Personalized myopia prevention and control and glasses matching optimization method and system, electronic equipment and storage medium

Abstract

The invention belongs to the field of electric digital data processing, and particularly relates to a personalized myopia prevention and control and glasses matching optimization method and system, electronic equipment and a storage medium. Physiological parameters, behavior parameters and environmental parameters of individuals are collected and integrated to form an individual comprehensive data set; constructing an individual physiological-behavioral environment interaction network according to the individual comprehensive data set; analyzing the individual physiological-behavioral environment interaction network by using a complex network analysis method, and evaluating the myopia risk of the individual; according to the individual myopia risk assessment result, generating personalized myopia prevention and control suggestions and glasses matching schemes; and collecting user feedback, and optimizing the system according to a feedback result. According to the method, the myopia risk can be comprehensively evaluated, and customized myopia prevention and control suggestions and glasses matching schemes are provided according to the individual physiological parameters and behavioral environment factors. By combining the advantages of a complex network analysis method, the accuracy and effectiveness of myopia prevention and control and glasses matching are improved.

Description

Technical Field

[0001] The present invention belongs to the field of electronic digital data processing, and specifically relates to a personalized myopia prevention and control and glasses fitting optimization method, system, electronic equipment, and storage medium. Background Art

[0002] With the accelerated pace of modern life and the popularity of electronic products, myopia has become one of the main problems affecting the visual health of young people around the world, especially in East Asia. According to data from the World Health Organization, the myopia rate among Chinese teenagers remains high, and is showing a trend of younger age and higher degree, which not only affects the quality of life of individuals, but also increases the risk of future eye diseases such as glaucoma, cataracts and retinal detachment. Therefore, how to effectively prevent and control myopia and provide accurate myopia intervention measures and glasses fitting solutions for different individuals has become an important issue that needs to be urgently addressed in the current field of ophthalmic health.

[0003] Traditional myopia prevention and control methods mostly rely on general eye hygiene education, increasing outdoor activity time, and wearing appropriate glasses or orthokeratology lenses. However, these methods often lack individual precision and fail to fully consider the impact of each person's physiological differences, eye habits, and environmental factors on the development of myopia. In addition, there is also a "one-size-fits-all" problem in eyeglass fitting, that is, fitting glasses based on a unified optometry standard, ignoring different individual physiological, behavioral, and environmental factors, as well as the individual's personalized needs for visual needs, comfort, and aesthetics.

[0004] In recent years, with the rapid development of technologies such as big data, artificial intelligence, and complex network analysis, new ideas and methods have been provided for myopia prevention and control and glasses fitting. Although the research and application prospects in this field are broad, there are still many challenges in technical implementation. How to efficiently and accurately collect and analyze a large amount of individual data, how to build a reasonable individual physiological-behavioral interaction network model, and how to generate truly personalized myopia prevention and control recommendations and glasses fitting solutions based on these models are all technical problems that need to be solved urgently. Summary of the invention

[0005] The purpose of the present invention is to overcome the shortcomings of the prior art and provide a personalized myopia prevention and control and glasses fitting optimization method, system, electronic device, and storage medium. By integrating advanced data acquisition technology, complex network analysis methods, and artificial intelligence algorithms, it provides individuals with accurate and personalized myopia prevention and control and glasses fitting services, in order to achieve better myopia prevention and control effects and improve people's visual health.

[0006] The technical solution adopted by the present invention to solve the technical problem is:

[0007] The present invention can construct an individualized physiological-behavioral environment interaction network by collecting and analyzing individual physiological parameters, eye behavior parameters, and environmental parameters, and then use complex network analysis methods to reveal the key factors and risk paths of myopia risk. On this basis, combined with machine learning algorithms, accurate quantitative assessment of individual myopia risk can be achieved, and personalized myopia prevention and control recommendations and glasses fitting solutions can be generated based on the assessment results. This myopia prevention and control and glasses fitting optimization system based on big data and artificial intelligence can not only improve the pertinence and effectiveness of prevention and control measures, but also meet the personalized needs of individuals in visual health, and improve the overall visual experience and quality of life.

