CN104951966A - Clothes commodity recommending method and device - Google Patents
Clothes commodity recommending method and device Download PDFInfo
- Publication number
- CN104951966A CN104951966A CN201510408418.0A CN201510408418A CN104951966A CN 104951966 A CN104951966 A CN 104951966A CN 201510408418 A CN201510408418 A CN 201510408418A CN 104951966 A CN104951966 A CN 104951966A
- Authority
- CN
- China
- Prior art keywords
- dress ornament
- classification
- collocation
- attribute tags
- commodity
- 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
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
An embodiment of the invention provides a clothes commodity recommending method and device. The clothes commodity recommending method comprises the following steps: a clothes picture is acquired; a first clothes category and at least one first clothes attribute tag of first clothes are recognized from the clothes picture; at least one second clothes category and at least one second clothes attribute tag which are matched with the first clothes are acquired from a preset clothes matching engine according to the first clothes category and the at least one first clothes attribute tag; information, matched with the second clothes category and the second clothes attribute tag, of a matching clothes commodity is selected from a clothes commodity database, wherein information of multiple clothes commodities and data of clothes categories and clothes attribute tags are stored in the clothes commodity database; the information of the matching clothes commodity is recommended to a user. The clothes commodity recommending method and device can provide the user with professional clothes matching suggestions automatically and save labor consumption.
Description
Technical field
The present invention relates to picture recognition technical field, particularly relate to a kind of method and the device of recommending dress ornament commodity.
Background technology
Loving beauty is part of human nature.Research shows, everyone has 55% to depend on our dressing to the primae impressionis that others stays for we.Visible, dress plays considerable role in our daily life.Corresponding, in life, a lot of people does not know how to go to arrange in pairs or groups oneself dress ornament to dress up oneself.
In prior art, individual mainly contains two kinds of methods when arranging in pairs or groups oneself dress ornament: a kind of method looks for private style counsellor to oneself providing suitable clothing matching, and another kind of mode uses for reference other people wear the clothes through carrying out clothing matching for oneself.For first method, private style counsellor can provide the clothing matching suggestion of specialty really, but cost is higher, is difficult to scale.For second method, other people wear the clothes through being applicable to oneself, and not architectonical.
Summary of the invention
Embodiments of the invention provide a kind of method and the device of recommending dress ornament commodity, automatically to provide specialized clothing matching to advise to user, save manpower and expend.
According to an aspect of the present invention, the invention provides a kind of method of recommending dress ornament commodity, described method comprises: obtain dress ornament picture; From the first dress ornament classification and at least one first dress ornament attribute tags of described dress ornament picture recognition first dress ornament; Obtain and at least one second dress ornament classification of described first clothing matching and at least one second dress ornament attribute tags from the clothing matching engine preset according to described first dress ornament classification and at least one first dress ornament attribute tags; From dress ornament merchandising database, choose the information of the collocation dress ornament commodity mated with described second dress ornament classification and the second dress ornament attribute tags, in described dress ornament merchandising database, have the information of multiple dress ornament commodity and the data of dress ornament classification and dress ornament attribute tags; By the information recommendation of described collocation dress ornament commodity to user.
Alternatively, described clothing matching engine has the collocation grade of fit weights between multiple candidate's dress ornament classification and between multiple candidate's dress ornament attribute tags, described acquisition from the clothing matching engine preset according to described first dress ornament classification and at least one the first dress ornament attribute tags comprises with at least one second dress ornament classification of described first clothing matching and the process of at least one the second dress ornament attribute tags: to arrange in pairs or groups grade of fit weights from the described clothing matching engine classification obtained respectively between described first dress ornament classification and multiple candidate's dress ornament classification, and obtain described attribute collocation grade of fit weights between at least one first dress ornament attribute tags and multiple candidate's dress ornament attribute tags respectively, classification collocation grade of fit weights according to obtaining correspondingly choose candidate's dress ornament classification of the first predetermined number as described second dress ornament classification, and correspondingly choose candidate's dress ornament attribute tags of the second predetermined number as described second dress ornament attribute tags according to the attribute collocation grade of fit weights of described second dress ornament classification and acquisition.
Alternatively, described method also comprises: the personality data obtaining user's input; Obtain with described personality Data Matching according to predetermined individual character dress ornament recommendation rules and be applicable to multiple 3rd dress ornament classification and the 3rd dress ornament attribute tags of current environmental condition; Calculate the Similarity matching angle value of described 3rd dress ornament classification and the 3rd dress ornament attribute tags and described second dress ornament classification and the second dress ornament attribute tags respectively; According to the size of described Similarity matching angle value, described second dress ornament classification and the second dress ornament attribute tags are sorted.
Alternatively, the information of the multiple dress ornament commodity had in described dress ornament merchandising database comprises the picture of described multiple dress ornament commodity, and the described information recommendation by described collocation dress ornament commodity also comprises to the process of user: by the picture presentation of described collocation dress ornament commodity to user.
Alternatively, described method also comprises: the information choosing the similar dress ornament commodity mated with the first dress ornament attribute tags with described first dress ornament classification from dress ornament merchandising database, and recommends user.
According to a further aspect in the invention, the invention provides a kind of method of recommending dress ornament commodity, described method comprises: the personality data obtaining user; Obtain and multiple dress ornament classification of described personality Data Matching and multiple dress ornament attribute tags according to predetermined individual character dress ornament recommendation rules; The collocation result between described multiple dress ornament classification and between multiple dress ornament attribute tags is obtained by the clothing matching engine preset; From dress ornament merchandising database, choose the information of the collocation dress ornament commodity of coupling respectively according to described collocation result, in described dress ornament merchandising database, have the information of multiple dress ornament commodity and the data of dress ornament classification and dress ornament attribute tags; By the information recommendation of described collocation dress ornament commodity to user.
Alternatively, described acquisition according to predetermined individual character dress ornament recommendation rules comprises with multiple dress ornament classification of described personality Data Matching and the process of multiple dress ornament attribute tags: obtain with described personality Data Matching according to predetermined individual character dress ornament recommendation rules and be applicable to multiple dress ornament classification of current environmental condition and multiple dress ornament attribute tags.
Alternatively, described clothing matching engine has the collocation grade of fit weights between multiple candidate's dress ornament classification and between multiple candidate's dress ornament attribute tags, the process of the collocation result that the described clothing matching engine by presetting obtains between described multiple dress ornament classification and between multiple dress ornament attribute tags comprises: for any two the dress ornament classifications in the middle of described multiple dress ornament classification and multiple dress ornament attribute tags and any two dress ornament attribute tags, perform following process: obtain the classification collocation grade of fit weights between described two dress ornament classifications respectively from described clothing matching engine, and the attribute collocation grade of fit weights obtained respectively between described two dress ornament attribute tags, correspondingly choose the dress ornament classification collocation result of the first predetermined number according to the classification collocation grade of fit weights obtained, and correspondingly choose the first dress ornament attribute tags combination of the second predetermined number and the combination of the second dress ornament attribute tags according to the attribute collocation grade of fit weights of described dress ornament classification collocation result and acquisition and to arrange in pairs or groups result as attribute.
According to a further aspect in the invention, the invention provides a kind of device recommending dress ornament commodity, described device comprises: dress ornament picture acquiring unit, for obtaining dress ornament picture; Recognition unit, for from the first dress ornament classification of described dress ornament picture recognition first dress ornament and at least one first dress ornament attribute tags; Attribute collocation unit, for obtaining and at least one second dress ornament classification of described first clothing matching and at least one second dress ornament attribute tags from the clothing matching engine preset according to described first dress ornament classification and at least one first dress ornament attribute tags; Collocation merchandise news acquiring unit, for choosing the information of the collocation dress ornament commodity mated with described second dress ornament classification and the second dress ornament attribute tags from dress ornament merchandising database, in described dress ornament merchandising database, there are the information of multiple dress ornament commodity and the data of dress ornament classification and dress ornament attribute tags; Collocation merchandise news recommendation unit, for by the information recommendation of described collocation dress ornament commodity to user.
