CN108363750A - Clothes recommend method and Related product - Google Patents
Clothes recommend method and Related product Download PDFInfo
- Publication number
- CN108363750A CN108363750A CN201810084286.4A CN201810084286A CN108363750A CN 108363750 A CN108363750 A CN 108363750A CN 201810084286 A CN201810084286 A CN 201810084286A CN 108363750 A CN108363750 A CN 108363750A
- Authority
- CN
- China
- Prior art keywords
- clothing
- mode
- recommendation
- output result
- clothes
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 46
- 239000013598 vector Substances 0.000 claims description 91
- 238000004364 calculation method Methods 0.000 claims description 32
- 238000012549 training Methods 0.000 claims description 23
- 238000004590 computer program Methods 0.000 claims description 15
- 238000010586 diagram Methods 0.000 description 14
- 239000000463 material Substances 0.000 description 11
- 230000006870 function Effects 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 229920000742 Cotton Polymers 0.000 description 4
- 210000004556 brain Anatomy 0.000 description 4
- 239000003086 colorant Substances 0.000 description 4
- 230000036651 mood Effects 0.000 description 4
- 238000013473 artificial intelligence Methods 0.000 description 3
- 239000000047 product Substances 0.000 description 3
- 239000004677 Nylon Substances 0.000 description 2
- 229920004933 Terylene® Polymers 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000001815 facial effect Effects 0.000 description 2
- 238000003780 insertion Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000012821 model calculation Methods 0.000 description 2
- 229920001778 nylon Polymers 0.000 description 2
- 239000005020 polyethylene terephthalate Substances 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 230000005236 sound signal Effects 0.000 description 2
- 229920006052 Chinlon® Polymers 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 230000037431 insertion Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007639 printing Methods 0.000 description 1
- 238000010079 rubber tapping Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
This application discloses a kind of clothes to recommend method and Related product, the method includes：Obtain Weather information, sign information and clothes scene information；The Weather information, sign information and clothes scene information are formed into input data, the input data, which is inputted default clothes recommended models, to be calculated, and output result is obtained；The first clothes way of recommendation is determined according to the output result, shows the first clothes way of recommendation.The accuracy of clothes recommendation can be improved using embodiments herein.
Description
Technical Field
The application relates to the technical field of electronics, in particular to a clothing recommendation method and a related product.
Background
With the development of artificial intelligence AI technology, the AI chip is gradually applied to various scenes in life, and various conveniences are brought to the life of people. For example, at present, before a user goes out daily, a user generally obtains some recommendations of clothing matching through network search, and selects a set of appropriate matching mode to dress the user according to the current weather and the mood of the user. However, the method for selecting the clothing matching recommendation is not necessarily suitable for the user to go out, and the accuracy is low.
Content of application
The embodiment of the application provides a clothing recommendation method and related products, which can determine a clothing recommendation mode according to information of a user and improve the accuracy of clothing recommendation.
In a first aspect, an embodiment of the present application provides a clothing recommendation method, where the method includes:
acquiring weather information, physical sign information and clothing scene information;
the weather information, the physical sign information and the clothing scene information form input data, and the input data are input into a preset clothing recommendation model for calculation to obtain an output result;
and determining a first clothing recommendation mode according to the output result, and displaying the first clothing recommendation mode.
In a second aspect, an embodiment of the present application provides an electronic device for recommending clothing recommendation, where the electronic device includes:
the acquisition unit is used for acquiring weather information, physical sign information and clothing scene information;
the input unit is used for forming input data by the weather information, the physical sign information and the clothing scene information, and inputting the input data into a preset clothing recommendation model for calculation to obtain an output result;
the determining unit is used for determining a first service recommendation mode according to the output result;
and the display unit is used for displaying the first clothing recommendation mode.
In a third aspect, an embodiment of the present application provides an electronic device, including: the system comprises an application processor AP, a touch display screen and a transceiver, wherein the touch display screen and the transceiver are connected with the application processor through at least one circuit;
the transceiver is used for acquiring weather information;
the AP is used for acquiring sign information and clothing scene information;
the AP is used for forming input data by the weather information, the physical sign information and the clothing scene information, and inputting the input data into a preset clothing recommendation model for calculation to obtain an output result;
the AP is used for determining a first service recommendation mode according to the output result;
the touch display screen is used for displaying the first clothing recommendation mode.
In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium storing a computer program for electronic data exchange, wherein the computer program causes a computer to execute the method according to the first aspect.
In a fifth aspect, embodiments of the present application provide a computer program product comprising a non-transitory computer-readable storage medium storing a computer program, the computer being operable to cause a computer to perform the method according to the first aspect.
The embodiment of the application has the following beneficial effects:
therefore, in the embodiment of the application, the obtained weather information, the obtained physical sign information and the obtained clothing scene information are input into the preset clothing recommendation model for calculation to obtain an output result, clothing is recommended to a user according to the output result, and the clothing recommendation mode is displayed. The clothing recommendation method and the system perform targeted clothing recommendation according to the weather conditions and the user information, and improve the accuracy of clothing recommendation.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1A is a schematic flowchart of a method for recommending clothing according to an embodiment of the present application;
FIG. 1B is a schematic diagram of input data provided by an embodiment of the present application;
fig. 1C is a schematic diagram of insertion of input data according to an embodiment of the present application;
FIG. 1D is a diagram illustrating a convolution calculation provided by an embodiment of the present application;
fig. 1E is a schematic diagram of an output result obtained by convolution calculation according to an embodiment of the present application;
FIG. 2 is a schematic flow chart diagram illustrating another method for recommending clothing according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure;
fig. 4 is a schematic structural diagram of another electronic device provided in the embodiment of the present application;
fig. 5 is a schematic structural diagram of another electronic device provided in the embodiments of the present application;
fig. 6 is a schematic structural diagram of a mobile phone according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some, but not all, embodiments of the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The terms "first," "second," "third," and "fourth," etc. in the description and claims of this application and in the accompanying drawings are used for distinguishing between different objects and not for describing a particular order. Furthermore, the terms "include" and "have," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus.
The electronic device in the present application may include a smart phone (e.g., an Android phone, an iOS phone, a windows phone, etc.), a tablet computer, a palm computer, a notebook computer, a Mobile internet device (MID, Mobile internet devices), or a wearable device, and the electronic devices are merely examples, but not exhaustive, and include but are not limited to the electronic devices, and for convenience of description, the electronic devices are referred to as User Equipment (UE) in the following embodiments. Of course, in practical applications, the user equipment is not limited to the above presentation form, and may also include: intelligent vehicle-mounted terminal, computer equipment and the like.