[0008] The first aspect of the present invention provides a personalized myopia prevention and control and glasses fitting optimization method, comprising the following steps:

[0009] S1: Collect individual physiological parameters, behavioral parameters and environmental parameters, and integrate them to form an individual comprehensive data set;

[0010] S2: Based on the individual comprehensive data set, construct an individual physiological-behavioral-environment interaction network;

[0011] S3: Use complex network analysis methods to analyze the individual physiological-behavioral environment interaction network and assess the individual's myopia risk;

[0012] S4: Generate personalized myopia prevention and control recommendations and glasses fitting plans based on individual myopia risk assessment results;

[0013] S5: Collect user feedback and optimize the system based on the feedback results.

[0014] Furthermore, the collecting of individual physiological parameters, behavioral parameters and environmental parameters in S1 specifically includes the following steps:

[0015] S11 uses professional ophthalmic testing equipment to collect individual physiological parameters, including but not limited to age, refraction, corneal curvature, axial length, lens transparency and other parameters;

[0016] S12 collects individual eye behavior data, such as reading distance, reading time, and frequency of electronic device use, through a designed questionnaire or by using wearable devices, smartphones, and other tools;

[0017] S13 collects environmental factor data, including but not limited to lighting conditions in the living or working environment, the impact of outdoor activity time on vision, etc. This data can be collected through field measurements, user self-reports, or using environmental sensors;

[0018] S14 integrates the above-collected physiological parameters, eye behavior data and environmental factor data to form an individual comprehensive data set, providing a basis for subsequent network construction and risk assessment.

[0019] Furthermore, S2 constructs the individual physiological network, the behavioral environment network, and the individual physiological-behavioral environment interaction network based on the collected data, specifically including the following steps:

[0020] S21 builds individual physiological network:

[0021] The collected physiological parameters are used as nodes in the network; according to the interaction relationship between physiological parameters (such as mutual influence, causal relationship, etc.), the connection (edge) between nodes is determined to construct an individual physiological network; the adjacency matrix is ​​used to mathematically describe the individual physiological network.

[0022] S22 builds a behavioral environment network:

[0023] The collected behavioral parameters and environmental parameters are used as nodes in the network; according to the correlation or causal relationship between the behavioral parameters and the environmental parameters, the connection between the nodes is determined to construct a behavioral environment network; the adjacency matrix is ​​also used to mathematically describe the behavioral environment network.

[0024] S23 builds an individual physiological-behavioral-environment interaction network:

[0025] Integrate the individual physiological network and the behavioral environment network, merge the nodes and edges in the two, and form an individual physiological-behavioral-environmental interaction network; in the individual physiological-behavioral-environmental interaction network, the connections between the newly added nodes may represent the mutual influence between physiological parameters and behavioral parameters and environmental parameters.

[0026] Furthermore, S3 uses complex network analysis methods to analyze the interactive network, and the assessment of individual myopia risk specifically includes the following steps:

[0027] S31 calculates network stability:

[0028] The overall network efficiency of the individual physiological-behavioral-environment interaction network is calculated to evaluate the stability of the network when it is subject to external interference (such as bad eye habits, environmental changes, etc.); a network with low stability may mean that the individual is at high risk of myopia.

[0029] Calculate the overall network efficiency of the interaction network to assess the stability of the network when subjected to external disturbances; a network with low stability means that individuals are at high risk of myopia;

[0030]

[0031] Where: E is the network stability, n is the total number of nodes in the interactive network, v i and vj are two different nodes in the network, d ij is the node v in the network i With node v j The shortest path when v i With v j When there is no path, d ij is infinite;

[0032] S32 identifies key nodes:

[0033] Complex network analysis methods were used to calculate the DC, CC, and BC index values ​​of each node in the interaction network. The weights of each centrality index were calculated based on maximizing the deviation, and the comprehensive centrality value of each node was calculated. The key nodes in the interaction network were identified based on the ranking of the comprehensive centrality values ​​of each node. These key nodes may represent physiological parameters or behavioral environmental factors that have an important impact on the risk of myopia.

