Light adjustment method and device of illumination device, computer equipment, storage medium and computer program product

Abstract

The invention relates to an illumination device light adjusting method and device, computer equipment, a storage medium and a computer program product. The method comprises the steps that electro-oculogram signals in first electroencephalogram signals of a to-be-analyzed object in different illumination intensity environments are filtered, and filtered electroencephalogram signals are obtained; inputting the filtered electroencephalogram signals into a trained light sensitivity prediction model to obtain predicted light sensitivity of the to-be-analyzed object; inputting the predicted light sensitivity, the initial sleep time period, the target sleep time period and the individual feature information of the to-be-analyzed object and the meteorological information of the position of the to-be-analyzed object into the trained illumination parameter prediction model to obtain predicted illumination parameters corresponding to the to-be-analyzed object; and according to the predicted illumination parameter, performing light adjustment on an illumination device corresponding to the to-be-analyzed object to obtain the illumination device after light adjustment. By adopting the method, the sleep quality of the object can be improved.

Description

Technical Field

[0001] The present application relates to the field of computer technologies, and particularly to a method and apparatus for adjusting light rays of a lighting device, a computer device, a computer-readable storage medium, and a computer program product. Background Art

[0002] Currently, how to improve the sleep quality of an object (such as a shift worker) is crucial for better adapting to different work schedules and environments and improving the work performance of the object.

[0003] In traditional technologies, in terms of improving the sleep quality of an object, previous inventions and research mainly focused on the calculation and analysis of circadian rhythms (such as the method of using a cosine function to fit an individual's circadian rhythm), ignored the aspect of adjusting circadian rhythms to adapt to an individual's work and life, and previous inventions and research often lacked personalized considerations and could not meet the unique needs of each person, resulting in a low sleep quality of the object. Summary of the Invention

[0004] Based on this, in view of the above technical problems, it is necessary to provide a method and apparatus for adjusting light rays of a lighting device, a computer device, a computer-readable storage medium, and a computer program product that can improve the sleep quality of an object.

[0005] In a first aspect, the present application provides a method for adjusting light rays of a lighting device, including:

[0006] Obtaining a first electroencephalogram (EEG) signal of an object to be analyzed in different light intensity environments;

[0007] Performing filtering processing on the electrooculogram (EOG) signal in the first EEG signal to obtain a filtered EEG signal;

[0008] Inputting the filtered EEG signal into a trained light sensitivity prediction model to obtain the predicted light sensitivity of the object to be analyzed;

[0009] Obtaining the initial sleep time period, target sleep time period, individual characteristic information of the object to be analyzed, and meteorological information of the location where the object to be analyzed is located, and inputting the predicted light sensitivity, the initial sleep time period, the target sleep time period, the individual characteristic information, and the meteorological information into a trained lighting parameter prediction model to obtain the predicted lighting parameters corresponding to the object to be analyzed;

[0010] Adjusting the light rays of the lighting device corresponding to the object to be analyzed according to the predicted lighting parameters to obtain a lighting device with adjusted light rays.

[0011] In one embodiment, filtering the electrooculogram signal in the first electroencephalogram signal to obtain a filtered electroencephalogram signal includes:

[0012] Segmenting the first electroencephalogram signal to obtain multiple sub - electroencephalogram signals;

[0013] Obtaining the standard deviation value of each sub - electroencephalogram signal, and screening out the sub - electroencephalogram signal with the largest standard deviation value from each sub - electroencephalogram signal as the first target sub - electroencephalogram signal, and screening out the sub - electroencephalogram signal with the smallest standard deviation value from each sub - electroencephalogram signal as the second target sub - electroencephalogram signal;

[0014] Filtering the electrooculogram signal in the first electroencephalogram signal according to the first target sub - electroencephalogram signal and the second target sub - electroencephalogram signal to obtain the filtered electroencephalogram signal.

[0015] In one embodiment, filtering the electrooculogram signal in the first electroencephalogram signal according to the first target sub - electroencephalogram signal and the second target sub - electroencephalogram signal to obtain the filtered electroencephalogram signal includes:

[0016] Obtaining the average value corresponding to the first target sub - electroencephalogram signal and the second target sub - electroencephalogram signal;

[0017] Determining the target threshold value corresponding to the sub - electroencephalogram signal according to the average value;

[0018] Screening out the sub - electroencephalogram signals smaller than the target threshold value from each sub - electroencephalogram signal as the electrooculogram signal in the first electroencephalogram signal;

[0019] Filtering the electrooculogram signal to obtain the filtered electroencephalogram signal.

[0020] In one embodiment, inputting the filtered electroencephalogram signal into a trained light sensitivity prediction model to obtain the predicted light sensitivity of the object to be analyzed includes:

[0021] Performing a conversion process on the filtered electroencephalogram signal to obtain an electroencephalogram spectrogram of the object to be analyzed;

[0022] Inputting the electroencephalogram spectrogram into the trained light sensitivity prediction model to obtain the predicted probabilities of the object to be analyzed at each preset light sensitivity;

[0023] Screening out the preset light sensitivity with the largest predicted probability from each preset light sensitivity as the predicted light sensitivity.

[0024] In one embodiment, obtaining the initial sleep time period, target sleep time period, and individual characteristic information of the object to be analyzed includes:

[0025] Obtaining the initial working time period, target working time period, sleep duration information, and core body temperature data of the object to be analyzed;

[0026] Determining the baseline circadian rhythm information of the object to be analyzed according to the core body temperature data; the baseline circadian rhythm information is used to represent the corresponding relationship between the core body temperature value of the object to be analyzed and the time;

[0027] Determining the time when the core body temperature value is the smallest as the target time of the object to be analyzed according to the baseline circadian rhythm information;

[0028] Determining the initial sleep time period according to the target time and the sleep duration information, and determining the target sleep time period according to the initial sleep time period, the initial working time period, and the target working time period.

[0029] In one embodiment, after adjusting the light of the lighting device corresponding to the object to be analyzed according to the predicted light parameters to obtain the lighting device with adjusted light, it further includes:

[0030] Obtaining the second electroencephalogram signal of the object to be analyzed under the predicted light parameters;

[0031] Preprocessing the second electroencephalogram signal to obtain a preprocessed electroencephalogram signal;

[0032] Performing continuous wavelet transform processing on the preprocessed electroencephalogram signal to obtain a time-frequency diagram corresponding to the second electroencephalogram signal;

[0033] Inputting the time-frequency diagram into a trained sleep staging model to obtain a sleep staging result of the object to be analyzed; the sleep staging result is used to represent the proportion of the duration of the object to be analyzed in different sleep stages;

[0034] Determining the sleep quality of the object to be analyzed according to the sleep staging result.

[0035] In a second aspect, the present application also provides a lighting device light adjustment device, including:

[0036] A signal acquisition module, configured to acquire the first electroencephalogram signal of the object to be analyzed in environments with different light intensities;

[0037] A signal processing module, configured to filter the electrooculogram signal in the first electroencephalogram signal to obtain a filtered electroencephalogram signal;

[0038] A model prediction module, configured to input the post-filtered EEG signal into a trained light sensitivity prediction model to obtain the predicted light sensitivity of the object to be analyzed;

[0039] A parameter prediction module, configured to obtain the initial sleep time period, target sleep time period, individual characteristic information of the object to be analyzed, and meteorological information of the location where the object to be analyzed is located, and input the predicted light sensitivity, the initial sleep time period, the target sleep time period, the individual characteristic information, and the meteorological information into a trained light parameter prediction model to obtain the predicted light parameters corresponding to the object to be analyzed;

[0040] A light adjustment module, configured to adjust the light of the lighting device corresponding to the object to be analyzed according to the predicted light parameters to obtain a lighting device with adjusted light.

