Sunlight illumination adjusting system and method for hospital based on work and rest rhythm of patient
By combining data acquisition and SVM models with an adaptive zoning strategy, the light source control zoning and fiber optic distribution paths are dynamically adjusted, solving the problem of insufficient response of hospital lighting systems to individual patient differences and environmental changes, and improving system flexibility and patient comfort.
Patent Information
- Application Number
- CN202510932007.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-07-07
- Publication Date
- 2025-10-21
AI Technical Summary
Existing hospital lighting systems lack the ability to respond in real time to individual patient differences and changes in ambient light. Furthermore, the centralized control logic leads to response delays, making it impossible to effectively address the differences in light stimulation sensitivity among different patients, and posing risks of overstimulation or reduced adaptability.
The system acquires patient information and environmental data through a data acquisition module, uses an SVM model to predict light sensitivity, and combines an adaptive zoning strategy and fiber optic splitting weight allocation to dynamically adjust the light source control zoning and fiber optic splitting path to achieve personalized illumination adjustment.
It enables precise assessment of patients' light sensitivity and control of light source zones, reduces the cost of fiber optic materials and cabling, improves system flexibility and patient comfort, and reduces light source loss and response delay.
Smart Images

Figure CN120825854A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of light path control, and in particular to a hospital sunlight lighting adjustment system and method based on a patient's work and rest rhythm. Background Art
[0002] With the continuous improvement of medical service levels, hospital environmental lighting has gradually developed from simply meeting visual needs to "rhythmic lighting" that supports patients' physical health and psychological rehabilitation.
[0003] In hospital inpatient departments, some patients, such as specific subgroups in neurology, psychiatry, or intensive care units, may have abnormal sensitivities to light stimulation. Furthermore, different patients may have significant differences in their responses to the same spectral intensity. This indicates that under certain pathological or drug conditions, the physiological or behavioral responses to light rhythm intervention are unpredictable, and there may even be a risk of overstimulation or reduced adaptability. Therefore, in system design, simply adjusting the light intensity using a standard curve may be ineffective for these sensitive patients or may result in significant fluctuations in the effect, requiring the provision of a more flexible or cautious mode.
[0004] Currently, most hospitals still use lighting systems that rely on constant, manually mixed, or preset modes. These systems lack the ability to respond to individual patient differences and ambient light variations in real time. Furthermore, control logic often runs on central servers, resulting in response delays and susceptibility to network jitter. These systems lack real-time room-level adaptability and ignore the impact of patient medication status and ambient light variations.
[0005] To this end, the present invention provides a hospital-use solar lighting adjustment system and method based on the patient's work and rest rhythm. Summary of the Invention
[0006] The purpose of the present invention is to provide a hospital sunlight lighting adjustment system and method based on the patient's work and rest rhythm to solve the existing problems raised in the above background technology.
[0007] To achieve the above objectives, the present invention provides the following technical solutions: a hospital-use sunlight lighting adjustment system and method based on the patient's work and rest rhythm, comprising: The data acquisition module is used to obtain patient type information and medication administration records through the hospital information system; at the same time, it obtains the current indoor spectrum, fiber distribution node status, external sunlight incident intensity and spectral characteristics, and status event trigger signals from the environmental sensor network; The photosensitivity prediction module is used to perform feature preprocessing and encoding at the edge node, call the SVM model to predict photosensitivity, and generate photosensitivity scores for the current initial partitioned patient and scene; An adaptive partitioning module is used to adjust the initial partitions through an adaptive partitioning strategy to obtain light source control partitions; The optical fiber shunt weight allocation module is used to set the optical fiber shunt algorithm according to the light sensitivity score to obtain the optical fiber shunt weight and path of each light source control zone.
