- expression and the mood score value
State the corresponding mood score of mood mode；
Label acquiring unit, for each mood score input label computation model to be obtained micro- expression label.
In some embodiments, commodity searching module includes commodity searching unit to be selected, user identifier acquiring unit, user
Tag determination unit, historical data acquiring unit and screening unit, in which:
Commodity searching unit to be selected, the commodity to be selected for lookup names and the commodity Keywords matching.
User identifier acquiring unit, for obtaining active user's mark.
User tag determination unit, for searching user information corresponding with active user mark, and according to described
User information calculates user's portrait label.
Historical data acquiring unit, for obtaining the corresponding history purchase user data of each commodity to be selected.
Screening unit, for buying user data and user portrait label to the quotient to be selected according to the history
Product are screened to obtain matching commodity.
In some embodiments, device further includes tag recognition module and removing module, in which:
Tag recognition module is identified for micro- expression label to the matching commodity.
Removing module, for deleting the corresponding matching when identifying micro- expression label includes detesting label
Commodity.
In another embodiment, sorting module includes expression coefficient acquiring unit, user identifier acquiring unit, user tag
Determination unit, recommends numerical calculation unit and sequencing unit at advowson weight searching unit, in which:
Expression coefficient acquiring unit, for obtaining the corresponding expression coefficient of micro- expression label；
User identifier acquiring unit, for obtaining active user's mark；
User tag determination unit, for searching user information corresponding with active user mark, and according to described
User information calculates user's portrait label；
Advowson weight searching unit, for searching the corresponding recommendation weight of user's portrait label；
Recommend numerical calculation unit, for going out according to the matching degree, the expression coefficient and the recommendation weight calculation
Recommend numerical value；
Sequencing unit obtains sequence knot for being ranked up according to the recommendation numerical value to the matching commodity found
Fruit.
Specific about commercial articles searching device limits the restriction that may refer to above for product search method, herein not
It repeats again.Modules in above-mentioned commercial articles searching device can be realized fully or partially through software, hardware and combinations thereof.On
Stating each module can be embedded in the form of hardware or independently of in the processor in computer equipment, can also store in a software form
In memory in computer equipment, the corresponding operation of the above modules is executed in order to which processor calls.
In one embodiment, a kind of computer equipment is provided, which can be server, internal junction
Composition can be as shown in Figure 9.The computer equipment include by system bus connect processor, memory, network interface and
Database.Wherein, the processor of the computer equipment is for providing calculating and control ability.The memory packet of the computer equipment
Include non-volatile memory medium, built-in storage.The non-volatile memory medium is stored with operating system, computer program and data
Library.The built-in storage provides environment for the operation of operating system and computer program in non-volatile memory medium.The calculating
The database of machine equipment is for storing commercial articles searching data, user information, merchandising and its history purchase user data etc.
Deng.The network interface of the computer equipment is used to communicate with external terminal by network connection.The computer program is processed
To realize a kind of product search method when device executes.
It will be understood by those skilled in the art that structure shown in Fig. 9, only part relevant to application scheme is tied
The block diagram of structure does not constitute the restriction for the computer equipment being applied thereon to application scheme, specific computer equipment
It may include perhaps combining certain components or with different component layouts than more or fewer components as shown in the figure.
In one embodiment, a kind of computer equipment, including memory and processor are provided, which is stored with
Computer program, the processor perform the steps of when executing computer program
Commercial articles searching instruction is received, and extracts commodity keyword from commercial articles searching instruction；
Search the matching commodity with the commodity Keywords matching；
Calculate the matching degree of each the matching commodity and the commodity keyword；
Obtain micro- expression label of each matching commodity；
The matching commodity are ranked up to obtain ranking results according to the matching degree and micro- expression label；
Commercial articles searching result is generated according to the ranking results.
In one embodiment, before the step of receiving commercial articles searching instruction is realized when processor executes computer program,
It is also used to: when the details page for detecting merchandising is opened, acquiring the current face image of user；To the current face
Image carries out micro- Expression analysis, obtains presetting micro- expression with the current face images match；According to matched described default
Micro- expression sets micro- expression label；Obtain active user's mark；By the active user mark, micro- expression label with it is described
Merchandising is associated storage.