Referring to fig. 1A, fig. 1A is a schematic flowchart of a method for recommending clothing according to an embodiment of the present application, where the method includes:
step 101: and acquiring weather information, physical sign information and clothing scene information.
The weather information comprises temperature information, sunlight information, wind power information and time information; the physical sign information comprises height, weight, skin color and hair style of the user; the clothing scene information comprises the travel information of the user, and the travel information means that the user is about to see someone or go to an appointed occasion to participate in the activity. Optionally, the physical sign information is input by the user in advance, stored in a memory unit of the electronic device, and directly obtained from the memory unit.
Optionally, a navigation route in the navigation software or the taxi taking software is extracted, and an object contracted by the user or a place to which the user goes is determined according to the route; or extracting the memo events in the user memo, and determining the object of the user appointment or the place to which the user goes.
optionally, the mood information of the user may be obtained by obtaining the speed of the user, or the mood information may be obtained by capturing a facial image of the user by photographing and analyzing the facial image, or the mood information may be obtained by capturing brain wave signals of the user, specifically, if β waves are detected as the dominant brain waves, it is determined that the user is in a relaxed state, if beta waves are detected as the dominant brain waves, it is determined that the user is in a stressed state, and if theta waves are detected as the dominant brain waves, it is determined that the user is in a drowsy or depressed state.
Step 102: and forming input data by the weather information, the physical sign information and the clothing scene information, and inputting the input data into a preset clothing recommendation model for calculation to obtain an output result.
Optionally, the preset clothing recommendation model is a pre-trained model, and the training method includes the following steps: obtaining satisfaction degrees corresponding to the historical clothing matching modes and the historical clothing matching modes, combining the historical clothing matching modes corresponding to the satisfaction degrees into training data if the satisfaction degrees are larger than a first preset threshold value, inputting all the training data into an initial clothing recommendation model, executing N layers of forward operation to obtain an output result, obtaining an output result gradient according to the output result, executing N layers of reverse operation on the output result gradient to obtain a weight gradient of each layer, updating the weight of each layer according to the weight gradient of each layer, obtaining a final weight through repeated iterative computation, and taking the final weight as a convolution kernel of the initial clothing recommendation model to obtain the preset clothing recommendation model.
For example, the satisfaction degrees are classified into A, B, C and D four levels in the order of the levels from small to large, wherein each satisfaction degree level can be reflected by the length of time, namely, the wearing time of the current clothing is obtained after the user finishes wearing the clothing. Specifically, the dressing time is 0 to t1Hour corresponds to grade A, dressing duration is t1～t2Hour corresponds to grade B, dressing duration is t2～t3Time corresponds to grade C, dressing time is longer than t3Time corresponds to a level D, where t3＞t2＞t1Is greater than 0. If the first preset threshold value is C, the dressing duration of the historical clothing matching is longer than t3And if the condition is met, combining the historical clothes matching mode meeting the condition, the weather information corresponding to the historical clothes matching and the travel information of the user into training data.
Optionally, the method for forming input data by the weather information, the physical sign information, and the clothing scene information specifically includes: extracting the quantity of preset input data, namely CI × H × W, of the preset clothing recommendation model, as shown in fig. 1B, wherein H is a height value, W is a width value, and CI is a depth value; extracting an information quantity a contained in weather information, an information quantity B contained in sign information, and an information quantity c contained in clothing scene information, comparing whether a + B + c is greater than CI × H × W, if a + B + c is greater than or equal to CI × H × W, adding the information quantities in the weather information, the sign information, and the clothing scene information without adding the information quantities in the weather information, the sign information, and the clothing scene information, if a + B + c is less than CI × H W, according to a zero-insertion adding strategy, so that a ' + B ' + c ' ═ CI × H W after adding is obtained, and fig. 1B shows that original input data are: h is 8, W is 7, CI is 3, H is 16, W is 7, and CI is 3 of the preset input data; the way of adding zeros may be to insert the zeros into the original input data in an interlaced manner, where the specific inserted data is shown in fig. 1C, and the gray interval in fig. 1C is the position of the inserted zero value, and of course, the strategy of adding zeros here is only an example, and is not limited to other strategies of adding zeros.
Optionally, the following describes a process of operation of the clothing recommendation model, and for the calculation of most models, the neural network is used for calculation, although there are multiple layers of calculation, the basic calculation is convolution operation, and the following takes the convolution operation of the neural network as an example for specific description.
Referring to a schematic diagram of convolution calculation shown in fig. 1D, as shown in fig. 1D, the input data is three-dimensional data, i.e., CI × H × W, if the convolution kernel of the clothing recommendation model is CO × CI × 3, the kernel of the convolution kernel is 3 × 3, and the input data and the convolution kernel cannot be directly convolved, so the operation manner may be that the convolution kernel, i.e., CO CI × 3 is cut into kernel [ 3 ]; then, convolution operation is performed on the input data CI × H with kernel [ 3 ] as the basic granularity, that is, the kernel [ 3 ] is used as the basic granularity to move on the input data, and a specific moving mode is schematically illustrated in fig. 1E, where a frame in fig. 1E is cut data after moving, and an output result CO (H-2) ((W-2)) can be obtained through the convolution operation in the moving mode as illustrated in fig. 1E.
Step 103: and determining a first clothing recommendation mode according to the output result, and displaying the first clothing recommendation mode.
Optionally, the electronic device obtains the clothing parameters according to the output result CO (H-2) × (W-2), and then integrates the clothing parameters of the same type into the clothing corresponding to the type, so as to generate the first clothing recommendation mode.
Further, the electronic device displays the first service recommendation mode on a display interface.
Optionally, in an example, after displaying the first recommendation mode for clothing, the method further includes:
inquiring K pieces of clothing with the same type as the ith piece of clothing in the first clothing recommendation mode in a wardrobe database, and acquiring K characteristic vectors of the K pieces of clothing, wherein i and K are positive integers;
calculating K similarity values of the feature vector of the i-th garment and the K feature vectors according to a similarity calculation formula, and inquiring a first garment corresponding to the feature vector with the maximum similarity value in the K feature vectors;
replacing the i-th clothing with the first clothing to obtain a second clothing recommendation mode, and displaying the second clothing recommendation mode;
wherein, the similarity calculation formula is as follows:
wherein, Sim (. beta.) isi,βj) is a similarity value, βiis the feature vector, beta, of the i-th garmentjIs the jth feature vector in the K feature vectors.