[0008] The present invention is further improved in that the data acquisition module includes establishing patient basic type characteristics, drug coding characteristics, event and time series characteristics; The patient's basic type characteristics include department type, age and gender, and the patient's heart rate and body temperature are obtained through wearable devices; The drug coding feature includes constructing an existing drug photosensitivity information database, using one-hot encoding for each drug photosensitivity information, and assigning a drug photosensitivity coefficient to the drug; The event and timing characteristics include time characteristics, event characteristics and environmental characteristics. The time characteristics include clock time; the event characteristics include state event trigger signals, specifically patrol, visit, treatment, and rest; the environmental characteristics include outdoor spectrum obtained by spectral sensor , indoor spectrum .
[0009] The present invention is further improved in that the photosensitivity prediction module includes extracting the outdoor spectrum , indoor spectrum , the spectrum difference value Sdv is obtained by cosine similarity; the difference between the weighted sum of the patient's heart rate and body temperature after standardization and the personnel status baseline value is calculated to obtain the patient's sensitivity value; the historical indoor spectrum The corresponding patient sensitivity values are sent as training data to the personnel sensitivity prediction model based on the SVM model. If the current patient is not wearing a device, the current indoor spectrum is used as the input data of the personnel sensitivity prediction model to obtain the current patient's photosensitivity value Psv; the drug photosensitivity coefficient Drp is extracted; and the photosensitivity score is obtained by combining the drug photosensitivity coefficient, the spectral difference value and the current patient's photosensitivity value.
[0010] A further improvement of the present invention is that the light sensitivity score is expressed as ,in represents the standardized drug photosensitivity coefficient, represents the normalized spectral difference value, Indicates the normalized current patient light sensitivity value.
[0011] The present invention is further improved in that the adaptive partitioning module includes assigning an initial weight ma to all initial partitions according to the light sensitivity score and assigning a fiber branch light source; then the sensitivity category, outdoor spectrum, indoor spectrum, and location of the ward are input into the adaptive partitioning strategy as the feature vector of each initial partition to obtain M light source control partitions; for each light source control partition, the neighborhood daylight distribution coupling factor is calculated. , represents the demand-impact coupling similarity, α represents any initial partition in the light source control partition β, Represents the set characteristic scale parameter.
[0012] A further improvement of the present invention is that the demand-impact coupling similarity is expressed as ,in, Indicates the initial partition fiber light source position, Represents a distance-based attenuation function in the form of Gaussian attenuation, represents the distance function, Represents a time series based on historical ideal spectral patterns The calculated dynamic time warping distance, Parameter weights representing the similarity of requirement-impact coupling.
[0013] A further improvement of the present invention is that the adaptive partitioning strategy includes a preliminary mapping output layer and an abstract clustering output layer; the specific steps include: The preliminary mapping output layer maps the original feature vector to a two-dimensional space and uses competitive learning to make adjacent initial partitions form K light source candidate partitions; the abstract clustering output layer includes extracting the cluster centers of K light source candidate partitions ; For each light source candidate partition, find the candidate partition center closest to it by Euclidean distance , and order Participate in the competition update; the original cluster center and Perform collaborative updates; when the absolute value of the difference between the demand-impact coupling similarity of the updated candidate cluster center and the mean value of the demand-impact coupling similarity of the candidate partition cluster is less than the set cluster difference threshold, stop the competition and obtain the light source control partition.
[0014] The present invention is further improved in that the optical fiber splitting weight distribution module includes taking the sum of the initial weights of the original partitions within the light source control partition as the new weight of the light source control partition to perform light source splitting; Redistribute the fiber optic branching weights of each initial partition in each light source control partition, expressed as , Indicates the The light source controls the i-th optical fiber branch light source in the partition, Indicates the The average light sensitivity score of each light source control partition; The optical fiber branch light source corresponding to the maximum value is used as the starting point of the optical fiber branching; Extract the set of optical fiber branch light sources that the next path passes through in each light source control partition. At this time, calculate the optical fiber branching weight of each optical fiber branch light source in the next optical fiber branch light source set, and allocate the optical fiber branching of each light source control partition according to the optical fiber branching weight of each optical fiber branch light source in the next optical fiber branch light source set to perform light source path planning.
