An ai-based dressing and makeup integrated terminal and front linkage service system

Abstract

The application provides an AI-based dressing and makeup integrated terminal and front linkage service system, and belongs to the technical field of service systems, which comprises a hardware terminal and a linkage service system, wherein the linkage service system comprises a privacy-first whole body data processing unit, a scenario-based aesthetics AI directional scheduling unit, a shopping mall differentiated customer flow shunting unit and a front store preparation order linkage unit; the hardware terminal is used for collecting user whole body data offline; the scenario-based aesthetics AI directional scheduling unit is used for generating a matching scheme accurately matched with offline store goods in combination with the offline collected user whole body data, then a differentiated customer flow shunting algorithm is used to realize balanced distribution of customer flow, and the problem of homogeneous malicious competition of shopping malls and stores can be avoided, and a front preparation order linkage mechanism is used to realize accurate linkage between user demand and store preparation, and improve user offline experience and customer flow conversion rate.

Description

Technical Field

[0001] This invention relates to an integrated clothing and makeup service system, specifically an AI-based integrated clothing and makeup terminal and a front-end integrated service system, belonging to the field of service system technology. Background Technology

[0002] The Outfit and Makeup Integration Service System is an AI-driven, end-to-end image management platform that integrates "clothing, makeup, store linkage, and customer flow control." It aims to solve the problem of homogeneous and malicious competition in shopping malls, while simultaneously creating new offline jobs and achieving a triple enhancement of commercial value, revitalization of the real economy, and protection of people's livelihoods.

[0003] Traditional outfit and makeup integrated service systems typically only involve virtual try-on, 3D virtual avatar construction, and multi-terminal outfit synchronization. They remain at the level of virtual image display and online data synchronization, and cannot achieve offline store pre-stocking linkage. They also do not address the issue of homogeneous competition among shopping mall stores, and cannot form a standardized pre-ordering process. They only focus on virtual experience optimization and are detached from the actual pain points of offline physical consumption.

[0004] A Chinese patent titled "An AI-Powered Smart Dressing and Synchronization System Based on Multi-Terminal Collaboration" (publication number CN121353602A) discloses an AI-powered smart dressing and synchronization technology. Utilizing a multi-terminal collaborative architecture, it achieves a seamless integration of online and offline shopping experiences. Through AI image processing technology, the system can accurately capture user body characteristics and generate highly realistic virtual try-on effects, significantly improving the accuracy and realism of virtual try-on. However, this system also fails to establish a standardized pre-order preparation process, focusing solely on virtual experience optimization and neglecting the actual pain points of offline physical consumption. Therefore, this paper proposes an AI-based integrated dressing and makeup terminal and a pre-order linkage service system. Summary of the Invention

[0005] In view of this, the present invention provides an AI-based integrated terminal for clothing and makeup, and a front-end linkage service system. Through full-body multimodal human feature acquisition and local real-time privacy desensitization preprocessing, combined with AI algorithms for human aesthetics, it generates suitable clothing and makeup solutions based on user data such as face shape, body shape, and weight, establishing a complete offline service loop. It focuses on improving store reception efficiency through a standardized pre-order linkage mechanism and solving the problem of homogeneous and malicious competition in shopping malls through a differentiated customer flow diversion algorithm with quantitative calculation formulas. Simultaneously, it drives the creation of new offline jobs, achieving a triple improvement in commercial value, revitalization of the real economy, and livelihood security; thus solving or alleviating the technical problems existing in the prior art, at least providing a beneficial alternative.