Optionally, the feature vector is bound to the features of the garment, that is, the features of the garment are vectorized. Generally, the characteristics of the garment include material, color, style, size, and pattern. Specifically, the features of the garment are represented by an n-dimensional vector X, i.e., X ═ X1, X2, X3, …, xn]Which isIn the formula, n is a positive integer. Assuming that the material comprises m (m < n) materials such as cotton, nylon and terylene, the first m dimension in the vector X is set to represent the material, each coordinate represents a material, and the coordinate X is set to represent the material1～xmThe specific formula is the proportion of m materials such as cotton, chinlon, terylene and the like in the total materials of the clothing, if one of the m materials is lacked in a certain piece of clothing, the corresponding coordinate of the material is 0; assuming that the colors include h colors such as black, white, red, yellow, blue, and green, m +1 to m + h dimensions of a vector X can be set to sequentially represent the colors, wherein the coordinate Xm+1～xm+hThe specific ratio of h colors such as black, white, red, yellow, blue, green and the like to the total area of the garment is; assuming that the style has suit, elegance, printing, fashion, evening dress, leisure and sports, the vector X represents the style in sequence from 7 dimensions after the dimension m + h, if the clothing contains a certain style, the corresponding coordinate is represented by 1, otherwise, the coordinate is represented by 0; assuming that the sizes of the upper garment are S, M, L, XL and XXL, and the size of the trousers is 28-38, so that the m + h + 1-n-3 dimensions of the vector X represent the sizes in sequence, if the garment belongs to a certain size, the corresponding coordinate is 1, and the corresponding coordinates of other sizes are all 0; assuming that the clothing pattern generally includes a plant pattern, an animal pattern and a geometric pattern, n-2 to n dimensions of a vector X are set to represent the patterns in order, and if a certain pattern is included, the corresponding coordinate of the pattern is 1, otherwise, the coordinate is 0.
For example, suppose the garment is a sweater made of cotton and nylon, wherein the cotton accounts for 70% of the whole material, so x1＝0.7，x2＝0.3，x3＝x4＝…＝xm0; if the color of the line clothing is black and white, the black accounts for 65 percent of the whole clothing area, so xm+1＝0.65，xm+2＝0.35，xm+3＝xm+4＝…＝xm+h0; if the shirt is a suit, xm+h+11, the coordinates of the other styles are all 0; if the size of the shirt is M, a coordinate x representing the size L is providedm+h+91, the remaining coordinates are 0, if the pattern of the sweater is a geometric pattern, xnX is 1n-1＝xn-2＝0Therefore, the feature vector of the line clothing is [0.7, 0.3, 0, …, 0.65, 0.35, 0, …, 1, 0, …, 0, 1, 0, …, 0, 0, 1, etc. ]]Where an ellipsis represents a zero coordinate in this dimension, it is replaced by an ellipsis for convenience of representation.
Optionally, before generating the first clothing recommendation manner, the electronic device acquires the characteristics of all the clothing by acquiring the tags of all the clothing in the user wardrobe, and vectorizes the characteristics according to the vectorization process. Further, after vectorization, storing the feature vectors of all the clothes in the wardrobe in a classified manner, namely storing the feature vectors of the same type of clothes in the same vector table, and establishing a wardrobe database. For example, the feature vectors of all the coats are stored in the vector table 1, the feature vectors of all the trousers are stored in the vector table 2, and so on. And when the characteristic vectors are saved, recording the clothes corresponding to each characteristic vector.
further, after determining the first matching manner, identifying the type of the i-th garment in the first matching manner (specifically, the i-th garment is the upper garment), the electronic device obtains a vector table (table 1) of the upper garment from the wardrobe database, assuming that K eigenvectors of the K upper garments are stored in the vector table, assuming that K is 4, and assuming that the eigenvectors corresponding to the four upper garments are β respectively1、β2、β3and beta4if the feature vector of the i-th garment is βicalculating beta according to the similarity formulaiand beta1、β2、β3and beta4Of (2) similarity value P1、P2、P3And P4If P is4at the maximum, query β4And the corresponding first clothing is used as a spare clothing of the ith clothing, the ith clothing is replaced by the first clothing to obtain a second clothing recommendation mode, the second clothing recommendation mode is displayed, and the second clothing recommendation mode is used as the spare clothing recommendation mode of the first clothing recommendation mode.
Further, the electronic device sequentially inquires the same type of clothes corresponding to the W pieces of clothes in the first clothes recommendation mode in the wardrobe database, determines W pieces of alternative clothes of the W pieces of clothes according to the method, replaces one piece of clothes in the W pieces of clothes with the alternative clothes corresponding to the clothes to obtain an alternative clothes recommendation mode, or replaces a plurality of pieces of clothes in the W pieces of clothes with a plurality of pieces of alternative clothes corresponding to the plurality of pieces of clothes to obtain an alternative clothes recommendation mode.
Optionally, in an example, the method further includes:
acquiring a first clothes matching mode, wherein the first clothes matching mode is an actual clothes recommendation mode;
determining the clothes with the recommended mode of the first clothes and the same type of the first clothes matching mode;
if the types of the M pieces of clothing in the first clothing recommending mode are the same as the types of the M pieces of clothing in the first clothing matching mode, obtaining M first characteristic vectors of the M pieces of clothing in the first clothing recommending mode, and obtaining M second characteristic vectors of the M pieces of clothing in the first clothing matching mode, wherein M is a positive integer;
determining similarity values of a first feature vector and a second feature vector of the same type of clothing, calculating a final similarity value according to a weighting formula, and if the final similarity value is smaller than a second preset threshold value, performing reverse training by taking the first clothing matching mode as input data to update the preset clothing recommendation model.
Wherein the weighting formula is:
S＝α1*S1+α2*S2+…+αM*SM
wherein S is the final similarity value, α1Is the weight value of the first type of clothing, S1a similarity value, alpha, corresponding to said first type of garment2Is the weight value of the second type of clothing, S2Is of the second kindsimilarity value, alpha, corresponding to type of garmentMWeight value of the Mth type of clothing, SMAnd the similarity value corresponding to the M type of clothing is obtained.
Wherein M, X and W are positive integers, M is less than or equal to X, and M is less than or equal to W.
Optionally, the clothing in the first clothing matching manner is clothing in the wardrobe of the user, and the feature vector corresponding to the X pieces of clothing in the first clothing matching manner is queried in the wardrobe database. Determining that the types of the X pieces of clothes are the same as the types of the W pieces of clothes in the first clothes recommendation mode, for example, if the first clothes matching mode and the first matching mode both have coats, determining that the two pieces of clothes are the same type of clothes. If the M pieces of clothing in the first matching mode are the same as the M pieces of clothing in the first matching mode, the M types of clothing are available in both the two clothing recommending modes. Acquiring M first characteristic vectors of the M pieces of clothing in the first clothing recommendation mode, wherein the first vectors refer to that the characteristic vectors corresponding to the M pieces of clothing in the first clothing recommendation mode are collectively called as first characteristic vectors, but any two first vectors are characteristic vectors of different clothing; obtaining M second feature vectors of the M pieces of clothing in the first clothing matching mode.