Alternatively, described clothing matching engine has the collocation grade of fit weights between multiple candidate's dress ornament classification and between multiple candidate's dress ornament attribute tags, described attribute collocation unit comprises: grade of fit weights obtain subelement, for obtaining the classification collocation grade of fit weights between described first dress ornament classification and multiple candidate's dress ornament classification respectively from described clothing matching engine, and obtain described attribute collocation grade of fit weights between at least one first dress ornament attribute tags and multiple candidate's dress ornament attribute tags respectively; Attribute chooses unit, for correspondingly choosing candidate's dress ornament classification of the first predetermined number as described second dress ornament classification according to the classification collocation grade of fit weights obtained, and correspondingly choose candidate's dress ornament attribute tags of the second predetermined number as described second dress ornament attribute tags according to the attribute collocation grade of fit weights of described second dress ornament classification and acquisition.
Alternatively, described device also comprises: personality acquiring unit, for obtaining the personality data of user's input; Personality attributes matching unit, for obtaining with described personality Data Matching according to predetermined individual character dress ornament recommendation rules and multiple 3rd dress ornament classification of applicable current environmental condition and the 3rd dress ornament attribute tags; Similarity matching angle value computing unit, for calculating the Similarity matching angle value of described 3rd dress ornament classification and the 3rd dress ornament attribute tags and described second dress ornament classification and the second dress ornament attribute tags respectively; Sequencing unit, for the size according to described Similarity matching angle value, sorts to described second dress ornament classification and the second dress ornament attribute tags; Described collocation merchandise news acquiring unit comprises: information chooses subelement, for choosing the information of the collocation dress ornament commodity mated with described second dress ornament classification and the second dress ornament attribute tags of the forward predetermined number that sorts from dress ornament merchandising database.
Alternatively, the information of the multiple dress ornament commodity had in described dress ornament merchandising database comprises the picture of described multiple dress ornament commodity, and described collocation merchandise news recommendation unit also comprises: display unit, for by the picture presentation of described collocation dress ornament commodity to user.
Alternatively, described device also comprises: similar merchandise news recommendation unit, for choosing the information of the similar dress ornament commodity mated with the first dress ornament attribute tags with described first dress ornament classification from dress ornament merchandising database, and recommends user.
According to a further aspect in the invention, the invention provides a kind of device recommending dress ornament commodity, described device comprises: personality acquiring unit, for obtaining the personality data of user; Match information acquiring unit, for obtaining and multiple dress ornament classification of described personality Data Matching and multiple dress ornament attribute tags according to predetermined individual character dress ornament recommendation rules; Collocation result acquiring unit, obtains the collocation result between described multiple dress ornament classification and between multiple dress ornament attribute tags for the clothing matching engine by presetting; Collocation merchandise news acquiring unit, for choosing the information of the collocation dress ornament commodity of coupling respectively from dress ornament merchandising database according to described collocation result, in described dress ornament merchandising database, there are the information of multiple dress ornament commodity and the data of dress ornament classification and dress ornament attribute tags; Collocation merchandise news recommendation unit, for by the information recommendation of described collocation dress ornament commodity to user.
Alternatively, described match information acquiring unit comprises: match information obtains subelement, for obtaining with described personality Data Matching according to predetermined individual character dress ornament recommendation rules and being applicable to multiple dress ornament classification of current environmental condition and multiple dress ornament attribute tags.
Alternatively, described clothing matching engine has the collocation grade of fit weights between multiple candidate's dress ornament classification and between multiple candidate's dress ornament attribute tags, described collocation result acquiring unit is used for for any two the dress ornament classifications in the middle of described multiple dress ornament classification and multiple dress ornament attribute tags and any two dress ornament attribute tags, perform following process: obtain the classification collocation grade of fit weights between described two dress ornament classifications respectively from described clothing matching engine, and obtain the attribute collocation grade of fit weights between described two dress ornament attribute tags respectively; Correspondingly choose the dress ornament classification collocation result of the first predetermined number according to the classification collocation grade of fit weights obtained, and correspondingly choose the first dress ornament attribute tags combination of the second predetermined number and the combination of the second dress ornament attribute tags according to the attribute collocation grade of fit weights of described dress ornament classification collocation result and acquisition and to arrange in pairs or groups result as attribute.
The method of the recommendation dress ornament commodity that the embodiment of the present invention provides and device, according to the Matching Relation between dress ornament classification and between dress ornament attribute tags, determine and the dress ornament classification of dress ornament picture match and dress ornament attribute tags or and multiple dress ornament classifications of personality Data Matching between and collocation result between multiple dress ornament attribute tags, and from dress ornament merchandising database, the information of corresponding collocation dress ornament commodity is chosen according to the dress ornament classification of described coupling and dress ornament attribute tags or described collocation result, finally by the information recommendation of described collocation dress ornament commodity to user, can automatically for user provides specialized clothing matching to advise, saving manpower expends.
Accompanying drawing explanation
Fig. 1 is the process flow diagram of the method for the recommendation dress ornament commodity that exemplary embodiment of the present one is shown;
Fig. 2 illustrates the schematic diagram recommending dress ornament commodity based on dress ornament picture;
Fig. 3 is the process flow diagram of the method for the recommendation dress ornament commodity that exemplary embodiment of the present two is shown;
Fig. 4 illustrates the schematic diagram based on personality data recommendation dress ornament commodity;
Fig. 5 is the logic diagram of the device of the recommendation dress ornament commodity that exemplary embodiment of the present three is shown;
Fig. 6 is the logic diagram of the device of the recommendation dress ornament commodity that exemplary embodiment of the present four is shown.
Embodiment
Basic conception of the present invention is, there is provided a kind of to recommend the method for dress ornament commodity and realize the device of method of described recommendation dress ornament commodity, for according to the Matching Relation between dress ornament classification and between dress ornament attribute tags, determine and the dress ornament classification of dress ornament picture match and dress ornament attribute tags or and multiple dress ornament classifications of personality Data Matching between and collocation result between multiple dress ornament attribute tags, and from dress ornament merchandising database, the information of corresponding collocation dress ornament commodity is chosen according to the dress ornament classification of described coupling and dress ornament attribute tags or described collocation result, finally by the information recommendation of described collocation dress ornament commodity to user.Correspondingly, the information of the dress ornament commodity stored in dress ornament merchandising database also needs at least to comprise the data of dress ornament classification about dress ornament commodity and dress ornament attribute tags.
Below in conjunction with accompanying drawing, the method for the recommendation dress ornament commodity of exemplary embodiment of the present and device are described in detail.
Embodiment one
Fig. 1 is the process flow diagram of the method for the recommendation dress ornament commodity that exemplary embodiment of the present one is shown.
With reference to Fig. 1, in step S110, obtain dress ornament picture.
Described dress ornament picture can be the dress ornament picture that mode that user passes through to take pictures obtains, and also can be the dress ornament picture on network or on various storage medium.
In step S120, from the first dress ornament classification and at least one first dress ornament attribute tags of described dress ornament picture recognition first dress ornament.
A kind of method and apparatus comprising the dress ornament classification of dress ornament picture and the information of (characteristic area) attribute from dress ornament picture recognition is disclosed in another patented claim that the name submitted on the same day applicant and the application is called " identifying mask method and the device of the method for dress ornament picture, dress ornament picture ".Particularly, according to the dress ornament disaggregated model set up in advance, obtain the information of dress ornament kind in described dress ornament picture; According to the dress ornament key point location model set up in advance, described dress ornament picture is positioned to the mark of key point; After this, according to the position of described dress ornament kind and locator key point, the picture region in representation feature region in dress ornament picture described at least one is extracted; The characteristic information representing this characteristic area is obtained respectively according to the provincial characteristics model of cognition corresponding with described characteristic area.Described characteristic information comprises the information of the attribute of dress ornament classification and/or characteristic area.