[0006] The technical solution of this invention is implemented as follows: an AI-based integrated pre-launch linkage service system for dressing and makeup, including a hardware terminal and a linkage service system, wherein the linkage service system includes a privacy-first full-body data processing unit, a scenario-based aesthetic AI-oriented scheduling unit, a shopping mall differentiated customer flow diversion unit, and a store pre-prepared order linkage unit. The hardware terminal is used to collect the user's full-body data offline. The scenario-based aesthetic AI-directed scheduling unit is used to call the built-in human aesthetic AI algorithm through AI scheduling logic, and combine the user's full-body collected data to directionally allocate and call the corresponding AI tools. The shopping mall's differentiated customer flow diversion unit incorporates a differentiated customer flow diversion algorithm, which is used to achieve balanced distribution of customer flow through differentiated product classification, weight assignment, and diversion score calculation. The store pre-order preparation linkage unit adopts a pre-order preparation linkage mechanism to establish a proactive pre-order linkage closed loop of "user confirmation - system order generation - real-time push - store pre-processing - user in-store consumption".

[0007] More preferably, the scenario-based aesthetic AI-oriented scheduling unit includes a dual-interaction module and a main control module; The dual-interaction module allows users to select scenarios and style preferences; The main control module employs AI scheduling logic and calls the built-in AI algorithm for human aesthetics.

[0008] Further optimized AI tools include hairstyle and makeup simulation tools and clothing aesthetics and style matching tools, which are linked to the physical product database of shopping malls to generate clothing and makeup styling solutions that can be purchased offline and implemented. Among them, hairstyle and makeup simulation tools include Hair Try, Hairab, and Perfect Corp. Among them, the tools for matching clothing aesthetics and styles include Doubao, Beauty AI, and xlook.

[0009] In a further preferred embodiment, the differentiated customer flow diversion algorithm is based on the offline physical goods and store layout. It pre-divides stores within the mall into N differentiated operating units according to category, style, fit, price, and floor location. No homogeneous products exist within the same operating unit. Fixed weights are assigned to the core dimensions of customer flow diversion, with a total weight sum of 1. The specific algorithm calculation formula is as follows: S = W1 × D + W2 × F + W3 × L + W4 × M; Wherein, S is the final recommendation score for a single store, D is the store differentiation coefficient (0-1), with D=0 for homogeneous stores and D=1 for differentiated stores, F is the store idleness coefficient (0-1), with F=1 for real-time idle status and F=0.3-0.5 for busy status, L is the distance fit coefficient (0-1), with L=1 for reasonable movement range and L=0.5 for extremely long movement range, M is the product matching coefficient (0-1), with M=1 for fully matching user body shape and style and M=0.6 for basic matching, W1 is the differentiation coefficient weight, W2 is the store idleness weight, W3 is the distance fit weight, and W4 is the product matching weight.

[0010] More preferably, after the S-value is calculated, the stores are sorted based on the S-value, and the differentiated store with the largest S-value is selected for push notification.

[0011] More preferably, the pre-preparation work order linkage mechanism is used to generate a standardized pre-preparation work order after the final matching scheme is confirmed, including user basic characteristics, product details, makeup and styling requirements, timeliness requirements and store feedback requirements. The timeliness requirement is the user's expected arrival time at the store, and the store confirmation requirement is that the store confirms the receipt within 1 minute of receiving it. If the timeout is exceeded, the system will automatically push the alternative store.

[0012] Furthermore, the pre-order linkage mechanism further includes push and receipt linkage logic, store pre-processing standards, and closed-loop completion; The push and receipt linkage logic utilizes the mall's intranet combined with wireless dual-mode communication to simultaneously push the work order to the corresponding store's POS terminal, the staff's mobile phone, and the stylist's work terminal, enabling simultaneous reception across multiple terminals. After the store confirms the receipt, the system automatically counts down and simultaneously sends feedback to the user's terminal, informing the user that the store has completed the preparation of the goods and the user can go directly to the store. Among them, the store pre-processing standard is that after receiving the work order, the store must complete the pre-processing in strict accordance with the time limit. If the pre-processing is not completed within the time limit, the system will automatically mark the store and reduce its subsequent traffic allocation weight. The closed-loop process involves users experiencing and consuming directly after arriving at the store. Once the consumption is completed, the system automatically updates the store's idle rate coefficient to provide data support for the next customer flow calculation.

[0013] More preferably, the user's full-body data includes face shape, overall body shape, weight, and skin color data; The privacy-priority full-body data processing unit uses a hardware-level desensitization chip to perform data desensitization and feature extraction on the collected user full-body data, generating a user feature parameter package without privacy information, including facial features, body proportions, weight values, and skin color, and transmitting it to the main control module.

[0014] An AI-based integrated terminal for dressing and makeup includes a full-body multimodal privacy collection module, a dual-mode interaction module, a main control linkage module, and a power supply and auxiliary module; The system includes a full-body multimodal privacy collection module for collecting user's full-body data; a dual-mode interaction module for human-computer interaction; and a main control linkage module that stores computer-readable instructions, which are executed by the main control linkage module to implement an AI-based integrated pre-launch linkage service system for dressing and makeup.

[0015] The embodiments of the present invention have the following advantages due to the adoption of the above technical solutions: The present invention generates matching schemes that are precisely adapted to the products in offline stores by using a scenario-based aesthetic AI-oriented scheduling unit combined with the full-body data of users collected offline. Then, it achieves balanced distribution of customer flow through a differentiated customer flow diversion algorithm, and can avoid the problem of homogeneous malicious competition among shopping mall stores. It can also use a pre-order linkage mechanism to achieve precise linkage between user needs and store inventory, thereby improving the offline user experience and customer flow conversion rate.

[0016] The above overview is for illustrative purposes only and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments, and features described above, further aspects, embodiments, and features of the invention will become readily apparent from the accompanying drawings and the following detailed description. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a schematic diagram of the system flow of the present invention. Detailed Implementation

[0019] In the following description, only certain exemplary embodiments are briefly described. As those skilled in the art will recognize, the described embodiments can be modified in various ways without departing from the spirit or scope of the invention. Therefore, the drawings and description are considered to be exemplary in nature and not restrictive.

[0020] It is important to note that terms such as "first," "second," "symmetric," and "array" are used only to distinguish between descriptive and positional descriptions and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, features specified with terms such as "first" or "symmetric" may explicitly or implicitly include one or more of that feature; similarly, when the quantity of certain features is not limited by words such as "two" or "three," it should be noted that such features also explicitly or implicitly include one or more features.

[0021] The embodiments of the present invention will now be described in detail with reference to the accompanying drawings. Example 1

[0022] like Figure 1 As shown, this embodiment of the invention provides an AI-based integrated pre-service system for dressing and makeup, including a hardware terminal and a linkage service system. The linkage service system includes a privacy-first full-body data processing unit, a scenario-based aesthetic AI-oriented scheduling unit, a shopping mall differentiated customer flow diversion unit, and a store pre-order linkage unit. The hardware terminal is used to collect the user's full-body data offline. The scenario-based aesthetic AI-directed scheduling unit is used to call the built-in human aesthetic AI algorithm through AI scheduling logic, and combine the user's full-body collected data to directionally allocate and call the corresponding AI tools. The shopping mall's differentiated customer flow diversion unit incorporates a differentiated customer flow diversion algorithm, which is used to achieve balanced distribution of customer flow through differentiated product classification, weight assignment, and diversion score calculation. The store pre-order preparation linkage unit adopts a pre-order preparation linkage mechanism to establish a proactive pre-order linkage closed loop of "user confirmation - system order generation - real-time push - store pre-processing - user in-store consumption".

[0023] In one embodiment, the scenario-based aesthetic AI-oriented scheduling unit includes a dual-interaction module and a main control module; The dual-interaction module allows users to select scenarios and style preferences; The main control module employs AI scheduling logic and calls the built-in AI algorithm for human aesthetics.

[0024] AI tools include hairstyle and makeup simulation tools and clothing aesthetics and style matching tools, which are linked to the physical product database of shopping malls to generate clothing and makeup styling solutions that can be purchased offline and implemented. Among them, hairstyle and makeup simulation tools include Hair Try, Hairab, and Perfect Corp. Among them, the tools for matching clothing aesthetics and styles include Doubao, Beauty AI, and xlook.