Further, similarity values of the first feature vector and the second feature vector of the same type of clothing are calculated respectively, for example, the similarity values of the first feature vector corresponding to the jacket in the first matching manner and the second feature vector corresponding to the jacket in the first matching manner are calculated to obtain M similarity values corresponding to M types of clothing, and the M similarity values respectively represent differences of the first matching manner and the first matching manner on the types of clothing. Since the variance may be a result of the user and not a problem with the model calculation, the variance needs to be considered as a whole. And if the final similarity value is smaller than a second preset threshold value, the first clothes matching mode is used as input data to perform reverse training to update the preset clothes recommendation model.
Wherein, the second preset threshold is 70%, 75%, 80%, 85% or other values.
Specifically, the way to assign the weights may be: the weight values assigned to the clothes that are easy to be ignored by the user are low, and the weight values assigned to the clothes that cannot be ignored by the user are high, for example, assuming that the clothes determined by the clothes recommendation model include five kinds of clothes, namely hat, jacket, trousers, shoes and bag, the specific weight values may be: the weight of the hat is 0.05, the weight of the bag is 0.10, the weight of the shoes is 0.15, the weight of the coat is 0.35, and the weight of the trousers is 0.35.
For example, if the first clothing recommendation mode includes five kinds of clothing, namely a hat, a jacket, trousers, shoes and a bag, and the first clothing recommendation mode includes only three kinds of clothing, namely a jacket, trousers and shoes, the two clothing recommendation modes include only three kinds of clothing with the same type, the trousers and the shoes in the two clothing recommendation modes are the same, and the first feature vector corresponding to the clothing in the first clothing recommendation mode is X1＝[0.7， 0.3，0，…，0.65，0.35，0，…，1，0，…，0，1，0，…，0，0，1]The second feature vector corresponding to the upper garment in the first garment matching mode is X2＝[0.7，0.3，0，…，0.45，0.55， 0，…，1，0，…，0，1，0，…，0，0，1]Therefore, the similarity value S corresponding to the upper garment in the two garment recommendation modes197.44% ═ 0.9744, the final similarity value S ═ 0.9744 × (0.35 +0.35 × (1 + 0.15) ≈ 0.85 can be obtained according to the weighting formula, and if the second predetermined threshold is 80%, the final similarity value is greater than the second predetermined threshold. Although the first clothing matching mode is not provided with a hat or a bag, the final similarity is larger than the second preset threshold value, so that the first clothing recommendation mode is correct, the clothing recommendation model does not need to be updated, and the problem of mistakenly updating the weight of the clothing recommendation model is avoided.
Therefore, the weather information, the physical sign information and the clothing scene information are obtained firstly, then the information is input into the preset clothing recommendation model for calculation, the output result is obtained, and the clothing recommendation mode suitable for the user is determined according to the output result. The clothes recommendation mode suitable for the user is obtained through model calculation, the environment, the characteristics, the preference and other factors are comprehensively considered, and the clothes recommendation accuracy is improved. And moreover, the clothes similarity is compared by combining the wardrobe of the user, and on the basis of displaying the first clothes recommendation mode, the alternative clothes recommendation mode with the maximum similarity is recommended for the user, so that more selection schemes are provided for the user, and the user experience is improved. Moreover, the difference between the recommended clothing recommending mode and the actual clothing matching mode is comprehensively considered, and the problem of mistakenly updating the model is avoided.
Another more detailed method flow is provided in the embodiment of the present application, as shown in fig. 2, fig. 2 is a schematic flow chart of another method for recommending clothing recommendation, where the method includes:
step 201: obtaining the satisfaction degrees corresponding to the historical clothes matching modes and the historical clothes matching modes, and combining the historical clothes matching modes with the satisfaction degrees larger than a first preset threshold value into training data.
Step 202: and carrying out forward training and reverse training on the training data to obtain a final weight, and constructing a preset clothing recommendation model.
Step 203: and acquiring weather information, physical sign information and clothing scene information.
Step 204: and forming input data by the weather information, the physical sign information and the clothing scene information, and inputting the input data into the preset clothing recommendation model for calculation to obtain an output result.
Step 205: and determining a first clothing recommendation mode according to the output result, inquiring K clothing with the same type as the ith clothing in the first clothing recommendation mode in a wardrobe database, and acquiring K characteristic vectors of the K clothing, wherein i and K are positive integers.
Step 206: and calculating K similarity values of the feature vector of the i-th garment and the K feature vectors according to a similarity calculation formula, and inquiring the first garment corresponding to the feature vector with the maximum similarity value in the K feature vectors.
Step 207: and replacing the ith clothing with the first clothing to obtain a second clothing recommendation mode, and displaying the first clothing recommendation mode and the second clothing recommendation mode.
Step 208: obtaining a first clothes matching mode, wherein the first clothes matching mode is an actual clothes matching mode.
Step 209: and determining the similarity value of the recommended mode of the first garment and the garment with the same type in the first garment matching mode.
Step 210: and calculating the final similarity value of the M similarity values of the clothes with the same type according to a weighting formula.
Step 211: and if the final similarity value is larger than a second preset threshold value, inputting the first clothes matching mode as input data into the preset clothes recommendation model, and updating the weight.
Referring to fig. 3, fig. 3 is a functional structure block diagram of a clothing recommendation device disclosed in the embodiment of the present application. The clothing recommendation device can be applied to an electronic device comprising a sensor and a processor, and comprises a training unit 301, an obtaining unit 302, an input unit 303, a determining unit 304, a display unit 305, a query unit 306, a calculating unit 307 and a replacing unit 308, wherein,
the training unit 301 is configured to obtain satisfaction degrees corresponding to historical clothing matching manners, combine the historical clothing matching manners corresponding to the satisfaction degrees into training data if the satisfaction degrees are greater than a first preset threshold, perform N-layer forward operation on the training data to obtain an output result, obtain an output result gradient according to the output result, perform N-layer reverse operation on the output result gradient to obtain a weight gradient of each layer, update the weight of each layer according to the weight gradient, obtain a final weight through multiple iterative computations, and construct the preset clothing recommendation model according to the final weight.
