Intelligent skin diagnosis and treatment method, system and equipment based on multi-source biological information fusion

Abstract

The invention relates to a multi-source biological information fusion skin intelligent diagnosis and treatment method, system and device, and belongs to the technical field of informatization cloud platform, the method comprises the following steps: inputting collected user information and environment information under a current timestamp into a cloud platform, and processing through a preset diagnosis and treatment model in the cloud platform; acquiring a diagnosis and treatment result fed back by the cloud platform; wherein the steps of processing the user information and the environment information by the diagnosis and treatment model to obtain the diagnosis and treatment result are as follows: extracting first factor data of the user information, and extracting second factor data of the environment information; the first factor data and the second factor data are input into corresponding condition algorithms respectively, calculated condition data are obtained, and at least one condition value is included; introducing the condition data through a material formula matrix, and determining corresponding material formula information; and integrating the user information and the material formula information, generating the diagnosis and treatment result, and outputting the diagnosis and treatment result.

Description

Technical Field

[0001] The present invention relates to the technical field of information cloud platforms, and in particular to a method, system and device for intelligent skin diagnosis and treatment that integrates multi-source biological information. Background Art

[0002] Most existing skin care methods are based on static formula design based on a single dimension (such as skin type or age), and lack the ability to dynamically respond to changes in skin conditions of different users in different seasons, climates, and physiological stages. Especially for people with problem skin, such as oily or sensitive skin, existing solutions cannot provide systematic and accurate formula matching suggestions.

[0003] At the same time, although traditional functional ingredients have anti-inflammatory, oil-control, repair, whitening, moisturizing and other effects, they have not yet been deeply integrated with modern modeling algorithms, resulting in the inability to model skin conditions and deduce personalized formulas from multiple dimensions such as physiology, environment, and season. Summary of the Invention

[0004] To achieve the above objectives, the present invention provides a multi-source biological information fusion intelligent skin diagnosis and treatment method, comprising the following steps:

[0005] The user information and environmental information collected at the current timestamp are input into the cloud platform and processed through the diagnosis and treatment model preset in the cloud platform;

[0006] Obtaining the diagnosis and treatment results fed back by the cloud platform; wherein the steps of the diagnosis and treatment model processing user information and environmental information to obtain the diagnosis and treatment results are:

[0007] extracting first factor data of the user information and extracting second factor data of the environment information;

[0008] Inputting the first factor data and the second factor data into corresponding conditional algorithms respectively to obtain calculated conditional data, wherein the conditional value includes at least one item;

[0009] Introducing the conditional data through a material formula matrix to determine corresponding material formula information;

[0010] Integrate the user information and material formula information to generate the diagnosis and treatment results and output them.

[0011] Furthermore, the material formula matrix is an efficacy matrix, which includes traditional Chinese medicine ingredients, natural ingredients and their corresponding efficacy weights; the conditional algorithm dynamically adjusts the weight ratio of the ingredients in the efficacy matrix, combines user information and environmental information, and outputs material formula information.

[0012] Furthermore, the training method of the diagnosis and treatment model includes:

[0013] Constructing training samples based on a data set that includes historical user information, dynamic environmental data, user-feedback skin physiological indicator change data, and corresponding material formula labels;

[0014] Through feature engineering, user age, climate factors, seasonal rhythms and component efficacy weights are nonlinearly coupled to generate a multidimensional feature vector;

[0015] A multi-task learning framework is used to train a diagnosis and treatment model based on a neural network model, in which the first sub-network learns the mapping relationship from user-environment features to efficacy requirement weights, and the second sub-network generates candidate prescriptions based on the efficacy matrix.