[0034]

[0035] Where: L k (w) is the deviation of the kth centrality index; Z ik is the normalized value of the kth centrality index of node vi, Z jk For node v j The normalized value of the kth centrality index of k is the weight of the kth centrality index, i and j are the nodes v i and v j The subscript numbers, n is the total number of nodes in the interaction network, and k is the centrality index number;

[0036]

[0037] Where: C i is the comprehensive centrality value of the i-th node;

[0038] S33 Identify key risk paths:

[0039] Complex network analysis methods are used to calculate the betweenness centrality of each connecting edge in the interaction network, sort the betweenness centralities of all connecting edges, and identify key risk paths; through path analysis methods, key paths from key physiological parameter nodes to myopia risk nodes (or myopia status) are identified in the interaction network; these paths may reveal the main channels or mechanisms for myopia progression.

[0040] b ij (l) = g ij (l) / g ij ;

[0041] Where: bij (l) is the betweenness centrality of the edge l in the interaction network; g ij (l) indicates that it passes through the connecting edge l and connects to the node v i and node v j The number of shortcuts, g ij Indicates passing through node v i and node v j The total number of all shortcuts.

[0042] S34 Risk Quantification Assessment:

[0043] Based on the above analysis results, a quantitative assessment of the individual's myopia risk is conducted, and the magnitude of the myopia risk is expressed in the form of risk level.

[0044]

[0045] R is the comprehensive risk of myopia of an individual.

[0046] Furthermore, S4 generates personalized myopia prevention and control recommendations and glasses fitting plans based on the individual myopia risk assessment results, which specifically include the following steps:

[0047] ① Based on the results of risk quantification assessment, generate an individualized myopia risk report, including myopia risk level, key influencing factors, recommended prevention and control measures, etc.;

[0048] ② Generate personalized myopia prevention and control recommendations for different myopia risk levels;

[0049] ③ Customize appropriate glasses fitting plans based on individual physiological parameters (such as corneal curvature, axial length, etc.) and eye needs; the plan includes lens type (such as monofocal, multifocal, blue light protection, etc.), lens power, frame selection, etc.; the system can also consider individual personal preferences and comfort and provide a variety of glasses fitting plans.

[0050] The second aspect of the present invention is to provide a personalized myopia prevention and control and glasses fitting optimization system for realizing the above-mentioned personalized myopia prevention and control and glasses fitting optimization method, comprising:

[0051] The acquisition module is used to collect individual physiological parameters, behavioral parameters and environmental parameters, and integrate them to form an individual comprehensive data set;

[0052] The network construction module constructs an individual physiological-behavioral-environment interaction network based on the individual comprehensive data set;

[0053] The risk assessment module uses complex network analysis methods to analyze the individual's physiological-behavioral-environmental interaction network to assess the individual's myopia risk;

[0054] Personalized suggestion generation module, which generates personalized myopia prevention and control suggestions and glasses fitting plans based on individual myopia risk assessment results;

[0055] The system optimization module collects user feedback and optimizes the system based on the feedback results.

[0056] Furthermore, the risk assessment module includes:

[0057] The network stability calculation module is used to calculate the overall network efficiency of the individual physiological-behavioral environment interaction network to evaluate the stability of the network when it is subjected to external interference;

[0058] The key node identification module uses complex network analysis methods to calculate the comprehensive centrality value of each node, and identifies the key nodes in the interactive network based on the ranking of the comprehensive centrality of each node;

[0059] The critical risk path identification module uses complex network analysis methods to calculate the intermediate centrality of each connection edge of the interactive network and identify the critical risk path;

[0060] The risk quantification assessment module conducts a quantitative assessment of an individual's myopia risk based on the analysis results; the risk level is used to indicate the magnitude of myopia risk.