Correspondingly, in the process of step S120, the method recorded by another patented claim described goes out the first dress ornament classification and at least one first dress ornament attribute tags (corresponding to the information of the attribute in preceding feature region) of the first dress ornament described dress ornament picture from the dress ornament picture recognition obtained in step S110.
The dress ornament classification identified can be such as, the dress ornament classifications such as shirt, T-shirt, cotton dress, Western-style clothes, disjunctor dress, jeans, casual pants or pants, also can according to sex, wear region and divide further.Such as, such as man-jacket, man-trousers, female-jacket, female-half body skirt, female-one-piece dress, female-trousers and female-integral trousers etc. can be divided into; Or, further, be divided into female-jacket-shirt, female-half body skirt-a line skirt, man-jacket-jacket etc.
The dress ornament attribute tags identified can comprise at least one in clothing type, skirt type, pants type, collar, sleeve type, clothing length, skirt length, trousers length and sleeve length, and each dress ornament attribute tags has the label value of oneself.
In the present invention specifically implements, the attribute of the attribute region of daily common dress ornament and property value can be carried out division as shown in Table 1 and Table 2.
Table 1 dress ornament attribute and list of attribute values one
Table 2 dress ornament attribute and list of attribute values two
In step S130, obtain and at least one second dress ornament classification of described first clothing matching and at least one second dress ornament attribute tags from the clothing matching engine preset according to described first dress ornament classification and at least one first dress ornament attribute tags.
Alternatively, described clothing matching engine has the collocation grade of fit weights between multiple candidate's dress ornament classification and between multiple candidate's dress ornament attribute tags.Correspondingly, in step S130, obtain the classification collocation grade of fit weights between described first dress ornament classification and multiple candidate's dress ornament classification respectively from described clothing matching engine, and obtain described attribute collocation grade of fit weights between at least one first dress ornament attribute tags and multiple candidate's dress ornament attribute tags respectively; Classification collocation grade of fit weights according to obtaining correspondingly choose candidate's dress ornament classification of the first predetermined number as described second dress ornament classification, and correspondingly choose candidate's dress ornament attribute tags of the second predetermined number as described second dress ornament attribute tags according to the attribute collocation grade of fit weights of described second dress ornament classification and acquisition.
Particularly, after acquisition described classification collocation grade of fit weights, described classification grade of fit weights can be sorted according to size, and using candidate's dress ornament classification corresponding for the classification of the first the most forward for sequence predetermined number collocation grade of fit weights as described second dress ornament classification.After acquisition described attribute collocation grade of fit weights, described attribute grade of fit weights can be sorted according to size, and using the most forward for sequence and the candidate's dress ornament attribute tags being included in the second predetermined number in described second dress ornament classification as described second dress ornament attribute tags.
Such as, the dress ornament classification in described dress ornament picture is female-jacket, and dress ornament attribute tags is white, long sleeves etc.The classification collocation grade of fit weights obtained from described clothing matching engine are respectively skirt 1, middle skirt 0, longuette 0, so can using skirt as the second dress ornament classification; Correspondingly, the attribute grade of fit weights obtained from described clothing matching engine are black 1, khaki 0, white-1, so optional black is the second dress ornament attribute tags, in conjunction with the second dress ornament classification and the second dress ornament attribute tags, finally black skirt can be recommended client.
In step S140, from dress ornament merchandising database, choose the information of the collocation dress ornament commodity mated with described second dress ornament classification and the second dress ornament attribute tags.
Wherein, the information of multiple dress ornament commodity and the data of dress ornament classification and dress ornament attribute tags are had in described dress ornament merchandising database.
Particularly, in described dress ornament merchandising database, foundation has the information of dress ornament commodity, the mapping relations between dress ornament classification and dress ornament attribute tags.Correspondingly, after input the second dress ornament classification and the second dress ornament attribute tags in described dress ornament merchandising database, the information of the dress ornament commodity corresponding with the second dress ornament classification and the second dress ornament attribute tags can be obtained.
In step S150, by the information recommendation of described collocation dress ornament commodity to user.
Particularly, by the information recommendation of described collocation dress ornament commodity to user, clothing matching is carried out to facilitate user.
The method of the recommendation dress ornament commodity that the embodiment of the present invention provides, according to the Matching Relation between dress ornament classification and between dress ornament attribute tags, determine and the dress ornament classification of dress ornament picture match and dress ornament attribute tags, and from dress ornament merchandising database, the information of corresponding collocation dress ornament commodity is chosen according to the dress ornament classification of described coupling and dress ornament attribute tags, finally by the information recommendation of described collocation dress ornament commodity to user, automatically for user provides specialized clothing matching to advise, manpower can be saved and expends.
In order to provide personalized dress ornament commercial product recommending scheme to user, according to a preferred embodiment of the invention, the method for described recommendation dress ornament commodity also can comprise: the personality data (as height, body weight, shape of face, the colour of skin etc.) obtaining user's input; Obtain with described personality Data Matching according to predetermined individual character dress ornament recommendation rules and be applicable to multiple 3rd dress ornament classification and the 3rd dress ornament attribute tags of current environmental condition, to obtain dress ornament classification and the characteristic information of applicable user; Calculate the Similarity matching angle value of described 3rd dress ornament classification and the 3rd dress ornament attribute tags and described second dress ornament classification and the second dress ornament attribute tags respectively, thus calculate the degree of closeness of the classification of each collocation dress ornament and the dress ornament classification of characteristic index and applicable user and characteristic index; According to the size of described Similarity matching angle value, described second dress ornament classification and the second dress ornament attribute tags are sorted, thus before the second relatively high for Similarity matching angle value dress ornament classification and the second dress ornament attribute tags can being come.Correspondingly, step S140 can comprise: the information choosing the collocation dress ornament commodity mated with described second dress ornament classification and the second dress ornament attribute tags of the forward predetermined number that sorts from dress ornament merchandising database.
Alternatively, the information of the multiple dress ornament commodity had in described dress ornament merchandising database comprises the picture of described multiple dress ornament commodity, and the described information recommendation by described collocation dress ornament commodity also can comprise to the process of user: by the picture presentation of described collocation dress ornament commodity to user.By the picture presentation of described collocation dress ornament commodity to user, more directly perceived to the sensation of user, convenient user selects dress ornament commodity.
Alternatively, the method for the recommendation dress ornament commodity of the embodiment of the present invention also can comprise: the information choosing the similar dress ornament commodity mated with the first dress ornament attribute tags with described first dress ornament classification from dress ornament merchandising database, and recommends user.By the information recommendation of similar dress ornament commodity that mates with the first dress ornament attribute tags with described first dress ornament classification to user, facilitate user to select dependent merchandise, provide the user and select space larger.
