Contact lens virtual try-on and intelligent makeup collaborative recommendation system and method

Abstract

The invention provides a contact lens virtual try-on and intelligent makeup collaborative recommendation system and method, and relates to the technical field of augmented reality, and the method comprises the steps: obtaining the facial features and matching demands of a user; recommending matched contact lenses and facial makeup to the user based on the facial features and the matching requirements; and the user is assisted to virtually try on the contact lenses and virtually put on the face. According to the method, the facial features and the matching requirements of the user are obtained, the matched contact lenses and facial makeup are automatically recommended to the user based on the facial features and the matching requirements, finally, the user is assisted to carry out virtual try-on on the contact lenses and carry out virtual face fitting on the facial makeup, intelligent contact lens wearing and makeup collaborative recommendation is provided for the user, and the user experience is improved. And the coordination of the overall makeup of the user is considered, so that the user experience is improved.

Description

Technical Field

[0001] The present invention relates to the field of augmented reality technology, and in particular to a contact lens virtual try-on and intelligent makeup collaborative recommendation system and method. Background Art

[0002] With the advancement of digital and intelligent technologies, virtual try-on systems have gradually become part of everyday life, particularly within the beauty industry. Traditional virtual try-on systems typically focus on showcasing a single product, such as contact lenses, lipstick, or eyeshadow. Users can upload photos or use a live camera feed to visualize how these products will look on their face. However, these systems often only display the effects of a single product and lack consideration for the overall coordination of the makeup look. This results in a limited user experience, particularly in scenarios involving makeup combinations, where intelligent recommendations and optimization are often inadequate.

[0003] Therefore, a solution is urgently needed. Summary of the Invention

[0004] One of the purposes of the present invention is to provide a contact lens virtual try-on and intelligent makeup collaborative recommendation system, which obtains the user's facial features and matching requirements, and automatically recommends matching contact lenses and facial makeup to the user based on the two. Finally, it assists the user to virtually try on contact lenses and virtually apply facial makeup, providing the user with intelligent contact lens wearing and makeup collaborative recommendations, taking into account the coordination of the user's overall makeup, and improving the user experience.

[0005] An embodiment of the present invention provides a contact lens virtual try-on and intelligent makeup collaborative recommendation system, comprising:

[0006] The acquisition module is used to obtain the user's facial features and matching requirements;

[0007] The recommendation module is used to recommend contact lenses and facial makeup to users based on facial features and matching requirements;

[0008] The auxiliary module is used to assist users in virtually trying on contact lenses and virtually applying facial makeup.

[0009] Optionally, the facial features include at least: face shape, eyebrow shape, eye size and shape, eye distance, nose shape, lip shape, skin color, and facial proportions;

[0010] The matching requirements include at least: travel scenarios, preferred makeup styles, types of activities to participate in, and functional requirements of contact lenses.

[0011] Optionally, the recommendation module recommends matching contact lenses and facial makeup to the user based on facial features and matching requirements, including:

[0012] Based on the pre-trained collaborative matching model, it recommends matching contact lenses and facial makeup to users according to their facial features and matching needs;

[0013] The pre-training steps of the collaborative collocation model are as follows:

[0014] A large amount of matching information marked with standard matching schemes is used as training samples for machine learning training to obtain a collaborative matching model.

[0015] Optionally, the auxiliary module assists the user in virtually trying on contact lenses and virtually applying facial makeup, including:

[0016] Plan the virtual rhythm of applying facial makeup and the virtual timing of wearing contact lenses respectively;

[0017] Based on the virtual makeup rhythm, interactively assist users to apply facial makeup;

[0018] During the process of interactively assisting the user in applying facial makeup, when entering the virtual wearing opportunity, the interactively assisting user performs a virtual try-on of the contact lenses.