[0061] The third aspect of the present invention is to provide an electronic device, including a processor and a memory, wherein the memory stores a computer program, and the processor executes the steps of the above-mentioned personalized myopia prevention and control and glasses fitting optimization method by calling the computer program stored in the memory.

[0062] A fourth aspect of the present invention is a storage medium having a computer program stored thereon, which, when executed by a processor, runs the steps of the above-mentioned personalized myopia prevention and control and glasses fitting optimization method.

[0063] Advantages and beneficial effects of the present invention:

[0064] 1. The present invention collects and analyzes individual physiological parameters, eye behavior parameters and environmental parameters, constructs an individual physiological-behavioral environment interactive network, and realizes accurate quantitative assessment of myopia risk. Myopia prevention and control measures can be customized according to the specific situation of the individual, greatly improving the pertinence and effectiveness of prevention and control. Compared with traditional "one-size-fits-all" prevention and control methods, the present invention can more effectively slow down the development of myopia and reduce the risk of high myopia and related eye diseases.

[0065] 2. The present invention not only focuses on myopia prevention and control, but also strives to enhance the personalized experience of eyeglass fitting. By making full use of complex network analysis methods and comprehensively considering factors such as individual visual needs, comfort and aesthetics, the present invention can provide individuals with accurate eyeglass fitting solutions. It not only meets the personalized needs of individuals in visual health, but also improves the overall satisfaction and visual experience of eyeglass fitting, which helps to enhance the individual's visual health awareness and self-management ability. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] Figure 1 This is an individual physiological-behavioral environment network diagram of an embodiment of the present invention.

[0067] Figure 2 A block diagram of an exemplary configuration of a personalized myopia prevention and control and glasses fitting optimization system according to an embodiment of the present invention.

[0068] Figure 3 A block diagram of an exemplary configuration of a risk assessment module according to an embodiment of the present invention.

[0069] Figure 4 A block diagram of an electronic device for personalized myopia prevention and control and glasses fitting optimization according to an embodiment of the present invention.

[0070] Among them, 100: personalized myopia prevention and control and glasses fitting optimization system; 101: acquisition module; 102: network construction module; 103: risk assessment module; 104: personalized suggestion generation module; 105: system optimization module; 113: network stability calculation module, 123: key node identification module, 133: key risk path identification module, 143: risk quantification assessment module; 200: electronic device; 201: memory; 202: processor. DETAILED DESCRIPTION

[0071] The present invention is further described in detail below through specific examples. The following examples are only illustrative and not restrictive, and the protection scope of the present invention cannot be limited thereto.

[0072] Suppose there is a 12-year-old teenager named Xiao Ming, whose eyesight has recently deteriorated due to long-term use of electronic devices and bad eye habits. His parents hope to find a personalized myopia prevention and control plan and hope to equip him with a pair of glasses that are both comfortable and meet his visual needs.

[0073] The present invention provides a personalized myopia prevention and control and glasses fitting optimization method, the steps are as follows:

[0074] S1: Collect individual physiological parameters and behavioral environment parameters, and integrate them to form an individual comprehensive data set;

[0075] ①Use professional ophthalmic equipment to collect Xiao Ming's physiological parameters, including age, refraction, corneal curvature, axial length, lens transparency and other parameters;

[0076] ② Collect Xiao Ming’s daily eye habits through wearable devices or mobile phone applications, such as reading distance, reading time, and frequency of electronic device use, and collect eye behavior data;

[0077] ③Record Xiao Ming’s daily outdoor activity time, indoor lighting conditions and other environmental factors, and collect environmental data.

[0078] S2: Based on the individual comprehensive data set, construct an individual physiological-behavioral-environment interaction network;

[0079] ① Based on individual physiological parameters, construct Xiao Ming’s individual physiological network;

[0080] ② Based on the behavioral environment data, build Xiao Ming’s behavioral environment network;

[0081] ③Integrate the individual physiological network and behavioral environment network to construct Xiao Ming’s individual physiological-behavioral environment network.