Below for Fig. 2, the technical scheme of the method for recommendation dress ornament commodity of the present invention is illustrated.Fig. 2 illustrates the schematic diagram recommending dress ornament commodity based on dress ornament picture.Particularly, after acquisition dress ornament picture, first dress ornament classification and the dress ornament attribute tags of the first dress ornament is gone out from described dress ornament picture recognition, and after the personality data of input user, in conjunction with individual character dress ornament recommendation rules and clothing matching engine, obtain the dress ornament classification and dress ornament attribute tags of mating with dress ornament classification and the dress ornament attribute tags of the first dress ornament in dress ornament picture.Finally, user recommended by the picture retrieving corresponding dress ornament commodity in dress ornament merchandising database.As shown in Figure 2, the dress ornament classification of the dress ornament picture identified is female-jacket-shirt, dress ornament attribute tags comprises cardigan, single-breasted, conventional money etc., input personality data (female, 23 years old, 168cm, 50kg, A font, fair complexion is partially red) and environmental data (29 degree, fine day) after, in conjunction with individual character dress ornament recommendation rules and clothing matching engine, the information of dress ornament classification and the dress ornament attribute tags of arranging in pairs or groups with the dress ornament classification in dress ornament picture and dress ornament attribute tags can be obtained, namely dress ornament classification is female-half body skirt, dress ornament attribute tags comprises skirt, fishtail skirt, black etc.Finally, the information of the dress ornament classification of arranging in pairs or groups with the dress ornament classification in dress ornament picture and dress ornament attribute tags obtained and dress ornament attribute tags is inputted in dress ornament merchandising database, retrieves the dress ornament picture of arranging in pairs or groups with the dress ornament picture inputted at first, and show user.
Embodiment two
Fig. 3 illustrates that exemplary embodiment of the present recommends the schematic flow sheet two of the method for dress ornament commodity.
With reference to Fig. 3, in step S310, obtain the personality data of user.
Particularly, the personality data obtaining user in this step can include, but not limited to the information such as height, body weight, shape of face, the colour of skin.
In step S320, obtain and multiple dress ornament classification of described personality Data Matching and multiple dress ornament attribute tags according to predetermined individual character dress ornament recommendation rules.
Particularly, described individual character dress ornament recommendation rules can come from the style counsellor of specialty, also can come from the criterion of wearing the clothes of architectonical in life, described personalization rule of wearing the clothes can be personality data and the mapping relations between dress ornament classification and dress ornament attribute tags.Such as, build is the jacket (dress ornament class label) that fat high people is applicable to wearing V neck (dress ornament attribute tags), then can set up mapping relations between fat height and jacket and V are led.Be understandable that, personality data and be not probably map one by one between dress ornament classification and dress ornament attribute tags, such as, build is the jacket that fat high people is also applicable to wearing U neck.
Alternatively, described acquisition according to predetermined individual character dress ornament recommendation rules can comprise with multiple dress ornament classification of described personality Data Matching and the process of multiple dress ornament attribute tags: obtain with described personality Data Matching according to predetermined individual character dress ornament recommendation rules and be applicable to multiple dress ornament classification of current environmental condition and multiple dress ornament attribute tags.
Particularly, we obtain according to predetermined individual character dress ornament recommendation rules with multiple dress ornament classification of described personality Data Matching and multiple dress ornament attribute tags after, current environmental condition can be inputted further in individual character dress ornament recommendation rules and multiple dress ornament classification of mating before and multiple dress ornament attribute tags are screened.Now, need in individual character dress ornament recommendation rules to set up environmental baseline and the mapping relations between dress ornament classification and dress ornament attribute tags.
In step S330, obtain the collocation result between described multiple dress ornament classification and between multiple dress ornament attribute tags by the clothing matching engine preset.
Alternatively, described clothing matching engine has the collocation grade of fit weights between multiple candidate's dress ornament classification and between multiple candidate's dress ornament attribute tags, the process of the collocation result that the described clothing matching engine by presetting obtains between described multiple dress ornament classification and between multiple dress ornament attribute tags comprises: for any two the dress ornament classifications in the middle of described multiple dress ornament classification and multiple dress ornament attribute tags and any two dress ornament attribute tags, perform following process: obtain the classification collocation grade of fit weights between described two dress ornament classifications respectively from described clothing matching engine, and the attribute collocation grade of fit weights obtained respectively between described two dress ornament attribute tags, correspondingly choose the dress ornament classification collocation result of the first predetermined number according to the classification collocation grade of fit weights obtained, and correspondingly choose the first dress ornament attribute tags combination of the second predetermined number and the combination of the second dress ornament attribute tags according to the attribute collocation grade of fit weights of described dress ornament classification collocation result and acquisition and to arrange in pairs or groups result as attribute.
In step S340, from dress ornament merchandising database, choose the information of the collocation dress ornament commodity of coupling respectively according to described collocation result.
Wherein, the information of multiple dress ornament commodity and the data of dress ornament classification and dress ornament attribute tags are had in described dress ornament merchandising database.When retrieving in dress ornament merchandising database according to described collocation result, the information of the collocation dress ornament commodity mated with result of arranging in pairs or groups can be obtained.
In step S350, by the information recommendation of described collocation dress ornament commodity to user.
Particularly, by the information recommendation of described collocation dress ornament commodity to user, clothing matching is carried out to facilitate user.
The method of the recommendation dress ornament commodity that the embodiment of the present invention provides, according to the Matching Relation between dress ornament classification and between dress ornament attribute tags, determine the collocation result between multiple dress ornament classifications of personality Data Matching and between multiple dress ornament attribute tags, and from dress ornament merchandising database, the information of corresponding collocation dress ornament commodity is chosen according to described collocation result, finally by the information recommendation of described collocation dress ornament commodity to user, automatically for user provides specialized clothing matching to advise, manpower can be saved and expends.
Below for Fig. 4, the technical scheme of the method for recommendation dress ornament commodity of the present invention is illustrated.Fig. 4 illustrates the schematic diagram based on personality data recommendation dress ornament commodity.Particularly, after the personality data obtaining user, obtain and multiple dress ornament classification of described personality Data Matching and multiple dress ornament attribute tags according to predetermined individual character dress ornament recommendation rules, and in conjunction with clothing matching engine, obtain the collocation result between dress ornament classification and dress ornament attribute tags.Finally, user recommended by the picture retrieving corresponding dress ornament commodity in dress ornament merchandising database.As shown in Figure 4, in personality data (female, 23 years old of input, 168cm, 50kg, A font, fair complexion is partially red) and environmental data (29 degree, fine day) after, in conjunction with individual character clothing matching rule and clothing matching engine, can obtain dress ornament classification is above the waist female-jacket-shirt, and dress ornament attribute tags comprises cardigan, single-breasted, conventional money etc., the dress ornament classification of the lower part of the body is female-half body skirt, and dress ornament attribute tags comprises skirt, fishtail skirt, black etc.Finally, the dress ornament classification obtained and dress ornament attribute tags are inputted in dress ornament merchandising database, retrieves the dress ornament picture mated with the dress ornament classification obtained and dress ornament attribute tags, and show user.
Embodiment three
Fig. 5 is the logic diagram of the device of the recommendation dress ornament commodity that exemplary embodiment of the present three is shown.
With reference to Fig. 5, the device of the recommendation dress ornament commodity of the embodiment of the present invention can perform the method for the recommendation dress ornament commodity of embodiment one.The device of the recommendation dress ornament commodity of the embodiment of the present invention can comprise: dress ornament picture acquiring unit 510, recognition unit 520, attribute collocation unit 530, first collocation merchandise news acquiring unit 540 and the first collocation merchandise news recommendation unit 550.
Dress ornament picture acquiring unit 510 is for obtaining dress ornament picture.
Recognition unit 520 is for from the first dress ornament classification of described dress ornament picture recognition first dress ornament and at least one first dress ornament attribute tags.
Attribute collocation unit 530 is for obtaining and at least one second dress ornament classification of described first clothing matching and at least one second dress ornament attribute tags from the clothing matching engine preset according to described first dress ornament classification and at least one first dress ornament attribute tags.
First collocation merchandise news acquiring unit 540, for choosing the information of the collocation dress ornament commodity mated with described second dress ornament classification and the second dress ornament attribute tags from dress ornament merchandising database, has the information of multiple dress ornament commodity and the data of dress ornament classification and dress ornament attribute tags in described dress ornament merchandising database.