[0016] Furthermore, the steps of nonlinearly coupling user age, climate factors, and seasonal rhythms through feature engineering to generate a multidimensional feature vector include:

[0017] At a certain moment, the user age is coupled to be the first feature vector h(A)=K A1 ,K A2 ,K A3 , where K A1 is the weight of the first age group, K A2 is the weight of the second age group, K A3 is the weight of the third age group;

[0018] At the same time, the climate factor is coupled and set as the second eigenvector, which includes the temperature vector f(T)=K T ×(TT ref ) and humidity vector g(H)=K H ×(HH ref ), where K in the temperature vector f(T) T is the temperature influence coefficient, T ref is the reference temperature, K in the humidity vector g(H) H is the humidity influence coefficient, H ref is the reference humidity;

[0019] At the same time, the seasonal rhythm is coupled to the third eigenvector S k =S1, S2, S3, S4, where S1 is the spring weight, S2 is the summer weight, S3 is the autumn weight, and S4 is the winter weight.

[0020] Furthermore, a multi-task learning framework is used to train a diagnosis and treatment model based on a neural network model, wherein the first sub-network learns the mapping relationship between user-environment features and efficacy requirement weights, including:

[0021] Construct the first sub-network processing expression and train to obtain the first drug formula P i1

[0022]

[0023] Among them, C j Express the temperature T at the moment, the humidity H at the moment, the user's age A at the moment, and the season S at the moment k The skin care demand factor is determined by the skin care demand factor C j In the weight matrix W ij Determine the corresponding weights.

[0024] Furthermore, a multi-task learning framework is used to train a diagnosis and treatment model based on a neural network model, wherein the second sub-network generates candidate prescriptions based on the efficacy matrix, including:

[0025] Construct the second network processing expression and train to obtain the second drug formula requirement P i2

[0026]

[0027] Among them, α j is the weight coefficient for adjusting the temperature vector f(T), β j is the weight coefficient for adjusting the humidity vector g(H), γ j To adjust the weight coefficient of the first eigenvector h(A), δ j is the third eigenvector S k The weight coefficient of .

[0028] Furthermore, a multi-task learning framework is used to train a diagnosis and treatment model based on a neural network model, wherein the first sub-network learns the mapping relationship between user-environment features and efficacy requirement weights, and the second sub-network generates candidate prescriptions based on the efficacy matrix, including:

[0029] Deploy an online incremental learning module to dynamically update the ingredient weights and model parameters in the efficacy matrix based on user skin detection data and subjective evaluation feedback.

[0030] The present invention proposes a skin intelligent diagnosis and treatment device that integrates multi-source biological information, comprising:

[0031] The collection module is used to input the user information and environmental information collected at the current timestamp into the cloud platform and process it through the diagnosis and treatment model preset in the cloud platform;

[0032] A feedback module is used to obtain the diagnosis and treatment results fed back by the cloud platform; wherein the cloud platform executes the step of processing user information and environmental information by the diagnosis and treatment model to obtain the diagnosis and treatment results, and the cloud platform includes:

[0033] an extraction unit, configured to extract first factor data of the user information and second factor data of the environment information;

[0034] a first calculation unit, configured to input the first factor data and the second factor data into corresponding conditional algorithms respectively to obtain calculated conditional data, wherein the conditional value includes at least one item;

[0035] A second calculation unit is used to introduce the condition data through a material formula matrix to determine corresponding material formula information;

[0036] The output unit is used to integrate the user information and material formula information, generate the diagnosis and treatment results, and output them.

[0037] The present invention also provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the above-mentioned skin intelligent diagnosis and treatment method based on multi-source biological information fusion are implemented.

[0038] The present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-mentioned skin intelligent diagnosis and treatment method based on multi-source biological information fusion.

[0039] The intelligent skin diagnosis and treatment method, system, and device based on multi-source biological information fusion provided by the present invention have the following beneficial effects:

[0040] (1) Integrate environmental variables, physiological characteristics, and seasonal rhythms to construct a three-dimensional skin diagnosis system;

[0041] (2) Introducing AI decision logic to improve the accuracy of system recommendations;

[0042] (3) The system can be integrated into apps, mini-programs, SaaS platforms, hardware terminals, etc.;

[0043] (4) Provide precise skin care decision support tailored to individual, time, and location;

[0044] (5) Support the subsequent user feedback data to improve the training ability of the recommendation system. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 1 is a flow chart of a method for intelligent skin diagnosis and treatment based on multi-source biological information fusion according to an embodiment of the present invention;

[0046] Figure 2 This is a structural block diagram of a skin intelligent diagnosis and treatment device integrating multi-source biological information in one embodiment of the present invention;

[0047] Figure 3It is a schematic block diagram of the structure of a computer device according to an embodiment of the present invention.