[0082] S3: Use complex network analysis methods to analyze the individual physiological-behavioral environment interaction network and assess the individual's myopia risk;

[0083] The specific steps include:

[0084] ① Calculate the network stability E, as shown in formula (1);

[0085]

[0086] Where: E is the stability index of the network, n is the total number of nodes in the interactive network, v i and v j are two different nodes in the network, d ij is the node v in the network i With node v j The shortest path when node v i With node v j When there is no path, d ij Is infinite.

[0087] ② Use complex network analysis methods to calculate the DC, CC, and BC index values ​​of each node in the interactive network, calculate the weight of each centrality index based on the maximum deviation, calculate the comprehensive degree of centrality of each node, and identify the key nodes in the interactive network based on the ranking of the comprehensive degree of centrality of each node;

[0088]

[0089] Where: L k (w) is the deviation of the kth centrality index; Z ik is the normalized value of the kth centrality index of node vi, Z jk For node v j The normalized value of the kth centrality index of k is the weight of the kth centrality index, i and j are the nodes v i and node v j The subscript number, n is the total number of nodes in the interaction network, and k is the centrality index number.

[0090]

[0091] Where: C i is the comprehensive centrality value of the i-th node.

[0092] ③ Use complex network analysis methods to calculate the intermediate centrality of each connection edge in the interactive network, sort the intermediate centrality of all connection edges, and identify key risk paths;

[0093] b ij (l) = g ij (l) / g ij (4);

[0094] Where: b ij (l) is the betweenness centrality of the edge l in the interaction network; g ij (l) indicates that it passes through the connecting edge l and connects to the node v i and node v j The number of shortcuts, g ij Indicates passing through node v i and node v j The total number of all shortcuts.

[0095] ④ Quantitatively evaluate the individual's comprehensive myopia risk R, determine the level, and generate personalized myopia prevention and control recommendations.

[0096]

[0097] R is the comprehensive risk of myopia of an individual.

[0098] Use professional ophthalmic equipment to collect Xiao Ming's individual physiological parameters and behavioral environment data. Figure 1 is Xiao Ming’s individual physiological-behavioral-environment interaction network.

[0099] The network stability E calculated by complex network analysis method is 0.468. The larger the network stability E value, the lower the individual myopia risk. Usually, the normal range of E value is between 0.6 and 0.8, and the maximum value can reach 1. Xiao Ming's E value is significantly lower than the normal range, indicating that Xiao Ming is facing the influence of external interference (such as bad eye habits, environmental changes, etc.), and the risk of myopia is relatively high. Xiao Ming may need to pay more attention to protecting his eyes, avoiding bad eye habits, and minimizing the adverse effects of environmental changes on his eyes.

[0100] The complex network analysis method was used to calculate the centrality comprehensive degree value of each node in the interactive network, and the risk degree of each parameter was judged according to the ranking results of the centrality comprehensive degree value. The results showed that among the individual physiological parameters, the centrality comprehensive degree values ​​of refraction and axial length were much greater than those of other parameters, which were 1.73 and 1.29 respectively; while among the behavioral environment parameters, the centrality comprehensive degree values ​​of outdoor activity time and indoor lighting conditions were higher, which were 0.57 and 0.28 respectively.

[0101] From the calculation of key risk paths, we know that risk paths such as "outdoor activity time → axial length → diopter", "indoor lighting conditions → lens transparency → diopter", and "diopter → reading distance → reading time" are the key paths that cause Xiao Ming's vision to decline. This shows that Xiao Ming's long-term lack of outdoor activities has led to changes in axial length, which in turn affects the change in diopter and increases the risk of myopia. In addition, poor indoor lighting conditions affect lens transparency, increase the burden on the eyes, and aggravate the risk of myopia. On the other hand, diopter leads to unreasonable reading distance and excessive reading time, which is an important inducement for the increased risk of myopia. Further calculation of Xiao Ming's comprehensive myopia risk R is 4.47. Table 1 shows that Xiao Ming's comprehensive myopia risk belongs to a medium risk level, and effective measures need to be taken to prevent and control it. According to the analysis results, formulate a personalized myopia prevention and control plan. At the same time, provide customized glasses fitting recommendations to ensure that they are comfortable to wear and meet visual quality requirements.