First collocation merchandise news recommendation unit 550 for by the information recommendation of described collocation dress ornament commodity to user.
The device of the recommendation dress ornament commodity that the embodiment of the present invention provides, according to the Matching Relation between dress ornament classification and between dress ornament attribute tags, determine and the dress ornament classification of dress ornament picture match and dress ornament attribute tags, and from dress ornament merchandising database, the information of corresponding collocation dress ornament commodity is chosen according to the dress ornament classification of described coupling and dress ornament attribute tags, finally by the information recommendation of described collocation dress ornament commodity to user, automatically for user provides specialized clothing matching to advise, manpower can be saved and expends.
Alternatively, described clothing matching engine has the collocation grade of fit weights between multiple candidate's dress ornament classification and between multiple candidate's dress ornament attribute tags, described attribute collocation unit 530 can comprise: grade of fit weights obtain subelement, for obtaining the classification collocation grade of fit weights between described first dress ornament classification and multiple candidate's dress ornament classification respectively from described clothing matching engine, and obtain described attribute collocation grade of fit weights between at least one first dress ornament attribute tags and multiple candidate's dress ornament attribute tags respectively; Attribute chooses unit, for correspondingly choosing candidate's dress ornament classification of the first predetermined number as described second dress ornament classification according to the classification collocation grade of fit weights obtained, and correspondingly choose candidate's dress ornament attribute tags of the second predetermined number as described second dress ornament attribute tags according to the attribute collocation grade of fit weights of described second dress ornament classification and acquisition.
Alternatively, described device also can comprise: the first personality acquiring unit, for obtaining the personality data of user's input; Personality attributes matching unit, for obtaining with described personality Data Matching according to predetermined individual character dress ornament recommendation rules and multiple 3rd dress ornament classification of applicable current environmental condition and the 3rd dress ornament attribute tags; Similarity matching angle value computing unit, for calculating the Similarity matching angle value of described 3rd dress ornament classification and the 3rd dress ornament attribute tags and described second dress ornament classification and the second dress ornament attribute tags respectively; Sequencing unit, for the size according to described Similarity matching angle value, sorts to described second dress ornament classification and the second dress ornament attribute tags; Described first collocation merchandise news acquiring unit comprises: information chooses subelement, for choosing the information of the collocation dress ornament commodity mated with described second dress ornament classification and the second dress ornament attribute tags of the forward predetermined number that sorts from dress ornament merchandising database.
Alternatively, the information of the multiple dress ornament commodity had in described dress ornament merchandising database comprises the picture of described multiple dress ornament commodity, and described first collocation merchandise news recommendation unit also can comprise: display unit, for by the picture presentation of described collocation dress ornament commodity to user.
Alternatively, described device also can comprise: similar merchandise news recommendation unit, for choosing the information of the similar dress ornament commodity mated with the first dress ornament attribute tags with described first dress ornament classification from dress ornament merchandising database, and recommends user.
Embodiment four
Fig. 6 is the logic diagram of the device of the recommendation dress ornament commodity that exemplary embodiment of the present four is shown.
With reference to Fig. 6, the device of the recommendation dress ornament commodity of the embodiment of the present invention can perform the device of the recommendation dress ornament commodity of embodiment two.The locating device of the dress ornament based on image content of the embodiment of the present invention can comprise: second individual character parameter acquiring unit 610, match information acquiring unit 620, collocation result acquiring unit 630, second collocation merchandise news acquiring unit 640 and the second collocation merchandise news recommendation unit 650.
Second individual character parameter acquiring unit 610 is for obtaining the personality data of user.
Match information acquiring unit 620 is for obtaining and multiple dress ornament classification of described personality Data Matching and multiple dress ornament attribute tags according to predetermined individual character dress ornament recommendation rules.
Collocation result acquiring unit 630 obtains the collocation result between described multiple dress ornament classification and between multiple dress ornament attribute tags for the clothing matching engine by presetting.
Second collocation merchandise news acquiring unit 640, for choosing the information of the collocation dress ornament commodity of coupling respectively from dress ornament merchandising database according to described collocation result, has the information of multiple dress ornament commodity and the data of dress ornament classification and dress ornament attribute tags in described dress ornament merchandising database.
Second collocation merchandise news recommendation unit 650 for by the information recommendation of described collocation dress ornament commodity to user.
The device of the recommendation dress ornament commodity that the embodiment of the present invention provides is according to the Matching Relation between dress ornament classification and between dress ornament attribute tags, determine the collocation result between multiple dress ornament classifications of personality Data Matching and between multiple dress ornament attribute tags, and from dress ornament merchandising database, the information of corresponding collocation dress ornament commodity is chosen according to described collocation result, finally by the information recommendation of described collocation dress ornament commodity to user, automatically for user provides specialized clothing matching to advise, manpower can be saved and expends.
Alternatively, described match information acquiring unit 620 can comprise: match information obtains subelement, for obtaining with described personality Data Matching according to predetermined individual character dress ornament recommendation rules and being applicable to multiple dress ornament classification of current environmental condition and multiple dress ornament attribute tags.
Alternatively, described clothing matching engine has the collocation grade of fit weights between multiple candidate's dress ornament classification and between multiple candidate's dress ornament attribute tags, described collocation result acquiring unit 630 is for for any two the dress ornament classifications in the middle of described multiple dress ornament classification and multiple dress ornament attribute tags and any two dress ornament attribute tags, perform following process: obtain the classification collocation grade of fit weights between described two dress ornament classifications respectively from described clothing matching engine, and obtain the attribute collocation grade of fit weights between described two dress ornament attribute tags respectively; Correspondingly choose the dress ornament classification collocation result of the first predetermined number according to the classification collocation grade of fit weights obtained, and correspondingly choose the first dress ornament attribute tags combination of the second predetermined number and the combination of the second dress ornament attribute tags according to the attribute collocation grade of fit weights of described dress ornament classification collocation result and acquisition and to arrange in pairs or groups result as attribute.
It may be noted that the needs according to implementing, each step described can be split as more multi-step, also the part operation of two or more step or step can be combined into new step, to realize object of the present invention in the application.
Above-mentioned can at hardware according to method of the present invention, realize in firmware, or be implemented as and can be stored in recording medium (such as CD ROM, RAM, floppy disk, hard disk or magneto-optic disk) in software or computer code, or be implemented and will be stored in the computer code in local recording medium by the original storage of web download in remote logging medium or nonvolatile machine readable media, thus method described here can be stored in use multi-purpose computer, such software process on the recording medium of application specific processor or able to programme or specialized hardware (such as ASIC or FPGA).Be appreciated that, computing machine, processor, microprocessor controller or programmable hardware comprise and can store or receive the memory module of software or computer code (such as, RAM, ROM, flash memory etc.), when described software or computer code by computing machine, processor or hardware access and perform time, realize disposal route described here.In addition, when the code for realizing the process shown in this accessed by multi-purpose computer, multi-purpose computer is converted to the special purpose computer for performing the process shown in this by the execution of code.
The above; be only the specific embodiment of the present invention, but protection scope of the present invention is not limited thereto, is anyly familiar with those skilled in the art in the technical scope that the present invention discloses; change can be expected easily or replace, all should be encompassed within protection scope of the present invention.Therefore, protection scope of the present invention should be as the criterion with the protection domain of described claim.
Claims (16)
1. recommend a method for dress ornament commodity, it is characterized in that, described method comprises:
Obtain dress ornament picture;
From the first dress ornament classification and at least one first dress ornament attribute tags of described dress ornament picture recognition first dress ornament;
Obtain and at least one second dress ornament classification of described first clothing matching and at least one second dress ornament attribute tags from the clothing matching engine preset according to described first dress ornament classification and at least one first dress ornament attribute tags;
From dress ornament merchandising database, choose the information of the collocation dress ornament commodity mated with described second dress ornament classification and the second dress ornament attribute tags, in described dress ornament merchandising database, have the information of multiple dress ornament commodity and the data of dress ornament classification and dress ornament attribute tags;
By the information recommendation of described collocation dress ornament commodity to user.