[0015] A further improvement of the present invention is that the optical fiber branching weight distribution module further includes defining the control parameters of each optical fiber branch light source , then the overall control quantity of each light source control partition is expressed as , N represents the number of optical fiber branch light sources in the light source control zone; when a status event trigger signal is triggered, the system automatically adjusts the control parameters of the corresponding optical fiber branch light source to the standard control parameters corresponding to the status event.
[0016] In another aspect, the present invention provides a method for adjusting solar lighting for hospitals based on the patient's work and rest rhythm, the specific steps comprising: S1. Obtain patient type information and medication administration records through the hospital information system; at the same time, obtain the current indoor spectrum, fiber distribution node status, external sunlight incident intensity and spectral characteristics, and status event trigger signals from the environmental sensor network; S2. Perform feature preprocessing and encoding at the edge node, call the SVM model to predict light sensitivity, and generate a light sensitivity score for the current initial partitioned patient and scene; S3. Adjust the initial partitions through the adaptive partitioning strategy to obtain light source control partitions; S4. Setting a fiber optic splitting algorithm according to the light sensitivity score to obtain a fiber optic splitting weight and path for each light source control partition.
[0017] Compared with the prior art, the present invention has the following beneficial effects: 1. This invention first adaptively generates light source control partitions by inputting the initial partitions based on light sensitivity, spectral characteristics, and spatial position into a multi-view competitive learning + abstract clustering module. It then constructs neighborhood coupling factors based on demand-impact coupling similarity to effectively characterize the collaborative dependencies between partitions, achieving a partition structure that balances local exclusivity with global coordination, ensuring high stability and robustness in clinical scenarios. 2. A neighborhood daylight distribution coupling factor is introduced to dynamically allocate fiber optic diversion weights and paths based on the sensitivity of each control partition. The optimal starting point is selected first and extended along the optimal path, so that the fiber optic diversion algorithm can fully reflect the relative position and neighborhood influence of each fiber optic light source in the entire control area, which helps to reduce local operation risks while saving fiber optic material and wiring costs and reducing light source losses. At the same time, it supports event-driven control parameter switching, taking into account both system flexibility and patient comfort. BRIEF DESCRIPTION OF THE DRAWINGS
[0018] Figure 1 This is a framework diagram of the hospital sunlight lighting adjustment system based on the patient's work and rest rhythm of the present invention. DETAILED DESCRIPTION
[0019] The technical solution of the present invention is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical solution of the present invention, rather than limitations on the technical solution of the present invention. In the absence of conflict, the embodiments of the present invention and the technical features in the embodiments can be combined with each other.
[0020] The term "and / or" is merely a description of the association relationship between associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone.
[0021] Example 1 Figure 1 The framework diagram of the solar lighting regulation system for hospitals based on the patient's sleep and rest rhythm disclosed in this embodiment is shown, including: The data acquisition module is used to obtain patient type information (such as department, diagnosis code, age, basic conditions, etc.) and medication administration records through the hospital information system (HIS / EMR). It also obtains the current indoor spectrum, fiber distribution node status, external sunlight incident intensity and spectral characteristics, and status event trigger signals from the environmental sensor network; The photosensitivity prediction module is used to perform feature preprocessing and encoding at the edge node, call the SVM model to predict photosensitivity, and generate photosensitivity scores for the current initial partitioned patient and scene; An adaptive partitioning module is used to adjust the initial partitions through an adaptive partitioning strategy to obtain light source control partitions; The optical fiber shunt weight allocation module is used to set the optical fiber shunt algorithm according to the light sensitivity score to obtain the optical fiber shunt weight and path of each light source control zone.