An obtaining unit 302, configured to obtain weather information, physical sign information, and clothing scene information;
the input unit 303 is configured to combine the weather information, the physical sign information, and the clothing scene information into input data, and input the input data into a preset clothing recommendation model for calculation to obtain an output result;
a determining unit 304, configured to determine a first service recommendation manner according to the output result;
a display unit 305, configured to display the first recommended mode of clothing;
a query unit 306, configured to query, in a wardrobe database, K pieces of clothing of the same type as an ith piece of clothing in the first clothing recommendation method, and obtain K feature vectors of the K pieces of clothing, where i and K are positive integers;
a calculating unit 307, configured to calculate, according to a similarity calculation formula, K similarity values between the feature vector of the i-th garment and the K feature vectors, and query a first garment corresponding to a feature vector with a maximum similarity value among the K feature vectors;
a replacing unit 308, configured to replace the i-th garment with the first garment to obtain a second garment recommendation manner.
The obtaining unit 302 is further configured to obtain a first clothing matching manner, where the first clothing matching manner is an actual clothing recommendation manner;
the determining unit 304 is further configured to determine a garment in which the first garment recommendation manner is the same as the first garment matching manner in type;
the obtaining unit 302 is further configured to, if the types of the M pieces of clothing in the first clothing recommendation manner are the same as the types of the M pieces of clothing in the first clothing matching manner, obtain M first feature vectors of the M pieces of clothing in the first clothing recommendation manner, and obtain M second feature vectors of the M pieces of clothing in the first clothing matching manner, where M is a positive integer;
the calculating unit 307 is further configured to determine similarity values of the first feature vector and the second feature vector of the same type of clothing, and calculate a final similarity value according to a weighting formula;
the input unit 303 is further configured to, if the final similarity value is smaller than a second preset threshold, input the first clothing matching manner to the preset clothing recommendation model for weight updating.
Referring to fig. 4, fig. 4 is a schematic structural diagram of another electronic device 400 according to an embodiment of the present disclosure, where the electronic device 400 includes: the device comprises an application processor AP410, a touch display screen 420, a transceiver 430 and a circuit 440, wherein the touch display screen and the transceiver are connected with the application processor AP through at least one circuit.
The transceiver 430 is used for acquiring weather information;
the AP410 is used for acquiring sign information and clothing scene information;
the AP410 is used for forming input data by the weather information, the physical sign information and the clothing scene information, and inputting the input data into a preset clothing recommendation model for calculation to obtain an output result;
the AP410 is configured to determine a first service recommendation manner according to the output result;
the touch display screen 420 is configured to display the first clothing recommendation method.
Referring to fig. 5, fig. 5 is a schematic structural diagram of another electronic device 500 according to an embodiment of the present disclosure. The electronic device 500 includes: an application processor 501, a memory 502, a communication interface 503, and one or more programs, wherein the one or more programs are stored in the memory 502 and configured to be executed by the application processor 501, the programs comprising instructions for:
acquiring weather information, physical sign information and clothing scene information;
the weather information, the physical sign information and the clothing scene information form input data, and the input data are input into a preset clothing recommendation model for calculation to obtain an output result;
and determining a first clothing recommendation mode according to the output result, and displaying the first clothing recommendation mode.
In an example, before obtaining the weather information, the physical sign information, and the clothing scene information, the program is further for executing the following steps:
obtaining satisfaction degrees corresponding to the historical clothes matching modes and the historical clothes matching modes, and combining the historical clothes matching modes with the satisfaction degrees larger than a first preset threshold value into training data;
executing N layers of forward operation on the training data to obtain an output result, obtaining an output result gradient according to the output result, executing N layers of reverse operation on the output result gradient to obtain a weight gradient of each layer, updating the weight of each layer according to the weight gradient, obtaining a final weight through multiple iterative computation, and constructing the preset clothing recommendation model according to the final weight.
In an example, after determining a first service recommendation manner according to the output result and displaying the first service recommendation manner, the program is further configured to execute the following steps:
inquiring K pieces of clothing with the same type as the ith piece of clothing in the first clothing recommendation mode in a wardrobe database, and acquiring K characteristic vectors of the K pieces of clothing, wherein i and K are positive integers;
calculating K similarity values of the feature vector of the i-th garment and the K feature vectors according to a similarity calculation formula, and inquiring a first garment corresponding to the feature vector with the maximum similarity value in the K feature vectors;
and replacing the i-th clothing with the first clothing to obtain a second clothing recommendation mode, and displaying the second clothing recommendation mode.
In one example, the program is further for instructions to perform the steps of:
acquiring a first clothes matching mode, wherein the first clothes matching mode is an actual clothes recommendation mode;
determining the clothes with the same type in the first clothes recommending mode and the first clothes matching mode;
if the types of the M pieces of clothing in the first clothing recommending mode are the same as the types of the M pieces of clothing in the first clothing matching mode, obtaining M first characteristic vectors of the M pieces of clothing in the first clothing recommending mode, and obtaining M second characteristic vectors of the M pieces of clothing in the first clothing matching mode, wherein M is a positive integer;
determining similarity values of a first feature vector and a second feature vector of the same type of clothing, calculating a final similarity value according to a weighting formula, and if the final similarity value is smaller than a second preset threshold value, performing reverse training on the first clothing matching mode as input data to update the preset clothing recommendation model.
Fig. 6 is a block diagram illustrating a partial structure of a mobile phone related to a terminal device provided in an embodiment of the present application. Referring to fig. 6, the handset includes: radio Frequency (RF) circuit 910, memory 920, input unit 930, sensor 950, audio circuit 960, Wireless Fidelity (WiFi) module 970, application processor AP980, and power supply 990. Those skilled in the art will appreciate that the handset configuration shown in fig. 6 is not intended to be limiting and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components.
The following describes each component of the mobile phone in detail with reference to fig. 6:
the input unit 930 may be used to receive input numeric or character information and generate key signal inputs related to user settings and function control of the cellular phone. Specifically, the input unit 930 may include a touch display screen 933, a fingerprint recognition apparatus 931, a face recognition apparatus 936, an iris recognition apparatus 937, and other input devices 932. The input unit 930 may also include other input devices 932. In particular, other input devices 932 may include, but are not limited to, one or more of physical keys, function keys (e.g., volume control keys, switch keys, etc.), a trackball, a mouse, a joystick, and the like. Wherein,
the AP980 is used for acquiring weather information, physical sign information and clothing scene information;
the weather information, the physical sign information and the clothing scene information form input data, and the input data are input into a preset clothing recommendation model for calculation to obtain an output result;
and determining a first clothing recommendation mode according to the output result, and displaying the first clothing recommendation mode.