2. method according to claim 1, is characterized in that, described clothing matching engine has the collocation grade of fit weights between multiple candidate's dress ornament classification and between multiple candidate's dress ornament attribute tags,
Described acquisition from the clothing matching engine preset according to described first dress ornament classification and at least one first dress ornament attribute tags comprises with at least one second dress ornament classification of described first clothing matching and the process of at least one the second dress ornament attribute tags:
Obtain the classification collocation grade of fit weights between described first dress ornament classification and multiple candidate's dress ornament classification respectively from described clothing matching engine, and obtain described attribute collocation grade of fit weights between at least one first dress ornament attribute tags and multiple candidate's dress ornament attribute tags respectively;
Classification collocation grade of fit weights according to obtaining correspondingly choose candidate's dress ornament classification of the first predetermined number as described second dress ornament classification, and correspondingly choose candidate's dress ornament attribute tags of the second predetermined number as described second dress ornament attribute tags according to the attribute collocation grade of fit weights of described second dress ornament classification and acquisition.
3. method according to claim 2, is characterized in that, described method also comprises:
Obtain the personality data of user's input;
Obtain with described personality Data Matching according to predetermined individual character dress ornament recommendation rules and be applicable to multiple 3rd dress ornament classification and the 3rd dress ornament attribute tags of current environmental condition;
Calculate the Similarity matching angle value of described 3rd dress ornament classification and the 3rd dress ornament attribute tags and described second dress ornament classification and the second dress ornament attribute tags respectively;
According to the size of described Similarity matching angle value, described second dress ornament classification and the second dress ornament attribute tags are sorted;
The process choosing the information of the collocation dress ornament commodity mated with described second dress ornament classification and the second dress ornament attribute tags from dress ornament merchandising database comprises:
The information of the collocation dress ornament commodity mated with described second dress ornament classification and the second dress ornament attribute tags of the forward predetermined number that sorts is chosen from dress ornament merchandising database.
4. the method according to any one of claims 1 to 3, is characterized in that, the information of the multiple dress ornament commodity had in described dress ornament merchandising database comprises the picture of described multiple dress ornament commodity, and
The described information recommendation by described collocation dress ornament commodity also comprises to the process of user:
By the picture presentation of described collocation dress ornament commodity to user.
5. method according to claim 4, is characterized in that, described method also comprises:
From dress ornament merchandising database, choose the information of the similar dress ornament commodity mated with the first dress ornament attribute tags with described first dress ornament classification, and recommend user.
6. recommend a method for dress ornament commodity, it is characterized in that, described method comprises:
Obtain the personality data of user;
Obtain and multiple dress ornament classification of described personality Data Matching and multiple dress ornament attribute tags according to predetermined individual character dress ornament recommendation rules;
The collocation result between described multiple dress ornament classification and between multiple dress ornament attribute tags is obtained by the clothing matching engine preset;
From dress ornament merchandising database, choose the information of the collocation dress ornament commodity of coupling respectively according to described collocation result, in described dress ornament merchandising database, have the information of multiple dress ornament commodity and the data of dress ornament classification and dress ornament attribute tags;
By the information recommendation of described collocation dress ornament commodity to user.
7. method according to claim 6, is characterized in that, described acquisition according to predetermined individual character dress ornament recommendation rules comprises with multiple dress ornament classification of described personality Data Matching and the process of multiple dress ornament attribute tags:
Obtain with described personality Data Matching according to predetermined individual character dress ornament recommendation rules and be applicable to multiple dress ornament classification of current environmental condition and multiple dress ornament attribute tags.
8. the method according to claim 6 or 7, is characterized in that, described clothing matching engine has the collocation grade of fit weights between multiple candidate's dress ornament classification and between multiple candidate's dress ornament attribute tags,
The process of the collocation result that the described clothing matching engine by presetting obtains between described multiple dress ornament classification and between multiple dress ornament attribute tags comprises:
For any two the dress ornament classifications in the middle of described multiple dress ornament classification and multiple dress ornament attribute tags and any two dress ornament attribute tags, perform following process:
Obtain the classification collocation grade of fit weights between described two dress ornament classifications respectively from described clothing matching engine, and obtain the attribute collocation grade of fit weights between described two dress ornament attribute tags respectively;
Correspondingly choose the dress ornament classification collocation result of the first predetermined number according to the classification collocation grade of fit weights obtained, and correspondingly choose the first dress ornament attribute tags combination of the second predetermined number and the combination of the second dress ornament attribute tags according to the attribute collocation grade of fit weights of described dress ornament classification collocation result and acquisition and to arrange in pairs or groups result as attribute.
9. recommend a device for dress ornament commodity, it is characterized in that, described device comprises:
Dress ornament picture acquiring unit, for obtaining dress ornament picture;
Recognition unit, for from the first dress ornament classification of described dress ornament picture recognition first dress ornament and at least one first dress ornament attribute tags;
Attribute collocation unit, for obtaining and at least one second dress ornament classification of described first clothing matching and at least one second dress ornament attribute tags from the clothing matching engine preset according to described first dress ornament classification and at least one first dress ornament attribute tags;
Collocation merchandise news acquiring unit, for choosing the information of the collocation dress ornament commodity mated with described second dress ornament classification and the second dress ornament attribute tags from dress ornament merchandising database, in described dress ornament merchandising database, there are the information of multiple dress ornament commodity and the data of dress ornament classification and dress ornament attribute tags;
Collocation merchandise news recommendation unit, for by the information recommendation of described collocation dress ornament commodity to user.
10. device according to claim 9, is characterized in that, described clothing matching engine has the collocation grade of fit weights between multiple candidate's dress ornament classification and between multiple candidate's dress ornament attribute tags,
Described attribute collocation unit comprises:
Grade of fit weights obtain subelement, for obtaining the classification collocation grade of fit weights between described first dress ornament classification and multiple candidate's dress ornament classification respectively from described clothing matching engine, and obtain described attribute collocation grade of fit weights between at least one first dress ornament attribute tags and multiple candidate's dress ornament attribute tags respectively;
Attribute chooses unit, for correspondingly choosing candidate's dress ornament classification of the first predetermined number as described second dress ornament classification according to the classification collocation grade of fit weights obtained, and correspondingly choose candidate's dress ornament attribute tags of the second predetermined number as described second dress ornament attribute tags according to the attribute collocation grade of fit weights of described second dress ornament classification and acquisition.
11. devices according to claim 10, is characterized in that, described device also comprises:
Personality acquiring unit, for obtaining the personality data of user's input;
Personality attributes matching unit, for obtaining with described personality Data Matching according to predetermined individual character dress ornament recommendation rules and multiple 3rd dress ornament classification of applicable current environmental condition and the 3rd dress ornament attribute tags;
Similarity matching angle value computing unit, for calculating the Similarity matching angle value of described 3rd dress ornament classification and the 3rd dress ornament attribute tags and described second dress ornament classification and the second dress ornament attribute tags respectively;
Sequencing unit, for the size according to described Similarity matching angle value, sorts to described second dress ornament classification and the second dress ornament attribute tags;
Described collocation merchandise news acquiring unit comprises:
Information chooses subelement, for choosing the information of the collocation dress ornament commodity mated with described second dress ornament classification and the second dress ornament attribute tags of the forward predetermined number that sorts from dress ornament merchandising database.
12. devices according to any one of claim 9 ~ 11, it is characterized in that, the information of the multiple dress ornament commodity had in described dress ornament merchandising database comprises the picture of described multiple dress ornament commodity, and
Described collocation merchandise news recommendation unit also comprises:
Display unit, for by the picture presentation of described collocation dress ornament commodity to user.