In one embodiment, it is realized when processor executes computer program and micro- expression is carried out to the current face image
Analysis, when obtaining the step for presetting micro- expression with the current face images match, is also used to: from the current face image
Middle extraction face feature point；Face action feature is calculated according to the face feature point；The face action feature is defeated
Expression classification model obtains each probability value for presetting micro- expression in a subtle way；It is selected and described current according to the calculated probability value
The described of facial images match presets micro- expression.
In one embodiment, it is realized when processor executes computer program and described preset micro- expression according to matched and set
It when the step of micro- expression label, is also used to: obtaining the mood score value preset under the corresponding each mood mode of micro- expression；According to
The probability value for presetting micro- expression and the mood score value calculate the corresponding mood score of each mood mode；It will be each described
Mood score input label computation model obtains micro- expression label.
In one embodiment, searched with the commodity Keywords matching is realized when processor executes computer program
When step with commodity, it is also used to: the commodity to be selected of lookup names and the commodity Keywords matching；Obtain active user's mark
Know；User information corresponding with active user mark is searched, and user's portrait label is calculated according to the user information；It obtains
Take the corresponding history purchase user data of each commodity to be selected；User data is bought according to the history and the user draws
As label screens the commodity to be selected to obtain matching commodity.
In one embodiment, it realizes when processor executes computer program according to the matching degree and micro- expression mark
It before label are ranked up the step of obtaining ranking results to the matching commodity, is also used to: to the described micro- of the matching commodity
Expression label is identified；When identifying micro- expression label includes detesting label, the corresponding matching commodity are deleted.
In one embodiment, it realizes when processor executes computer program according to the matching degree and micro- expression mark
It when label are ranked up to obtain the step of ranking results to the matching commodity of lookup, is also used to: obtaining micro- expression label
Corresponding expression coefficient；Obtain active user's mark；User information corresponding with active user mark is searched, and according to institute
It states user information and calculates user's portrait label；Search the corresponding recommendation weight of user's portrait label；According to the matching degree,
The expression coefficient and the recommendation weight calculation go out to recommend numerical value；According to the recommendation numerical value to the matching quotient found
Product are ranked up to obtain ranking results.
In one embodiment, a kind of computer readable storage medium is provided, computer program is stored thereon with, is calculated
Machine program performs the steps of when being executed by processor
Commercial articles searching instruction is received, and extracts commodity keyword from commercial articles searching instruction；
Search the matching commodity with the commodity Keywords matching；
Calculate the matching degree of each the matching commodity and the commodity keyword；
Obtain micro- expression label of each matching commodity；
The matching commodity are ranked up to obtain ranking results according to the matching degree and micro- expression label；
Commercial articles searching result is generated according to the ranking results.
In one embodiment, it is realized when computer program is executed by processor before receiving the step of commercial articles searching instructs
It is also used to: when the details page for detecting merchandising is opened, acquiring the current face image of user；To the current face
Image carries out micro- Expression analysis, obtains presetting micro- expression with the current face images match；According to matched described default
Micro- expression sets micro- expression label；Obtain active user's mark；By the active user mark, micro- expression label with it is described
Merchandising is associated storage.
In one embodiment, it is realized when computer program is executed by processor and micro- table is carried out to the current face image
Mutual affection analysis, obtains being also used to when the step for presetting micro- expression with the current face images match: from the current face figure
Face feature point is extracted as in；Face action feature is calculated according to the face feature point；By the face action feature
It inputs micro- expression classification model and obtains each probability value for presetting micro- expression；Work as according to the calculated probability value is selected with described
The described of front face images match presets micro- expression.
In one embodiment, computer program is realized when being executed by processor described preset micro- expression and sets according to matched
It is also used to when the step of fixed micro- expression label: obtaining the mood score value preset under the corresponding each mood mode of micro- expression；Root
The corresponding mood score of each mood mode is calculated according to the probability value for presetting micro- expression and the mood score value；By each institute
It states mood score input label computation model and obtains micro- expression label.
In one embodiment, it realizes and searches and the commodity Keywords matching when computer program is executed by processor
It is also used to when matching the step of commodity: the commodity to be selected of lookup names and the commodity Keywords matching；Obtain active user's mark
Know；User information corresponding with active user mark is searched, and user's portrait label is calculated according to the user information；It obtains
Take the corresponding history purchase user data of each commodity to be selected；User data is bought according to the history and the user draws
As label screens the commodity to be selected to obtain matching commodity.