[0022] The data acquisition module includes establishing patient basic type characteristics, drug coding characteristics, event and time series characteristics; The basic characteristics of the patient include department type, age and gender, and the patient's heart rate and body temperature are obtained through wearable devices, which are used for patient behavior scoring in subsequent models; The drug coding feature includes constructing an existing drug photosensitivity information database, such as a list of photosensitivity drugs, derived from clinical pharmacology literature or databases, using one-hot coding for each drug's photosensitivity information, and assigning a drug photosensitivity coefficient to the drug; The event and time series features include time features, event features, and environmental features. The time features include clock time, such as hours, relative time periods relative to the patient's personal schedule, and date information, reflecting different seasonal or hospital sunlight conditions. The event characteristics include state event trigger signals, specifically patrol, visit, treatment, and rest; the environmental characteristics include outdoor spectrum obtained by spectral sensor , indoor spectrum ; Outdoor daylight intensity / spectrum (estimated indoor available daylight characteristics through the meteorological API combined with optical models); current indoor spectrum / illuminance (measured by spectrum / illuminance sensors).
[0023] The photosensitive prediction module includes extracting the outdoor spectrum , indoor spectrum , the spectrum difference value Sdv is obtained by cosine similarity; the difference between the weighted sum of the patient's heart rate and body temperature after standardization and the personnel status baseline value is calculated to obtain the patient's sensitivity value; the historical indoor spectrum The corresponding patient sensitivity values are sent as training data to the personnel sensitivity prediction model based on the SVM model. If the current patient is not wearing a device, the current indoor spectrum is used as the input data of the personnel sensitivity prediction model to obtain the current patient's photosensitivity value Psv; the drug photosensitivity coefficient Drp is extracted; and the photosensitivity score is obtained by combining the drug photosensitivity coefficient, the spectral difference value and the current patient's photosensitivity value.
[0024] The calculation process of spectral difference value is expressed as , , indicating the change of spectral shape. If the two directions are close, then If the difference is large, then The larger the spectral difference, the smaller the light, the greater the amount of compensation required, and the more tolerant the light source input control amount; the drug photosensitivity coefficient and the patient's sensitivity value are more sensitive to the light source input control amount, so the photosensitivity score is expressed as ,in represents the standardized drug photosensitivity coefficient, represents the normalized spectral difference value, Indicates the normalized current patient light sensitivity value.
[0025] The adaptive partitioning module includes assigning an initial weight ma to all initial partitions according to the light sensitivity score. The more sensitive the partition, the higher the weight. For example, the light sensitivity score is the proportion of the sum of the light sensitivity scores of all initial partitions, and a fiber optic branch light source is assigned. Then, the sensitivity category, outdoor spectrum, indoor spectrum, and location of the ward are input into the adaptive partitioning strategy as the feature vector of each initial partition to obtain M light source control partitions. For each light source control partition, the neighborhood daylight distribution coupling factor is calculated. , represents the demand-impact coupling similarity, α represents any initial partition in the light source control partition β, Represents the set characteristic scale parameter, which is used to control the sensitivity of attenuation, similar to the "bandwidth" of the Gaussian kernel function; pass The more similar the partitions, the higher the degree of coupling, and the greater the contribution to the total value; for areas with very different demands, big, will approach 0, which means that the area has little impact on the target area. In light environment control, if the coupling relationship is not considered, the lighting control of some highly sensitive wards may be over-focused, resulting in an imbalance in overall resource scheduling. After that, it can automatically determine whether the lighting of a certain area is easily affected by the lighting of other areas, which is used for weighted dimming or feedback strategy. In this embodiment, the spatial relationship between each fiber optic light source is integrated in a nonlinear way to extract local density information. Each light source control partition can be calculated through local information and communication with neighboring nodes. Reduce the pressure of centralized computing; and the neighborhood coupling factor can reflect the degree of interdependence within the local cluster, providing a basis for introducing collaborative control into the fiber optic splitting weight distribution module.