[0041] In a third aspect, the present application further provides a computer device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0042] Obtain the first EEG signal of the object to be analyzed in environments with different light intensities;

[0043] Perform filtering processing on the electrooculogram signal in the first EEG signal to obtain a post-filtered EEG signal;

[0044] Input the post-filtered EEG signal into a trained light sensitivity prediction model to obtain the predicted light sensitivity of the object to be analyzed;

[0045] Obtain the initial sleep time period, target sleep time period, individual characteristic information of the object to be analyzed, and meteorological information of the location where the object to be analyzed is located, and input the predicted light sensitivity, the initial sleep time period, the target sleep time period, the individual characteristic information, and the meteorological information into a trained light parameter prediction model to obtain the predicted light parameters corresponding to the object to be analyzed;

[0046] Adjust the light of the lighting device corresponding to the object to be analyzed according to the predicted light parameters to obtain a lighting device with adjusted light.

[0047] In a fourth aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0048] Obtain the first EEG signal of the object to be analyzed in environments with different light intensities;

[0049] Perform filtering processing on the electrooculogram signal in the first EEG signal to obtain a post-filtered EEG signal;

[0050] Input the electroencephalogram signal after filtering into the trained light sensitivity prediction model to obtain the predicted light sensitivity of the object to be analyzed;

[0051] Obtain the initial sleep time period, target sleep time period, individual characteristic information of the object to be analyzed, and meteorological information of the location where the object to be analyzed is located, and input the predicted light sensitivity, the initial sleep time period, the target sleep time period, the individual characteristic information, and the meteorological information into the trained lighting parameter prediction model to obtain the predicted lighting parameters corresponding to the object to be analyzed;

[0052] Adjust the light of the lighting device corresponding to the object to be analyzed according to the predicted lighting parameters to obtain a lighting device with adjusted light.

[0053] In a fifth aspect, the present application also provides a computer program product, including a computer program, which when executed by a processor implements the following steps:

[0054] Obtain the first electroencephalogram signal of the object to be analyzed in an environment with different light intensities;

[0055] Filter the electrooculogram signal in the first electroencephalogram signal to obtain an electroencephalogram signal after filtering;

[0056] Input the electroencephalogram signal after filtering into the trained light sensitivity prediction model to obtain the predicted light sensitivity of the object to be analyzed;

[0057] Obtain the initial sleep time period, target sleep time period, individual characteristic information of the object to be analyzed, and meteorological information of the location where the object to be analyzed is located, and input the predicted light sensitivity, the initial sleep time period, the target sleep time period, the individual characteristic information, and the meteorological information into the trained lighting parameter prediction model to obtain the predicted lighting parameters corresponding to the object to be analyzed;

[0058] Adjust the light of the lighting device corresponding to the object to be analyzed according to the predicted lighting parameters to obtain a lighting device with adjusted light.

[0059] The above-mentioned light adjustment method, device, computer device, storage medium and computer program product for a lighting device first obtain the first electroencephalogram (EEG) signal of the object to be analyzed in environments with different light intensities, then filter the electrooculogram (EOG) signal in the first EEG signal to obtain the filtered EEG signal. Next, the filtered EEG signal is input into a trained light sensitivity prediction model to obtain the predicted light sensitivity of the object to be analyzed. Then, the initial sleep time period, target sleep time period, individual characteristic information of the object to be analyzed, and meteorological information of the location where the object to be analyzed is located are obtained, and the predicted light sensitivity, initial sleep time period, target sleep time period, individual characteristic information and meteorological information are input into a trained lighting parameter prediction model to obtain the predicted lighting parameters corresponding to the object to be analyzed. Finally, according to the predicted lighting parameters, the lighting device corresponding to the object to be analyzed is adjusted for light, and the lighting device after light adjustment is obtained. In this way, during the process of adjusting the light of the lighting device, through filtering and model prediction processing of the EEG signal of the object to be analyzed in environments with different light intensities, a more accurate predicted light sensitivity of the object to be analyzed can be obtained, and combined with the initial sleep time period, target sleep time period, individual characteristic information of the object to be analyzed, and meteorological information of the location where the object to be analyzed is located, a more accurate predicted lighting parameter of the object to be analyzed can be obtained. Furthermore, according to the predicted lighting parameters, the light of the lighting device can be adjusted more accurately, so that the lighting device after light adjustment can provide light with a more matched intensity and color temperature for the object to be analyzed, that is, a customized lighting scheme is designed according to the object to be analyzed, and personalized rhythm regulation support is provided for the object to be analyzed, which is beneficial to improving the sleep quality of the object. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] To more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following will briefly introduce the drawings required for use in the description of the embodiments of the present application or related technologies. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0061] Figure 1 It is a schematic flowchart of the light adjustment method for a lighting device in an embodiment;

[0062] Figure 2 It is a schematic flowchart of the steps for obtaining the filtered EEG signal in an embodiment;

[0063] Figure 3 It is a schematic flowchart of the light adjustment method for a lighting device in another embodiment;

[0064] Figure 4 It is a structural block diagram of the light adjustment device for a lighting device in an embodiment;

[0065] Figure 5 It is the internal structure diagram of a computer device in an embodiment. Detailed implementation manners

[0066] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application 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 application and are not used to limit the present application.

[0067] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data need to comply with relevant regulations.

[0068] In an exemplary embodiment, as Figure 1 shown, a method for adjusting the light of a lighting device is provided. In this embodiment, the method is exemplified by being applied to a server; it can be understood that the method can also be applied to a terminal, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. Among them, the terminal can be but is not limited to various personal computers, laptop computers, smart phones and tablet computers; the server can be implemented by an independent server or a server cluster composed of multiple servers. In this embodiment, the method includes the following steps:

[0069] Step S101, obtaining first electroencephalogram signals of an object to be analyzed in environments with different light intensities.

[0070] Among them, the light intensity environment includes light intensity and light color temperature.

[0071] Among them, the object to be analyzed refers to the object that needs to be analyzed. In an actual scenario, the analysis object refers to the shift workers who need to be analyzed.

[0072] Among them, the first electroencephalogram signal refers to the electroencephalogram signal of the object to be analyzed in environments with different light intensities.

[0073] Exemplarily, in response to a light adjustment instruction for the lighting device of the object to be analyzed, the server screens out an electroencephalogram acquisition device that matches the object to be analyzed from the candidate electroencephalogram acquisition devices as the target electroencephalogram acquisition device; then, the server acquires the electroencephalogram signal of the object to be analyzed in environments with different light intensities through the target electroencephalogram acquisition device as the first electroencephalogram signal.

[0074] Step S102: Filter the electrooculogram signal in the first electroencephalogram signal to obtain the filtered electroencephalogram signal.

[0075] Among them, the electrooculogram signal refers to the bioelectric signal generated by the eyes.

[0076] Among them, the filtered electroencephalogram signal refers to the first electroencephalogram signal after filtering out the electrooculogram signal contained therein.

[0077] Exemplarily, the server identifies the electrooculogram signal in the first electroencephalogram signal from multiple sub-electroencephalogram signals of the first electroencephalogram signal, and filters the electrooculogram signal in the first electroencephalogram signal to obtain the filtered electroencephalogram signal.