[0025] Users can choose usage scenarios and style preferences such as dating, business, leisure, and commuting based on the dual interactive modules. The main control module uses a unique AI scheduling logic to call the built-in human aesthetic AI algorithm, combined with the user's full-body data (face shape, body shape, weight), to allocate and call the corresponding AI tools. It is bound to the mall's physical product database and generates clothing and makeup styling solutions that fit the user's body shape, weight, and face shape, which can be purchased offline and implemented. It completely abandons pure virtual simulation and ensures that the matching solutions are both beautiful and practical.

[0026] In one embodiment, the differentiated customer flow diversion algorithm is based on offline physical goods and store layout. It pre-divides stores within the mall into N differentiated operating units according to category, style, fit, price, and floor location. No homogeneous products exist within the same operating unit. Fixed weights are assigned to the core dimensions of customer flow diversion, with a total weight sum of 1. The specific algorithm calculation formula is as follows: S = W1 × D + W2 × F + W3 × L + W4 × M; Wherein, S is the final recommendation score for a single store, D is the store differentiation coefficient (0-1), with D=0 for homogeneous stores and D=1 for differentiated stores, F is the store idleness coefficient (0-1), with F=1 for real-time idle status and F=0.3-0.5 for busy status, L is the distance fit coefficient (0-1), with L=1 for reasonable movement range and L=0.5 for extremely long movement range, M is the product matching coefficient (0-1), with M=1 for fully matching user body shape and style and M=0.6 for basic matching, W1 is the differentiation coefficient weight, W2 is the store idleness weight, W3 is the distance fit weight, and W4 is the product matching weight.

[0027] After the S-value is calculated, the stores are sorted based on the S-value, and the differentiated stores with the largest S-values ​​are selected for push notification.

[0028] The differentiated customer flow distribution algorithm breaks away from traditional random or proximity-based recommendation models. Through differentiated product classification, weight assignment, and distribution score calculation, it achieves balanced customer flow distribution, preventing malicious competition between stores of the same category or style. All calculations are based on offline physical products and store layout, without any virtual modeling steps. The specific implementation steps are as follows: Step 1: Basic Classification of Stores and Products: Divide the stores in the mall into N differentiated operating units in advance according to category, style, pattern, price, and floor location. There are no homogeneous products in the same operating unit to avoid concentrated competition of similar products. Step 2: Assigning Weight Parameters: Set fixed weights for the core dimensions of passenger flow distribution, with a total weight sum of 1, to avoid uneven distribution due to weight imbalance. The specific assignments are as follows: Differentiation coefficient (W1): 0.4 (prioritizes avoiding homogenization, highest weight); Store occupancy rate (W2): 0.3 (stores with low customer traffic are given priority); Distance adaptability (W3): 0.2 (considering the rationality of user movement); Product matching accuracy (W4): 0.1 (basic compatibility as a backup); Step 3: Based on S=W1×D+W2×F+W3×L+W4×M, substitute in the fixed weight values, i.e. S=0.4D+0.3F+0.2L+0.1M; Wherein, S: final recommendation score for a single store (the higher the score, the higher the recommendation priority); D: Store differentiation coefficient (0-1), homogeneous stores D=0, differentiated stores D=1; F: Store vacancy coefficient (0-1), real-time vacancy F=1, busy status F=0.3-0.5; L: Distance fit coefficient (0-1), L=1 within a reasonable movement range, L=0.5 for extremely long movement ranges; M: Product matching coefficient (0-1), M=1 for a perfect fit to the user's body shape and style, and M=0.6 for a basic fit; Step 4: Traffic Diversion Execution Rules: The system calculates the S-value of all stores that meet the product requirements, selects the top 2 differentiated stores with the highest S-values ​​for push notifications, and strictly prohibits pushing notifications to 3 or more stores of the same product category. A single user can only have a maximum of 2 stores corresponding to a single plan, thus technically preventing customer traffic concentration and homogeneous competition.

[0029] In one embodiment, the pre-preparation work order linkage mechanism is used to generate a standardized pre-preparation work order after the final matching scheme is confirmed, including user basic characteristics, product details, makeup and styling requirements, timeliness requirements and store receipt requirements. The timeliness requirement is the user's expected arrival time at the store, and the store confirmation requirement is that the store confirms the receipt within 1 minute of receiving it. If the timeout is exceeded, the system will automatically push the alternative store.

[0030] The pre-order linkage mechanism also includes push and receipt linkage logic, store pre-processing standards, and closed-loop closing. The push and receipt linkage logic utilizes the mall's intranet combined with wireless dual-mode communication to simultaneously push the work order to the corresponding store's POS terminal, the staff's mobile phone, and the stylist's work terminal, enabling simultaneous reception across multiple terminals. After the store confirms the receipt, the system automatically counts down and simultaneously sends feedback to the user's terminal, informing the user that the store has completed the preparation of the goods and the user can go directly to the store. Among them, the store pre-processing standard is that after receiving the work order, the store must complete the pre-processing in strict accordance with the time limit. If the pre-processing is not completed within the time limit, the system will automatically mark the store and reduce its subsequent traffic allocation weight. The closed-loop process involves users experiencing and consuming directly after arriving at the store. Once the consumption is completed, the system automatically updates the store's idle rate coefficient to provide data support for the next customer flow calculation.

[0031] The pre-order preparation and linkage mechanism abandons the traditional passive model of recommending products first and then preparing goods upon arrival at the store. It establishes a proactive pre-order linkage closed loop of "user confirmation - system order generation - real-time push - store pre-processing - user in-store consumption". The entire process is standardized and executed without human error, which greatly improves the efficiency of customer service. The specific steps are as follows: Step 1: Pre-processing work order generation rules: After the user confirms the final configuration plan, the system automatically generates a standardized pre-processing work order. The work order includes fixed required fields with no missing information, specifically including: User basic characteristics: Body type (S / M / L / XL / XXL, calculated based on weight and body shape), face type, skin color; Product details: style number, color, size, quantity, matching requirements; Makeup and styling requirements: Hairstyle and makeup style that suit the face shape; Time requirement: Estimated arrival time (default 10-15 minutes, user-defined time is supported); Store confirmation requirements: Stores must confirm receipt within 1 minute of receiving the document; otherwise, the system will automatically push the confirmation to a backup store. Step 2: Push and Receipt Linkage Logic: Through the mall's intranet + wireless dual-mode communication, the preparation order is pushed synchronously to the corresponding store's cashier terminal, the staff's mobile phone, and the stylist's work terminal, so as to achieve multi-terminal synchronous reception; after the store confirms the receipt, the system automatically counts down and synchronously feeds back to the user's terminal, informing the user that the store has completed the preparation of the goods and the user can go directly to the store. Step 3: After receiving the work order, the store shall complete the pre-processing strictly in accordance with the time limit: Clothing stores: Prepare the corresponding size of goods, arrange the matching, and reserve fitting rooms within 10 minutes; Beauty and hair salons: Prepare the corresponding styling tools and cosmetics within 5 minutes and plan the operation process; If preprocessing is not completed within the time limit: The system will automatically mark the store and reduce its subsequent traffic allocation weight to ensure user experience; Step 4: Closing the loop: After arriving at the store, users directly experience and consume. After the consumption is completed, the system automatically updates the store's idleness coefficient to provide data support for the next traffic distribution calculation, forming a complete closed loop.

[0032] In one embodiment, the user's full-body data includes facial shape, overall body shape, weight, and skin color data; the privacy-priority full-body data processing unit uses a hardware-level desensitization chip to perform data desensitization and feature extraction on the collected user's full-body data, generating a user feature parameter package without privacy information containing facial features, body proportions, weight values, and skin color numbers, and transmitting it to the main control module.

[0033] The system collects user images and weight-related information from a user standing 1.5m-2m in front of the terminal via a hardware terminal. The data is then uploaded to a privacy-priority full-body data processing unit. A hardware-level desensitization chip performs real-time data desensitization and feature extraction, generating a user feature parameter package containing facial features, body proportions, weight values, and skin tone, free of privacy information. This package is then transmitted to the main control module. The system does not store or transmit the original user's body posture or facial data throughout the process, thus avoiding privacy leaks and improving user privacy protection. Example 2

[0034] This invention also provides an AI-based integrated terminal for dressing and makeup, including a full-body multimodal privacy collection module, a dual-mode interaction module, a main control linkage module, and a power supply and auxiliary module; The full-body multimodal privacy collection module is used to collect user's full-body data; the dual-mode interaction module is used for human-computer interaction; the main control linkage module stores computer-readable instructions, which are executed by the main control linkage module to implement an AI-based integrated dressing and makeup front-end linkage service system as described in Embodiment 1. Multimodal privacy collection module: integrates a wide-angle high-definition portrait camera, a non-contact infrared body contour scanning component, a skin color and texture photoelectric detection sensor, and a weight sensing collection unit. The four collection components are arranged in an integrated closed layout. Among them, the wide-angle camera covers the full face shape and overall body posture, the infrared scanning component accurately captures the body contour and body proportion, and the weight sensing unit realizes contactless weight data collection, comprehensively obtaining the core data needed for user aesthetic matching. Dual-mode interactive module: used for visually displaying matching schemes, product information, and user interface; Main control linkage module: built-in lightweight quad-core processor, AI aesthetic algorithm scheduling middleware storage unit, wired + wireless dual-mode communication unit; Power supply and auxiliary modules: Built-in voltage regulator unit, with independent power switch and overload protection device, supports direct mains power supply without the need for an additional power adapter. It also has a built-in small backup power supply, which can support the device to complete the current process and shut down after a power failure, thus protecting data security.

[0035] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various variations or substitutions within the technical scope disclosed in the present invention, and these should all be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. An AI-based integrated pre-service system for outfit matching and makeup, comprising a hardware terminal and an integrated service system, characterized in that, The linked service system includes a privacy-first full-body data processing unit, a scenario-based aesthetic AI-driven scheduling unit, a shopping mall differentiated customer flow diversion unit, and a store pre-prepared order linkage unit. The hardware terminal is used to collect the user's full-body data offline. The scenario-based aesthetic AI-directed scheduling unit is used to call the built-in human aesthetic AI algorithm through AI scheduling logic, and combine the user's full-body collected data to directionally allocate and call the corresponding AI tools. The shopping mall's differentiated customer flow diversion unit incorporates a differentiated customer flow diversion algorithm, which is used to achieve balanced distribution of customer flow through differentiated product classification, weight assignment, and diversion score calculation. The store pre-order preparation linkage unit adopts a pre-order preparation linkage mechanism to establish a proactive pre-order linkage closed loop of "user confirmation - system order generation - real-time push - store pre-processing - user in-store consumption".

2. The AI-based integrated pre-service system for outfit matching and makeup as described in claim 1, characterized in that: The scenario-based aesthetic AI-oriented scheduling unit includes a dual-interaction module and a main control module; The dual-interaction module allows users to select scenarios and style preferences; The main control module employs AI scheduling logic and calls the built-in AI algorithm for human aesthetics.

3. The AI-based integrated pre-service system for outfit matching and makeup as described in claim 1, characterized in that: AI tools include hairstyle and makeup simulation tools and clothing aesthetics and style matching tools, which are linked to the physical product database of shopping malls to generate clothing and makeup styling solutions that can be purchased offline and implemented. Among them, hairstyle and makeup simulation tools include Hair Try, Hairab, and Perfect Corp. Among them, the tools for matching clothing aesthetics and styles include Doubao, Beauty AI, and xlook.