[0026] The requirement-impact coupling similarity is expressed as ,in, Indicates the initial partition fiber light source position, Represents a distance-based attenuation function in the form of Gaussian attenuation, represents the distance function, Represents a time series based on historical ideal spectral patterns The calculated dynamic time warping distance represents the ideal output pattern of the device in its affected area at different times or in different event scenarios, and calculates similarity, such as dynamic time warping (DTW) distance or correlation coefficient. Parameter weights representing the similarity of requirement-impact coupling: The demand-impact coupling similarity reflects the degree of mutual dependence of each partition in the cluster on the central partition. A high similarity means that the two devices jointly affect the same highly sensitive sub-area and have similar demand patterns, which means they are more dependent. If the dependence is strong, a stronger weight is assigned.
[0027] The adaptive partitioning strategy includes a preliminary mapping output layer and an abstract clustering output layer; the specific steps include: The preliminary mapping output layer maps the original feature vector to a two-dimensional space and uses competitive learning to make adjacent initial partitions form K light source candidate partitions; the abstract clustering output layer includes extracting the cluster centers of K light source candidate partitions ; For each light source candidate partition, find the candidate partition center closest to it by Euclidean distance , and order Participate in competitive update, the formula is expressed as ;in Indicates the learning rate that is set to gradually decay with iteration. When the distance is the smallest, the center will be selected as the "winner" and updated; In order to activate the similar candidate centers at the same time, the original cluster center and the Perform collaborative updates.
[0028] The original cluster center and Perform collaborative updates; when the absolute value of the difference between the demand-impact coupling similarity of the updated candidate cluster center and the mean value of the demand-impact coupling similarity of the candidate partition cluster is less than the set cluster difference threshold, stop the competition and obtain the light source control partition.
[0029] The adaptive partitioning strategy has adaptive learning capabilities and can dynamically adjust the clustering results of light source control partitions based on real-time data. This allows for stable clustering centers even when data noise in the ward is high, effectively reducing system control errors. The optical fiber splitting weight distribution module includes taking the sum of the initial weights of the original partitions within the light source control partition as the new weight of the light source control partition to perform light source splitting; Redistribute the fiber optic branching weights of each initial partition in each light source control partition, expressed as , Indicates the The light source controls the i-th optical fiber branch light source in the partition, Indicates the The average light sensitivity score of each light source control partition; Select The optical fiber branch light source corresponding to the maximum value is used as the starting point of the optical fiber diversion, saving optical fiber consumables and minimizing light source loss; when Higher, both photosensitivity is high and it is more sensitive to photosensitivity adjustment actions, weight Decrease; when the neighborhood sunlight distribution coupling factor A higher value indicates that the fiber optic light source is in a more complex area and there is a synergistic and complementary effect. Therefore, the single point weight is reduced to achieve global synergistic distribution.
[0030] The fiber optic splitting weight allocation module includes extracting the set of fiber optic branch light sources that the next path passes through in each light source control zone, then calculating the fiber optic splitting weight of each fiber optic branch light source in the next fiber optic branch light source set, and allocating the fiber optic splitting of each light source control zone according to the fiber optic splitting weight of each fiber optic branch light source in the next fiber optic branch light source set, and performing light source path planning. For example, when allocating weights, the next path of the fiber from the first starting point A in the zone can select Q light source path points in the zone. At this time, the fiber optic splitting weights of these Q path points are calculated, and the proportion of the Q fiber optic splitting weights in the total of the Q fiber optic splitting weights is calculated. The maximum fiber optic splitting weight is selected as the next node, and so on, until all allocations are completed.
[0031] The optical fiber branch weight distribution module also includes a control parameter defining each optical fiber branch light source. , then the overall control quantity of each light source control partition is expressed as , N represents the number of optical fiber branch light sources in the light source control zone; when a status event trigger signal is triggered, the system automatically adjusts the control parameters of the corresponding optical fiber branch light source to the standard control parameters corresponding to the status event.
[0032] The thresholds, weights and other setting values may be set by default according to the present invention, or may be set by those skilled in the art.