[0078] Step S103: Input the filtered electroencephalogram signal into the trained light sensitivity prediction model to obtain the predicted light sensitivity of the object to be analyzed.

[0079] Among them, the light sensitivity prediction model refers to a network model that can use the filtered electroencephalogram signal of the object to be analyzed to obtain the predicted light sensitivity of the object to be analyzed, such as a convolutional neural network model.

[0080] Among them, the predicted light sensitivity refers to the predicted value of the sensitivity of the eyes of the object to be analyzed to light.

[0081] Exemplarily, the server inputs the filtered electroencephalogram signal into the trained light sensitivity prediction model, and through the trained light sensitivity prediction model, screens out the predicted light sensitivity of the object to be analyzed from each preset light sensitivity.

[0082] Step S104: Obtain the initial sleep time period, target sleep time period, individual characteristic information of the object to be analyzed, and meteorological information of the location where the object to be analyzed is located, and input the predicted light sensitivity, initial sleep time period, target sleep time period, individual characteristic information, and meteorological information into the trained light parameter prediction model to obtain the predicted light parameters corresponding to the object to be analyzed.

[0083] Among them, the initial sleep time period refers to the sleep time period of the object to be analyzed in the normal time period, such as from 11 pm to 7 am.

[0084] Among them, the target sleep time period refers to the sleep time period of the object to be analyzed in the shift time period, such as from 9 am to 5 pm.

[0085] Among them, the individual characteristic information includes the gender information and biological clock type of the object to be analyzed.

[0086] Among them, the meteorological information refers to the basic meteorological elements corresponding to the location where the object to be analyzed is located, including information such as temperature, precipitation, and humidity.

[0087] Among them, the light parameter prediction model refers to a network model that can use the predicted light sensitivity, initial sleep time period, target sleep time period, individual characteristic information, and meteorological information of the object to be analyzed to obtain the predicted light parameters corresponding to the object to be analyzed, such as a recurrent neural network model.

[0088] Among them, the predicted light parameter refers to the predicted value corresponding to the light parameter matched with the object to be analyzed.

[0089] Exemplarily, the server obtains the identification information of the object to be analyzed, and based on this identification information, determines the initial sleep time period, target sleep time period, individual characteristic information of the object to be analyzed, and the meteorological information of the location where the object to be analyzed is located; then, the server inputs the predicted light sensitivity, initial sleep time period, target sleep time period, individual characteristic information, and meteorological information into the trained light parameter prediction model to obtain the first light parameter corresponding to the object to be analyzed; then, the server inputs the predicted light sensitivity, initial sleep time period, target sleep time period, individual characteristic information, and meteorological information into the historical light parameter prediction model corresponding to the trained light parameter prediction model to obtain the second light parameter corresponding to the object to be analyzed; then, the server determines the first model weight of the trained light parameter prediction model and the second model weight of the historical light parameter prediction model, and performs a summation process on the first light parameter and the second light parameter according to the first model weight and the second model weight to obtain the predicted light parameter corresponding to the object to be analyzed.

[0090] Step S105, according to the predicted light parameter, adjust the light of the light device corresponding to the object to be analyzed to obtain the light device with adjusted light.

[0091] Among them, the light device refers to a device used to irradiate the object to be analyzed, such as an incandescent lamp, a fluorescent lamp, a light-emitting diode, etc.

[0092] Exemplarily, the server determines the data type of the predicted light parameter, and based on this data type, queries the corresponding relationship between the data type and the parameter conversion method to obtain the parameter conversion method corresponding to the predicted light parameter; then, the server converts the predicted light parameter into a light adjustment instruction according to this parameter conversion method; then, the server adjusts the light of the light device corresponding to the object to be analyzed according to this light adjustment instruction to obtain the light device with adjusted light.

[0093] In the above method for adjusting the light of the lighting device, first, the first electroencephalogram (EEG) signal of the object to be analyzed in environments with different light intensities is obtained. Then, the electrooculogram (EOG) signal in the first EEG signal is filtered to obtain the filtered EEG signal. Next, the filtered EEG signal is input into the trained light sensitivity prediction model to obtain the predicted light sensitivity of the object to be analyzed. Then, the initial sleep time period, target sleep time period, individual characteristic information of the object to be analyzed, and meteorological information of the location where the object to be analyzed is located are obtained. The predicted light sensitivity, initial sleep time period, target sleep time period, individual characteristic information, and meteorological information are input into the trained lighting parameter prediction model to obtain the predicted lighting parameters corresponding to the object to be analyzed. Finally, according to the predicted lighting parameters, the lighting device corresponding to the object to be analyzed is adjusted for light, and the lighting device after light adjustment is obtained. In this way, during the process of adjusting the light of the lighting device, through filtering and model prediction processing of the EEG signal of the object to be analyzed in environments with different light intensities, a more accurate predicted light sensitivity of the object to be analyzed can be obtained. Combining the initial sleep time period, target sleep time period, individual characteristic information of the object to be analyzed, and meteorological information of the location where the object to be analyzed is located, a more accurate predicted lighting parameter of the object to be analyzed can be obtained. Furthermore, according to the predicted lighting parameters, the light of the lighting device can be adjusted more accurately, so that the lighting device after light adjustment can provide light with a more matched intensity and color temperature for the object to be analyzed, that is, a customized lighting scheme is designed according to the object to be analyzed, providing personalized rhythm regulation support for the object to be analyzed, which is beneficial to improving the sleep quality of the object.

[0094] In an exemplary embodiment, as Figure 2 shown, in step S102 above, filtering the electrooculogram (EOG) signal in the first electroencephalogram (EEG) signal to obtain the filtered EEG signal specifically includes the following steps:

[0095] Step S201: Segment the first EEG signal to obtain multiple sub-EEG signals.

[0096] Step S202: Obtain the standard deviation of each sub-EEG signal, and select the sub-EEG signal with the largest standard deviation from each sub-EEG signal as the first target sub-EEG signal, and select the sub-EEG signal with the smallest standard deviation from each sub-EEG signal as the second target sub-EEG signal.

[0097] Step S203: Filter the electrooculogram (EOG) signal in the first EEG signal according to the first target sub-EEG signal and the second target sub-EEG signal to obtain the filtered EEG signal.

[0098] Among them, the sub-EEG signal refers to a partial EEG signal obtained by segmenting the first EEG signal.

[0099] Among them, the standard deviation value is used to represent the degree of difference between each data point in the operator's electroencephalogram (EEG) signal and the mean value of the sub-EEG signal.

[0100] Among them, the first target sub-EEG signal refers to the sub-EEG signal with the largest standard deviation value in each segment of the sub-EEG signal.

[0101] Among them, the second target sub-EEG signal refers to the sub-EEG signal with the smallest standard deviation value in each segment of the sub-EEG signal.

[0102] Exemplarily, the server segments the first EEG signal according to a preset segmentation method (such as a preset number of segments) to obtain multiple segments of sub-EEG signals; then, the server obtains the average value of the sub-EEG signals, and determines the standard deviation value of each segment of the sub-EEG signal according to the average value and the value of each segment of the sub-EEG signal; then, the server screens out the sub-EEG signal with the largest standard deviation value from each segment of the sub-EEG signal, and uses this sub-EEG signal as the first target sub-EEG signal, and screens out the sub-EEG signal with the smallest standard deviation value from each segment of the sub-EEG signal, and uses this sub-EEG signal as the second target sub-EEG signal.

