An AI-driven skin assessment and skincare decision-making system and method

Abstract

The present invention discloses an AI-driven skin assessment and skincare decision-making system and method, belonging to the fields of big data and artificial intelligence. The system includes: a data acquisition module for obtaining skin images and user information; a skin assessment module for performing skin condition assessment through multimodal data fusion; a recommendation decision-making module for generating personalized skincare plans through reinforcement learning; a resource scheduling module for intelligently scheduling offline skincare resources; and an effect tracking module for obtaining post-care skin images corresponding to the expected skin improvement cycle in the expected effect and comparing and analyzing them with pre-care skin images to obtain the care effect. The present invention can perform skin condition assessment through multimodal data fusion and generate personalized skincare plans in combination with reinforcement learning.

Description

Technical Field

[0001] The present invention relates to the technical fields of big data and artificial intelligence, and particularly relates to a skin assessment and skin care decision-making system and method driven by AI. Background Art

[0002] Existing skin care decision-making methods only rely on image analysis and do not integrate multiple data such as users' living habits, resulting in a single evaluation dimension; when recommending skin care products, fixed rules are generally used to match products, and the strategy cannot be optimized according to the dynamic feedback of users. Existing skin care decision-making systems only stop at online suggestions and do not achieve intelligent connection with offline skin care services. Summary of the Invention

[0003] The present invention aims to solve at least one of the technical problems existing in the prior art. For this purpose, the present invention provides a skin assessment and skin care decision-making system and method driven by AI, which can evaluate the skin condition through multimodal data fusion, generate personalized skin care plans by combining reinforcement learning, and intelligently schedule offline skin care resources considering spatio-temporal constraints.

[0004] An embodiment of the present invention provides a skin assessment and skin care decision-making system driven by AI, including: a data acquisition module for acquiring skin images and user information, where the user information includes age, gender, skin type, work and rest information, skin care time preference, and skin care history information; a skin assessment module for obtaining the global skin problem classification probability, local lesion detection results, and multi-dimensional skin quality scoring results through a skin image classification model, a skin lesion detection model, and a skin quality scoring model, and fusing the user information to perform multi-model feature integration and dynamic weighting to generate a joint feature vector; a recommendation decision module for inputting the joint feature vector, performing collaborative filtering based on the user historical behavior matrix, obtaining potential factor vectors and population preference distributions through SVD++ decomposition; calculating the similarity of product ingredients to obtain a list of candidate products; constructing a state vector based on the potential factor vectors and population preference distributions, and based on the state vector, obtaining an action vector through the DDPG algorithm to optimize the list of candidate products; and generating a skin care plan based on the action vector; a resource scheduling module for obtaining the profiles and real-time status of skin care therapists, recommending skin care therapists based on the matching of the therapist-user bipartite graph; generating a scheduling plan based on the appointment request and the resource calendar, and obtaining the time period demand and the load of skin care therapists, and obtaining the real-time service price based on the dynamic pricing model; an effect tracking module for obtaining the skin image after skin care corresponding to the expected skin improvement cycle in the expected effect and comparing it with the skin image before skin care to obtain the skin care effect; adjusting the skin care cycle of the skin care plan based on the skin care effect and incrementally updating the therapist-user bipartite graph.

[0005] According to some embodiments of the present invention, the data acquisition module includes: an image acquisition unit for obtaining a standardized skin image based on light compensation and face positioning; a user input unit for obtaining user information and obtaining a standardized user vector through a rule encoder; the skin evaluation module includes:

[0006] An image classification unit for constructing a skin image classification model based on EfficientNet to obtain the global skin problem classification probability, and the formula is: ; where is the global skin problem classification probability, is the global skin problem classification weight matrix, is the classification bias term, is the image feature vector; a lesion detection unit for constructing a skin lesion detection model based on YOLOv8 to locate local skin abnormal points and quantify to obtain local lesion detection results, and the local lesion detection results include lesion location, lesion quantity and inflammation area; the detection formula is: ; where is the confidence level, is the probability of the existence of each lesion type within the prediction box, represents the predicted bounding box and the true bounding box the overlap degree between them; a quality scoring unit for constructing a skin quality scoring model based on ResNet50 + SE attention mechanism to obtain a multi-dimensional skin quality scoring result; the skin quality scoring model is: ; where is the score of the i-th skin quality dimension, and the skin quality dimension includes at least one of the following: fineness, glossiness and firmness, is the activation function, is the weight function of the regression head, k is the feature channel index, d is the total number of ResNet feature channels, marks the regression task parameters, is the feature map extracted by ResNet, is the global average pooling result of the ResNet feature map; a multi-modal fusion unit for performing multi-modal fusion and dynamic weighting on the skin image features and user information based on the first fusion formula to obtain a first joint feature vector; the fusion formula is: ; where is the first joint feature vector, and are the image feature weight coefficient and the user feature weight coefficient respectively, is the standardized user vector obtained according to the user information; adjust the image feature weight coefficient according to the skin image clarity, and adjust the user feature weight coefficient according to the user information integrity.