[0019] Optionally, the separately planning of the virtual rhythm of applying facial makeup and the virtual timing of wearing contact lenses includes:

[0020] Analyze multiple makeup elements of facial makeup;

[0021] Based on the makeup element matching constraints, the makeup elements are matched to obtain multiple makeup slices;

[0022] Based on the serialization processing constraints, each makeup slice is serialized to obtain a makeup slice sequence;

[0023] Give the makeup slice sequence rhythm control mechanism to obtain the virtual face application rhythm;

[0024] Generating a virtual wearing time of the contact lens, including: the user's average actual acceptance of the virtual upper face of the makeup slices for a threshold number of consecutive times exceeds an actual acceptance threshold;

[0025] The makeup element matching constraints include:

[0026] The same makeup element is included in at least two makeup slices;

[0027] And, each makeup slice contains at least one makeup element related to the eyes;

[0028] Also, the similarity between any two makeup slices does not exceed the similarity threshold;

[0029] The serialization processing constraints include:

[0030] The user predicted preference and sequence order of each makeup slice in the makeup slice sequence are mapped into the curve coordinate system to form a complete peak;

[0031] Among them, the rhythm control mechanism includes:

[0032] Step 1: Virtually apply each makeup slice in the makeup slice sequence to the face in sequence;

[0033] Step 2: When the i-th makeup slice in the makeup slice sequence is virtually applied to the face, the j value is determined based on the user's actual acceptance at that time;

[0034] Step 3: Apply the i+jth makeup slice in the makeup slice sequence to the face virtually, and use the i+jth makeup slice as the new i-th makeup slice to return to step 2 and repeat the cycle;

[0035] Wherein, 1≤i+j≤N, N is the total number of makeup slices in the makeup slice sequence.

[0036] Optionally, the auxiliary module assists the user in virtually trying on contact lenses and virtually applying facial makeup, and further includes:

[0037] When the user does not like the contact lenses / facial makeup that they have tried on virtually, the user is assisted in quickly selecting alternative contact lenses / facial makeup to try on virtually / apply on virtually;

[0038] The quick selection steps for replacing contact lenses / changing facial makeup are as follows:

[0039] Obtaining a sequence of user operation records of partially zooming in on a target interface displaying a virtual contact lens try-on or a virtual facial makeup application within a recent preset time period;

[0040] Analyze the operation frequency of the operation record sequence;

[0041] When the operation frequency does not exceed the frequency threshold, a first quick selection list is generated based on a first replacement material library of contact lenses / facial makeup that the user does not like that virtually tried on, and the user is allowed to quickly select a replacement contact lens / facial makeup from the first quick selection list;

[0042] Otherwise, the filtering period of the operation record sequence is parsed; wherein the first and last moments of the filtering period are the two moments with the greatest distance between them among the multiple moments when the user stays in the same area for a period exceeding the stay time threshold.

[0043] parsing an operation element set of an operation area in a screening period of the operation record sequence;

[0044] Based on the set of operating elements, matching a second replacement material library;

[0045] Based on the second replacement material library, a second quick selection list is generated, and the user is allowed to quickly select replacement contact lenses / replacement facial makeup from the second quick selection list.

[0046] An embodiment of the present invention provides a method for collaboratively recommending contact lens virtual try-on and intelligent makeup, comprising:

[0047] Obtain the user's facial features and matching requirements;

[0048] Recommend matching contact lenses and facial makeup to users based on facial features and matching needs;

[0049] Assist users to virtually try on contact lenses and virtually apply facial makeup.

[0050] Optionally, the facial features include at least: face shape, eyebrow shape, eye size and shape, eye distance, nose shape, lip shape, skin color, and facial proportions;

[0051] The matching requirements include at least: travel scenarios, preferred makeup styles, types of activities to participate in, and functional requirements of contact lenses.

[0052] Optionally, the recommendation module recommends matching contact lenses and facial makeup to the user based on facial features and matching requirements, including:

[0053] Based on the pre-trained collaborative matching model, it recommends matching contact lenses and facial makeup to users according to their facial features and matching needs;

[0054] The pre-training steps of the collaborative collocation model are as follows:

[0055] A large amount of matching information marked with standard matching schemes is used as training samples for machine learning training to obtain a collaborative matching model.