[0103] In this embodiment, by segmenting the first EEG signal and calculating the standard deviation value of each segment of the sub-EEG signal, the fluctuation characteristics of different segments of the EEG signal can be highlighted, and the first target sub-EEG signal with the largest standard deviation value and the second target sub-EEG signal with the smallest standard deviation value are screened out, which is beneficial to accurately locate and extract the representative parts in the EEG signal and facilitate subsequent analysis and processing.

[0104] In an exemplary embodiment, according to the first target sub-EEG signal and the second target sub-EEG signal, the electrooculogram (EOG) signal in the first EEG signal is filtered to obtain the filtered EEG signal, which specifically includes the following content: obtaining the average value corresponding to the first target sub-EEG signal and the second target sub-EEG signal; determining the target threshold value corresponding to the sub-EEG signal according to the average value; screening out the sub-EEG signal smaller than the target threshold value from each segment of the sub-EEG signal as the EOG signal in the first EEG signal; filtering the EOG signal to obtain the filtered EEG signal.

[0105] Among them, the average value is used to represent the average value of all data points in the first target sub-EEG signal and the second target sub-EEG signal.

[0106] Among them, the target threshold value is used to represent the threshold value for judging each segment of the sub-EEG signal.

[0107] Exemplarily, the server determines all data points of the first target sub-electroencephalogram signal, adds up the values of all data points in the first target sub-electroencephalogram signal to obtain a first total value, and determines the number of data points of all data points in the first target sub-electroencephalogram signal as the first data point number; then, the server determines all data points of the second target sub-electroencephalogram signal, adds up the values of all data points in the second target sub-electroencephalogram signal to obtain a second total value, and determines the number of data points of all data points in the second target sub-electroencephalogram signal as the second data point number; then, the server sums the first total value and the second total value to obtain a target total value, and sums the first data point number and the second data point number to obtain a target data point number; then, the server divides the target total value by the target data point number to obtain an average value corresponding to the first target sub-electroencephalogram signal and the second target sub-electroencephalogram signal; then, the server obtains an average value adjustment coefficient corresponding to the average value (such as 1.25), and multiplies the average value by the average value adjustment coefficient to obtain a target threshold corresponding to the sub-electroencephalogram signal; then, the server filters out sub-electroencephalogram signals smaller than the target threshold from each segment of the sub-electroencephalogram signal, and uses these sub-electroencephalogram signals as electrooculogram signals in the first electroencephalogram signal; then, the server filters the electrooculogram signals according to the filtering method corresponding to the electrooculogram signals to obtain the filtered electroencephalogram signal.

[0108] In this embodiment, by determining the target threshold based on the average value corresponding to the first target sub-electroencephalogram signal and the second target sub-electroencephalogram signal, the part that conforms to the characteristics of the electrooculogram signal can be separated from many sub-electroencephalogram signals, avoiding over-screening or misjudgment of useful information in the electroencephalogram signal, and improving the accuracy of electroencephalogram signal filtering.

[0109] In an exemplary embodiment, in step S103 above, inputting the filtered electroencephalogram signal into the trained light sensitivity prediction model to obtain the predicted light sensitivity of the object to be analyzed specifically includes the following content: performing conversion processing on the filtered electroencephalogram signal to obtain an electroencephalogram spectrogram of the object to be analyzed; inputting the electroencephalogram spectrogram into the trained light sensitivity prediction model to obtain the predicted probabilities of the object to be analyzed under each preset light sensitivity; screening out the preset light sensitivity with the largest predicted probability from each preset light sensitivity as the predicted light sensitivity.

[0110] Among them, the electroencephalogram spectrogram is used to display the distribution of different frequency components in the filtered electroencephalogram signal.

[0111] Among them, the preset light sensitivity refers to the preset light sensitivity, including insensitive, slightly sensitive, sensitive, more sensitive, and very sensitive. It should be noted that the preset light sensitivity depends on the situation.

[0112] Among them, the prediction probability is used to represent the possibility that the light sensitivity prediction model determines the preset light sensitivity as correct.

[0113] Exemplarily, the server performs short-time Fourier transform processing on the filtered posterior electroencephalogram signal to obtain the electroencephalogram spectrogram of the object to be analyzed; then, the server uses the classification labels and the sample set to iteratively train the light sensitivity prediction model to be trained, obtains the trained light sensitivity prediction model, and inputs the electroencephalogram spectrogram into the trained light sensitivity prediction model to obtain the prediction probability of the object to be analyzed under each preset light sensitivity; then, the server screens out the preset light sensitivity with the largest prediction probability from each preset light sensitivity and uses this preset light sensitivity as the predicted light sensitivity.

[0114] In this embodiment, through the electroencephalogram spectrogram and the prediction model, the light sensitivity is converted into specific probability values and prediction results, thereby realizing the quantitative analysis of the light sensitivity; moreover, the entire prediction process does not require manual intervention, reducing the interference of human factors, which is beneficial to improving the reliability and stability of the light sensitivity prediction, and further improving the determination accuracy of the predicted light sensitivity.

[0115] In an exemplary embodiment, the above step S104, obtaining the initial sleep period, the target sleep period, and the individual characteristic information of the object to be analyzed, specifically includes the following content: obtaining the initial working period, the target working period, the sleep duration information, and the core body temperature data of the object to be analyzed; determining the baseline circadian rhythm information of the object to be analyzed according to the core body temperature data; the baseline circadian rhythm information is used to represent the corresponding relationship between the core body temperature value of the object to be analyzed and the time; determining the time with the minimum core body temperature value as the target time of the object to be analyzed according to the baseline circadian rhythm information; determining the initial sleep period according to the target time and the sleep duration information, and determining the target sleep period according to the initial sleep period, the initial working period, and the target working period.

[0116] Among them, the initial working period refers to the working period of the object to be analyzed during the normal period, such as from 9:00 am to 5:00 pm.

[0117] Among them, the target working period refers to the working period of the object to be analyzed during the shift period, such as from 11:00 pm to 7:00 am.

[0118] Among them, the sleep duration information refers to the sleep duration value of the object to be analyzed, such as 8 hours.

[0119] Among them, the core body temperature data includes the core body temperature value of the object to be analyzed and the corresponding time, such as at 22:00 at night, the core body temperature value is 36.8°C.

[0120] Among them, the baseline circadian rhythm information is used to represent the corresponding relationship between the core body temperature value of the object to be analyzed and the time.

[0121] Among them, the target time refers to the time when the core body temperature value is the smallest.

[0122] Exemplarily, the server obtains the identification information of the object to be analyzed, and based on this identification information, determines the initial working time period, target working time period, sleep duration information, and core body temperature data of the object to be analyzed; among them, the initial working time period, target working time period, and sleep duration information of the object to be analyzed can be collected through the form of questionnaires; then, the server uses the special event marking method to filter out the outliers in the core body temperature data, and then uses the cosine method to perform fitting processing on the core body temperature data after filtering out the outliers to obtain the corresponding relationship between the core body temperature value of the object to be analyzed and the time, as the baseline circadian rhythm information; then, the server determines the time when the core body temperature value is the smallest according to the baseline circadian rhythm information, and takes this time as the target time of the object to be analyzed; then, the server determines the initial sleep start time and initial sleep end time of the object to be analyzed according to the target time and sleep duration information, and determines the initial sleep time period of the object to be analyzed according to the initial sleep start time and initial sleep end time; then, the server determines the time difference between the initial working time period and the target working time period, and determines the target sleep start time and target sleep end time of the object to be analyzed according to the initial sleep start time, initial sleep end time, and time difference, and determines the target sleep time period of the object to be analyzed according to the target sleep start time and target sleep end time.