13. devices according to claim 12, is characterized in that, described device also comprises:
Similar merchandise news recommendation unit, for choosing the information of the similar dress ornament commodity mated with the first dress ornament attribute tags with described first dress ornament classification from dress ornament merchandising database, and recommends user.
14. 1 kinds of devices recommending dress ornament commodity, it is characterized in that, described device comprises:
Personality acquiring unit, for obtaining the personality data of user;
Match information acquiring unit, for obtaining and multiple dress ornament classification of described personality Data Matching and multiple dress ornament attribute tags according to predetermined individual character dress ornament recommendation rules;
Collocation result acquiring unit, obtains the collocation result between described multiple dress ornament classification and between multiple dress ornament attribute tags for the clothing matching engine by presetting;
Collocation merchandise news acquiring unit, for choosing the information of the collocation dress ornament commodity of coupling respectively from dress ornament merchandising database according to described collocation result, in described dress ornament merchandising database, there are the information of multiple dress ornament commodity and the data of dress ornament classification and dress ornament attribute tags;
Collocation merchandise news recommendation unit, for by the information recommendation of described collocation dress ornament commodity to user.
15. devices according to claim 14, is characterized in that, described match information acquiring unit comprises:
Match information obtains subelement, for obtaining with described personality Data Matching according to predetermined individual character dress ornament recommendation rules and being applicable to multiple dress ornament classification of current environmental condition and multiple dress ornament attribute tags.
16. devices according to claims 14 or 15, it is characterized in that, described clothing matching engine has the collocation grade of fit weights between multiple candidate's dress ornament classification and between multiple candidate's dress ornament attribute tags,
Described collocation result acquiring unit is used for for any two the dress ornament classifications in the middle of described multiple dress ornament classification and multiple dress ornament attribute tags and any two dress ornament attribute tags, performs following process:
Obtain the classification collocation grade of fit weights between described two dress ornament classifications respectively from described clothing matching engine, and obtain the attribute collocation grade of fit weights between described two dress ornament attribute tags respectively;
Correspondingly choose the dress ornament classification collocation result of the first predetermined number according to the classification collocation grade of fit weights obtained, and correspondingly choose the first dress ornament attribute tags combination of the second predetermined number and the combination of the second dress ornament attribute tags according to the attribute collocation grade of fit weights of described dress ornament classification collocation result and acquisition and to arrange in pairs or groups result as attribute.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510408418.0A CN104951966A (en) | 2015-07-13 | 2015-07-13 | Clothes commodity recommending method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510408418.0A CN104951966A (en) | 2015-07-13 | 2015-07-13 | Clothes commodity recommending method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN104951966A true CN104951966A (en) | 2015-09-30 |
Family
ID=54166602
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510408418.0A Pending CN104951966A (en) | 2015-07-13 | 2015-07-13 | Clothes commodity recommending method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104951966A (en) |
Cited By (25)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105224775A (en) * | 2015-11-12 | 2016-01-06 | 中国科学院重庆绿色智能技术研究院 | Based on the method and apparatus that picture processing is arranged in pairs or groups to clothes |
CN105426462A (en) * | 2015-11-13 | 2016-03-23 | 深圳码隆科技有限公司 | Image searching method and device based on image element |
CN105761127A (en) * | 2016-02-05 | 2016-07-13 | 上海和鹰机电科技股份有限公司 | Clothing style intelligent matching method based on sign information and system thereof |
CN106055893A (en) * | 2016-05-27 | 2016-10-26 | 杭州土网络科技有限公司 | Clothes matching scheme generation method based on fashion template database and automatic matching |
CN106156297A (en) * | 2016-06-29 | 2016-11-23 | 北京小米移动软件有限公司 | Method and device recommended by dress ornament |
CN106570714A (en) * | 2015-10-08 | 2017-04-19 | 阿里巴巴集团控股有限公司 | Method and apparatus for recommending matching object picture, and method and apparatus for establishing mapping relation |
CN106649383A (en) * | 2015-11-02 | 2017-05-10 | 阿里巴巴集团控股有限公司 | Clothes management method and system |
CN106846122A (en) * | 2017-02-20 | 2017-06-13 | 北京京东尚科信息技术有限公司 | Commodity data treating method and apparatus |
CN107679155A (en) * | 2017-09-27 | 2018-02-09 | 百度在线网络技术(北京)有限公司 | Clothing matching storehouse method for building up, information recommendation method, device, equipment and medium |
CN107833082A (en) * | 2017-09-15 | 2018-03-23 | 广州唯品会研究院有限公司 | A kind of recommendation method and apparatus of commodity picture |
CN107833092A (en) * | 2017-10-27 | 2018-03-23 | 深圳狗尾草智能科技有限公司 | Virtual portrait trial assembly method and system based on scene and state |
CN108230082A (en) * | 2017-06-16 | 2018-06-29 | 深圳市商汤科技有限公司 | The recommendation method and apparatus of collocation dress ornament, electronic equipment, storage medium |
CN108319680A (en) * | 2018-01-31 | 2018-07-24 | 维沃移动通信有限公司 | A kind of clothes recommend method and terminal device |
CN108427749A (en) * | 2018-03-12 | 2018-08-21 | 上海哔哩哔哩科技有限公司 | Commercial goods labels management method, server and Commercial goods labels manage system |
CN109635198A (en) * | 2018-12-17 | 2019-04-16 | 杭州柚子街信息科技有限公司 | The method, apparatus of presentation user's search result, medium and electronic equipment on merchandise display platform |
WO2019120031A1 (en) * | 2017-12-20 | 2019-06-27 | Oppo广东移动通信有限公司 | Method, device, storage medium, and mobile terminal for making recommendation about clothing matching |
WO2020044099A1 (en) * | 2018-08-29 | 2020-03-05 | 优视科技新加坡有限公司 | Service processing method and apparatus based on object recognition |
CN110866168A (en) * | 2018-08-27 | 2020-03-06 | 阿里巴巴集团控股有限公司 | Information recommendation method and device, terminal and server |
WO2020119170A1 (en) * | 2018-12-14 | 2020-06-18 | 北京京东尚科信息技术有限公司 | Information presentation method and device |
CN111382747A (en) * | 2018-12-29 | 2020-07-07 | 杭州光启人工智能研究院 | Data marking method, computer device and computer readable storage medium |
WO2020156306A1 (en) * | 2019-01-31 | 2020-08-06 | 阿里巴巴集团控股有限公司 | Clothing collocation information processing method, system and device, and data object processing method, system and device |
CN111582979A (en) * | 2020-04-29 | 2020-08-25 | 上海风秩科技有限公司 | Clothing matching recommendation method and device and electronic equipment |
CN111611504A (en) * | 2019-02-26 | 2020-09-01 | 深圳云天励飞技术有限公司 | Processing method, device, equipment and system |
TWI728787B (en) * | 2020-04-22 | 2021-05-21 | 國立勤益科技大學 | Commodity model identification and recommendation system |
WO2021218973A1 (en) * | 2020-04-27 | 2021-11-04 | Jingdong Digits Technology Holding Co., Ltd. | System and method for fashion style recommendation |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102033931A (en) * | 2010-12-17 | 2011-04-27 | 华为终端有限公司 | Clothing matching information searching method, device and system |