Optionally, the AP980 is further configured to obtain satisfaction degrees corresponding to historical clothing matching manners and historical clothing matching manners, combine the historical clothing matching manners corresponding to the satisfaction degrees greater than a first preset threshold into training data, perform N layers of forward operations on the training data to obtain an output result, obtain an output result gradient according to the output result, perform N layers of reverse operations on the output result gradient to obtain a weight gradient of each layer, update the weight of each layer according to the weight gradient, obtain a final weight through multiple iterative computations, and construct the preset clothing recommendation model according to the final weight.
Optionally, the AP980 is further configured to query, in a wardrobe database, K pieces of clothing of the same type as the ith piece of clothing in the first clothing recommendation method, and obtain K feature vectors of the K pieces of clothing, where i and K are positive integers;
calculating K similarity values of the feature vector of the i-th garment and the K feature vectors according to a similarity calculation formula, and inquiring a first garment corresponding to the feature vector with the maximum similarity value in the K feature vectors;
and replacing the i-th clothing with the first clothing to obtain a second clothing recommendation mode, and displaying the second clothing recommendation mode.
The AP980 is a control center of the mobile phone, connects various parts of the entire mobile phone by using various interfaces and lines, and performs various functions and processes of the mobile phone by operating or executing software programs and/or modules stored in the memory 920 and calling data stored in the memory 920, thereby integrally monitoring the mobile phone. Optionally, AP980 may include one or more processing units; alternatively, the AP980 may integrate an application processor that handles primarily the operating system, user interface, and applications, etc., and a modem processor that handles primarily wireless communications. It will be appreciated that the modem processor described above may not be integrated into the AP 980.
Further, the memory 920 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device.
RF circuitry 910 may be used for the reception and transmission of information. In general, the RF circuit 910 includes, but is not limited to, an antenna, at least one Amplifier, a transceiver, a coupler, a Low Noise Amplifier (LNA), a duplexer, and the like. In addition, the RF circuit 910 may also communicate with networks and other devices via wireless communication. The wireless communication may use any communication standard or protocol, including but not limited to Global System for mobile communications (GSM), General Packet Radio Service (GPRS), Code Division Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), Long Term Evolution (LTE), email, Short Messaging Service (SMS), and the like.
The handset may also include at least one sensor 950, such as a light sensor, motion sensor, and other sensors. Specifically, the light sensor may include an ambient light sensor and a proximity sensor, wherein the ambient light sensor may adjust the brightness of the touch display screen according to the brightness of ambient light, and the proximity sensor may turn off the touch display screen and/or the backlight when the mobile phone moves to the ear. As one of the motion sensors, the accelerometer sensor can detect the magnitude of acceleration in each direction (generally, three axes), can detect the magnitude and direction of gravity when stationary, and can be used for applications of recognizing the posture of a mobile phone (such as horizontal and vertical screen switching, related games, magnetometer posture calibration), vibration recognition related functions (such as pedometer and tapping), and the like; as for other sensors such as a gyroscope, a barometer, a hygrometer, a thermometer, and an infrared sensor, which can be configured on the mobile phone, further description is omitted here.
Audio circuitry 960, speaker 961, microphone 962 may provide an audio interface between a user and a cell phone. The audio circuit 960 may transmit the electrical signal converted from the received audio data to the speaker 961, and the audio signal is converted by the speaker 961 to be played; on the other hand, the microphone 962 converts the collected sound signal into an electrical signal, and the electrical signal is received by the audio circuit 960 and converted into audio data, and the audio data is processed by the audio playing AP980, and then sent to another mobile phone via the RF circuit 910, or played to the memory 920 for further processing.
WiFi belongs to short-distance wireless transmission technology, and the mobile phone can help a user to receive and send e-mails, browse webpages, access streaming media and the like through the WiFi module 970, and provides wireless broadband Internet access for the user. Although fig. 6 shows the WiFi module 970, it is understood that it does not belong to the essential constitution of the handset, and can be omitted entirely as needed within the scope of not changing the essence of the application.
The handset also includes a power supply 990 (e.g., a battery) for supplying power to various components, and optionally, the power supply may be logically connected to the AP980 via a power management system, so that functions of managing charging, discharging, and power consumption are implemented via the power management system.
Although not shown, the mobile phone may further include a camera, a bluetooth module, a light supplement device, a light sensor, and the like, which are not described herein again.
Embodiments of the present application also provide a computer storage medium, wherein the computer storage medium stores a computer program for electronic data exchange, and the computer program enables a computer to execute part or all of the steps of any one of the fall data calculation methods based on artificial intelligence as described in the above method embodiments.
Embodiments of the present application also provide a computer program product comprising a non-transitory computer readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps of any one of the artificial intelligence based fall data calculation methods as set forth in the above method embodiments.
The steps of a method or algorithm described in the embodiments of the present application may be implemented in hardware, or may be implemented by a processor executing software instructions. The software instructions may be comprised of corresponding software modules that may be stored in Random Access Memory (RAM), flash Memory, Read Only Memory (ROM), Erasable Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), registers, a hard disk, a removable disk, a compact disc Read only Memory (CD-ROM), or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor such the processor can read information from, and write information to, the storage medium. Of course, the storage medium may also be integral to the processor. The processor and the storage medium may reside in an ASIC. Additionally, the ASIC may reside in an access network device, a target network device, or a core network device. Of course, the processor and the storage medium may reside as discrete components in an access network device, a target network device, or a core network device.
Those skilled in the art will appreciate that in one or more of the examples described above, the functionality described in the embodiments of the present application may be implemented, in whole or in part, by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the application to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored on a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website, computer, server, or data center to another website, computer, server, or data center via wire (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that incorporates one or more of the available media. The usable medium may be a magnetic medium (e.g., a floppy Disk, a hard Disk, a magnetic tape), an optical medium (e.g., a Digital Video Disk (DVD)), or a semiconductor medium (e.g., a Solid State Disk (SSD)), among others.
The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the embodiments of the present application in further detail, and it should be understood that the above-mentioned embodiments are only specific embodiments of the present application, and are not intended to limit the scope of the embodiments of the present application, and any modifications, equivalent substitutions, improvements and the like made on the basis of the technical solutions of the embodiments of the present application should be included in the scope of the embodiments of the present application.
Claims (11)
1. A method for recommending clothing, comprising:
acquiring weather information, physical sign information and clothing scene information;
the weather information, the physical sign information and the clothing scene information form input data, and the input data are input into a preset clothing recommendation model for calculation to obtain an output result;
and determining a first clothing recommendation mode according to the output result, and displaying the first clothing recommendation mode.