[0123] Illustratively, the processing of the cosine method can be carried out through the following formula:

[0124] y = A × cos(2π × (x - φ) ∕ T), Equation (1)

[0125] Among them, x refers to the time, y refers to the core body temperature value, A is the amplitude, that is, the difference between the highest core body temperature and the lowest core body temperature of an individual; φ is the acrophase, and φ determines the time when the lowest core body temperature of an individual appears. For example, when φ = 0, the time when the lowest core body temperature of an individual appears is (2kπ - π) / T; T is the period of the core body temperature data, that is, the difference between the time when the lowest core body temperature of an individual appears this time and the time when the lowest core body temperature appeared last time.

[0126] It should be noted that each individual has its own core body temperature curve, and the time when the lowest core body temperature appears can be obtained according to the curve. By collecting the time when the lowest core body temperature appears and the work information of shift workers, the required circadian rhythm phase shift demand can be calculated, so as to provide more accurate circadian rhythm adjustment for them.

[0127] In this embodiment, by obtaining core body temperature data to determine baseline circadian rhythm information, the physiological rhythm characteristics of the object to be analyzed can be accurately reflected, and then the target moment with the minimum core body temperature value can be accurately found. Based on this, the initial sleep time period is determined in combination with sleep duration information. This method fully considers the individual physiological characteristics and is beneficial to improving sleep quality and work efficiency.

[0128] In an exemplary embodiment, after the above step S105, after adjusting the light of the lighting device corresponding to the object to be analyzed according to the predicted light parameters to obtain the lighting device with adjusted light, the following specific contents are included: obtaining the second electroencephalogram signal of the object to be analyzed under the predicted light parameters; preprocessing the second electroencephalogram signal to obtain the preprocessed electroencephalogram signal; performing continuous wavelet transform processing on the preprocessed electroencephalogram signal to obtain the time-frequency diagram corresponding to the second electroencephalogram signal; inputting the time-frequency diagram into the trained sleep staging model to obtain the sleep staging result of the object to be analyzed; the sleep staging result is used to represent the proportion of the duration of the object to be analyzed in different sleep stages; according to the sleep staging result, the sleep quality of the object to be analyzed is determined.

[0129] Among them, the second electroencephalogram signal refers to the electroencephalogram signal of the object to be analyzed under the predicted light parameters.

[0130] Among them, the preprocessed electroencephalogram signal refers to the second electroencephalogram signal after preprocessing.

[0131] Among them, the time-frequency diagram is a visualization tool used to display the variation characteristics of the preprocessed electroencephalogram signal in the two dimensions of time and frequency.

[0132] Among them, the sleep staging model is a network model that can obtain the sleep staging result of the object to be analyzed, such as a convolutional neural network model.

[0133] Among them, the sleep staging result is used to represent the proportion of the duration of the object to be analyzed in different sleep stages.

[0134] Among them, the sleep stages include the wakefulness stage, the falling asleep stage, the light sleep stage, the deep sleep stage, and the dreaming stage.

[0135] Among them, the sleep quality includes excellent, good, qualified, and poor.

[0136] Exemplarily, the server obtains the second electroencephalogram signal of the object to be analyzed under the predicted lighting parameters from the database according to the identification information of the object to be analyzed; then, the server filters the second electroencephalogram signal to obtain the preprocessed electroencephalogram signal; then, the server performs continuous wavelet transform processing on the preprocessed electroencephalogram signal to obtain the time-frequency diagram corresponding to the second electroencephalogram signal; then, the server inputs the time-frequency diagram into the trained sleep staging model to obtain the proportion of the duration of the object to be analyzed in different sleep stages, as the sleep staging result of the object to be analyzed; then, the server determines the proportion of the deep sleep period of the object to be analyzed in the total sleep duration according to the sleep staging result, and determines the sleep quality of the object to be analyzed according to the proportion of the deep sleep period of the object to be analyzed in the total sleep duration; for example, when the proportion of the deep sleep period in the total sleep duration is less than 20%, it is considered that the sleep quality of the shift worker is poor; when the proportion of the deep sleep period in the total sleep duration is greater than 20% and less than 30%, it is considered that the sleep quality of the shift worker is qualified; when the proportion of the deep sleep period in the total sleep duration is greater than 30% and less than 40%, it is considered that the sleep quality of the shift worker is good; when the proportion of the deep sleep period in the total sleep duration is greater than 40% and less than 50%, it is considered that the sleep quality of the shift worker is excellent.

[0137] In this embodiment, through a series of processing and analysis of the electroencephalogram signal, the proportion of the duration of the object to be analyzed in different sleep stages can be accurately obtained, and then its sleep quality can be accurately evaluated. This evaluation method based on objective data avoids the error of subjective judgment and provides a scientific and reliable basis for the evaluation of sleep quality.

[0138] In an exemplary embodiment, as Figure 3 shown, another method for adjusting the light of a lighting device is provided. Taking this method applied to a server as an example, it specifically includes the following steps:

[0139] Step S301, obtain the first electroencephalogram signal of the object to be analyzed in environments with different light intensities.

[0140] Step S302, perform segmentation processing on the first electroencephalogram signal to obtain multiple sub-electroencephalogram signals.

[0141] Step S303, obtain the standard deviation of each sub-electroencephalogram signal, and select the sub-electroencephalogram signal with the largest standard deviation from each sub-electroencephalogram signal as the first target sub-electroencephalogram signal, and select the sub-electroencephalogram signal with the smallest standard deviation from each sub-electroencephalogram signal as the second target sub-electroencephalogram signal.

[0142] Step S304, obtain the average value corresponding to the first target sub-electroencephalogram signal and the second target sub-electroencephalogram signal; determine the target threshold corresponding to the sub-electroencephalogram signal according to the average value.

[0143] Step S305: From each segment of electroencephalogram (EEG) signals, screen out the EEG signals smaller than the target threshold as the electrooculogram (EOG) signals in the first EEG signals; perform filtering processing on the EOG signals to obtain the filtered EEG signals.

[0144] Step S306: Perform conversion processing on the filtered EEG signals to obtain the EEG spectrogram of the object to be analyzed.

[0145] Step S307: Input the EEG spectrogram into the trained light sensitivity prediction model to obtain the prediction probabilities of the object to be analyzed under each preset light sensitivity.

[0146] Step S308: From each preset light sensitivity, screen out the preset light sensitivity with the maximum prediction probability as the predicted light sensitivity.

[0147] Step S309: Obtain the initial sleep time period, target sleep time period, individual characteristic information of the object to be analyzed, and the meteorological information of the location where the object to be analyzed is located, and input the predicted light sensitivity, initial sleep time period, target sleep time period, individual characteristic information, and meteorological information into the trained lighting parameter prediction model to obtain the predicted lighting parameters corresponding to the object to be analyzed.

[0148] Step S310: Adjust the light of the lighting device corresponding to the object to be analyzed according to the predicted lighting parameters to obtain the lighting device with adjusted light.

[0149] In the above lighting device light adjustment method, during the process of adjusting the light of the lighting device, by performing filtering processing and model prediction processing on the EEG signals of the object to be analyzed under different light intensity environments, a more accurate predicted light sensitivity of the object to be analyzed can be obtained, and combined with the initial sleep time period, target sleep time period, individual characteristic information of the object to be analyzed, and the meteorological information of the location where the object to be analyzed is located, a more accurate predicted lighting parameter of the object to be analyzed can be obtained. Furthermore, according to the predicted lighting parameters, the light of the lighting device can be adjusted more accurately, so that the lighting device with adjusted light can provide light with a more matched intensity and color temperature for the object to be analyzed, that is, design a customized lighting plan according to the object to be analyzed and provide personalized rhythm regulation support for the object to be analyzed, which is beneficial to improving the sleep quality of the object.