4. The AI-based integrated pre-service system for outfit matching and makeup as described in claim 1, characterized in that: The differentiated customer flow diversion algorithm is based on offline physical goods and store layout. It pre-divides stores within the mall into N differentiated operating units according to category, style, fit, price, and floor location. No homogeneous products exist within the same operating unit. Fixed weights are assigned to the core dimensions of customer flow diversion, with a total weight sum of 1. The specific algorithm calculation formula is as follows: S = W1 × D + W2 × F + W3 × L + W4 × M; Wherein, S is the final recommendation score for a single store, D is the store differentiation coefficient (0-1), with D=0 for homogeneous stores and D=1 for differentiated stores, F is the store idleness coefficient (0-1), with F=1 for real-time idle status and F=0.3-0.5 for busy status, L is the distance fit coefficient (0-1), with L=1 for reasonable movement range and L=0.5 for extremely long movement range, M is the product matching coefficient (0-1), with M=1 for fully matching user body shape and style and M=0.6 for basic matching, W1 is the differentiation coefficient weight, W2 is the store idleness weight, W3 is the distance fit weight, and W4 is the product matching weight.

5. The AI-based integrated pre-service system for outfit matching and makeup as described in claim 4, characterized in that: After the S-value is calculated, the stores are sorted based on the S-value, and the differentiated stores with the largest S-values ​​are selected for push notification.

6. The AI-based integrated pre-service system for outfit matching and makeup as described in claim 1, characterized in that: The aforementioned pre-preparation work order linkage mechanism is used to generate a standardized pre-preparation work order after the final matching scheme is confirmed. This includes user basic characteristics, product details, makeup and styling requirements, timeliness requirements, and store feedback requirements. The timeliness requirement is the user's expected arrival time at the store, and the store confirmation requirement is that the store confirms the receipt within 1 minute of receiving it. If the timeout is exceeded, the system will automatically push the alternative store.

7. The AI-based integrated pre-service system for outfit matching and makeup as described in claim 6, characterized in that: The pre-order linkage mechanism also includes push and receipt linkage logic, store pre-processing standards, and closed-loop closing. The push and receipt linkage logic utilizes the mall's intranet combined with wireless dual-mode communication to simultaneously push the work order to the corresponding store's POS terminal, the staff's mobile phone, and the stylist's work terminal, enabling simultaneous reception across multiple terminals. After the store confirms the receipt, the system automatically counts down and simultaneously sends feedback to the user's terminal, informing the user that the store has completed the preparation of the goods and the user can go directly to the store. Among them, the store pre-processing standard is that after receiving the work order, the store must complete the pre-processing in strict accordance with the time limit. If the pre-processing is not completed within the time limit, the system will automatically mark the store and reduce its subsequent traffic allocation weight. The closed-loop process involves users experiencing and consuming directly after arriving at the store. Once the consumption is completed, the system automatically updates the store's idle rate coefficient to provide data support for the next customer flow calculation.

8. The AI-based integrated pre-service system for outfit matching and makeup as described in claim 2, characterized in that: The user's full-body data includes facial shape, overall body shape, weight, and skin color data; The privacy-priority full-body data processing unit uses a hardware-level desensitization chip to perform data desensitization and feature extraction on the collected user full-body data, generating a user feature parameter package without privacy information, including facial features, body proportions, weight values, and skin color, and transmitting it to the main control module.

9. An AI-based integrated terminal for dressing and makeup, characterized in that: It includes a full-body multimodal privacy collection module, a dual-mode interaction module, a main control linkage module, and a power supply and auxiliary module; The system includes a full-body multimodal privacy collection module for collecting user's full-body data; a dual-mode interaction module for human-computer interaction; and a main control linkage module storing computer-readable instructions, which are executed by the main control linkage module to implement the AI-based integrated dressing and makeup pre-linkage service system as described in any one of claims 1-8.

Images