In one embodiment, it realizes when computer program is executed by processor according to the matching degree and micro- expression
Label is also used to before being ranked up the step of obtaining ranking results to the matching commodity: to the described micro- of the matching commodity
Expression label is identified；When identifying micro- expression label includes detesting label, the corresponding matching commodity are deleted.
In one embodiment, it realizes when computer program is executed by processor according to the matching degree and micro- expression
Label is also used to when being ranked up to the matching commodity of lookup and obtain the step of ranking results: obtaining micro- expression label
Corresponding expression coefficient；Obtain active user's mark；User information corresponding with active user mark is searched, and according to institute
It states user information and calculates user's portrait label；Search the corresponding recommendation weight of user's portrait label；According to the matching degree,
The expression coefficient and the recommendation weight calculation go out to recommend numerical value；According to the recommendation numerical value to the matching quotient found
Product are ranked up to obtain ranking results.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the computer program can be stored in a non-volatile computer
In read/write memory medium, the computer program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein,
To any reference of memory, storage, database or other media used in each embodiment provided herein,
Including non-volatile and/or volatile memory.Nonvolatile memory may include read-only memory (ROM), programming ROM
(PROM), electrically programmable ROM (EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include
Random access memory (RAM) or external cache.By way of illustration and not limitation, RAM is available in many forms,
Such as static state RAM (SRAM), dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), enhancing
Type SDRAM (ESDRAM), synchronization link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM
(RDRAM), direct memory bus dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
Each technical characteristic of above embodiments can be combined arbitrarily, for simplicity of description, not to above-described embodiment
In each technical characteristic it is all possible combination be all described, as long as however, the combination of these technical characteristics be not present lance
Shield all should be considered as described in this specification.
The several embodiments of the application above described embodiment only expresses, the description thereof is more specific and detailed, but simultaneously
It cannot therefore be construed as limiting the scope of the patent.It should be pointed out that coming for those of ordinary skill in the art
It says, without departing from the concept of this application, various modifications and improvements can be made, these belong to the protection of the application
Range.Therefore, the scope of protection shall be subject to the appended claims for the application patent.
Claims (10)
1. a kind of product search method, which comprises
Commercial articles searching instruction is received, and extracts commodity keyword from commercial articles searching instruction；
Search the matching commodity with the commodity Keywords matching；
Calculate the matching degree of each the matching commodity and the commodity keyword；
Obtain micro- expression label of each matching commodity；
The matching commodity are ranked up to obtain ranking results according to the matching degree and micro- expression label；
Commercial articles searching result is generated according to the ranking results.
2. the method according to claim 1, wherein before reception commercial articles searching instruction, further includes:
When the details page for detecting merchandising is opened, the current face image of user is acquired；
Micro- Expression analysis is carried out to the current face image, obtains presetting micro- expression with the current face images match；
It described preset micro- expression according to matched and sets micro- expression label；
Obtain active user's mark；
Active user mark, micro- expression label and the merchandising are associated storage.
3. according to the method described in claim 2, it is characterized in that, described carry out micro- expression point to the current face image
Analysis obtains presetting micro- expression with the current face images match, comprising:
Face feature point is extracted from the current face image；
Face action feature is calculated according to the face feature point；
The face action feature is inputted into micro- expression classification model and obtains each probability value for presetting micro- expression；
Micro- expression is preset with the described of the current face images match according to the calculated probability value is selected.
4. according to the method described in claim 2, it is characterized in that, described described preset micro- expression and set micro- table according to matched
Feelings label, comprising:
Obtain the mood score value preset under the corresponding each mood mode of micro- expression；
The corresponding mood score of each mood mode is calculated according to the probability value for presetting micro- expression and the mood score value；
Each mood score input label computation model is obtained into micro- expression label.
5. the method according to claim 1, wherein the matching quotient of the lookup and the commodity Keywords matching
Product, comprising:
The commodity to be selected of lookup names and the commodity Keywords matching；
Obtain active user's mark；
User information corresponding with active user mark is searched, and user's portrait label is calculated according to the user information；
Obtain the corresponding history purchase user data of each commodity to be selected；
It buys user data and the user label of drawing a portrait according to the history commodity to be selected are screened to obtain
With commodity.