[0150] In an exemplary embodiment, to more clearly illustrate the light adjustment method of the lighting device provided in the embodiments of the present application, the following uses a specific embodiment to specifically describe the light adjustment method of the lighting device. In one embodiment, the present application also provides a method and system for improving the sleep quality of shift workers. During the process of adjusting the light of the lighting device, first obtain the first electroencephalogram signal of the object to be analyzed in different light intensity environments, then filter the electrooculogram signal in the first electroencephalogram signal to obtain the filtered electroencephalogram signal. Next, input the filtered electroencephalogram signal into the trained light sensitivity prediction model to obtain the predicted light sensitivity of the object to be analyzed. Then, obtain the initial sleep time period, target sleep time period, individual characteristic information of the object to be analyzed, and meteorological information of the location where the object to be analyzed is located, and input the predicted light sensitivity, initial sleep time period, target sleep time period, individual characteristic information, and meteorological information into the trained lighting parameter prediction model to obtain the predicted lighting parameters corresponding to the object to be analyzed. Finally, according to the predicted lighting parameters, adjust the light of the lighting device corresponding to the object to be analyzed to obtain the lighting device after light adjustment. Specifically, it includes the following content:

[0151] Step S1: Collect the work information and core body temperature data of shift workers. The work information includes the start work time, end work time, and sleep duration of shift workers;

[0152] In step S1, the start work time, end work time, and sleep duration information of each shift worker can be collected in the form of a questionnaire, so as to accurately determine the individual's circadian rhythm adjustment needs and perform personalized adjustment. The start work time, end work time, and sleep duration information are respectively recorded as SWT (start work time), EWT (end work time), and TSD (typical sleep duration).

[0153] Step S2: Analyze and process the core body temperature data of shift workers to obtain the baseline circadian rhythm of shift workers;

[0154] The analysis and processing of the core body temperature data of shift workers specifically include:

[0155] S21: Use the special event marking method to filter out the outliers in the core body temperature data of shift workers;

[0156] S22: Then use the cosine method to fit the core body temperature data after filtering out the outliers to obtain the baseline circadian rhythm.

[0157] Among them, the processing of the cosine method is as follows:

[0158] y = A×cos(2π×(x - φ) / T), Equation (1)

[0159] In the above formula, x refers to time, y refers to core body temperature, A is the amplitude, that is, the difference between the individual's highest core body temperature and the lowest core body temperature; φ is the acrophase, and φ determines the moment when the individual's lowest core body temperature appears. For example, when φ = 0, the moment when the individual's lowest core body temperature appears is (2kπ - π) / T; T is the period of the core body temperature data, that is, the difference between the moment when the individual's lowest core body temperature appears this time and the moment when the lowest core body temperature appeared last time. Each individual has its own core body temperature curve, and the time when the lowest core body temperature appears can be obtained according to the curve. By collecting the time when the lowest core body temperature appears and the work information of shift workers, the required circadian rhythm phase shift demand can be calculated, so as to provide a more accurate circadian rhythm adjustment for them. The moment when the lowest core body temperature appears is recorded as CBT (Core Body Temperature Minimum).

[0160] Step S3: Determine the first sleep period of the shift workers during the normal period according to the baseline circadian rhythm. The normal period is the period when the shift workers do not have a shift.

[0161] The first sleep period that conforms to the individual's circadian rhythm phase during the period when the shift workers do not have a shift is specifically expressed as [CBT - (TSD - 2h), CBT + 2h].

[0162] Step S4: Determine the second sleep period of the shift workers during the shift period according to the work information of the shift workers.

[0163] Record the shift workers' starting work time as SWT and the ending work time as EWT. According to the shift workers' starting work time and ending work time, the second sleep period that conforms to the individual's circadian rhythm phase during the shift period for the shift workers is CBT + 2h < SWT (starting work time); CBT - (TSD - 2h) > EWT (ending work time).

[0164] Step S5: Use a lighting device to irradiate the shift workers and adjust the first sleep period of the shift workers to the second sleep period.

[0165] In this step, by using a lighting device to adjust the light around the environment of the shift workers, the first sleep period of the shift workers can be adjusted to the second sleep period to help them better adapt to the shift work time and improve their sleep quality and work efficiency. Among them, the adjustment of the light specifically includes the color temperature, intensity, and duration of the light irradiation. However, considering that each individual has different sensitivities to light, further in this embodiment, it is also necessary to measure the light sensitivity of each individual to achieve the purpose of personalized adjustment.

[0166] In the prior art, pupil response tests are usually used to explore the light sensitivity of an individual. However, this method requires continuous stimulation of the individual's pupils with different light intensities, which brings great discomfort to the human body. In this embodiment, the electroencephalogram (EEG) signals of the human body under different light intensities are collected, and the light sensitivity of the human body is further determined according to the fluctuations of the EEG signals. Specifically:

[0167] S51. Collect the EEG signals of shift workers in environments with different light intensities;

[0168] In this step, an EEG acquisition device is used to collect the EEG signals of shift workers in environments with different light intensities.

[0169] S52. Remove the electrooculogram (EOG) signals from the EEG signals to obtain the first EEG signal;

[0170] Although using EEG signals to determine the light sensitivity of shift workers does not directly stimulate the pupils of an individual, there are still some slight interferences to the eyes, which will cause the occurrence of behaviors such as eye movement or blinking, generating EOG signals. The EOG signals interfere with the EEG signals and will lead to inaccurate prediction results. Therefore, in this step, it is necessary to remove the EOG signals to improve the accuracy of classifying the light sensitivity of an individual, including the following steps:

[0171] (1) Segment the first EEG signal to obtain multiple segments of EEG signals;

[0172] (2) Calculate the standard deviation of each segment of EEG signal to obtain the standard deviation value of each segment of EEG signal;

[0173] (3) Select the EEG signal with the maximum standard deviation value and the EEG signal with the minimum standard deviation value among them, and denote them as the first EEG signal segment and the second EEG signal segment;

[0174] (4) Calculate the mean values of the first EEG signal segment and the second EEG signal segment to obtain threshold information;

[0175] In this step, 1.25 times the mean values of the first EEG signal segment and the second EEG signal segment is used as the threshold information.

[0176] (5) Use the threshold information to filter out the EOG signals in the first EEG signal.

[0177] S53. Convert the first EEG signal into an EEG spectrogram;

[0178] In this step, the first EEG signal is processed by short-time Fourier transform to convert it into an EEG spectrogram.

[0179] S54. Send the electroencephalogram spectrogram to the trained neural network to obtain the classification result;

[0180] In this step, the neural network is trained using the classification labels and the sample set. The classification labels include insensitive, slightly sensitive, sensitive, more sensitive, and very sensitive. The sample set includes at least one electroencephalogram spectrogram. By sending the classification labels and the sample set to the neural network for training until convergence, the trained neural network is obtained. The neural network in this embodiment selects a convolutional neural network.

[0181] S55. Determine the light sensitivity of the human body according to the classification result.

[0182] In this step, the classification result includes insensitive, slightly sensitive, sensitive, more sensitive, and very sensitive. According to the classification result, the light sensitivity of the shift workers is divided into five levels, so as to divide the shift workers into five groups with different light sensitivities.