[0007] According to some embodiments of the present invention, the data acquisition module further includes: a sensor integration unit for obtaining environmental information based on an environmental detection device, where the environmental information includes temperature and humidity data and an ultraviolet index; a biometric unit for obtaining real-time physiological indicators in the user information based on a smart wearable device, and the real-time physiological indicators at least include a heart rate or a sebum secretion index.

[0008] According to some embodiments of the present invention, the multimodal fusion unit is used to perform multimodal fusion and dynamic weighting on skin image features, user information, environmental information, and real-time physiological indicators based on a second fusion formula to obtain a second joint feature vector; the second fusion formula: ; where is the second joint feature vector, and are the environmental feature weight coefficient and the physiological feature weight coefficient respectively, is the normalized environmental feature vector obtained according to the environmental information, is the normalized physiological feature vector obtained according to the real-time physiological indicators.

[0009] According to some embodiments of the present invention, the recommendation decision module includes: a collaborative filtering unit for obtaining a user historical behavior matrix R, , where is the user latent factor matrix, is the product latent factor matrix, N is the number of users, M is the number of products, and a latent factor vector and a group preference distribution are obtained, represents the product category; a product matching unit for obtaining the current skin problem vector output by EfficientNet and a product ingredient matrix , calculating the symptom-ingredient matching degree , and obtaining a candidate product list , is the ingredient vector of the jth product; a reinforcement learning policy unit for constructing a state vector according to the latent factor vector , the group preference distribution , the caregiver graph embedding vector , and the environmental feature vector , , and updating the action vector , the DDPG policy is as follows: , where are the policy network parameters, is the Gaussian exploration noise, is the value function, E is the mathematical expectation, r is the reward signal at the current moment, is the future reward discount factor, s’ is the new state transferred to after executing the action ; are the new policy network parameters corresponding to the new state s’; , where, is the product usage intensity coefficient, is the weight of the in-store care frequency, is the cost-sensitive adjustment factor, obtain the candidate product list , and screen the candidate product list according to the action vector ; The solution generation unit is used to obtain the candidate product list , the action vector and the user taboo rule library, filter the candidate product list according to the product usage intensity coefficient and adjust the concentration threshold of the candidate product, re-rank the priorities of the candidate products according to the cost-sensitive adjustment factor and the graph embedding similarity, calculate the care cycle according to the in-store care frequency weight and the caregiver load; output the care plan, and the care plan includes the product combination, the in-store cycle and the expected cost.

[0010] According to some embodiments of the present invention, the resource scheduling module includes: a caregiver recommendation unit, which is used to obtain the caregiver profile and real-time status, construct a caregiver-user bipartite graph, and the node types include caregiver nodes based on caregiver skill characteristics, user nodes based on skin characteristics, and store nodes based on location or device characteristics, and the edge types include service relationship edges based on service scores or repurchase times and membership relationship edges based on the subordination relationship between the caregiver and the store; match and recommend caregivers based on the caregiver-user bipartite graph: the caregiver graph matching formula is: , where, is the embedding of the -th layer caregiver node, is the embedding of the -th layer user node, W is the graph convolution weight matrix, is the activation function, and MEAN is the aggregation function; a spatio-temporal optimization unit, which is used to generate a scheduling plan according to the appointment request and the resource calendar; a dynamic pricing unit, which is used to obtain the period demand and the caregiver load, and obtain the real-time service price based on the dynamic pricing model: , where, is the basic service price, is the period demand heat, is the historical demand mean, is the demand standard deviation.

[0011] According to some embodiments of the present invention, the effect tracking module includes: a comparative analysis unit, configured to obtain a post-care skin image and a pre-care skin image for comparative analysis, and calculate an improvement degree : ; and are the pre-care image feature vector and the post-care image feature vector respectively, and are the pre-care skin quality score and the post-care skin quality score respectively; a change detection unit, configured to obtain a post-care skin image and a pre-care skin image, and obtain a pixel-level change heat map based on U-Net.