[0056] Optionally, the auxiliary module assists the user in virtually trying on contact lenses and virtually applying facial makeup, including:

[0057] Plan the virtual rhythm of applying facial makeup and the virtual timing of wearing contact lenses respectively;

[0058] Based on the virtual makeup rhythm, interactively assist users to apply facial makeup;

[0059] During the process of interactively assisting the user in applying facial makeup, when entering the virtual wearing opportunity, the interactively assisting user performs a virtual try-on of the contact lenses.

[0060] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or will be understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0061] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0063] Figure 1 Schematic diagram of a contact lens virtual try-on and intelligent makeup collaborative recommendation system according to an embodiment of the present invention;

[0064] Figure 2 Schematic diagram of a method for collaboratively recommending contact lens virtual try-on and intelligent makeup according to an embodiment of the present invention. DETAILED DESCRIPTION

[0065] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0066] The embodiment of the present invention provides a contact lens virtual try-on and intelligent makeup collaborative recommendation system, such as Figure 1 Shown, including:

[0067] Acquisition module 1, used to obtain the user's facial features and matching requirements;

[0068] Recommendation module 2 is used to recommend matching contact lenses and facial makeup to users based on facial features and matching requirements;

[0069] Auxiliary module 3, used to assist users in virtually trying on contact lenses and virtually applying facial makeup;

[0070] The facial features include at least: face shape, eyebrow shape, eye size and shape, eye distance, nose shape, lip shape, skin color, and facial proportions;

[0071] The matching requirements include at least: travel scenarios, preferred makeup styles, types of activities to participate in, and functional requirements of contact lenses.

[0072] Facial features can be acquired by taking photos with the camera of the user's smart terminal. Matching requirements can be acquired by inputting them through the smart terminal. The smart terminal can be a mobile phone used by the user or a service device placed in a public place. The system automatically recommends matching contact lenses and facial makeup to the user based on facial features and matching requirements, and then assists the user in virtually trying on contact lenses and applying facial makeup.

[0073] For example, a female user is about to attend a formal dance and has the following characteristics and needs:

[0074] Face shape: Oval

[0075] Skin tone: Warm (slightly golden)

[0076] Eyes: Large, almond-shaped

[0077] Matching requirements: Prefer elegant and romantic makeup, and use contact lenses to increase the brightness and depth of the eyes.

[0078] The prom is a formal occasion, so she needs a sophisticated, glamorous makeup look to complement her contact lenses. Based on her face shape, the system recommends makeup that accentuates her features, such as soft blush and well-placed highlights. Her warm skin tone is well-suited to gold or copper eyeshadow and a warm lip color, which enhances her complexion. Because her large eyes and almond shape lend themselves well to a more intense eye makeup, the system recommends a smoky eye or metallic eyeshadow, along with mascara to amplify and brighten her eyes. Since the user wants to add brightness and depth to her eyes, the system recommends a dark brown or purple contact lens. After selecting the recommended contact lenses and makeup style, the system uses augmented reality to show the user how they would look with the lenses and makeup. She can observe in real time how the lenses enhance the depth of her eyes and how the makeup complements her face shape and skin tone.

[0079] This application obtains the user's facial features and matching needs, and automatically recommends matching contact lenses and facial makeup to the user based on the two. Finally, it assists the user to virtually try on contact lenses and virtually apply facial makeup, providing the user with intelligent contact lens wearing and makeup collaborative recommendations, taking into account the coordination of the user's overall makeup, and improving the user experience.

[0080] In one embodiment, the recommendation module recommends matching contact lenses and facial makeup to the user based on facial features and matching requirements, including:

[0081] Based on the pre-trained collaborative matching model, it recommends matching contact lenses and facial makeup to users according to their facial features and matching needs;

[0082] The pre-training steps of the collaborative collocation model are as follows:

[0083] A large amount of matching information marked with standard matching schemes is used as training samples for machine learning training to obtain a collaborative matching model.