6. the method according to claim 1, wherein described according to the matching degree and micro- expression label pair
The matching commodity are ranked up to obtain before ranking results, further includes:
Micro- expression label of the matching commodity is identified；
When identifying micro- expression label includes detesting label, the corresponding matching commodity are deleted.
7. the method according to claim 1, wherein described according to the matching degree and micro- expression label pair
The matching commodity searched are ranked up to obtain ranking results, comprising:
Obtain the corresponding expression coefficient of micro- expression label；
Obtain active user's mark；
User information corresponding with active user mark is searched, and user's portrait label is calculated according to the user information；
Search the corresponding recommendation weight of user's portrait label；
Go out to recommend numerical value according to the matching degree, the expression coefficient and the recommendation weight calculation；
The matching commodity found are ranked up to obtain ranking results according to the recommendation numerical value.
8. a kind of commercial articles searching device, which is characterized in that described device includes:
Extraction module is instructed, extracts commodity keyword for receiving commercial articles searching instruction, and from commercial articles searching instruction；
Commodity searching module, for searching and the matching commodity of the commodity Keywords matching；
Matching degree computing module, for calculating the matching degree of each the matching commodity and the commodity keyword；
Label acquisition module, for obtaining micro- expression label of each matching commodity；
Sorting module is sorted for being ranked up according to the matching degree and micro- expression label to the matching commodity
As a result；
Search result generation module, for generating commercial articles searching result according to the ranking results.
9. a kind of computer equipment, including memory and processor, the memory are stored with computer program, feature exists
In the step of processor realizes any one of claims 1 to 7 the method when executing the computer program.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer program
The step of method described in any one of claims 1 to 7 is realized when being executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811546846.XA CN109766491A (en) | 2018-12-18 | 2018-12-18 | Product search method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811546846.XA CN109766491A (en) | 2018-12-18 | 2018-12-18 | Product search method, device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109766491A true CN109766491A (en) | 2019-05-17 |
Family
ID=66451444
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811546846.XA Pending CN109766491A (en) | 2018-12-18 | 2018-12-18 | Product search method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109766491A (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110222252A (en) * | 2019-06-14 | 2019-09-10 | 宜春宜联科技有限公司 | Information retrieval method, device and equipment |
| CN110298245A (en) * | 2019-05-22 | 2019-10-01 | 平安科技（深圳）有限公司 | Interest collection method, device, computer equipment and storage medium |
| CN110555167A (en) * | 2019-08-22 | 2019-12-10 | 上海摩库数据技术有限公司 | Chemical industry-based associated commodity recommendation method |
| CN110737833A (en) * | 2019-09-29 | 2020-01-31 | 海南省火蓝数据有限公司 | commodity pushing method based on recommendation degree |
| CN111062788A (en) * | 2019-12-28 | 2020-04-24 | 广东奥园奥买家电子商务有限公司 | E-commerce platform commodity recommendation method, device and equipment based on search |
| CN111079555A (en) * | 2019-11-25 | 2020-04-28 | Oppo广东移动通信有限公司 | User preference degree determining method and device, electronic equipment and readable storage medium |
| CN111598671A (en) * | 2020-07-20 | 2020-08-28 | 北京每日优鲜电子商务有限公司 | Commodity recommendation method based on human-computer interaction |