[0012] According to some embodiments of the present invention, the system includes: a graph data management module, configured to manage graph data; including: a graph storage unit, configured to obtain real-time interaction data and obtain a dynamic relationship graph based on Neo4j + Cypher; a graph sampling unit, configured to obtain original graph data and obtain a training sub-graph through sampling; a graph version control unit, configured to obtain a version snapshot of the graph structure based on the differential storage algorithm according to the graph operation log.

[0013] According to some embodiments of the present invention, the system further includes: a model update module, configured to obtain an incremental data set and obtain updated model weights based on federated learning.

[0014] The AI-driven skin assessment and skin care decision-making system according to the embodiments of the present invention has at least the following beneficial effects: The embodiments of the present invention can perform skin state assessment through multi-modal data fusion, generate personalized skin care plans in combination with reinforcement learning, and consider intelligent scheduling of offline skin care resources with spatio-temporal constraints.

[0015] Another aspect of the embodiments of the present invention provides an AI-driven skin assessment and skincare decision-making method, including the following steps: S100. Obtain skin images and user information, where the user information includes age, gender, skin type, work and rest information, nursing time preference, and nursing history information; S200. Obtain the global skin problem classification probability, local lesion detection results, and multi-dimensional skin quality scoring results through a skin image classification model, a skin lesion detection model, and a skin quality scoring model, and integrate the user information, perform multi-model feature integration and dynamic weighting to generate a joint feature vector; S300. Input the joint feature vector, perform collaborative filtering based on the user historical behavior matrix, obtain the latent factor vector and the population preference distribution through SVD++ decomposition; calculate the product ingredient similarity to obtain a list of candidate products; and construct a state vector based on the latent factor vector and the population preference distribution, and based on the state vector, obtain an action vector through the DDPG algorithm to optimize the list of candidate products; and generate a nursing plan based on the action vector; S400. Obtain the profiles and real-time status of nurses, recommend nurses based on the nurse-user bipartite graph matching; generate a scheduling plan based on the appointment request and the resource calendar, and obtain the time period demand and the nurse load, and obtain the real-time service price based on the dynamic pricing model; S500. Obtain the post-care skin image corresponding to the expected skin improvement cycle in the expected effect and compare it with the pre-care skin image for analysis to obtain the nursing effect; adjust the nursing cycle of the nursing plan based on the nursing effect and incrementally update the nurse-user bipartite graph.

[0016] One of the beneficial effects of the AI-driven skin assessment and skincare decision-making method of the embodiments of the present invention at least includes the following: The method of the embodiments of the present invention is used to implement the system of any one of the above, so the method of the embodiments of the present invention has all the beneficial effects possessed by the above system.

[0017] The additional aspects and advantages of the present invention will be partly given in the following description, partly will become obvious from the following description, or will be understood through the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The above and / or additional aspects and advantages of the present invention will become obvious and easy to understand from the description of the embodiments in conjunction with the following drawings, in which:

[0019] Figure 1 is a schematic block diagram of the modules of the system according to the embodiments of the present invention;

[0020] Figure 2 is a schematic flowchart of the method according to the embodiments of the present invention.

[0021] Reference numerals:

[0022] Data acquisition module 100, skin assessment module 200, recommendation decision module 300, resource scheduling module 400, and effect tracking module 500. Detailed implementation manners

[0023] The embodiments of the present invention will be described in detail below. The examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals represent the same or similar elements or elements with the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention and should not be construed as a limitation to the present invention.

[0024] In the description of the present invention, the meaning of several is one or more, the meaning of multiple is two or more, greater than, less than, exceeding, etc. are understood as not including the present number, and above, below, within, etc. are understood as including the present number. If the first and second are described only for the purpose of distinguishing technical features, they should not be understood as indicating or implying relative importance or implicitly indicating the quantity of the indicated technical features or implicitly indicating the sequence relationship of the indicated technical features.

[0025] Referring to Figure 1 , an AI-driven skin assessment and skincare decision-making system is proposed in an embodiment of the present invention, including:

[0026] A data acquisition module 100, configured to obtain skin images and user information, where the user information includes: age, gender, skin type, work and rest information, care time preference, and care history information.

[0027] A skin assessment module 200, configured to obtain the global skin problem classification probability, local lesion detection results, and multi-dimensional skin quality scoring results through a skin image classification model, a skin lesion detection model, and a skin quality scoring model, and fuse the user information to perform multi-model feature integration and dynamic weighting to generate a joint feature vector.

[0028] A recommendation decision module 300, configured to input the joint feature vector, perform collaborative filtering based on the user historical behavior matrix, obtain the latent factor vector and the population preference distribution through SVD++ decomposition; calculate the product ingredient similarity to obtain a candidate product list; and construct a state vector based on the latent factor vector and the population preference distribution, and based on the state vector, obtain an action vector through the DDPG algorithm to optimize the candidate product list; and generate a care plan based on the action vector.

[0029] A resource scheduling module 400, configured to obtain the caregiver profile and real-time status, recommend a caregiver based on the caregiver-user bipartite graph matching; generate a scheduling plan based on the appointment request and the resource calendar, and obtain the time period demand and the caregiver load, and obtain the real-time service price based on the dynamic pricing model.

[0030] The effect tracking module 500 is used to obtain the post-care skin image corresponding to the expected skin improvement cycle in the expected effect and compare it with the pre-care skin image for analysis to obtain the care effect; based on the care effect, adjust the care cycle of the care plan and incrementally update the caregiver-user bipartite graph.

[0031] In some embodiments, the data acquisition module 100 includes:

[0032] The image acquisition unit is used to obtain a standardized skin image based on light compensation and face localization.

[0033] The user input unit is used to obtain user information and obtain a standardized user vector through a rule encoder.

[0034] In some embodiments, the skin assessment module 200 includes:

[0035] The image classification unit is used to build a skin image classification model based on EfficientNet to obtain the global skin problem classification probability. The formula is:

[0036] ;

[0037] Among them, is the global skin problem classification probability, is the global skin problem classification weight matrix, is the classification bias term, is the image feature vector. EfficientNet dominates multi-modal fusion and provides a basic skin type judgment (such as oily / dry).

[0038] The lesion detection unit is used to build a skin lesion detection model based on YOLOv8, locate local skin abnormal points and quantify to obtain local lesion detection results. The local lesion detection results include lesion location, lesion quantity and inflammation area. The skin lesion detection model quantifies the severity (such as the number / area of acne) and triggers a specific care plan (such as local application of acid products). For example, if active inflammation is detected (such as more than 3 pustules), the weight of anti-inflammatory ingredients is automatically increased in the recommended plan.

[0039] The quality scoring unit is used to build a skin quality scoring model based on ResNet50 + SE attention mechanism to obtain a multi-dimensional skin quality scoring result; it is used for effect tracking (Δ score calculation) and guides cycle adjustment (such as shortening the care interval when the score improvement is slow). For example, when the firmness score is low, radio frequency care items are preferentially recommended. The skin quality scoring model of this embodiment is:

[0040] ;

[0041] Among them, is the score for the i-th skin quality dimension, and the skin quality dimensions include at least one of the following: fineness, glossiness, and firmness. is the activation function. is the weight function of the regression head, k is the feature channel index, and d is the total number of ResNet feature channels. Marks the regression task parameters. is the feature map extracted by ResNet. is the global average pooling result of the ResNet feature map.

[0042] The multimodal fusion unit is used to perform multimodal fusion and dynamic weighting on the skin image features and user information based on the first fusion formula to obtain the first joint feature vector; the fusion formula is:

[0043] ;

[0044] where is the first joint feature vector, and are the image feature weight coefficient and user feature weight coefficient respectively, is the normalized user vector obtained according to the user information; the image feature weight coefficient is adjusted according to the skin image clarity, and the user feature weight coefficient is adjusted according to the user information integrity.

[0045] In a specific embodiment, the user detected 2 inflammatory papules (YOLOv8 output), and the ResNet50 oiliness score was 8.5 / 10. Dynamic fusion: The YOLOv8 feature weight was increased to 0.4 (active lesions detected); Generate joint feature vector: [0.87, 6.8, 8.2, 2, 48, 0.85,...] (including global classification probability, number of lesions, inflammation area, oiliness score, etc.); Recommendation decision: Collaborative filtering: Match similar users (oily + local inflammation), Reinforcement learning: Select 1.5% salicylic acid (to avoid over-stimulation of 2% on active inflammation); Resource scheduling: Prioritize nurses who are good at acne care and have a daily load < 70%. The outputs of the three evaluation models in this embodiment jointly affect the decision through feature-level fusion (not used independently).

[0046] In some embodiments, the data acquisition module 100 further includes:

[0047] The sensor integration unit is used to obtain environmental information based on environmental detection devices, and the environmental information includes temperature and humidity data and ultraviolet index.

[0048] The biometric unit is used to obtain real-time physiological indicators in the user information based on intelligent wearable devices, and the real-time physiological indicators at least include heart rate or sebum secretion indicators.

[0049] In a specific embodiment, the environment: temperature 28°C, humidity 35%, UV = 9; physiology: sebum secretion rate 25 μg / cm² / min, pH = 6.0. The finally adapted recommended decision is: environmental adaptation: recommend SPF50+ sunscreen; physiological adaptation: increase the salicylic acid concentration to 2.5% (sebum secretion rate > 20 threshold).

[0050] In some embodiments, the multimodal fusion unit is configured to perform multimodal fusion and dynamic weighting on skin image features, user information, environmental information, and real-time physiological indicators based on a second fusion formula to obtain a second joint feature vector; the second fusion formula:

[0051] ;

[0052] wherein, is the second joint feature vector, and are the environmental feature weight coefficient and the physiological feature weight coefficient respectively, is the normalized environmental feature vector obtained according to the environmental information, is the normalized physiological feature vector obtained according to the real-time physiological indicators.

[0053] In some embodiments, the recommended decision module 300 includes:

[0054] A collaborative filtering unit, configured to obtain the user historical behavior matrix R, , where is the user latent factor matrix, is the product latent factor matrix, N is the number of users, M is the number of products, to obtain the latent factor vector and the group preference distribution , represents the product category.

[0055] A product matching unit, configured to obtain the current skin problem vector output by EfficientNet and the product ingredient matrix , calculate the symptom-ingredient matching degree , to obtain the candidate product list , is the ingredient vector of the j-th product.

[0056] A reinforcement learning policy unit, configured to construct a state vector according to the latent factor vector , the group preference distribution , the caregiver graph embedding vector , and the environmental feature vector , , update the action vector based on the DDPG strategy , , where is the product usage intensity coefficient, is the weight of the in-store care frequency, is the cost-sensitive adjustment factor, and obtain a list of candidate products , filter the list of candidate products according to the action vector .

[0057] The solution generation unit is used to obtain a list of candidate products and the action vector (it can also include a user taboo rule library), filter the list of candidate products according to the product usage intensity coefficient and adjust the concentration threshold of the candidate products, re-rank the priorities of the candidate products according to the cost-sensitive adjustment factor and the graph embedding similarity, and calculate the care cycle according to the in-store care frequency weight and the caregiver load; output a care plan, and the care plan includes a product combination, an in-store cycle, and an expected cost.

[0058] In the solution generation unit of this embodiment, a state vector is constructed according to the caregiver graph embedding vector, a product graph embedding vector is obtained through the product knowledge graph, the graph embedding similarity is obtained based on the product graph embedding vector and the caregiver graph embedding vector, the user-caregiver matching degree is obtained, and then the caregiver load used when calculating the care cycle by re-ranking the product priorities can be read from the graph node attributes of the caregiver graph embedding vector.

[0059] In some embodiments, the resource scheduling module 400 includes:

[0060] The caregiver recommendation unit is used to obtain the caregiver profile and real-time status, construct a caregiver-user bipartite graph, the node types include caregiver nodes based on caregiver skill characteristics, user nodes based on skin characteristics, and store nodes based on location or device characteristics, and the edge types include service relationship edges based on service scores or repeat purchase times and membership relationship edges based on the subordination relationship between the caregiver and the store; match and recommend caregivers based on GraphSAGE and the caregiver-user bipartite graph: the caregiver graph matching formula is: , where is the -layer caregiver node embedding, is the -layer user node embedding, W is the graph convolution weight matrix, is the activation function, and MEAN is the aggregation function.

[0061] The spatio-temporal optimization unit is used to generate a scheduling plan according to the appointment request and the resource calendar. The spatio-temporal optimization unit of this embodiment is optimized through GAT + constraint programming and GNN matching.

[0062] A dynamic pricing unit for obtaining the demand during a period and the load of nurses, and obtaining the real-time service price based on a dynamic pricing model: , where is the basic service price, is the demand heat during a period, is the historical demand average value, is the demand standard deviation.

[0063] In this embodiment, first, data preparation is performed to construct a bipartite graph of nurses - users (historical service records) and pre-trained graph neural network embeddings (cold start initialization). Then, data is collected for multimodal fusion to generate joint features. Nurses are recommended through graph attention matching, and dynamic pricing and scheduling optimization are performed. Finally, feedback learning is carried out: collecting nursing effect data and incrementally updating the graph structure.

[0064] In some embodiments, the effect tracking module 500 includes:

[0065] A comparative analysis unit for obtaining the skin image after nursing and the skin image before nursing for comparative analysis, and calculating the improvement degree : ; and are the image feature vectors before and after nursing respectively, and are the skin quality scores before and after nursing respectively.

[0066] A change detection unit for obtaining the skin image after nursing and the skin image before nursing, and obtaining a pixel-level change heat map based on U-Net.

[0067] In some embodiments, the system of the embodiment of the present invention includes: a graph data management module for managing graph data; including:

[0068] A graph storage unit for obtaining real-time interaction data and obtaining a dynamic relationship graph based on Neo4j + Cypher.

[0069] A graph sampling unit for obtaining original graph data and obtaining a training subgraph through sampling.

[0070] A graph version control unit for obtaining a version snapshot of the graph structure based on the differential storage algorithm according to the graph operation log.

[0071] In some embodiments, the system of the embodiment of the present invention further includes:

[0072] A model update module for obtaining an incremental data set and obtaining updated model weights based on federated learning.

[0073] Refer to Figure 2, an embodiment of the present invention proposes an AI-driven skin assessment and skincare decision-making method, including the following steps:

[0074] S100. Obtain a skin image and user information, where the user information includes: age, gender, skin type, work and rest information, nursing time preference, and nursing history information.

[0075] S200. Obtain the global skin problem classification probability, local lesion detection result, and multi-dimensional skin quality scoring result through a skin image classification model, a skin lesion detection model, and a skin quality scoring model, and integrate the user information, perform multi-model feature integration and dynamic weighting to generate a joint feature vector.

[0076] S300. Input the joint feature vector, perform collaborative filtering based on the user historical behavior matrix, obtain the latent factor vector and the population preference distribution through SVD++ decomposition; calculate the product ingredient similarity to obtain a list of candidate products; and construct a state vector based on the latent factor vector and the population preference distribution. Based on the state vector, obtain an action vector through the DDPG algorithm to optimize the list of candidate products; and generate a nursing plan based on the action vector.

[0077] S400. Obtain the nurse profile and real-time status, recommend a nurse based on the nurse-user bipartite graph matching; generate a scheduling plan based on the appointment request and the resource calendar, and obtain the time period demand and the nurse load, and obtain the real-time service price based on the dynamic pricing model.

[0078] S500. Obtain the post-care skin image corresponding to the expected skin improvement cycle in the expected effect and compare it with the pre-care skin image for analysis to obtain the nursing effect; adjust the nursing cycle of the nursing plan based on the nursing effect and incrementally update the nurse-user bipartite graph.

[0079] Although specific embodiments are described herein, those of ordinary skill in the art will recognize that many other modifications or alternative embodiments are also within the scope of the present disclosure. For example, any one of the functions and / or processing capabilities described in connection with a particular device or component can be performed by any other device or component. Additionally, although various illustrative specific implementations and architectures have been described in accordance with embodiments of the present disclosure, those of ordinary skill in the art will recognize that many other modifications to the illustrative specific implementations and architectures described herein are also within the scope of the present disclosure.

[0080] Those of ordinary skill in the art will appreciate that all or some of the steps and systems disclosed above can be implemented as software, firmware, hardware, and appropriate combinations thereof. Some or all of the physical components can be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit. Such software can be distributed on a computer-readable medium, which can include a computer storage medium (or non-transitory medium) and a communication medium (or transitory medium). As is well known to those of ordinary skill in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information, such as computer-readable instructions, data structures, program modules, or other data. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and that can be accessed by a computer. In addition, it is well known to those of ordinary skill in the art that communication media typically embodies computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and can include any information delivery media.

[0081] The above is a specific description of the preferred embodiments of the present application, but the present application is not limited to the above embodiments. Those skilled in the art can make various equivalent deformations or substitutions without departing from the spirit of the present application, and these equivalent deformations or substitutions are all included within the scope defined by the claims of the present application.

Claims

1. An AI-driven skin assessment and skin care decision-making system, characterized in that: include: A data acquisition module is used to obtain skin images and user information, wherein the user information includes age, gender, skin quality, work and rest information, nursing time preference and nursing history information; The skin assessment module is used to obtain the global skin problem classification probability, local lesion detection results and skin quality multi-dimensional scoring results through the skin image classification model, skin lesion detection model and skin quality scoring model, and fuse the user information, perform multi-model feature integration and dynamic weighting to generate a joint feature vector; A recommendation decision module is used to input the joint feature vector, perform collaborative filtering based on the user historical behavior matrix, obtain the potential factor vector and group preference distribution through SVD++ decomposition; calculate the product component similarity to obtain a candidate product list; and construct a state vector based on the potential factor vector and group preference distribution, and based on the state vector, obtain an action vector through the DDPG algorithm to optimize the candidate product list; and generate a care plan based on the action vector; Resource scheduling module, which is used to obtain nurses' profiles and real-time status, and recommend nurses based on nurse-user bipartite graph matching; generate scheduling plans based on appointment requests and resource calendars, obtain time period demand and nurse load, and obtain real-time service prices based on dynamic pricing models; The effect tracking module is used to obtain the skin images after care corresponding to the expected skin improvement cycle in the expected effect and compare and analyze the skin images before care to obtain the care effect; adjust the care cycle of the care plan based on the care effect and update the nurse-user bipartite graph.

2. The AI-driven skin assessment and skin care decision system according to claim 1, characterized in that: The data acquisition module comprises: An image acquisition unit, used for acquiring a standardized skin image based on illumination compensation and face positioning; A user input unit, used to obtain user information and obtain a standardized user vector through a rule encoder; The skin assessment module includes: The image classification unit is used to build a skin image classification model based on EfficientNet and obtain the global skin problem classification probability. The formula is: ； in, is the global skin problem classification probability, is the global skin problem classification weight matrix, is the classification bias term, is the image feature vector; Softmax is the activation function; A lesion detection unit is used to build a skin lesion detection model based on YOLOv8, locate local skin abnormalities and quantify local lesion detection results, where the local lesion detection results include lesion location, lesion number and inflammation area; The quality scoring unit is used to build a skin quality scoring model based on the ResNet50+SE attention mechanism to obtain a multi-dimensional skin quality scoring result; the skin quality scoring model is: ； in, is the score of the i-th skin quality dimension, wherein the skin quality dimension includes at least one of the following items: fineness, glossiness and firmness, is the activation function, is the weight function of the regression head, k is the feature channel index, d is the total number of ResNet feature channels, Mark the regression task parameters, The feature map extracted by ResNet, is the global average pooling result of the ResNet feature map; The multimodal fusion unit is used to perform multimodal fusion and dynamic weighting on the skin image features and the user information based on a first fusion formula to obtain a first joint feature vector; the fusion formula is: ； in, is the first joint eigenvector, and are the image feature weight coefficient and the user feature weight coefficient respectively, is a standardized user vector obtained according to the user information; the image feature weight coefficient is adjusted according to the clarity of the skin image, and the user feature weight coefficient is adjusted according to the completeness of the user information.

3. The AI-driven skin assessment and skin care decision system according to claim 2, characterized in that: The data acquisition module also includes: A sensor integrated unit, used to obtain environmental information based on the environmental detection device, wherein the environmental information includes temperature and humidity data and ultraviolet index; The biometric unit is used to obtain real-time physiological indicators in user information based on the smart wearable device, and the real-time physiological indicators at least include heart rate or sebum secretion indicators.

4. The AI-driven skin assessment and skin care decision system according to claim 3, characterized in that: The multimodal fusion unit is used to perform multimodal fusion and dynamic weighting on the skin image features, user information, environmental information and real-time physiological indicators based on a second fusion formula to obtain a second joint feature vector; the second fusion formula is: ； in, is the second joint eigenvector, and are the environmental characteristic weight coefficient and the physiological characteristic weight coefficient, respectively. is a normalized environmental feature vector obtained according to the environmental information, is a normalized physiological feature vector obtained according to the real-time physiological index.

5. The AI-driven skin assessment and skin care decision system according to claim 4, characterized in that: The recommendation decision module includes: Collaborative filtering unit, used to obtain the user's historical behavior matrix R, , in is the user potential factor matrix, is the product potential factor matrix, N is the number of users, M is the number of products, and the potential factor vector is obtained and group preference distribution , Indicates the product category; Product matching unit, used to obtain the current skin problem vector output by EfficientNet and product ingredient matrix , calculate the symptom-component match , get a list of candidate products , is the component vector of the j-th product; Reinforcement learning policy unit, used to learn , Group Preference Distribution , nurse graph embedding vector , environmental feature vector Constructing the state vector , , update the action vector based on the DDPG strategy , ,in, is the product usage intensity coefficient, is the weight of the frequency of in-store care, Get a list of candidate products for cost-sensitive adjustment factors , filter the candidate product list according to the action vector ; Among them, the embedding vector of the nurse graph is the nurse-user bipartite graph; Solution generation unit, used to obtain a list of candidate products and motion vector , filter the candidate product list and adjust the concentration threshold of the candidate products according to the product usage intensity coefficient, re-prioritize the candidate products according to the cost-sensitive adjustment factor and the graph embedding similarity, calculate the nursing cycle according to the in-store care frequency weight and the nurse load; output the nursing plan, which includes the product portfolio, the in-store cycle and the expected cost.

6. The AI-driven skin assessment and skin care decision system according to claim 1, characterized in that: The resource scheduling module includes: The nurse recommendation unit is used to obtain the nurse's profile and real-time status, and construct a nurse-user bipartite graph. The node types include nurse nodes based on nurse skill characteristics, user nodes based on skin characteristics, and store nodes based on location or equipment characteristics. The edge types include service relationship edges based on service ratings or repurchase times and affiliation edges based on the affiliation between nurses and stores. Recommend nurses based on nurse-user bipartite graph matching: The nurse graph matching formula is: ,in, For the Layer nurse node embedding, For the Layer user node embedding, W is the graph convolution weight matrix, is the activation function, MEAN is the aggregation function; A time-space optimization unit, which is used to generate scheduling plans based on appointment requests and resource calendars; The dynamic pricing unit is used to obtain time period demand and nurse load, and obtain real-time service prices based on the dynamic pricing model: ,in, The basic service price is is the demand heat of the time period, is the historical demand average, is the demand standard deviation.

7. The AI-driven skin assessment and skin care decision system according to claim 1, characterized in that: The effect tracking module includes: The comparison and analysis unit is used to obtain the skin image after care and the skin image before care for comparison and analysis, and calculate the improvement degree. : ; and are the image feature vectors before and after care, respectively. and are the skin quality scores before and after care, respectively, and sign is a symbolic function used to determine the directionality of the care effect; The change detection unit is used to obtain the skin image before and after care, and obtain a pixel-level change heat map based on U-Net.

8. The AI-driven skin assessment and skin care decision system according to claim 6, characterized in that: The system includes: a graph data management module for managing graph data; the graph data management module includes: Graph storage unit, used to obtain real-time interactive data and obtain dynamic relationship graphs based on Neo4j+Cypher; A graph sampling unit, used to obtain the original graph data and obtain the training subgraph through sampling; The graph version control unit is used to obtain a version snapshot of the graph structure based on the graph operation log based on the differential storage algorithm.

9. The AI-driven skin assessment and skin care decision system according to claim 1, characterized in that: The system further comprises: The model update module is used to obtain incremental data sets and obtain updated model weights based on federated learning.

10. An AI-driven skin assessment and skin care decision-making method, used in the system according to any one of claims 1 to 9, characterized in that: The following steps are involved: S100, obtaining skin images and user information, wherein the user information includes: age, gender, skin quality, work and rest information, nursing time preference and nursing history information; S200, obtaining the global skin problem classification probability, local lesion detection results and skin quality multi-dimensional scoring results through the skin image classification model, the skin lesion detection model and the skin quality scoring model, fusing the user information, performing multi-model feature integration and dynamic weighting, and generating a joint feature vector; S300, input the joint feature vector, perform collaborative filtering based on the user historical behavior matrix, obtain the potential factor vector and group preference distribution through SVD++ decomposition; calculate the product component similarity to obtain a candidate product list; and construct a state vector based on the potential factor vector and group preference distribution, and based on the state vector, obtain an action vector through the DDPG algorithm to optimize the candidate product list; and generate a care plan based on the action vector; S400, obtain the nurse's profile and real-time status, and recommend nurses based on the nurse-user bipartite graph matching; generate a scheduling plan based on the appointment request and resource calendar, and obtain the time period demand and nurse load, and obtain the real-time service price based on the dynamic pricing model; S500, obtaining the skin image after care corresponding to the expected skin improvement cycle in the expected effect and comparing it with the skin image before care to obtain the care effect; adjusting the care cycle of the care plan based on the care effect and updating the nurse-user bipartite graph.

Images