[0084] Standard matching plans are contact lens and facial makeup combinations pre-created by matching experts based on matching criteria information; matching criteria information refers to the facial features and matching needs of different people. By using a large amount of matching criteria information labeled with standard matching plans as training samples for machine learning, the resulting collaborative matching model can adaptively recommend matching contact lenses and facial makeup to users based on facial features and matching needs, improving the efficiency of matching contact lens and facial makeup recommendations.

[0085] In particular, most of the current virtual makeup try-on technologies work by virtually projecting pre-set makeup effects directly onto the user's face. These makeups are usually standard effects set by designers or programs, covering different makeup styles, tones, and combinations. However, since most of these makeups are relatively complex or too strong, many users may feel uncomfortable when they see them for the first time, or feel that the effects are too exaggerated, leading to a rejection reaction. For example, for users who prefer natural makeup, when they see that the virtual try-on presents a heavy smoky makeup or a bright red lip makeup, they may immediately give up trying it on, or even directly close the virtual try-on interface. This not only wastes the opportunity to try on virtual makeup, but also affects the user experience.

[0086] Furthermore, in virtual try-on technology, the timing of contact lens application is crucial because it directly impacts the user experience, especially how it matches the makeup look. Putting contact lenses on right from the start can disrupt the user's overall perception of the makeup.

[0087] In order to solve the above technical problems, in one embodiment, the auxiliary module assists the user in virtually trying on contact lenses and virtually applying facial makeup, including:

[0088] Plan the virtual rhythm of applying facial makeup and the virtual timing of wearing contact lenses respectively;

[0089] Based on the virtual makeup rhythm, interactively assist users to apply facial makeup;

[0090] During the process of interactively assisting the user in applying facial makeup, when entering the virtual wearing opportunity, the interactively assisting user performs a virtual try-on of the contact lenses.

[0091] The virtual face-applying rhythm is the rhythm of applying facial makeup in layers and in sequence; the virtual wearing opportunity is the opportunity when the user is applying facial makeup to virtually wear contact lenses; after the respective planning is completed, based on the virtual face-applying rhythm, the user is interactively assisted in applying facial makeup. During the process of interactively assisting the user in applying facial makeup, when entering the virtual wearing opportunity, the user is interactively assisted in virtually trying on contact lenses.

[0092] The embodiment of the present invention interactively assists the user in applying facial makeup according to the virtual makeup rhythm, avoids directly applying facial makeup to the user virtually, which may cause adverse feelings such as discomfort, avoids wasting opportunities for virtual try-on, and improves user experience; secondly, in the process of interactively assisting the user in applying facial makeup, when entering the virtual wearing opportunity, the user is interactively assisted in virtually trying on contact lenses, avoids directly trying on contact lenses virtually and interfering with the user's overall perception of makeup, and further improves user experience.

[0093] In one embodiment, the steps of separately planning the virtual application rhythm of facial makeup and the virtual wearing timing of contact lenses include:

[0094] Analyze multiple makeup elements of facial makeup; makeup elements include at least: foundation, eye makeup, lip makeup, contouring and highlighting, decorative items, etc.

[0095] Based on the makeup element matching constraints, the makeup elements are matched to obtain multiple makeup slices; under the constraints of serialization processing constraints, the multiple groups of matched makeup elements each form a different makeup slice;

[0096] Based on the serialization processing constraint, each makeup slice is serialized to obtain a makeup slice sequence; under the constraint of the serialization processing constraint, each makeup slice is sorted to form a makeup slice sequence;

[0097] A makeup slice sequence rhythm control mechanism is given to obtain a virtual face-applying rhythm; the makeup slice sequence indicates the makeup slices that need to be virtually applied to the user's face in sequence, and given a rhythm control mechanism, a virtual face-applying rhythm of the facial makeup is formed;