[0048] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0050] Reference Figure 1 , is a flowchart of a multi-source biological information fusion skin intelligent diagnosis and treatment method proposed by the present invention, the method comprising the following steps:

[0051] S1, input the user information and environmental information collected at the current timestamp into the cloud platform and process it through the diagnosis and treatment model preset in the cloud platform;

[0052] S2, obtaining the diagnosis and treatment results fed back by the cloud platform; wherein the steps of the diagnosis and treatment model processing user information and environmental information to obtain the diagnosis and treatment results are:

[0053] S100, extracting first factor data of the user information and second factor data of the environment information;

[0054] S200, inputting the first factor data and the second factor data into corresponding conditional algorithms respectively to obtain calculated conditional data, wherein the conditional value includes at least one item;

[0055] S300, introducing the condition data through a material formula matrix to determine corresponding material formula information;

[0056] S400, integrating the user information and material formula information, generating the diagnosis and treatment results, and outputting them.

[0057] In one embodiment, the material formula matrix is an efficacy matrix, which includes natural ingredients and their corresponding efficacy weights; the conditional algorithm dynamically adjusts the weight ratio of the ingredients in the efficacy matrix, combines user information and environmental information, and outputs material formula information.

[0058] During specific implementation, the material formula matrix is:

[0059]

[0060] In one embodiment, the training method of the diagnosis and treatment model includes:

[0061] Constructing training samples based on a data set that includes historical user information, dynamic environmental data, user-feedback skin physiological indicator change data, and corresponding material formula labels;

[0062] Through feature engineering, user age, climate factors, seasonal rhythms and the efficacy weights of traditional Chinese medicine ingredients are nonlinearly coupled to generate a multidimensional feature vector;

[0063] A multi-task learning framework is used to train a diagnosis and treatment model based on a neural network model, in which the first sub-network learns the mapping relationship from user-environment features to efficacy requirement weights, and the second sub-network generates candidate prescriptions based on the efficacy matrix.

[0064] The steps of nonlinearly coupling user age, climate factors, and seasonal rhythms through feature engineering to generate a multidimensional feature vector include:

[0065] At a certain moment, the user age is coupled to be the first feature vector h(A)=K A1 ,K A2 ,K A3 , where K A1 is the weight of the first age group, K A2 is the weight of the second age group, K A3 is the weight of the third age group;

[0066] At the same time, the climate factor is coupled and set as the second eigenvector, which includes the temperature vector f(T)=K T ×(TT ref ) and humidity vector g(H)=K H ×(HH ref ), where K in the temperature vector f(T) T is the temperature influence coefficient, T ref is the reference temperature, K in the humidity vector g(H) H is the humidity influence coefficient, H ref is the reference humidity;

[0067] At the same time, the seasonal rhythm is coupled to the third eigenvector S k =S1, S2, S3, S4, where S1 is the spring weight, S2 is the summer weight, S3 is the autumn weight, and S4 is the winter weight.

[0068] Specifically:

[0069] Construct a mathematical modeling system with climate factors (temperature T, humidity H), individual age A, and core skin care goals (oil control, moisturizing, repair, etc.) as input variables;

[0070] Temperature and humidity modeling: Set the linear temperature function f(T) and humidity function g(H); the requirements are,

[0071] High temperature (>25℃): Increased demand for oil control, slightly increased demand for whitening, and decreased demand for moisturizing Low temperature (<10℃): Increased demand for moisturizing and repairing

[0072] Linear relationship setting: f(T)=K T ×(TT ref ), which is one of the second eigenvectors;

[0073] where K T is the temperature influence coefficient, T ref is the reference temperature (e.g. 20°C)