2. The method of claim 1, wherein prior to obtaining weather information, sign information, and clothing context information, the method further comprises:
obtaining satisfaction degrees corresponding to the historical clothes matching modes and the historical clothes matching modes, and combining the historical clothes matching modes with the satisfaction degrees larger than a first preset threshold value into training data;
executing N layers of forward operation on the training data to obtain an output result, obtaining an output result gradient according to the output result, executing N layers of reverse operation on the output result gradient to obtain a weight gradient of each layer, updating the weight of each layer according to the weight gradient, obtaining a final weight through multiple iterative computation, and constructing the preset clothing recommendation model according to the final weight.
3. The method according to claim 1 or 2, wherein the determining a first clothing recommendation manner according to the output result, and displaying the first clothing recommendation manner further comprises:
inquiring K pieces of clothing with the same type as the ith piece of clothing in the first clothing recommendation mode in a wardrobe database, and acquiring K characteristic vectors of the K pieces of clothing, wherein i and K are positive integers;
calculating K similarity values of the feature vector of the i-th garment and the K feature vectors according to a similarity calculation formula, and inquiring a first garment corresponding to the feature vector with the maximum similarity value in the K feature vectors;
replacing the i-th clothing with the first clothing to obtain a second clothing recommendation mode, and displaying the second clothing recommendation mode;
wherein, the similarity calculation formula is as follows:
wherein, Sim (. beta.) isi,βj) is a similarity value, βiIs that it ischaracteristic vector of the i-th garment, βjIs the jth feature vector in the K feature vectors.
4. The method of claim 1, further comprising:
acquiring a first clothes matching mode, wherein the first clothes matching mode is an actual clothes matching mode;
determining the clothes with the same type in the first clothes recommending mode and the first clothes matching mode;
if the types of the M pieces of clothing in the first clothing recommending mode are the same as the types of the M pieces of clothing in the first clothing matching mode, obtaining M first characteristic vectors of the M pieces of clothing in the first clothing recommending mode, and obtaining M second characteristic vectors of the M pieces of clothing in the first clothing matching mode, wherein M is a positive integer;
determining similarity values of a first feature vector and a second feature vector of the same type of clothing, calculating a final similarity value according to a weighting formula, and updating the weight value of the preset clothing recommendation model by taking the first clothing matching mode as input data if the final similarity value is smaller than a second preset threshold value.
5. The method of claim 4, wherein determining the final similarity value according to a weighting formula comprises:
the weighting formula is as follows:
S＝α1*S1+α2*S2+…+αM*SM
wherein S is the final similarity value, α1Is the weight value of the first type of clothing, S1a similarity value, alpha, corresponding to said first type of garment2Is the weight value of the second type of clothing, S2a similarity value, alpha, corresponding to said second type of garmentMWeight value of the Mth type of clothing, SMAnd the similarity value corresponding to the M type of clothing is obtained.
6. An electronic device for garment recommendation, the electronic device comprising:
the acquisition unit is used for acquiring weather information, physical sign information and clothing scene information;
the input unit is used for forming input data by the weather information, the physical sign information and the clothing scene information, and inputting the input data into a preset clothing recommendation model for calculation to obtain an output result;
the determining unit is used for determining a first service recommendation mode according to the output result;
and the display unit is used for displaying the first clothing recommendation mode.
7. An electronic device, the electronic device comprising: the system comprises an application processor AP, a touch display screen and a transceiver, wherein the touch display screen and the transceiver are connected with the application processor through at least one circuit;
the transceiver is used for acquiring weather information;
the AP is used for acquiring sign information and clothing scene information;
the AP is used for forming input data by the weather information, the physical sign information and the clothing scene information, and inputting the input data into a preset clothing recommendation model for calculation to obtain an output result;
the AP is used for determining a first service recommendation mode according to the output result;
the touch display screen is used for displaying the first clothing recommendation mode.
8. The electronic device of claim 7,
the AP is further used for obtaining the satisfaction degrees corresponding to the historical clothing matching modes and the historical clothing matching modes, combining the historical clothing matching modes corresponding to the satisfaction degrees larger than a first preset threshold value into training data, executing N layers of forward operation on the training data to obtain an output result, obtaining an output result gradient according to the output result, executing N layers of reverse operation on the output result gradient to obtain a weight gradient of each layer, updating the weight of each layer according to the weight gradient, obtaining a final weight through multiple iterative computation, and constructing the preset clothing recommendation model according to the final weight.
9. The electronic device according to claim 7 or 8,
the AP is further used for inquiring K pieces of clothing with the same type as the ith piece of clothing in the first clothing recommendation mode in a wardrobe database, and acquiring K characteristic vectors of the K pieces of clothing, wherein i and K are positive integers;
the AP is further used for calculating K similarity values of the feature vector of the i-th garment and the K feature vectors according to a similarity calculation formula, and inquiring the first garment corresponding to the feature vector with the maximum similarity value in the K feature vectors;
the AP is used for replacing the i-th garment with the first garment to obtain a second garment recommendation mode;
the touch display screen is further used for displaying the second clothing recommendation mode.
10. A computer-readable storage medium, characterized in that it stores a computer program for electronic data exchange, wherein the computer program causes a computer to perform the method according to any one of claims 1-5.