[0098] Generating a virtual wearing opportunity for contact lenses includes: the user's average actual acceptance of the virtual application of makeup slices for a consecutive threshold number of times exceeds the actual acceptance threshold; each time a makeup slice is used to virtually apply the makeup to the user, an actual acceptance feedback form is pushed to the user for the user to fill in the actual acceptance, and the actual acceptance represents the user's acceptance of the makeup slice for the virtual application; the threshold may be 4; the actual acceptance threshold is a threshold representing a greater acceptance of the user's virtual application of makeup slices; when the user's average actual acceptance of the virtual application of makeup slices for a consecutive threshold number of times exceeds the actual acceptance threshold, indicating that the user has been relatively accepting of the makeup slices for each virtual application, and at this time the user has basically understood the overall perception of the makeup and can virtually wear the contact lenses, and then the virtual wearing opportunity is entered;

[0099] The makeup element matching constraints include:

[0100] The same makeup element is included in at least two makeup slices;

[0101] Furthermore, each makeup slice contains at least one makeup element related to the eyes; makeup elements related to the eyes include at least: eye shadow, eyeliner, eyebrows, eye primer, etc.;

[0102] In addition, the similarity between any two makeup slices does not exceed the similarity threshold; the similarity threshold is the threshold representing a greater degree of similarity between two makeup slices; first, ensure that each makeup element appears in at least two makeup slices, so that the use of makeup elements can be more balanced and coordinated, and avoid some elements from appearing too abrupt or unbalanced. Secondly, each makeup slice must contain at least one makeup element related to the eyes, ensuring that the eyes always occupy a prominent position in the makeup slice, so that the overall design is more visually focused on the eyes and is consistent with the virtual wearing effect of contact lenses. Finally, by limiting the similarity between makeup slices, the uniqueness and creativity of each slice is enhanced, ensuring the diversity and personalization of makeup styles. Overall, these constraints help to match a makeup slice that is balanced, beautiful, varied and creative.

[0103] The serialization processing constraints include:

[0104] The curve obtained by mapping the user's predicted preference and sequence order for each makeup slice in the makeup slice sequence into a curve coordinate system forms a complete peak; the horizontal axis of the curve coordinate system is the sequence order, and the vertical axis is the predicted preference. Mapping the user's predicted preference and sequence order for each makeup slice into the curve coordinate system will obtain a coordinate point. The curve is formed by connecting the left points in sequence. If the curve forms a peak, it means that when the makeup slices in the makeup slice sequence are virtually applied to the face in the order of sequence, the user will gradually adapt and accept it (the rising phase of the complete peak), reaching the highest acceptance (the peak of the complete peak), and then slowly try out makeup that may be less acceptable (the falling phase of the complete peak), greatly improving the user experience. The user's predicted preference can be calculated as the average selection frequency of different makeup element pairs in the user's historical selection of makeup slices.

[0105] Among them, the rhythm control mechanism includes:

[0106] Step 1: Virtually apply each makeup slice in the makeup slice sequence to the face in sequence;

[0107] Step 2: When the i-th makeup slice in the makeup slice sequence is virtually applied to the face, the j value is determined based on the user's actual acceptance at that time;

[0108] Step 3: Apply the i+jth makeup slice in the makeup slice sequence to the face virtually, and use the i+jth makeup slice as the new i-th makeup slice to return to step 2 and repeat the cycle;

[0109] Wherein, 1≤i+j≤N, N is the total number of makeup slices in the makeup slice sequence.

[0110] The j value is positively correlated with the user's actual acceptance of the given look. The greater the user's actual acceptance of the given look, the more likely the makeup slices will be skipped during the next virtual makeup application, and the larger the j value. Specifically, a lookup table containing j values corresponding to different user acceptance levels can be pre-set by technical personnel, and the j value can be queried each time the j value is determined. By evaluating the user's actual acceptance of each virtual makeup slice in real time, the order of subsequent makeup presentations can be dynamically adjusted. Specifically, based on user feedback, the system calculates the j value to determine how many makeup slices to skip and then displays the next most suitable makeup slice for virtual application. When the actual acceptance is high, the j value increases, allowing the system to skip more makeup slices and quickly display makeup slices of different styles. When the acceptance is low, the j value is reduced, minimizing the order of virtual makeup application and avoiding rapid switching. This makes the virtual makeup application process more personalized and interactive, further improving the user experience, avoiding redundant presentations, and significantly optimizing the pacing and effectiveness of virtual makeup recommendations.