[0074] Humidity H (humidity), humidity influence function: g(H)

[0075] Low humidity (<40%): The skin barrier is damaged and the need for moisturizing is increased

[0076] High humidity (>70%): Increased oil secretion and increased need for oil control

[0077] Linear relationship setting: g(H)=K H ×(HH ref )

[0078] where K T is the humidity influence coefficient, T ref Reference humidity (50%)

[0079] Age segmentation function: A = 15-25, 26-40, 41+, mapping the weights of oil control / repair / anti-aging needs

[0080] Age impact function: h(A): Taking oily skin as an example: 15-25 years old: the demand for oil control is the highest, and the demand for moisturizing is relatively low; 26-40 years old: the demand for repair and anti-aging increases, and the demand for oil control is moderate; 41+ years old: the demand for anti-aging, whitening, and repair is high, and the demand for oil control is the lowest. Set the piecewise function:

[0081]

[0082] Seasonal impact factor S k :

[0083] The impact of different seasons: Spring (S1): moderate temperature, moderate humidity, and average overall efficacy; Summer (S2): high temperature and high humidity, with the highest demand for oil control; Autumn (S3): falling temperature, moderate humidity, and increased demand for repair; Winter (S4): low temperature and low humidity, with the highest demand for moisturizing, repair, and anti-aging; Set:

[0084]

[0085] In one embodiment, a multi-task learning framework is used to train a diagnosis and treatment model based on a neural network model, wherein the step of the first sub-network learning the mapping relationship between user-environment features and efficacy requirement weights includes:

[0086] Construct the first sub-network processing expression and train to obtain the first drug formula P i1

[0087]

[0088] Among them, C j Express the temperature T at the moment, the humidity H at the moment, the user's age A at the moment, and the season S at the moment k The skin care demand factor is determined by the skin care demand factor C j In the weight matrix W ij Determine the corresponding weights.

[0089] In one embodiment, a multi-task learning framework is used to train a diagnosis and treatment model based on a neural network model, wherein the step of generating candidate prescriptions based on the efficacy matrix by the second sub-network includes:

[0090] Construct the second network processing expression and train to obtain the second drug formula requirement P i2

[0091]

[0092] Among them, α j is the weight coefficient for adjusting the temperature vector f(T), β j is the weight coefficient for adjusting the humidity vector g(H), γ j To adjust the weight coefficient of the first eigenvector h(A), δ j is the third eigenvector S k The weight coefficient of .

[0093] In one embodiment, a multi-task learning framework is used to train a diagnosis and treatment model based on a neural network model, wherein the first sub-network learns the mapping relationship between user-environment features and efficacy requirement weights, and the second sub-network generates candidate prescriptions based on the efficacy matrix, including:

[0094] Deploy an online incremental learning module to dynamically update the ingredient weights and model parameters in the efficacy matrix based on user skin detection data and subjective evaluation feedback.

[0095] Reference Attachment Figure 2 This is a schematic diagram of the structure of a multi-source biological information fusion intelligent skin diagnosis and treatment device proposed by the present invention, which includes:

[0096] The collection module is used to input the user information and environmental information collected at the current timestamp into the cloud platform and process it through the diagnosis and treatment model preset in the cloud platform;

[0097] A feedback module is used to obtain the diagnosis and treatment results fed back by the cloud platform; wherein the cloud platform executes the step of processing user information and environmental information by the diagnosis and treatment model to obtain the diagnosis and treatment results, and the cloud platform includes:

[0098] an extraction unit, configured to extract first factor data of the user information and second factor data of the environment information;

[0099] a first calculation unit, configured to input the first factor data and the second factor data into corresponding conditional algorithms respectively to obtain calculated conditional data, wherein the conditional value includes at least one item;

[0100] A second calculation unit is used to introduce the condition data through a material formula matrix to determine corresponding material formula information;

[0101] The output unit is used to integrate the user information and material formula information, generate the diagnosis and treatment results, and output them.