[0183] S56. Obtain meteorological data and individual characteristic information. The meteorological data includes weather type, temperature, and humidity. The individual characteristic information includes the gender and time type of the shift workers;

[0184] In this step, the individual characteristic information of each shift worker is collected through a preset questionnaire to further enrich the personalized characteristics of each shift worker. The meteorological data can be obtained through meteorological satellites. The acquisition method of the meteorological data in this embodiment is not limited.

[0185] S57. Obtain the preset lighting parameters for each shift worker according to the meteorological data and the individual characteristic information;

[0186] In this step, the light in the rest room can be adjusted according to the parameters required by each shift worker to meet the unique needs of each shift worker.

[0187] S58. Adjust the light of the lighting device according to the preset lighting parameters.

[0188] To further achieve personalized adjustment, this embodiment not only considers the light sensitivity of the shift workers, but also increases the personalized characteristics of the shift workers by collecting the gender and time type of the shift workers. It should be noted that different genders have different sensitivities to different colored lights. Specifically, male individuals have better sustained attention performance under light. The response of the primary visual cortex to the step intensity of red and blue lights shows that the stimulus-response curve of males is twice that of females. Therefore, compared with females, the set light intensity for males is smaller and the light time is shorter; compared with early time types, it is easier for late time type individuals to have a maximum scale rhythm phase delay. Therefore, the set light intensity for late time type individuals is smaller and the light time is shorter.

[0189] In this embodiment, different lighting parameters are preset based on different shift workers to adjust the sleep time period of the shift workers. At the same time, the physiological parameters of the shift workers under the current lighting conditions are recorded to evaluate their sleep quality, and further optimize and adjust the lighting parameters. Among them, the evaluation of sleep quality is specifically as follows:

[0190] Step S6: Collect the electroencephalogram (EEG) signals of the shift workers under the preset lighting parameters;

[0191] Under the preset lighting parameters, monitor the physiological data of the shift workers, and evaluate the sleep quality of the shift workers through the physiological data. The physiological data selected in this embodiment is the EEG signal, and the rhythm wave of the EEG signal can characterize the sleep state of the shift workers.

[0192] Step S7: Preprocess the EEG signals to obtain the preprocessed EEG signals;

[0193] Since the frequency of the sleep EEG signal is usually within 30 HZ, the EEG signal is filtered by using a filter with a cut-off frequency of 35 HZ to filter out the noise greater than 35 HZ, and the preprocessed EEG signal is obtained.

[0194] Step S8: Analyze the preprocessed EEG signals by using continuous wavelet transform to obtain the time-frequency diagram corresponding to the EEG signals;

[0195] Continuous wavelet transform has good ability to represent the local characteristics of signals in both time and frequency domains. Therefore, in this embodiment, continuous wavelet transform is used to analyze and process the EEG signals. Further, the wavelet basis functions of wavelet transform include Haar wavelet, Morlet wavelet, Coiflets wavelet, etc. Since the time-frequency diagram obtained by using Morlet wavelet transform can better represent different sleep stages, in this embodiment, Morlet wavelet is selected for analysis.

[0196] Step S9: Send the time-frequency diagram corresponding to the EEG signals to the sleep staging model to obtain the classification result.

[0197] Sleep stages are usually divided into 5 stages: wakefulness, drowsiness, light sleep, deep sleep, and dreaming. By analyzing and processing the EEG signals in different periods by using continuous wavelet transform, the corresponding time-frequency diagrams of each period can be obtained. A large number of time-frequency diagrams of different sleep stages are collected to form a data set, and the data set is divided into a training set, a validation set, and a test set. A CNN (Convolutional Neural Network) model is established, and the convolutional neural network model is trained by using the training set, and adjusted and evaluated by using the test set and the validation set to obtain the sleep staging model, and the classification result of the sleep stage is used as the output of the model.

[0198] Step S10: Determine the sleep quality of the shift workers according to the staging result.

[0199] Since the output of the model is the classification result of the sleep stages, according to the classification result, the duration of the shift workers in different sleep stages during sleep can be determined. Generally speaking, the light sleep period accounts for 40%-55% of the total sleep duration, and the deep sleep period accounts for 20%-50% of the total sleep duration. According to the proportion of the deep sleep period in the total sleep duration, the sleep quality of the shift workers can be evaluated. When the proportion of the deep sleep period in the total sleep duration is less than 20%, it is considered that the sleep quality of the shift workers is poor; when the proportion of the deep sleep period in the total sleep duration is greater than 20% and less than 30%, it is considered that the sleep quality of the shift workers is qualified; when the proportion of the deep sleep period in the total sleep duration is greater than 30% and less than 40%, it is considered that the sleep quality of the shift workers is good; when the proportion of the deep sleep period in the total sleep duration is greater than 40% and less than 50%, it is considered that the sleep quality of the shift workers is excellent.

[0200] When the sleep quality is poor, at this time, it is necessary to further optimize the light parameters to improve the sleep quality of the shift workers and further achieve the purpose of personalized adjustment.

[0201] In the above embodiment, during the process of adjusting the light of the lighting device, by performing filtering processing and model prediction processing on the electroencephalogram signals of the object to be analyzed in different light intensity environments, a more accurate predicted light sensitivity of the object to be analyzed can be obtained, and combined with the initial sleep time period, target sleep time period, individual characteristic information of the object to be analyzed, and the meteorological information of the location where the object to be analyzed is located, a more accurate predicted light parameter of the object to be analyzed can be obtained. Furthermore, according to the predicted light parameter, the light of the lighting device can be adjusted more accurately, so that the lighting device after the light adjustment can provide light with a more matched intensity and color temperature for the object to be analyzed, that is, design a customized lighting scheme according to the object to be analyzed and provide personalized rhythm adjustment support for the object to be analyzed, which is beneficial to improving the sleep quality of the object.

[0202] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are sequentially shown according to the indication of the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear description in this article, there is no strict order limit for the execution of these steps, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same moment, but can be executed at different moments. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or steps or stages in other steps.

[0203] Based on the same inventive concept, an embodiment of the present application further provides a light adjustment device for a lighting device for implementing the light adjustment method of the lighting device involved above. The solution provided by this device to solve the problem is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the light adjustment device for a lighting device provided below can refer to the limitations on the light adjustment method of the lighting device in the above text, and will not be repeated here.

[0204] In an exemplary embodiment, as Figure 4 shown, a light adjustment device for a lighting device is provided, including: a signal acquisition module 401, a signal processing module 402, a model prediction module 403, a parameter prediction module 404, and a light adjustment module 405, where:

[0205] The signal acquisition module 401 is configured to acquire a first electroencephalogram signal of an object to be analyzed in an environment with different light intensities.

[0206] The signal processing module 402 is configured to perform filtering processing on the electrooculogram signal in the first electroencephalogram signal to obtain a filtered electroencephalogram signal.

[0207] The model prediction module 403 is configured to input the filtered electroencephalogram signal into a trained light sensitivity prediction model to obtain the predicted light sensitivity of the object to be analyzed.

[0208] The parameter prediction module 404 is configured to acquire the initial sleep time period, target sleep time period, individual characteristic information of the object to be analyzed, and meteorological information of the location where the object to be analyzed is located, and input the predicted light sensitivity, initial sleep time period, target sleep time period, individual characteristic information, and meteorological information into a trained lighting parameter prediction model to obtain the predicted lighting parameters corresponding to the object to be analyzed.