[0111] In one embodiment, the auxiliary module assists the user in virtually trying on contact lenses and virtually applying facial makeup, and further includes:

[0112] When the user does not like the contact lenses / facial makeup that they have tried on virtually, the user is assisted in quickly selecting alternative contact lenses / facial makeup to try on virtually / apply on virtually;

[0113] The quick selection steps for replacing contact lenses / changing facial makeup are as follows:

[0114] Obtain a sequence of user operation records of zooming in on a target interface displaying a virtual contact lens or virtual facial makeup application within a recent preset time period; the recent preset time period may be the last 100 seconds; the operation record sequence is a sequence of zooming in operation records sorted in chronological order, including the operation time, zoomed in area, etc.

[0115] Analyze the operation frequency of the operation record sequence; based on the operation record sequence, determine the frequency of the user's partial zoom viewing on the target interface within a recent preset time;

[0116] When the operation frequency does not exceed the frequency threshold, a first quick selection list is generated based on the first replacement material library of the contact lenses / facial makeup that the user does not like the virtual try-on, and the user is allowed to quickly select replacement contact lenses / replacement facial makeup from the first quick selection list; the frequency threshold is a threshold representing a higher viewing frequency; generally, when the user does not like the contact lenses / facial makeup that the user does not like the virtual try-on, if he does not like it at all, he will not zoom in on the target interface for viewing; therefore, when the operation frequency does not exceed the frequency threshold, it means that the user basically does not like the virtual try-on contact lenses / facial makeup that the user does not like, and a first quick selection list is generated directly based on the first replacement material library of the contact lenses / facial makeup that the user does not like the virtual try-on, and the user is allowed to quickly select replacement contact lenses / replacement facial makeup from the first quick selection list; the first replacement material library contains a large number of materials that can replace the contact lenses / facial makeup that the user does not like the virtual try-on;

[0117] Otherwise, the filtering period of the operation record sequence is analyzed; the first and last moments of the filtering period are the two moments with the greatest distance between them among the multiple moments in which the user stays and zooms in on the same area for more than the dwell time threshold; otherwise, it indicates that the user is still interested in a certain part of the virtual contact lens try-on / virtual facial makeup; the dwell time threshold is a threshold representing a longer dwell time for zooming in on the same area; the two moments with the greatest distance between them among the multiple moments in which the user stays and zooms in on the same area for more than the dwell time threshold are used as the first and last moments of the filtering period, thereby making it easier to find the part of interest to the user within the filtering period;

[0118] Parsing an operation record sequence for an operation element set in an operation area during a screening period; the operation element set includes makeup elements, contact lens elements, etc. in the operation area;

[0119] Based on the set of operation elements, a second replacement material library is matched; the second replacement material library contains materials that are related to the set of operation elements and are different from the contact lenses or facial makeup that the user does not like to virtually try on;

[0120] Based on the second replacement material library, a second quick selection list is generated, and the user is allowed to quickly select replacement contact lenses / replacement facial makeup from the second quick selection list.

[0121] The embodiments of the present invention help users find contact lenses or makeup that better suits their needs through fast and accurate personalized recommendations, reduce unnecessary operations and waiting time, and enhance the accuracy and satisfaction of virtual try-ons; based on the operation frequency of the operation record sequence, it quickly determines whether the user basically completely dislikes the virtually tried-on contact lenses / virtual facial makeup and takes corresponding quick selection assistance for replacing contact lenses / replacing facial makeup, which greatly improves the accuracy of assisting users in quickly selecting replacement contact lenses / replacing facial makeup and improves the applicability of the system.