CN104391971A (en) * | 2014-12-05 | 2015-03-04 | 常州飞寻视讯信息科技有限公司 | Intelligent automatic dress collocation recommending method |
-
2015
- 2015-07-13 CN CN201510408418.0A patent/CN104951966A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102033931A (en) * | 2010-12-17 | 2011-04-27 | 华为终端有限公司 | Clothing matching information searching method, device and system |
CN104391971A (en) * | 2014-12-05 | 2015-03-04 | 常州飞寻视讯信息科技有限公司 | Intelligent automatic dress collocation recommending method |
Cited By (32)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106570714B (en) * | 2015-10-08 | 2021-01-15 | 阿里巴巴集团控股有限公司 | Recommendation method for matching object picture, and mapping relation establishment method and device |
CN106570714A (en) * | 2015-10-08 | 2017-04-19 | 阿里巴巴集团控股有限公司 | Method and apparatus for recommending matching object picture, and method and apparatus for establishing mapping relation |
CN106649383A (en) * | 2015-11-02 | 2017-05-10 | 阿里巴巴集团控股有限公司 | Clothes management method and system |
CN105224775A (en) * | 2015-11-12 | 2016-01-06 | 中国科学院重庆绿色智能技术研究院 | Based on the method and apparatus that picture processing is arranged in pairs or groups to clothes |
CN105426462A (en) * | 2015-11-13 | 2016-03-23 | 深圳码隆科技有限公司 | Image searching method and device based on image element |
CN105761127A (en) * | 2016-02-05 | 2016-07-13 | 上海和鹰机电科技股份有限公司 | Clothing style intelligent matching method based on sign information and system thereof |
CN106055893A (en) * | 2016-05-27 | 2016-10-26 | 杭州土网络科技有限公司 | Clothes matching scheme generation method based on fashion template database and automatic matching |
CN106055893B (en) * | 2016-05-27 | 2018-08-31 | 杭州一土网络科技有限公司 | Garment coordination scheme generation method based on fashion template library and Auto-matching |
CN106156297A (en) * | 2016-06-29 | 2016-11-23 | 北京小米移动软件有限公司 | Method and device recommended by dress ornament |
CN106846122B (en) * | 2017-02-20 | 2021-02-26 | 北京京东尚科信息技术有限公司 | Commodity data processing method and device |
CN106846122A (en) * | 2017-02-20 | 2017-06-13 | 北京京东尚科信息技术有限公司 | Commodity data treating method and apparatus |
CN108230082A (en) * | 2017-06-16 | 2018-06-29 | 深圳市商汤科技有限公司 | The recommendation method and apparatus of collocation dress ornament, electronic equipment, storage medium |
US11232324B2 (en) | 2017-06-16 | 2022-01-25 | Shenzhen Sensetime Technology Co., Ltd. | Methods and apparatus for recommending collocating dress, electronic devices, and storage media |
WO2018228448A1 (en) * | 2017-06-16 | 2018-12-20 | 深圳市商汤科技有限公司 | Method and apparatus for recommending matching clothing, electronic device and storage medium |
CN107833082A (en) * | 2017-09-15 | 2018-03-23 | 广州唯品会研究院有限公司 | A kind of recommendation method and apparatus of commodity picture |
CN107679155A (en) * | 2017-09-27 | 2018-02-09 | 百度在线网络技术(北京)有限公司 | Clothing matching storehouse method for building up, information recommendation method, device, equipment and medium |
CN107833092A (en) * | 2017-10-27 | 2018-03-23 | 深圳狗尾草智能科技有限公司 | Virtual portrait trial assembly method and system based on scene and state |
CN109949116A (en) * | 2017-12-20 | 2019-06-28 | 广东欧珀移动通信有限公司 | Clothing matching recommended method, device, storage medium and mobile terminal |
WO2019120031A1 (en) * | 2017-12-20 | 2019-06-27 | Oppo广东移动通信有限公司 | Method, device, storage medium, and mobile terminal for making recommendation about clothing matching |
CN108319680A (en) * | 2018-01-31 | 2018-07-24 | 维沃移动通信有限公司 | A kind of clothes recommend method and terminal device |
CN108427749A (en) * | 2018-03-12 | 2018-08-21 | 上海哔哩哔哩科技有限公司 | Commercial goods labels management method, server and Commercial goods labels manage system |
CN110866168A (en) * | 2018-08-27 | 2020-03-06 | 阿里巴巴集团控股有限公司 | Information recommendation method and device, terminal and server |
WO2020044099A1 (en) * | 2018-08-29 | 2020-03-05 | 优视科技新加坡有限公司 | Service processing method and apparatus based on object recognition |
WO2020119170A1 (en) * | 2018-12-14 | 2020-06-18 | 北京京东尚科信息技术有限公司 | Information presentation method and device |
CN109635198A (en) * | 2018-12-17 | 2019-04-16 | 杭州柚子街信息科技有限公司 | The method, apparatus of presentation user's search result, medium and electronic equipment on merchandise display platform |
CN111382747A (en) * | 2018-12-29 | 2020-07-07 | 杭州光启人工智能研究院 | Data marking method, computer device and computer readable storage medium |
CN111507790A (en) * | 2019-01-31 | 2020-08-07 | 阿里巴巴集团控股有限公司 | Processing method of clothing matching information, data object processing method, system and equipment |
WO2020156306A1 (en) * | 2019-01-31 | 2020-08-06 | 阿里巴巴集团控股有限公司 | Clothing collocation information processing method, system and device, and data object processing method, system and device |
CN111611504A (en) * | 2019-02-26 | 2020-09-01 | 深圳云天励飞技术有限公司 | Processing method, device, equipment and system |
TWI728787B (en) * | 2020-04-22 | 2021-05-21 | 國立勤益科技大學 | Commodity model identification and recommendation system |
WO2021218973A1 (en) * | 2020-04-27 | 2021-11-04 | Jingdong Digits Technology Holding Co., Ltd. | System and method for fashion style recommendation |
CN111582979A (en) * | 2020-04-29 | 2020-08-25 | 上海风秩科技有限公司 | Clothing matching recommendation method and device and electronic equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104951966A (en) | Clothes commodity recommending method and device | |
JP7136156B2 (en) | Search support system, search support method and program | |
CN109670591B (en) | Neural network training method and image matching method and device | |
Liu et al. | Hi, magic closet, tell me what to wear! | |
US20180308149A1 (en) | Systems and methods to curate, suggest and maintain a wardrobe | |
CN107679960B (en) | Personalized clothing recommendation method based on clothing image and label text bimodal content analysis | |
CN105224775B (en) | Method and device for matching clothes based on picture processing | |
JP2010055391A (en) | Merchandise analyzing device, merchandise offering device, and merchandise analysis method and program | |
KR101639657B1 (en) | Method and server for searching similar goods | |
CN106649383A (en) | Clothes management method and system | |
CN104584033A (en) | Interactive clothes searching in online stores | |
KR20200045668A (en) | Method, apparatus and computer program for style recommendation | |
KR20200046924A (en) | The Automatic Recommendation System and Method of the Fashion Coordination | |
CN106354768B (en) | Color-based user and commodity matching method and commodity matching recommendation method | |
CN102332034A (en) | Portrait picture retrieval method and device | |
CN109360050A (en) | Personal care garment management and personalized collocation recommendation intelligence system based on perceptual demand | |
CN106951448A (en) | A kind of personalization, which is worn, takes recommendation method and system | |
JP7062960B2 (en) | Information processing system, program, information processing device and information output method | |
Shimizu et al. | Fashion intelligence system: An outfit interpretation utilizing images and rich abstract tags | |
JP2014229129A (en) | Combination presentation system and computer program | |
CN108596646A (en) | A kind of garment coordination recommendation method of fusion face character analysis | |
CN112016608A (en) | Garment perceptual intention classification method based on convolutional neural network, classification model and construction method thereof | |
Huang et al. | A sparse-coding based approach to clothing image retrieval | |
KR20200084647A (en) | A method of providing a fashion item recommendation service to a user using a date | |
KR102509507B1 (en) | Product information tag device and method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20150930 |
|
RJ01 | Rejection of invention patent application after publication |