[0102] Reference Figure 3 In an embodiment of the present invention, a computer device is also provided. The computer device may be a server, and its internal structure may be as follows: Figure 3 As shown. The computer device includes a processor, memory, display screen, input device, network interface and database connected via a system bus. The processor of the computer design is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store the corresponding data in this embodiment. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, the above method is implemented.

[0103] Those skilled in the art will understand that Figure 3 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present invention and does not constitute a limitation on the computer device to which the solution of the present invention is applied.

[0104] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which implements the above-described method when executed by a processor. It is understood that the computer-readable storage medium in this embodiment can be a volatile readable storage medium or a non-volatile readable storage medium.

[0105] To sum up, the user information and environmental information collected at the current timestamp are input into the cloud platform, and processed through the diagnosis and treatment model preset in the cloud platform; the diagnosis and treatment results fed back by the cloud platform are obtained; wherein, the steps of the diagnosis and treatment model processing the user information and environmental information to obtain the diagnosis and treatment results are: extracting the first factor data of the user information, and extracting the second factor data of the environmental information; inputting the first factor data and the second factor data into the corresponding conditional algorithm respectively to obtain the calculated conditional data, and the conditional value includes at least one item; introducing the conditional data through the material formula matrix to determine the corresponding material formula information; integrating the user information and material formula information to generate the diagnosis and treatment results, and outputting it, thereby constructing a function model based on environmental temperature and humidity, user age group and skin care efficacy factors, and performing personalized formula calculations through traditional Chinese medicine efficacy databases and AI algorithms, which is suitable for customized development of products such as cleansers, facial masks, essences, and cosmetics, and can cover people aged 15-60; and can be deployed on SaaS platforms, Apps or smart terminals.

[0106] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the above-described method embodiments. Among them, any reference to memory, storage, database, or other media provided by the present invention and used in the embodiments can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double-speed SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct RAM bus dynamic RAM (DRDRAM), and RAMbus dynamic RAM.

[0107] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, apparatus, article, or method comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, apparatus, article, or method. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, apparatus, article, or method comprising the element.

[0108] The above description is only a preferred embodiment of the present invention and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the present invention description and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A skin intelligent diagnosis and treatment method based on multi-source biological information fusion, characterized by: The following steps are involved: The user information and environmental information collected at the current timestamp are input into the cloud platform and processed through the diagnosis and treatment model preset in the cloud platform; Obtaining the diagnosis and treatment results fed back by the cloud platform; wherein the steps of the diagnosis and treatment model processing user information and environmental information to obtain the diagnosis and treatment results are: extracting first factor data of the user information and extracting second factor data of the environment information; Inputting the first factor data and the second factor data into corresponding conditional algorithms respectively to obtain calculated conditional data, wherein the conditional value includes at least one item; Introducing the conditional data through a material formula matrix to determine corresponding material formula information; Integrate the user information and material formula information to generate the diagnosis and treatment results and output them.

2. The skin intelligent diagnosis and treatment method based on multi-source biological information fusion according to claim 1 is characterized in that: The material formula matrix is an efficacy matrix, which includes traditional Chinese medicine ingredients, natural ingredients and their corresponding efficacy weights; the conditional algorithm dynamically adjusts the weight ratio of the ingredients in the efficacy matrix, combines user information and environmental information, and outputs material formula information.

3. The skin intelligent diagnosis and treatment method based on multi-source biological information fusion according to claim 1 is characterized in that: The training method of the diagnosis and treatment model includes: Constructing training samples based on a data set that includes historical user information, dynamic environmental data, user-feedback skin physiological indicator change data, and corresponding material formula labels; Through feature engineering, user age, climate factors, seasonal rhythms and the efficacy weights of traditional Chinese medicine ingredients are nonlinearly coupled to generate a multidimensional feature vector; A multi-task learning framework is used to train a diagnosis and treatment model based on a neural network model, in which the first sub-network learns the mapping relationship from user-environment features to efficacy requirement weights, and the second sub-network generates candidate prescriptions based on the efficacy matrix.