11. A computer program product, characterized in that the computer program product comprises a non-transitory computer readable storage medium storing a computer program operable to cause a computer to perform the method according to any of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810084286.4A CN108363750B (en) | 2018-01-29 | 2018-01-29 | Clothing recommendation method and related products |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810084286.4A CN108363750B (en) | 2018-01-29 | 2018-01-29 | Clothing recommendation method and related products |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108363750A true CN108363750A (en) | 2018-08-03 |
| CN108363750B CN108363750B (en) | 2022-01-04 |
Family
ID=63007511
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810084286.4A Active CN108363750B (en) | 2018-01-29 | 2018-01-29 | Clothing recommendation method and related products |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108363750B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109242555A (en) * | 2018-08-24 | 2019-01-18 | 深圳艺达文化传媒有限公司 | Voice-based advertisement broadcast method and Related product |
| CN109242554A (en) * | 2018-08-24 | 2019-01-18 | 深圳艺达文化传媒有限公司 | The switching method and Related product of elevator card |
| CN109255652A (en) * | 2018-08-24 | 2019-01-22 | 深圳艺达文化传媒有限公司 | Advertisement broadcast method and Related product based on face |
| CN109800357A (en) * | 2019-01-24 | 2019-05-24 | 江苏工程职业技术学院 | A kind of clothes recommended method and system based on weather |
| CN110647688A (en) * | 2019-09-30 | 2020-01-03 | 上海掌门科技有限公司 | Information presentation method and device, electronic equipment and computer readable medium |
| CN111626818A (en) * | 2020-05-20 | 2020-09-04 | 中电(福建)工业互联网研究院有限公司 | Children shoe size prediction method and system |
| CN111797663A (en) * | 2019-08-02 | 2020-10-20 | 北京京东尚科信息技术有限公司 | Collocation scene recognition method and device |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006031200A (en) * | 2004-07-14 | 2006-02-02 | Nec Corp | Commodity retrieval system and method, and terminal device, server device and program used therefor |
| CN103248658A (en) * | 2012-02-10 | 2013-08-14 | 富士通株式会社 | Service recommendation device, service recommendation method and mobile device |
| CN103440587A (en) * | 2013-08-27 | 2013-12-11 | 刘丽君 | Personal image designing and product recommendation method based on online shopping |
| CN105808774A (en) * | 2016-03-28 | 2016-07-27 | 北京小米移动软件有限公司 | Information providing method and device |
| CN106446065A (en) * | 2016-09-06 | 2017-02-22 | 珠海市魅族科技有限公司 | Clothes collocation recommendation 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 |
| CN106649494A (en) * | 2016-10-10 | 2017-05-10 | 北京光年无限科技有限公司 | Intelligent robot clothing recommendation method and recommendation system based on multimodal information |
| CN107147852A (en) * | 2017-06-29 | 2017-09-08 | 维沃移动通信有限公司 | Image capturing method, mobile terminal and computer-readable recording medium |
-
2018
- 2018-01-29 CN CN201810084286.4A patent/CN108363750B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006031200A (en) * | 2004-07-14 | 2006-02-02 | Nec Corp | Commodity retrieval system and method, and terminal device, server device and program used therefor |
| CN103248658A (en) * | 2012-02-10 | 2013-08-14 | 富士通株式会社 | Service recommendation device, service recommendation method and mobile device |
| CN103440587A (en) * | 2013-08-27 | 2013-12-11 | 刘丽君 | Personal image designing and product recommendation method based on online shopping |
| 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 |
| CN105808774A (en) * | 2016-03-28 | 2016-07-27 | 北京小米移动软件有限公司 | Information providing method and device |
| CN106446065A (en) * | 2016-09-06 | 2017-02-22 | 珠海市魅族科技有限公司 | Clothes collocation recommendation method and device |
| CN106649494A (en) * | 2016-10-10 | 2017-05-10 | 北京光年无限科技有限公司 | Intelligent robot clothing recommendation method and recommendation system based on multimodal information |
| CN107147852A (en) * | 2017-06-29 | 2017-09-08 | 维沃移动通信有限公司 | Image capturing method, mobile terminal and computer-readable recording medium |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109242555A (en) * | 2018-08-24 | 2019-01-18 | 深圳艺达文化传媒有限公司 | Voice-based advertisement broadcast method and Related product |
| CN109242554A (en) * | 2018-08-24 | 2019-01-18 | 深圳艺达文化传媒有限公司 | The switching method and Related product of elevator card |
| CN109255652A (en) * | 2018-08-24 | 2019-01-22 | 深圳艺达文化传媒有限公司 | Advertisement broadcast method and Related product based on face |
| CN109242555B (en) * | 2018-08-24 | 2021-07-02 | 苏州市明日企业形象策划传播有限公司 | Voice-based advertisement playing method and related product |
| CN109255652B (en) * | 2018-08-24 | 2021-09-03 | 深圳市启鹏天辰科技有限公司 | Advertisement playing method based on human face and related product |
| CN109800357A (en) * | 2019-01-24 | 2019-05-24 | 江苏工程职业技术学院 | A kind of clothes recommended method and system based on weather |
| CN111797663A (en) * | 2019-08-02 | 2020-10-20 | 北京京东尚科信息技术有限公司 | Collocation scene recognition method and device |
| CN110647688A (en) * | 2019-09-30 | 2020-01-03 | 上海掌门科技有限公司 | Information presentation method and device, electronic equipment and computer readable medium |
| CN111626818A (en) * | 2020-05-20 | 2020-09-04 | 中电(福建)工业互联网研究院有限公司 | Children shoe size prediction method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108363750B (en) | 2022-01-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108363750B (en) | Clothing recommendation method and related products | |
| CN111260665B (en) | Image segmentation model training method and device | |
| CN108520058B (en) | Merchant information recommendation method and mobile terminal | |
| CN110021061B (en) | Collocation model construction method, clothing recommendation method, device, medium and terminal | |
| CN107480496B (en) | Unlocking control method and related product | |
| CN109918975A (en) | A kind of processing method of augmented reality, the method for Object identifying and terminal | |
| CN110738211A (en) | object detection method, related device and equipment | |
| CN104200249B (en) | A kind of method of clothing automatic collocation, apparatus and system | |
| CN108875594B (en) | Face image processing method, device and storage medium | |
| CN105303149B (en) | The methods of exhibiting and device of character image | |
| CN110516113B (en) | Video classification method, video classification model training method and device | |
| CN107451454B (en) | Unlocking control method and related product | |
| CN114450690A (en) | Network model training method, image attribute identification method and device and electronic equipment | |
| CN108170817A (en) | Differentiation video acquiring method, device and the readable storage medium storing program for executing of photo main body | |
| CN112766406B (en) | Method and device for processing object image, computer equipment and storage medium | |
| CN111353100A (en) | Clothing information recommendation method and device, mobile terminal and storage medium | |
| CN111797148A (en) | Data processing method, data processing device, storage medium and electronic equipment | |
| CN117765564A (en) | User gesture recognition method and device, electronic equipment and storage medium | |
| CN113709385B (en) | Video processing method and device, computer equipment and storage medium | |
| CN113015996A (en) | Advertisement pushing method and related equipment | |
| CN110443852B (en) | Image positioning method and related device | |
| CN108388842A (en) | Intelligent prompt method and Related product | |
| CN115171196B (en) | Face image processing method, related device and storage medium | |
| CN108197898B (en) | Dressing recommendation method and mobile terminal | |
| CN107832690B (en) | Face recognition method and related product |
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 | ||
| CB02 | Change of applicant information |
Address after: 523860 No. 18, Wusha Haibin Road, Chang'an Town, Dongguan City, Guangdong Province Applicant after: Oppo Guangdong Mobile Communication Co., Ltd Address before: 523860 No. 18, Wusha Haibin Road, Chang'an Town, Dongguan City, Guangdong Province Applicant before: Guangdong opper Mobile Communication Co., Ltd |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |