Skin care product private customization system based on AI

Abstract

The invention provides an AI-based skin care product private customization system, and relates to the technical field of digital beauty industry. According to the invention, through the objective dimension management unit, the subjective dimension management unit and the category dimension management unit, classification management can be carried out on extracted objective skin care requirements, user subjective requirements and skin care category requirements, and professional skin care suggestions of professionals are involved in weights of different dimensions through the weight dimension management unit. The skin care product has a balanced formula ratio, so that the customization is more scientific and professional; training management and matching management are carried out on a plurality of cloud formula models through a cloud model management unit of the cloud; the user, the store and the factory do not need to be provided with a special management system, and the execution condition of each stage is mastered by the cloud; the problems that in the prior art, skin care products can be customized only according to user face data, adjustment strategies of different dimensions are lacked, and customization requirements of other dimensions cannot be met are solved.

Description

Technical Field

[0001] The present invention relates to the field of digital beauty technology, and in particular to an AI-based personal customization system for skin care products. Background Art

[0002] As we all know, due to different skin conditions of each person, the required skin care ingredients will also be different. This is the so-called "one thousand faces for one thousand people"; however, at this stage, skin care products are seriously homogenized, and the components of various skin care products are highly similar, resulting in the skin care effects of the products being similar, and unable to provide customers with targeted needs.

[0003] When users have a certain skin care need, they need to understand the differences between different products and professional skin care knowledge, and choose skin care products by themselves to meet their personalized needs. This method is time-consuming, labor-intensive, and has low accuracy, and cannot guarantee the ultimate skin care effect.

[0004] Therefore, we need to formulate skin care products according to the customer's skin condition, so as to obtain products that can meet the customer's skin care needs, which is what we call customized skin care products. However, the current customized skin care product system has many problems, the most important of which is that it can only customize skin care products based on the user's facial data, lacks adjustment strategies in different dimensions, and cannot meet customization needs in other dimensions.

[0005] Therefore, there is an urgent need for an AI-based skin care product customization system to solve the problem that the current skin care product customization system lacks adjustment strategies in different dimensions and cannot meet the customization needs in other dimensions. Summary of the invention

[0006] The purpose of the present invention is to overcome the shortcomings of the prior art and provide an AI-based skin care product customization system, which mainly solves the problem that the prior art can only customize skin care products according to user facial data, lacks adjustment strategies in different dimensions, and cannot meet customization needs in other dimensions.

[0007] The purpose of the present invention is achieved through the following technical solutions:

[0008] The present invention provides an AI-based skin care product customization system, which is deployed in the cloud and communicated with each smart terminal respectively, including a smart terminal acquisition unit, an objective dimension management unit, a subjective dimension management unit, a category dimension management unit, a weight dimension management unit, a cloud model management unit and a private customization production management unit; wherein,

[0009] The smart terminal acquisition unit is used to collect user portrait data and user setting data through the smart terminal, and upload the user portrait data and user setting data to the cloud; wherein the user portrait data includes user facial feature data, user personal information data, user location information data and collection time information data;

[0010] The objective dimension management unit is used to manage objective dimension feature data; wherein the objective dimension feature data is non-artificially set data, which is obtained by analyzing and processing user portrait data;

[0011] The subjective dimension management unit is used to manage subjective dimension feature data; wherein the subjective dimension feature data is artificially set data, obtained by analyzing and processing user setting data;

[0012] The category dimension management unit is used to manage category dimension feature data; wherein the category dimension feature data is used to describe the skin care product types and the degree attributes corresponding to each skin care product type;

[0013] The weight dimension management unit is used to adjust the training weight value of each data item of objective dimension feature data, subjective dimension feature data and category dimension feature data; wherein the training weight value is determined by professionals;

[0014] The cloud model management unit is used to manage a number of cloud recipe models; wherein, cloud model training is performed by combining objective dimension feature data, subjective dimension feature data and category dimension feature data with training weight values ​​of each data item, thereby obtaining a number of cloud recipe models; the cloud recipe models are used to generate private customized recipe data;

[0015] The private customized production management unit is used to manage the production of private customized formula data.

[0016] As a further solution, the objective dimensional feature data includes facial partition data; the facial partition data is obtained by processing the user's facial feature data and is used to describe the skin type of each skin area on the user's face; wherein the skin type includes dry skin, neutral skin, oily skin and combination skin.

[0017] As a further solution, the objective dimension feature data includes regional partition data and regional climate data; wherein the regional partition data is used to describe the regional location of the user; and the regional climate data is used to describe the climate of the user's region.

[0018] As a further solution, the objective dimension feature data includes user age data; wherein the user age data is used to describe the user's current age stage.

[0019] As a further solution, the objective dimensional feature data includes skin stratification data; wherein, the skin stratification data is used to describe the skin condition of different skin layers of the user's facial skin; wherein, the skin layers include the epidermis, dermis and mesoderm.

[0020] As a further solution, the subjective dimension feature data includes skin care product fragrance data; wherein the skin care product fragrance data is used to describe the skin care product fragrance selected by the user.

[0021] As a further solution, the subjective dimension feature data includes skin care product packaging data; wherein the skin care product packaging data is used to describe the skin care product packaging style selected by the user.

[0022] As a further solution, the skin care product types include freckle removal type, acne removal type, wrinkle removal type, moisturizing type, whitening type, redness reduction type, itching relief type, anti-aging type, anti-allergic type, oil control and eye care type; wherein, the skin care products include one or more skin care product types.

[0023] As a further solution, when customizing skin care products: the cloud model management unit uses the user's objective dimension feature data, subjective dimension feature data, and category dimension feature data, and queries the cloud formula model with the highest similarity to the training feature data; and inputs the user's objective dimension feature data, subjective dimension feature data, and category dimension feature data into the cloud formula model with the highest similarity, thereby obtaining the best custom formula data.

[0024] As a further solution, the private customization production management unit includes a home customization management module, a store customization management module and a factory customization management module; wherein the home customization management module is used to manage the private customization formula data of skin care products of the home customization terminal; the store customization management module is used to manage the private customization formula data of skin care products of the store customization terminal; the factory customization management module is used to manage the private customization formula data of skin care products sent to the customization factory.

[0025] Compared with related technologies, the AI-based skin care product customization system provided by the present invention has the following advantages:

[0026] The present invention collects user portrait data and user setting data through the intelligent terminal collection unit. The user portrait data not only includes user facial feature data, but also includes user personal information data, user location information data and collection time information data; through these data, we can extract feature data of different dimensions, thereby guiding us to produce personalized customized skin care products that meet objective skin care needs, user subjective needs and skin care category needs.

[0027] In addition, through the objective dimension management unit, subjective dimension management unit and category dimension management unit, we can classify and manage the extracted objective skin care needs, user subjective needs and skin care category needs, and through the weight dimension management unit, we can incorporate the professional skin care suggestions of professionals into the weights of different dimensions. Professionals can adjust the weight values ​​to make skin care products have a balanced formula ratio, so that customization is more scientific and professional.

[0028] Finally, the cloud model management unit in the cloud is used to manage the training and matching of several cloud formula models. Users, stores, and factories do not need to set up a dedicated management system. They only need to log in to the cloud to obtain the corresponding private customized formula data. In addition, the cloud can grasp the execution status of each stage. Therefore, the customization process can be tracked and live broadcasted throughout, ensuring that the entire customization process is open and transparent, increasing user participation and respecting their subjective choice intentions. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 A schematic diagram of the structure of an AI-based skin care product customization system provided by the present invention. DETAILED DESCRIPTION

[0030] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0031] See also Figure 1 The present invention provides an AI-based skin care product customization system, which is deployed in the cloud and communicates with each smart terminal respectively, including a smart terminal acquisition unit, an objective dimension management unit, a subjective dimension management unit, a category dimension management unit, a weight dimension management unit, a cloud model management unit and a private customization production management unit; wherein,

[0032] The smart terminal acquisition unit is used to collect user portrait data and user setting data through the smart terminal, and upload the user portrait data and user setting data to the cloud; wherein the user portrait data includes user facial feature data, user personal information data, user location information data and collection time information data;

[0033] The objective dimension management unit is used to manage objective dimension feature data; wherein the objective dimension feature data is non-artificially set data, which is obtained by analyzing and processing user portrait data;

[0034] The subjective dimension management unit is used to manage subjective dimension feature data; wherein the subjective dimension feature data is artificially set data, obtained by analyzing and processing user setting data;

[0035] The category dimension management unit is used to manage category dimension feature data; wherein the category dimension feature data is used to describe the skin care product types and the degree attributes corresponding to each skin care product type;

[0036] The weight dimension management unit is used to adjust the training weight value of each data item of objective dimension feature data, subjective dimension feature data and category dimension feature data; wherein the training weight value is determined by professionals;

[0037] The cloud model management unit is used to manage a number of cloud recipe models; wherein, cloud model training is performed by combining objective dimension feature data, subjective dimension feature data and category dimension feature data with training weight values ​​of each data item, thereby obtaining a number of cloud recipe models; the cloud recipe models are used to generate private customized recipe data;

[0038] The private customized production management unit is used to manage the production of private customized formula data.

[0039] It should be noted that the traditional method of customized skin care products is to directly use the user's facial data, analyze and process the user's facial data through an image analysis model, and send it directly to the back-end production terminal for production customization; this method has changed the serious problem of homogeneity of existing skin care products to a certain extent, but its customized process lacks the intervention of other dimensions; resulting in the customized products finally produced not necessarily meeting the user's usage needs.

[0040] Therefore, this embodiment collects user portrait data and user setting data through the intelligent terminal collection unit. The user portrait data not only includes user facial feature data, but also includes user personal information data, user location information data and collection time information data; through these data, we can extract feature data of different dimensions, thereby guiding us to produce customized skin care products that meet objective skin care needs, user subjective needs and skin care category needs.

[0041] In addition, through the objective dimension management unit, subjective dimension management unit and category dimension management unit, we can classify and manage the extracted objective skin care needs, user subjective needs and skin care category needs, and through the weight dimension management unit, we can incorporate the professional skin care suggestions of professionals into the weights of different dimensions. Professionals can adjust the weight values ​​to make skin care products have a balanced formula ratio, so that customization is more scientific and professional.

[0042] Finally, the cloud model management unit in the cloud is used to manage the training and matching of several cloud formula models. Users, stores, and factories do not need to set up a dedicated management system. They only need to log in to the cloud to obtain the corresponding private customized formula data. In addition, the cloud can grasp the execution status of each stage. Therefore, the customization process can be tracked and live broadcasted throughout, ensuring that the entire customization process is open and transparent, increasing user participation and respecting their subjective choice intentions.

[0043] As a further solution, the objective dimensional feature data includes facial partition data; the facial partition data is obtained by processing the user's facial feature data and is used to describe the skin type of each skin area on the user's face; wherein the skin type includes dry skin, neutral skin, oily skin and combination skin.

[0044] It should be noted that the facial skin is divided into different areas, and the skin types in different areas are also different; therefore, when customizing, we need to consider the skin type of the skin used in the skin care products, and specifically match the formula data corresponding to different skin types, so as to meet the objective skin type customization needs.

[0045] As a further solution, the objective dimension feature data includes regional partition data and regional climate data; wherein the regional partition data is used to describe the regional location of the user; and the regional climate data is used to describe the climate of the user's region.

[0046] It should be noted that: due to the different regions where users are located, their geographical conditions and climate conditions will also be different; for example, plateau areas need to strengthen ultraviolet protection, and dry climates need to focus on moisturizing skin care, etc.; therefore, this embodiment considers the two objective dimensions of geographical location and regional climate, and sets corresponding objective dimension feature data to describe its characteristics; so that our customized skin care products can meet the needs of this dimension.

[0047] As a further solution, the objective dimension feature data includes user age data; wherein the user age data is used to describe the user's current age stage.

[0048] It should be noted that user age is also a key objective dimension; skin conditions change with age, so our skin care formulas need to be adjusted accordingly for different age groups to meet the skin care needs of customers of different age groups.

[0049] As a further solution, the objective dimensional feature data includes skin stratification data; wherein, the skin stratification data is used to describe the skin condition of different skin layers of the user's facial skin; wherein, the skin layers include the epidermis, dermis and mesoderm.

[0050] It should be noted that due to the different skin layers, we need to carry out targeted and personalized customization according to the skin conditions of different layers, so as to meet the objective care needs of different skin layers.

[0051] As a further solution, the subjective dimension feature data includes skin care product fragrance data; wherein the skin care product fragrance data is used to describe the skin care product fragrance selected by the user.

[0052] It should be noted that the subjective dimension is mainly to meet the subjective feelings of users. For example, customer 1 wants skin care products with rose scent, while customer 2 wants skin care products with lavender scent. These demands have no objective basis but are changed according to the subjective needs of users. Traditional customized cosmetics systems do not take this dimension into consideration, which leads to a decline in user experience. This embodiment takes this subjective dimension into consideration and customizes skin care products that meet the subjective needs of customers by affecting the corresponding fragrance formula.

[0053] As a further solution, the subjective dimension feature data includes skin care product packaging data; wherein the skin care product packaging data is used to describe the skin care product packaging style selected by the user.

[0054] It should be noted that: similarly, packaging style is also one of the dimensions that customers can choose subjectively; we fully respect customers' subjective choices and set packaging styles that meet customer needs when customizing skin care products, so as to further meet customers' subjective needs.

[0055] As a further solution, the skin care product types include freckle removal type, acne removal type, wrinkle removal type, moisturizing type, whitening type, redness reduction type, itching relief type, anti-aging type, anti-allergic type, oil control and eye care type; wherein, the skin care products include one or more skin care product types.

[0056] It should be noted that this part is composed of three parts: objective dimension, subjective dimension and professionals, which jointly influence the type of skin care products, and adjust the emphasis of different types according to the degree attributes corresponding to each type of skin care products; for example, in a specific scenario, we use 12 levels to describe the proportion of different types; in this way, we can focus on skin care and achieve the purpose of precise care.

[0057] The objective dimension is mainly determined by the user's facial condition, such as acne, allergies, spots, lines, dark circles, large pores, blackheads, dry / oily / combined skin, etc., and there are also different degrees of objective needs in terms of firmness and skin tone. We determine the type of skin care products by determining these objective needs;

[0058] The subjective dimension is mainly based on the subjective wishes of the user. For example, although the customer's skin is not very dry, the customer subjectively needs the skin to be moisturized. Therefore, we need to adjust the type of skin care products to water type according to the customer's subjective needs, and comprehensively consider the degree of hydration to ensure a balance between the objective dimension, subjective dimension and professionals.

[0059] Professionals mainly make fine adjustments based on subjective and objective dimensions, so that different functional types of skin care products can be coordinated and integrated, making the final output formula more scientific and reasonable.

[0060] As a further solution, when customizing skin care products: the cloud model management unit uses the user's objective dimension feature data, subjective dimension feature data, and category dimension feature data, and queries the cloud formula model with the highest similarity to the training feature data; and inputs the user's objective dimension feature data, subjective dimension feature data, and category dimension feature data into the cloud formula model with the highest similarity, thereby obtaining the best custom formula data.

[0061] It should be noted that: We use similar model searches to quickly respond to customers' customization needs. After one training, we can reuse it countless times and output the best private customized formula data that meets customers' customization needs.

[0062] As a further solution, the private customization production management unit includes a home customization management module, a store customization management module and a factory customization management module; wherein the home customization management module is used to manage the private customization formula data of skin care products of the home customization terminal; the store customization management module is used to manage the private customization formula data of skin care products of the store customization terminal; the factory customization management module is used to manage the private customization formula data of skin care products sent to the customization factory.

[0063] It should be noted that we implement centralized cloud management for different customized terminals to facilitate recipe tracking and distribution, and achieve full data traceability. On this basis, we can broadcast the entire customization process live to users to increase the transparency of the customization process.

[0064] The above embodiments only express preferred implementation modes, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present invention. It should be pointed out that, for ordinary technicians in this field, several modifications and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention.

Claims

1. An AI-based skin care product customization system, deployed in the cloud and connected to each smart terminal, characterized in that: It includes intelligent terminal acquisition unit, objective dimension management unit, subjective dimension management unit, category dimension management unit, weight dimension management unit, cloud model management unit and private customized production management unit; among which, The smart terminal acquisition unit is used to collect user portrait data and user setting data through the smart terminal, and upload the user portrait data and user setting data to the cloud; wherein the user portrait data includes user facial feature data, user personal information data, user location information data and collection time information data; The objective dimension management unit is used to manage objective dimension feature data; wherein the objective dimension feature data is non-artificially set data, which is obtained by analyzing and processing user portrait data; The subjective dimension management unit is used to manage subjective dimension feature data; wherein the subjective dimension feature data is artificially set data, obtained by analyzing and processing user setting data; The category dimension management unit is used to manage category dimension feature data; wherein the category dimension feature data is used to describe the skin care product types and the degree attributes corresponding to each skin care product type; The weight dimension management unit is used to adjust the training weight value of each data item of objective dimension feature data, subjective dimension feature data and category dimension feature data; wherein the training weight value is determined by professionals; The cloud model management unit is used to manage a number of cloud recipe models; wherein, cloud model training is performed by combining objective dimension feature data, subjective dimension feature data and category dimension feature data with training weight values ​​of each data item, thereby obtaining a number of cloud recipe models; the cloud recipe models are used to generate private customized recipe data; The private customized production management unit is used to manage the production of private customized formula data.

2. The AI-based skin care product customization system according to claim 1, characterized in that: The objective dimension feature data includes facial partition data; the facial partition data is obtained by processing the user's facial feature data and is used to describe the skin type of each skin area on the user's face; wherein the skin type includes dry skin, neutral skin, oily skin and combination skin.

3. The AI-based skin care product customization system according to claim 1, characterized in that: The objective dimension feature data includes regional partition data and regional climate data; wherein the regional partition data is used to describe the regional location of the user; and the regional climate data is used to describe the climate of the user's region.

4. The AI-based skin care product customization system according to claim 1, characterized in that: The objective dimension feature data includes user age data; wherein the user age data is used to describe the user's current age stage.

5. The AI-based skin care product customization system according to claim 1, characterized in that: The objective dimension feature data includes skin stratification data; wherein, the skin stratification data is used to describe the skin condition of different skin layers of the user's facial skin; wherein, the skin layers include the epidermis, dermis and mesoderm.

6. The AI-based skin care product customization system according to claim 1, characterized in that: The subjective dimension feature data includes skin care product fragrance data; wherein the skin care product fragrance data is used to describe the skin care product fragrance selected by the user.

7. The AI-based skin care product customization system according to claim 1, characterized in that: The subjective dimension feature data includes skin care product packaging data; wherein the skin care product packaging data is used to describe the skin care product packaging style selected by the user.

8. The AI-based skin care product customization system according to claim 1, characterized in that: The types of skin care products include freckle removal type, acne removal type, wrinkle removal type, moisturizing type, whitening type, redness reduction type, itching relief type, anti-aging type, anti-allergic type, oil control and eye care type; wherein, the skin care products include one or more types of skin care products.

9. The AI-based skin care product customization system according to any one of claims 1 to 8, characterized in that: When performing personalized customization of skin care products: the cloud model management unit uses the user's objective dimension feature data, subjective dimension feature data and category dimension feature data, and queries the cloud formula model with the highest similarity to the training feature data; and inputs the user's objective dimension feature data, subjective dimension feature data and category dimension feature data into the cloud formula model with the highest similarity, thereby obtaining the best personalized customization formula data.

10. The AI-based skin care product customization system according to claim 1, characterized in that: The private customization production management unit includes a home customization management module, a store customization management module and a factory customization management module; wherein the home customization management module is used to manage the private customization formula data of skin care products of the home customization terminal; the store customization management module is used to manage the private customization formula data of skin care products of the store customization terminal; the factory customization management module is used to manage the private customization formula data of skin care products sent to the customization factory.

Images