[0122] The embodiment of the present invention provides a method for collaboratively recommending contact lens virtual try-on and intelligent makeup. Figure 2 Shown, including:

[0123] S1. Obtain the user's facial features and matching requirements;

[0124] S2: Recommend matching contact lenses and facial makeup to users based on facial features and matching needs;

[0125] S3. Assist users to virtually try on contact lenses and virtually apply facial makeup.

[0126] The facial features include at least: face shape, eyebrow shape, eye size and shape, eye distance, nose shape, lip shape, skin color, and facial proportions;

[0127] The matching requirements include at least: travel scenarios, preferred makeup styles, types of activities to participate in, and functional requirements of contact lenses.

[0128] The recommendation module recommends matching contact lenses and facial makeup to users based on facial features and matching requirements, including:

[0129] Based on the pre-trained collaborative matching model, it recommends matching contact lenses and facial makeup to users according to their facial features and matching needs;

[0130] The pre-training steps of the collaborative collocation model are as follows:

[0131] A large amount of matching information marked with standard matching schemes is used as training samples for machine learning training to obtain a collaborative matching model.

[0132] The auxiliary module assists the user in virtually trying on contact lenses and virtually applying facial makeup, including:

[0133] Plan the virtual rhythm of applying facial makeup and the virtual timing of wearing contact lenses respectively;

[0134] Based on the virtual makeup rhythm, interactively assist users to apply facial makeup;

[0135] During the process of interactively assisting the user in applying facial makeup, when entering the virtual wearing opportunity, the interactively assisting user performs a virtual try-on of the contact lenses.

[0136] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A contact lens virtual try-on and intelligent makeup collaborative recommendation system, characterized in that: include: The acquisition module is used to obtain the user's facial features and matching requirements; The recommendation module is used to recommend contact lenses and facial makeup to users based on facial features and matching requirements; The auxiliary module is used to assist users in virtually trying on contact lenses and virtually applying facial makeup.

2. The contact lens virtual try-on and intelligent makeup collaborative recommendation system according to claim 1, characterized in that: The facial features include at least: face shape, eyebrow shape, eye size and shape, eye distance, nose shape, lip shape, skin color, and facial proportions; The matching requirements include at least: travel scenarios, preferred makeup styles, types of activities to participate in, and functional requirements of contact lenses.

3. The contact lens virtual try-on and intelligent makeup collaborative recommendation system according to claim 1, characterized in that: The recommendation module recommends matching contact lenses and facial makeup to users based on facial features and matching requirements, including: Based on the pre-trained collaborative matching model, it recommends matching contact lenses and facial makeup to users according to their facial features and matching needs; The pre-training steps of the collaborative collocation model are as follows: A large amount of matching information marked with standard matching schemes is used as training samples for machine learning training to obtain a collaborative matching model.

4. The contact lens virtual try-on and intelligent makeup collaborative recommendation system according to claim 1, characterized in that: The auxiliary module assists the user in virtually trying on contact lenses and virtually applying facial makeup, including: Plan the virtual rhythm of applying facial makeup and the virtual timing of wearing contact lenses respectively; Based on the virtual makeup rhythm, interactively assist users to apply facial makeup; During the process of interactively assisting the user in applying facial makeup, when entering the virtual wearing opportunity, the interactively assisting user performs a virtual try-on of the contact lenses.

5. The contact lens virtual try-on and intelligent makeup collaborative recommendation system according to claim 4, characterized in that: The planning of the virtual application rhythm of facial makeup and the virtual wearing timing of contact lenses respectively includes: Analyze multiple makeup elements of facial makeup; Based on the makeup element matching constraints, the makeup elements are matched to obtain multiple makeup slices; Based on the serialization processing constraints, each makeup slice is serialized to obtain a makeup slice sequence; Give the makeup slice sequence rhythm control mechanism to obtain the virtual face application rhythm; Generating a virtual wearing time of the contact lens, including: the user's average actual acceptance of the virtual upper face of the makeup slices for a threshold number of consecutive times exceeds an actual acceptance threshold; The makeup element matching constraints include: The same makeup element is included in at least two makeup slices; And, each makeup slice contains at least one makeup element related to the eyes; Also, the similarity between any two makeup slices does not exceed the similarity threshold; The serialization processing constraints include: The user predicted preference and sequence order of each makeup slice in the makeup slice sequence are mapped into the curve coordinate system to form a complete peak; Among them, the rhythm control mechanism includes: Step 1: Virtually apply each makeup slice in the makeup slice sequence to the face in sequence; Step 2: When the i-th makeup slice in the makeup slice sequence is virtually applied to the face, the j value is determined based on the user's actual acceptance at that time; Step 3: Apply the i+jth makeup slice in the makeup slice sequence to the face virtually, and use the i+jth makeup slice as the new i-th makeup slice to return to step 2 and repeat the cycle; Wherein, 1≤i+j≤N, N is the total number of makeup slices in the makeup slice sequence.

6. The contact lens virtual try-on and intelligent makeup collaborative recommendation system according to claim 4, characterized in that: The auxiliary module assists the user in performing virtual try-on of contact lenses and virtual application of facial makeup, and further includes: When the user does not like the contact lenses / facial makeup that they have tried on virtually, the user is assisted in quickly selecting alternative contact lenses / facial makeup to try on virtually / apply on virtually; The quick selection steps for replacing contact lenses / changing facial makeup are as follows: Obtaining a sequence of user operation records of partially zooming in on a target interface displaying a virtual contact lens try-on or a virtual facial makeup application within a recent preset time period; Analyze the operation frequency of the operation record sequence; When the operation frequency does not exceed the frequency threshold, a first quick selection list is generated based on a first replacement material library of contact lenses / facial makeup that the user does not like that virtually tried on, and the user is allowed to quickly select a replacement contact lens / facial makeup from the first quick selection list; Otherwise, the filtering period of the operation record sequence is parsed; wherein the first and last moments of the filtering period are the two moments with the greatest distance between them among the multiple moments when the user stays in the same area for a period exceeding the stay time threshold. parsing an operation element set of an operation area in a screening period of the operation record sequence; Based on the set of operating elements, matching a second replacement material library; Based on the second replacement material library, a second quick selection list is generated, and the user is allowed to quickly select replacement contact lenses / replacement facial makeup from the second quick selection list.

7. A contact lens virtual try-on and intelligent makeup collaborative recommendation method, characterized in that: include: Obtain the user's facial features and matching requirements; Recommend matching contact lenses and facial makeup to users based on facial features and matching needs; Assist users to virtually try on contact lenses and virtually apply facial makeup.

8. The contact lens virtual try-on and intelligent makeup collaborative recommendation method according to claim 7, characterized in that: The facial features include at least: face shape, eyebrow shape, eye size and shape, eye distance, nose shape, lip shape, skin color, and facial proportions; The matching requirements include at least: travel scenarios, preferred makeup styles, types of activities to participate in, and functional requirements of contact lenses.

9. The contact lens virtual try-on and intelligent makeup collaborative recommendation method according to claim 7, characterized in that: The method of recommending matching contact lenses and facial makeup to users based on facial features and matching needs includes: Based on the pre-trained collaborative matching model, it recommends matching contact lenses and facial makeup to users according to their facial features and matching needs; The pre-training steps of the collaborative collocation model are as follows: A large amount of matching information marked with standard matching schemes is used as training samples for machine learning training to obtain a collaborative matching model.

10. The contact lens virtual try-on and intelligent makeup collaborative recommendation method according to claim 7, characterized in that: The assisting user to virtually try on contact lenses and virtually apply facial makeup comprises: Plan the virtual rhythm of applying facial makeup and the virtual timing of wearing contact lenses respectively; Based on the virtual makeup rhythm, interactively assist users to apply facial makeup; During the process of interactively assisting the user in applying facial makeup, when entering the virtual wearing opportunity, the interactively assisting user performs a virtual try-on of the contact lenses.

Images