[0102] Table 1 Division of risk levels and R value ranges

[0103]

[0104] like Figure 2 As shown, the present invention further provides a personalized myopia prevention and control and glasses fitting optimization system 100 for implementing the above method, comprising:

[0105] The collection module 101 is used to collect individual physiological parameters, behavioral parameters and environmental parameters, and integrate them to form an individual comprehensive data set;

[0106] A network construction module 102 constructs an individual physiological-behavioral-environment interaction network based on the individual comprehensive data set;

[0107] The risk assessment module 103 uses a complex network analysis method to analyze the individual's physiological-behavioral environment interaction network to assess the individual's myopia risk;

[0108] A personalized suggestion generation module 104 generates personalized myopia prevention and control suggestions and glasses fitting solutions based on individual myopia risk assessment results;

[0109] The system optimization module 105 collects user feedback and optimizes the system according to the feedback results.

[0110] Furthermore, the risk assessment module 103 includes:

[0111] A network stability calculation module 113 is used to calculate the overall network efficiency of the individual physiological-behavioral environment interaction network to evaluate the stability of the network when it is subject to external interference;

[0112] The key node identification module 123 calculates the comprehensive centrality value of each node using a complex network analysis method, and identifies the key nodes in the interactive network according to the ranking of the comprehensive centrality values ​​of each node;

[0113] The critical risk path identification module 133 uses a complex network analysis method to calculate the intermediate centrality of each connection edge of the interactive network and identify the critical risk path;

[0114] The risk quantification assessment module 143 performs a quantitative assessment of the individual's myopia risk based on the analysis results, and uses a risk level to indicate the magnitude of the myopia risk.

[0115] The details of the operations and functions of the various parts of the personalized myopia prevention and control and glasses fitting optimization system 100 may be the same as or similar to the relevant parts of the embodiment of the personalized myopia prevention and control and glasses fitting optimization method of the present disclosure described above, and will not be described in detail here.

[0116] It should be noted here that Figure 2 , Figure 3 The structure of the personalized myopia prevention and control and glasses fitting optimization system 100 and its components are only exemplary, and those skilled in the art can modify them as needed. Figure 2 Modify the structural block diagram shown.

[0117] The above-mentioned personalized myopia prevention and control and glasses fitting optimization system 100 can be implemented by hardware, or by software, or by a combination of hardware and software.

[0118] In the present disclosure, the personalized myopia prevention and control and glasses fitting optimization system 100 can be implemented using an electronic device 200. Figure 4As shown, the electronic device may include at least one processor 202, which executes at least one computer-readable instruction (ie, the above-mentioned element implemented in the form of software) stored or encoded in a computer-readable storage medium (ie, memory 201).

[0119] It should be understood that the computer-executable instructions stored in the memory, when executed, cause at least one processor to perform the various operations and functions described in the embodiments of the present disclosure.

[0120] According to one embodiment, a machine-readable storage medium is provided. The machine-readable storage medium may have machine-executable instructions (ie, the above-mentioned elements implemented in the form of software), which, when executed by a machine, enables the machine to perform various operations and functions in the embodiments of the present disclosure.