| CN111753158A (en) * | 2020-01-20 | 2020-10-09 | 全息空间(深圳)智能科技有限公司 | Live broadcast platform commodity searching method and device, computer equipment and storage medium |
| CN112052388A (en) * | 2020-08-20 | 2020-12-08 | 深思考人工智能科技(上海)有限公司 | Method and system for recommending gourmet stores |
| CN113256397A (en) * | 2021-07-02 | 2021-08-13 | 佛山市墨纳森智能科技有限公司 | Commodity recommendation method and system based on big data and computer-readable storage medium |
| CN113297499A (en) * | 2021-06-22 | 2021-08-24 | 北京创世路信息技术有限公司 | Information recommendation system, method, computer equipment and storage medium |
| CN113723984A (en) * | 2021-03-03 | 2021-11-30 | 京东城市(北京)数字科技有限公司 | Method and device for acquiring crowd consumption portrait information and storage medium |
| CN117333250A (en) * | 2023-08-22 | 2024-01-02 | 广州市玄武无线科技股份有限公司 | Dynamic configuration method and system for mall labels |
Citations (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR100687906B1 (en) * | 2005-12-31 | 2007-02-27 | 주식회사지앤지커머스 | System for recommendation the goods and method therefor |
| JP2009134656A (en) * | 2007-12-01 | 2009-06-18 | Fujifilm Corp | Commodity presentation system and commodity search server |
| CN102402765A (en) * | 2011-12-27 | 2012-04-04 | 纽海信息技术（上海）有限公司 | Electronic-commerce recommendation method based on user expression analysis |
| CN103294677A (en) * | 2012-02-22 | 2013-09-11 | 阿里巴巴集团控股有限公司 | Searching method of electronic commerce search engine and electronic commerce search engine |
| CN103838883A (en) * | 2014-03-31 | 2014-06-04 | 上海久科信息技术有限公司 | Intelligent SKU matching method |
| CN104317945A (en) * | 2014-10-31 | 2015-01-28 | 亚信科技（南京）有限公司 | E-commerce website commodity recommending method on basis of search behaviors |
| JP2015133033A (en) * | 2014-01-15 | 2015-07-23 | 株式会社日本総合研究所 | Recommendation device, recommendation method and program |
| CN105320706A (en) * | 2014-08-05 | 2016-02-10 | 阿里巴巴集团控股有限公司 | Processing method and device of search result |
| US20160103833A1 (en) * | 2012-06-01 | 2016-04-14 | Google Inc. | Ranking query results using biometric parameters |
| CN105677810A (en) * | 2015-12-30 | 2016-06-15 | 天津盛购科技发展有限公司 | Online shopping product searching system based on keyword analysis |
| CN105894357A (en) * | 2016-03-30 | 2016-08-24 | 北京金山安全软件有限公司 | Commodity information pushing method and device |
| US20160247083A1 (en) * | 2015-02-25 | 2016-08-25 | International Business Machines Corporation | Recommendation for an individual based on a mood of the individual |
| CN106096026A (en) * | 2016-06-24 | 2016-11-09 | 武汉合创源科技有限公司 | A kind of product search method and system |
| CN106327232A (en) * | 2015-07-01 | 2017-01-11 | 向莉妮 | Personalized commodity recommendation system |
| CN107369075A (en) * | 2017-07-26 | 2017-11-21 | 万帮充电设备有限公司 | Methods of exhibiting, device and the electronic equipment of commodity |
| KR20180002197A (en) * | 2016-06-29 | 2018-01-08 | 주식회사 엘지유플러스 | Emotional Chatting Application, Chatting Service Method Of Thereof And Chatting Server |
| US20180089715A1 (en) * | 2016-09-26 | 2018-03-29 | Vicomi | System and method for analyzing and predicting emotion reaction |
| CN107944913A (en) * | 2017-11-21 | 2018-04-20 | 重庆邮电大学 | High potential user's purchase intention Forecasting Methodology based on big data user behavior analysis |
| CN108108380A (en) * | 2016-11-25 | 2018-06-01 | 阿里巴巴集团控股有限公司 | Search ordering method, searching order device, searching method and searcher |
| CN108182624A (en) * | 2017-12-26 | 2018-06-19 | 努比亚技术有限公司 | Method of Commodity Recommendation, server and computer readable storage medium |
| CN108572992A (en) * | 2017-03-14 | 2018-09-25 | 苏宁云商集团股份有限公司 | A kind of method and device of commodity sequence |
| CN108717663A (en) * | 2018-05-18 | 2018-10-30 | 深圳壹账通智能科技有限公司 | Face label fraud judgment method, device, equipment and medium based on micro- expression |
| CN108846724A (en) * | 2018-06-06 | 2018-11-20 | 北京京东尚科信息技术有限公司 | Data analysing method and system |
-
2018
- 2018-12-18 CN CN201811546846.XA patent/CN109766491A/en active Pending