[0033] Example 2 Based on the same inventive concept as in Example 1, the present invention provides a method for adjusting a patient's work and rest rhythm in a hospital using sunlight lighting, comprising: S1. Obtain patient type information and medication administration records through the hospital information system; at the same time, obtain the current indoor spectrum, fiber distribution node status, external sunlight incident intensity and spectral characteristics, and status event trigger signals from the environmental sensor network; S2. Perform feature preprocessing and encoding at the edge node, call the SVM model to predict light sensitivity, and generate a light sensitivity score for the current initial partitioned patient and scene; S3. Adjust the initial partitions through the adaptive partitioning strategy to obtain light source control partitions; S4. Setting a fiber optic splitting algorithm according to the light sensitivity score to obtain a fiber optic splitting weight and path for each light source control partition.
[0034] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0035] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0036] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.
[0037] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.
[0038] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the purpose of the present invention and the claims, which are all protected by the present invention.
Claims
1. A solar lighting adjustment system for hospitals based on the patient's daily rhythm, characterized by: include: Data collection module, used to obtain patient type information and medication administration records through the hospital information system; At the same time, it obtains the current indoor spectrum, fiber distribution node status, external sunlight incident intensity and spectrum characteristics, and status event trigger signals from the environmental sensor network; The photosensitivity prediction module is used to perform feature preprocessing and encoding at the edge node, call the SVM model to predict photosensitivity, and generate photosensitivity scores for the current initial partitioned patient and scene; An adaptive partitioning module is used to adjust the initial partitions through an adaptive partitioning strategy to obtain light source control partitions; The optical fiber shunt weight allocation module is used to set the optical fiber shunt algorithm according to the light sensitivity score to obtain the optical fiber shunt weight and path of each light source control zone.
2. The solar lighting adjustment system for hospitals based on the patient's work and rest rhythm according to claim 1, characterized in that: The data acquisition module includes establishing patient basic type characteristics, drug coding characteristics, event and time series characteristics; The patient's basic type characteristics include department type, age and gender, and the patient's heart rate and body temperature are obtained through wearable devices; The drug coding feature includes constructing an existing drug photosensitivity information database, using one-hot encoding for each drug photosensitivity information, and assigning a drug photosensitivity coefficient to the drug; The event and timing characteristics include time characteristics, event characteristics and environmental characteristics. The time characteristics include clock time; the event characteristics include state event trigger signals, specifically patrol, visit, treatment, and rest; the environmental characteristics include outdoor spectrum obtained by spectral sensor , indoor spectrum .
3. The solar lighting adjustment system for hospitals based on the patient's work and rest rhythm according to claim 1, characterized in that: The photosensitive prediction module includes extracting the outdoor spectrum , indoor spectrum , the spectrum difference value Sdv is obtained by cosine similarity; the difference between the weighted sum of the patient's heart rate and body temperature after standardization and the personnel status baseline value is calculated to obtain the patient's sensitivity value; the historical indoor spectrum The corresponding patient sensitivity value is used as training data and sent to the personnel sensitivity prediction model based on the SVM model. If the current patient does not wear the device, the current indoor spectrum is used as the input data of the personnel sensitivity prediction model to obtain the current patient light sensitivity value Psv; Extract the drug photosensitivity coefficient Drp; combine the drug photosensitivity coefficient, spectral difference value and the current patient photosensitivity value to obtain the photosensitivity score.
4. The solar lighting adjustment system for hospitals based on the patient's work and rest rhythm according to claim 3, characterized in that: The light sensitivity score is expressed as ,in represents the standardized drug photosensitivity coefficient, represents the normalized spectral difference value, Indicates the normalized current patient light sensitivity value.
5. The solar lighting adjustment system for hospitals based on the patient's work and rest rhythm according to claim 4, characterized in that: The adaptive partitioning module includes assigning an initial weight ma to all initial partitions according to the light sensitivity score and assigning a fiber branch light source; then the sensitivity category, outdoor spectrum, indoor spectrum, and location of the ward are input into the adaptive partitioning strategy as the feature vector of each initial partition to obtain M light source control partitions; for each light source control partition, the neighborhood daylight distribution coupling factor is calculated. , represents the demand-impact coupling similarity, α represents any initial partition in the light source control partition β, Represents the set characteristic scale parameter.
6. The solar lighting adjustment system for hospitals based on the patient's work and rest rhythm according to claim 5, characterized in that: The requirement-impact coupling similarity is expressed as ,in, Indicates the initial partition fiber light source position, Represents a distance-based attenuation function in the form of Gaussian attenuation, represents the distance function, Represents a time series based on historical ideal spectral patterns The calculated dynamic time warping distance, Parameter weights representing the similarity of requirement-impact coupling.
7. The solar lighting adjustment system for hospitals based on the patient's work and rest rhythm according to claim 6, characterized in that: The adaptive partitioning strategy includes a preliminary mapping output layer and an abstract clustering output layer; The specific steps include: The preliminary mapping output layer maps the original feature vector to a two-dimensional space and uses competitive learning to make adjacent initial partitions form K light source candidate partitions; the abstract clustering output layer includes extracting the cluster centers of K light source candidate partitions ; For each light source candidate partition, find the candidate partition center closest to it by Euclidean distance , and order Participate in the competition update; the original cluster center and Perform collaborative updates; when the absolute value of the difference between the demand-impact coupling similarity of the updated candidate cluster center and the mean value of the demand-impact coupling similarity of the candidate partition cluster is less than the set cluster difference threshold, stop the competition and obtain the light source control partition.
8. The solar lighting adjustment system for hospitals based on the patient's work and rest rhythm according to claim 7, characterized in that: The optical fiber splitting weight distribution module includes taking the sum of the initial weights of the original partitions within the light source control partition as the new weight of the light source control partition to perform light source splitting; Redistribute the fiber optic branching weights of each initial partition in each light source control partition, expressed as , Indicates the The light source controls the i-th optical fiber branch light source in the partition, Indicates the The average light sensitivity score of each light source control partition; The optical fiber branch light source corresponding to the maximum value is used as the starting point of the optical fiber branching; Extract the set of optical fiber branch light sources that the next path passes through in each light source control partition. At this time, calculate the optical fiber branching weight of each optical fiber branch light source in the next optical fiber branch light source set, and allocate the optical fiber branching of each light source control partition according to the optical fiber branching weight of each optical fiber branch light source in the next optical fiber branch light source set to perform light source path planning.
9. The solar lighting adjustment system for hospitals based on the patient's work and rest rhythm according to claim 8, characterized in that: The optical fiber branch weight distribution module also includes a control parameter defining each optical fiber branch light source. , then the overall control quantity of each light source control partition is expressed as , N represents the number of optical fiber branch light sources in the light source control zone; when a status event trigger signal is triggered, the system automatically adjusts the control parameters of the corresponding optical fiber branch light source to the standard control parameters corresponding to the status event.
10. A method for regulating solar lighting for hospitals based on a patient's work and rest rhythm, for implementing a solar lighting regulation system for hospitals based on a patient's work and rest rhythm as claimed in any one of claims 1 to 9, characterized in that: The specific steps include: S1. Obtain patient type information and medication administration records through the hospital information system; at the same time, obtain the current indoor spectrum, fiber distribution node status, external sunlight incident intensity and spectral characteristics, and status event trigger signals from the environmental sensor network; S2. Perform feature preprocessing and encoding at the edge node, call the SVM model to predict light sensitivity, and generate a light sensitivity score for the current initial partitioned patient and scene; S3. Adjust the initial partitions through the adaptive partitioning strategy to obtain light source control partitions; S4. Setting a fiber optic splitting algorithm according to the light sensitivity score to obtain a fiber optic splitting weight and path for each light source control partition.