[0121] Table 2 Centrality of each node in the interaction network

[0122] node DC (node ​​degree centrality) CC (Closeness Centrality) BC (Betweenness Centrality) Comprehensive degree value age 55.556 69.231 2.778 0.28 Diopter 100 100 19.907 1.73 Corneal curvature 44.444 64.286 0.694 0.02 Axial length 88.889 90 14.12 1.29 Lens transparency 44.44 64.286 1.62 0.04 Reading distance 44.44 64.286 0.1 0.01 Reading time 55.556 69.231 1.62 0.24 Frequency of use of electronic devices 44.444 64.286 0.694 0.02 indoor lighting 55.556 69.231 3.009 0.28 Outdoor activity time 66.667 75 5.556 0.57

[0123] The results in Table 2 show that the degree centrality and closeness centrality of diopter are both 100%, which also shows that it is one of the most core nodes in the network and has a close connection with other nodes. At the same time, its betweenness centrality is also high, indicating that it plays an important intermediary role in the network, connecting different nodes and paths. In addition, the comprehensive degree of centrality of diopter and axial length is much greater than the comprehensive degree of centrality of other parameters, which are 1.73 and 1.29 respectively. It also shows that in the interactive network, diopter and axial length are two extremely critical nodes, which have a significant impact on the structure and function of the network.

[0124] The degree centrality and closeness centrality of axial length are also high, and the betweenness centrality cannot be ignored, which further emphasizes the importance of axial length in the occurrence and development of myopia. Among the behavioral environment parameters, the comprehensive degree of centrality of outdoor activity time and indoor lighting conditions is relatively high, at 0.57 and 0.28, respectively. This shows that it has a close connection with multiple nodes in the network and has a positive impact on the stability of the network. At the same time, its betweenness centrality also shows that it plays an important role in connecting different nodes and paths. In summary, the results in Table 2 reveal the importance and influence of each node in the interactive network, providing valuable reference information for myopia prevention and control.

[0125] The above description is only a preferred embodiment of the present invention. It should be pointed out that a person skilled in the art can make several modifications and improvements without departing from the inventive concept, which all belong to the protection scope of the present invention.

Claims

1. A personalized myopia prevention and control and glasses fitting optimization method, characterized in that: The following steps are involved: S1: Collect individual physiological parameters, behavioral parameters and environmental parameters, and integrate them to form an individual comprehensive data set; S2: Based on the individual comprehensive data set, construct an individual physiological-behavioral environment interaction network, wherein the individual physiological-behavioral environment interaction network is formed by integrating the individual physiological network and the behavioral environment network, merging the nodes and edges in the two; In the individual physiological-behavioral-environmental interaction network, the connections between the newly added nodes represent the mutual influence between physiological parameters, behavioral parameters, and environmental parameters; S3: Use complex network analysis methods to analyze the individual physiological-behavioral environment interaction network and assess the individual's myopia risk, including: calculating network stability, identifying key nodes, identifying key risk paths and quantitative risk assessment; S4: Generate personalized myopia prevention and control recommendations and glasses fitting plans based on individual myopia risk assessment results; S5: Collect user feedback and optimize the system based on the feedback results; The calculation formula of the network stability is as follows: a network with low stability means that the individual has a high risk of myopia; Where: E is the network stability, n is the total number of nodes in the interactive network, v i and v j are two different nodes in the network, d ij is the node v in the network i With node v j The shortest path when node v i With node v j When there is no path, d ij is infinite; The identification of the key risk path is to use a complex network analysis method to calculate the intermediate centrality of each connection edge of the interactive network, sort the intermediate centrality of all connection edges, and then identify the key risk path; b ij (l)=g ij (l) / g ij ; Where: b ij (l) is the betweenness centrality of the edge l in the interaction network; g ij (l) indicates that it passes through the connecting edge l and connects to the node v i and node v j The number of shortcuts, g ij Indicates passing through node v i and node v j The total number of all shortcuts.

2. The personalized myopia prevention and control and glasses fitting optimization method according to claim 1, characterized in that: The specific steps of S3 are as follows: the identification of key nodes is to use complex network analysis methods to calculate the DC, CC, and BC index values ​​of each node in the interactive network, calculate the weight of each centrality index based on the maximum deviation, calculate the comprehensive degree value of the centrality of each node, and identify the key nodes in the interactive network according to the ranking of the comprehensive degree of centrality of each node; Where: L k (w) is the deviation of the kth centrality index; Z ik For node v i The normalized value of the kth centrality index, Z jk For node v j The normalized value of the kth centrality index of k is the weight of the kth centrality index, i and j are the nodes v i and v j The subscript numbers, n is the total number of nodes in the interaction network, and k is the centrality index number; Where: C i is the comprehensive centrality value of the i-th node; The risk quantification assessment is to quantify the myopia risk of an individual based on the analysis results; the risk level is used to indicate the magnitude of myopia risk; R is the comprehensive risk of myopia of an individual.