Patent Citations (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR100687906B1 (en) * | 2005-12-31 | 2007-02-27 | 주식회사지앤지커머스 | System for recommendation the goods and method therefor |
| JP2009134656A (en) * | 2007-12-01 | 2009-06-18 | Fujifilm Corp | Commodity presentation system and commodity search server |
| CN102402765A (en) * | 2011-12-27 | 2012-04-04 | 纽海信息技术（上海）有限公司 | Electronic-commerce recommendation method based on user expression analysis |
| CN103294677A (en) * | 2012-02-22 | 2013-09-11 | 阿里巴巴集团控股有限公司 | Searching method of electronic commerce search engine and electronic commerce search engine |
| US20160103833A1 (en) * | 2012-06-01 | 2016-04-14 | Google Inc. | Ranking query results using biometric parameters |
| JP2015133033A (en) * | 2014-01-15 | 2015-07-23 | 株式会社日本総合研究所 | Recommendation device, recommendation method and program |
| CN103838883A (en) * | 2014-03-31 | 2014-06-04 | 上海久科信息技术有限公司 | Intelligent SKU matching method |
| CN105320706A (en) * | 2014-08-05 | 2016-02-10 | 阿里巴巴集团控股有限公司 | Processing method and device of search result |
| CN104317945A (en) * | 2014-10-31 | 2015-01-28 | 亚信科技（南京）有限公司 | E-commerce website commodity recommending method on basis of search behaviors |
| US20160247083A1 (en) * | 2015-02-25 | 2016-08-25 | International Business Machines Corporation | Recommendation for an individual based on a mood of the individual |
| CN106327232A (en) * | 2015-07-01 | 2017-01-11 | 向莉妮 | Personalized commodity recommendation system |
| CN105677810A (en) * | 2015-12-30 | 2016-06-15 | 天津盛购科技发展有限公司 | Online shopping product searching system based on keyword analysis |
| CN105894357A (en) * | 2016-03-30 | 2016-08-24 | 北京金山安全软件有限公司 | Commodity information pushing method and device |
| CN106096026A (en) * | 2016-06-24 | 2016-11-09 | 武汉合创源科技有限公司 | A kind of product search method and system |
| KR20180002197A (en) * | 2016-06-29 | 2018-01-08 | 주식회사 엘지유플러스 | Emotional Chatting Application, Chatting Service Method Of Thereof And Chatting Server |
| US20180089715A1 (en) * | 2016-09-26 | 2018-03-29 | Vicomi | System and method for analyzing and predicting emotion reaction |
| CN108108380A (en) * | 2016-11-25 | 2018-06-01 | 阿里巴巴集团控股有限公司 | Search ordering method, searching order device, searching method and searcher |
| CN108572992A (en) * | 2017-03-14 | 2018-09-25 | 苏宁云商集团股份有限公司 | A kind of method and device of commodity sequence |
| CN107369075A (en) * | 2017-07-26 | 2017-11-21 | 万帮充电设备有限公司 | Methods of exhibiting, device and the electronic equipment of commodity |
| CN107944913A (en) * | 2017-11-21 | 2018-04-20 | 重庆邮电大学 | High potential user's purchase intention Forecasting Methodology based on big data user behavior analysis |
| CN108182624A (en) * | 2017-12-26 | 2018-06-19 | 努比亚技术有限公司 | Method of Commodity Recommendation, server and computer readable storage medium |
| CN108717663A (en) * | 2018-05-18 | 2018-10-30 | 深圳壹账通智能科技有限公司 | Face label fraud judgment method, device, equipment and medium based on micro- expression |
| CN108846724A (en) * | 2018-06-06 | 2018-11-20 | 北京京东尚科信息技术有限公司 | Data analysing method and system |
Non-Patent Citations (3)
| Title |
|---|
| 李彤等: "基于人脸认知模式的相似脸搜索", 《中国图象图形学报》, no. 10, 16 October 2016 (2016-10-16) * |
| 温云辉等: "多关键词查找相关产品的一种实现", 《黎明职业大学学报》, no. 04, 31 December 2009 (2009-12-31) * |
| 郭俊霞等: "基于用户浏览轨迹的商品推荐", 《计算机科学》, vol. 43, no. 12, 31 January 2016 (2016-01-31) * |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110298245B (en) * | 2019-05-22 | 2023-10-13 | 平安科技（深圳）有限公司 | Interest collection method, interest collection device, computer equipment and storage medium |
| CN110298245A (en) * | 2019-05-22 | 2019-10-01 | 平安科技（深圳）有限公司 | Interest collection method, device, computer equipment and storage medium |
| CN110222252A (en) * | 2019-06-14 | 2019-09-10 | 宜春宜联科技有限公司 | Information retrieval method, device and equipment |
| CN110555167A (en) * | 2019-08-22 | 2019-12-10 | 上海摩库数据技术有限公司 | Chemical industry-based associated commodity recommendation method |
| CN110737833A (en) * | 2019-09-29 | 2020-01-31 | 海南省火蓝数据有限公司 | commodity pushing method based on recommendation degree |