4. The skin intelligent diagnosis and treatment method based on multi-source biological information fusion according to claim 3 is characterized in that: The steps of nonlinearly coupling user age, climate factors, and seasonal rhythms through feature engineering to generate a multidimensional feature vector include: At a certain moment, the user age is coupled to be the first feature vector h(A)=K A1 ,K A2 ,K A3 , where K A1 is the weight of the first age group, K A2 is the weight of the second age group, K A3 is the weight of the third age group; At the same time, the climate factor is coupled and set as the second eigenvector, which includes the temperature vector f(T)=K T ×(TT ref ) and humidity vector g(H)=K H ×(HH ref ), where K in the temperature vector f(T) T is the temperature influence coefficient, T ref is the reference temperature, K in the humidity vector g(H) H is the humidity influence coefficient, H ref is the reference humidity; At the same time, the seasonal rhythm is coupled to the third eigenvector S k =S1, S2, S3, S4, where S1 is the spring weight, S2 is the summer weight, S3 is the autumn weight, and S4 is the winter weight.

5. The skin intelligent diagnosis and treatment method based on multi-source biological information fusion according to claim 4 is characterized in that: A multi-task learning framework is used to train a diagnosis and treatment model based on a neural network model, wherein the first sub-network learns the mapping relationship between user-environment features and efficacy requirement weights, including: Construct the first sub-network processing expression and train to obtain the first drug formula P i1 Among them, C j Express the temperature T at the moment, the humidity H at the moment, the user's age A at the moment, and the season S at the moment k The skin care demand factor is determined by the skin care demand factor C j In the weight matrix W ij Determine the corresponding weights.

6. The skin intelligent diagnosis and treatment method based on multi-source biological information fusion according to claim 5 is characterized in that: A multi-task learning framework is used to train a diagnosis and treatment model based on a neural network model, wherein the second sub-network generates candidate prescriptions based on the efficacy matrix, including: Construct the second network processing expression and train to obtain the second drug formula requirement P i2 Among them, α j is the weight coefficient for adjusting the temperature vector f(T), β j is the weight coefficient for adjusting the humidity vector g(H), γ j To adjust the weight coefficient of the first eigenvector h(A), δ j is the third eigenvector S k The weight coefficient of .

7. The skin intelligent diagnosis and treatment method based on multi-source biological information fusion according to claim 1 is characterized in that: A multi-task learning framework is used to train a neural network-based diagnosis and treatment model. The first sub-network learns the mapping relationship between user-environment features and efficacy requirement weights, and the second sub-network generates candidate prescriptions based on the efficacy matrix. The model includes: Deploy an online incremental learning module to dynamically update the ingredient weights and model parameters in the efficacy matrix based on user skin detection data and subjective evaluation feedback.

8. A skin intelligent diagnosis and treatment device integrating multi-source biological information, characterized in that: include: The collection module is used to input the user information and environmental information collected at the current timestamp into the cloud platform and process it through the diagnosis and treatment model preset in the cloud platform; A feedback module is used to obtain the diagnosis and treatment results fed back by the cloud platform; wherein the cloud platform executes the step of processing user information and environmental information by the diagnosis and treatment model to obtain the diagnosis and treatment results, and the cloud platform includes: an extraction unit, configured to extract first factor data of the user information and second factor data of the environment information; a first calculation unit, configured to input the first factor data and the second factor data into corresponding conditional algorithms respectively to obtain calculated conditional data, wherein the conditional value includes at least one item; A second calculation unit is used to introduce the condition data through a material formula matrix to determine corresponding material formula information; The output unit is used to integrate the user information and material formula information, generate the diagnosis and treatment results, and output them.

9. A computer device comprising a memory and a processor, wherein a computer program is stored in the memory, wherein: When the processor executes the computer program, the steps of the skin intelligent diagnosis and treatment method of multi-source biological information fusion according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the skin intelligent diagnosis and treatment method according to any one of claims 1 to 7 are implemented by the multi-source biological information fusion method.

Images