3. The personalized myopia prevention and control and glasses fitting optimization method according to claim 1, characterized in that: The individual physiological network described in S2 uses the collected physiological parameters as nodes in the network, determines the connection between the nodes according to the interaction relationship between the physiological parameters, and uses the adjacency matrix to mathematically describe the individual physiological network.

4. The personalized myopia prevention and control and glasses fitting optimization method according to claim 1, characterized in that: The behavior environment network described in S2 uses the collected behavior parameters and environment parameters as nodes in the network, determines the connection between nodes based on the correlation or causal relationship between the behavior parameters and the environment parameters, and uses the adjacency matrix to mathematically describe the behavior environment network.

5. The personalized myopia prevention and control and glasses fitting optimization method according to claim 1, characterized in that: The individual's physiological parameters in S1 include age, refractive power, corneal curvature, axial length, and lens transparency; the behavioral parameters include reading distance, reading time, and frequency of use of electronic devices; the environmental parameters include lighting conditions in the living or working environment and time spent outdoors.

6. The personalized myopia prevention and control and glasses fitting optimization method according to claim 1, characterized in that: S4 includes the following steps: ① Based on the results of the risk quantification assessment, generate an individualized myopia risk report, including myopia risk level, key influencing factors, and recommended prevention and control measures; ② Generate personalized myopia prevention and control recommendations for different myopia risk levels; ③ Customize appropriate glasses fitting plans based on individual physiological parameters and eye needs, including lens type, lens power, and frame selection.

7. A personalized myopia prevention and control and glasses fitting optimization system according to the personalized myopia prevention and control and glasses fitting optimization method according to any one of claims 1 to 6, characterized in that: include: A collection module (101) is used to collect individual physiological parameters, behavioral parameters and environmental parameters, and integrate them to form an individual comprehensive data set; A network construction module (102) constructs an individual physiological-behavioral-environment interaction network based on the individual comprehensive data set; A risk assessment module (103) uses complex network analysis methods to analyze the individual's physiological-behavioral environment interaction network to assess the individual's myopia risk; A personalized suggestion generation module (104) generates personalized myopia prevention and control suggestions and glasses fitting plans based on individual myopia risk assessment results; The system optimization module (105) collects user feedback and optimizes the system according to the feedback results.

8. The personalized myopia prevention and control and glasses fitting optimization system of the personalized myopia prevention and control and glasses fitting optimization method according to claim 7, characterized in that: The risk assessment module (103) comprises: A network stability calculation module (113), used to calculate the overall network efficiency of the individual physiological-behavioral environment interaction network to evaluate the stability of the network when subjected to external interference; A key node identification module (123) calculates the comprehensive centrality value of each node using a complex network analysis method, and identifies the key nodes in the interactive network according to the ranking of the comprehensive centrality values ​​of each node; A critical risk path identification module (133) uses a complex network analysis method to calculate the intermediate centrality of each connection edge of the interactive network and identify the critical risk path; The risk quantification assessment module (143) performs a quantitative assessment of the individual's myopia risk based on the analysis results, and uses a risk level to indicate the magnitude of the myopia risk.

9. An electronic device, characterized in that: It includes a processor and a memory, wherein a computer program is stored in the memory, and the processor is used to execute the steps of the personalized myopia prevention and control and glasses fitting optimization method described in any one of claims 1 to 6 by calling the computer program stored in the memory.

10. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the personalized myopia prevention and control and glasses fitting optimization method according to any one of claims 1 to 6 are executed.

Images