| CN111079555A (en) * | 2019-11-25 | 2020-04-28 | Oppo广东移动通信有限公司 | User preference degree determining method and device, electronic equipment and readable storage medium |
| CN111062788A (en) * | 2019-12-28 | 2020-04-24 | 广东奥园奥买家电子商务有限公司 | E-commerce platform commodity recommendation method, device and equipment based on search |
| CN111753158A (en) * | 2020-01-20 | 2020-10-09 | 全息空间(深圳)智能科技有限公司 | Live broadcast platform commodity searching method and device, computer equipment and storage medium |
| CN111598671A (en) * | 2020-07-20 | 2020-08-28 | 北京每日优鲜电子商务有限公司 | Commodity recommendation method based on human-computer interaction |
| CN111598671B (en) * | 2020-07-20 | 2020-10-30 | 北京每日优鲜电子商务有限公司 | Commodity recommendation method based on human-computer interaction |
| CN112052388A (en) * | 2020-08-20 | 2020-12-08 | 深思考人工智能科技(上海)有限公司 | Method and system for recommending gourmet stores |
| CN113723984A (en) * | 2021-03-03 | 2021-11-30 | 京东城市(北京)数字科技有限公司 | Method and device for acquiring crowd consumption portrait information and storage medium |
| CN113297499A (en) * | 2021-06-22 | 2021-08-24 | 北京创世路信息技术有限公司 | Information recommendation system, method, computer equipment and storage medium |
| CN113256397A (en) * | 2021-07-02 | 2021-08-13 | 佛山市墨纳森智能科技有限公司 | Commodity recommendation method and system based on big data and computer-readable storage medium |
| CN117333250A (en) * | 2023-08-22 | 2024-01-02 | 广州市玄武无线科技股份有限公司 | Dynamic configuration method and system for mall labels |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109766491A (en) | Product search method, device, computer equipment and storage medium | |
| US9633045B2 (en) | Image ranking based on attribute correlation | |
| CN107424043B (en) | Product recommendation method and device and electronic equipment | |
| CN108874992B (en) | Public opinion analysis method, system, computer equipment and storage medium | |
| Kucer et al. | Leveraging expert feature knowledge for predicting image aesthetics | |
| CN109783730A (en) | Products Show method, apparatus, computer equipment and storage medium | |
| US20200342320A1 (en) | Non-binary gender filter | |
| US20100313141A1 (en) | System and Method for Learning User Genres and Styles and for Matching Products to User Preferences | |
| CN111460130A (en) | Information recommendation method, device, equipment and readable storage medium | |
| JP2012529122A (en) | System and method for learning user genre and style and matching products to user preferences | |
| CN108334632B (en) | Entity recommendation method and device, computer equipment and computer-readable storage medium | |
| CN108509466A (en) | A kind of information recommendation method and device | |
| US10776417B1 (en) | Parts-based visual similarity search | |
| US10074032B2 (en) | Using images and image metadata to locate resources | |
| US11238515B1 (en) | Systems and method for visual search with attribute manipulation | |
| US11682060B2 (en) | Methods and apparatuses for providing search results using embedding-based retrieval | |
| US20220358552A1 (en) | Methods and systems for hair-service based digital image searching and ranking | |
| CN109800319A (en) | Image processing method, device, computer equipment and storage medium | |
| Park et al. | Personalized image aesthetic quality assessment by joint regression and ranking | |
| CN115147130A (en) | Problem prediction method, apparatus, storage medium, and program product | |
| CN111327930A (en) | Method and device for acquiring target object, electronic equipment and storage medium | |
| CN114579843A (en) | Personalized search method and device, computer equipment and storage medium | |
| Ak et al. | Fashionsearchnet-v2: learning attribute representations with localization for image retrieval with attribute manipulation | |
| CN116823410A (en) | Data processing method, object processing method, recommending method and computing device | |
| CN110889748A (en) | Store-merchant platform product recommendation method and device, computer equipment and storage medium |
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 |