[0209] The light adjustment module 405 is configured to adjust the light of the lighting device corresponding to the object to be analyzed according to the predicted lighting parameters to obtain a lighting device with adjusted light.

[0210] In an exemplary embodiment, the signal processing module 402 is further configured to segment the first electroencephalogram signal to obtain multiple sub - electroencephalogram signals; acquire the standard deviation value of each sub - electroencephalogram signal, and screen out the sub - electroencephalogram signal with the largest standard deviation value from each sub - electroencephalogram signal as the first target sub - electroencephalogram signal, and screen out the sub - electroencephalogram signal with the smallest standard deviation value from each sub - electroencephalogram signal as the second target sub - electroencephalogram signal; filter the electro - oculogram signal in the first electroencephalogram signal according to the first target sub - electroencephalogram signal and the second target sub - electroencephalogram signal to obtain the filtered electroencephalogram signal.

[0211] In an exemplary embodiment, the signal processing module 402 is further configured to acquire the average value corresponding to the first target sub - electroencephalogram signal and the second target sub - electroencephalogram signal; determine the target threshold value corresponding to the sub - electroencephalogram signal according to the average value; screen out the sub - electroencephalogram signal smaller than the target threshold value from each sub - electroencephalogram signal as the electro - oculogram signal in the first electroencephalogram signal; filter the electro - oculogram signal to obtain the filtered electroencephalogram signal.

[0212] In an exemplary embodiment, the model prediction module 403 is further configured to perform a conversion process on the filtered electroencephalogram signal to obtain an electroencephalogram spectrogram of the object to be analyzed; input the electroencephalogram spectrogram into the trained light sensitivity prediction model to obtain the prediction probabilities of the object to be analyzed at each preset light sensitivity; screen out the preset light sensitivity with the largest prediction probability from each preset light sensitivity as the predicted light sensitivity.

[0213] In an exemplary embodiment, the parameter prediction module 404 is further configured to acquire the initial working time period, the target working time period, the sleep duration information, and the core body temperature data of the object to be analyzed; determine the baseline circadian rhythm information of the object to be analyzed according to the core body temperature data; the baseline circadian rhythm information is used to represent the corresponding relationship between the core body temperature value of the object to be analyzed and the time; determine the time with the smallest core body temperature value as the target time of the object to be analyzed according to the baseline circadian rhythm information; determine the initial sleep time period according to the target time and the sleep duration information, and determine the target sleep time period according to the initial sleep time period, the initial working time period, and the target working time period.

[0214] In an exemplary embodiment, the light adjustment device of the lighting device further includes a quality determination module, configured to obtain a second electroencephalogram signal of an object to be analyzed under predicted light parameters; preprocess the second electroencephalogram signal to obtain a preprocessed electroencephalogram signal; perform continuous wavelet transform processing on the preprocessed electroencephalogram signal to obtain a time-frequency diagram corresponding to the second electroencephalogram signal; input the time-frequency diagram into a trained sleep staging model to obtain a sleep staging result of the object to be analyzed; the sleep staging result is used to represent the duration ratio of the object to be analyzed in different sleep stages; and determine the sleep quality of the object to be analyzed according to the sleep staging result.

[0215] Each module in the above-mentioned light adjustment device of the lighting device can be implemented in whole or in part by software, hardware, and their combination. The above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or stored in a memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above-mentioned modules.

[0216] In an exemplary embodiment, a computer device is provided. The computer device can be a server, and its internal structure diagram can be as Figure 5 shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device 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 the computer program in the non-volatile storage medium. The database of the computer device is used to store data such as predicted light sensitivity and predicted light parameters. The input / output interface of the computer device is used for the processor to exchange information with external devices. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it implements a method for adjusting the light of a lighting device.

[0217] Those skilled in the art can understand that Figure 5 the structure shown in

[0218] In an exemplary embodiment, a computer device is further provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the steps in the above method embodiments are implemented.

[0219] In an exemplary embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0220] In an exemplary embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0221] Those of ordinary skill in the art can understand that all or part of the processes of implementing the above method embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the above method embodiments. Among them, any reference to a memory, a database, or other media used in the embodiments provided in the present application can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in the present application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in the present application can be general-purpose processors, central processors, graphics processors, digital signal processors, programmable logic devices, data processing logics based on quantum computing, etc., without limitation.

[0222] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this specification.

[0223] The above embodiments only express several implementation manners of the present application, and their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of the patent of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.

Claims

1. A method for adjusting light of an illumination device, characterized in that: The method comprises: Acquire the first EEG signal of the object to be analyzed under different light intensity environments; Filtering the electrooculogram signal in the first electroencephalogram signal to obtain a filtered electroencephalogram signal; Inputting the filtered EEG signal into the trained light sensitivity prediction model to obtain the predicted light sensitivity of the object to be analyzed; Acquire the initial sleep time period, target sleep time period, individual characteristic information of the object to be analyzed, and meteorological information of the location where the object to be analyzed is located, and input the predicted light sensitivity, the initial sleep time period, the target sleep time period, the individual characteristic information and the meteorological information into the trained illumination parameter prediction model to obtain the predicted illumination parameters corresponding to the object to be analyzed; According to the predicted illumination parameters, light adjustment is performed on the illumination device corresponding to the object to be analyzed to obtain the illumination device after light adjustment.

2. The method according to claim 1, characterized in that The filtering of the electrooculogram signal in the first electroencephalogram signal to obtain the electroencephalogram signal after filtering includes: Processing the first electroencephalogram signal in segments to obtain multiple sub-electroencephalogram signals; Obtaining the standard deviation value of each sub-EEG signal, and screening out the sub-EEG signal with the largest standard deviation value from each sub-EEG signal as the first target sub-EEG signal, and screening out the sub-EEG signal with the smallest standard deviation value from each sub-EEG signal as the second target sub-EEG signal; According to the first target sub-EEG signal and the second target sub-EEG signal, the electrooculogram signal in the first EEG signal is filtered out to obtain the filtered EEG signal.

3. The method according to claim 2, characterized in that The filtering of the electrooculogram signal in the first EEG signal according to the first target EEG signal and the second target EEG signal to obtain the filtered EEG signal includes: Obtaining an average value corresponding to the first target sub-EEG signal and the second target sub-EEG signal; Determining a target threshold corresponding to the sub-EEG signal according to the average value; From each segment of the EEG sub-signal, filter out the EEG sub-signal that is smaller than the target threshold as the eye contact signal in the first EEG signal; The electrooculogram signal is filtered to obtain the filtered electroencephalogram signal.

4. The method according to claim 1, characterized in that: The step of inputting the filtered EEG signal into a trained light sensitivity prediction model to obtain the predicted light sensitivity of the object to be analyzed comprises: Performing conversion processing on the filtered EEG signal to obtain an EEG spectrum of the object to be analyzed; Inputting the EEG spectrum into the trained light sensitivity prediction model to obtain the predicted probability of the object to be analyzed under each preset light sensitivity; From the preset light sensitivities, the preset light sensitivity with the maximum prediction probability is selected as the predicted light sensitivity.

5. The method according to claim 1, characterized in that The obtaining of the initial sleep time period, the target sleep time period, and the individual characteristic information of the subject to be analyzed includes: Acquiring the initial working time period, target working time period, sleep duration information and core body temperature data of the subject to be analyzed; Determining baseline circadian rhythm information of the subject to be analyzed based on the core body temperature data; the baseline circadian rhythm information is used to indicate a corresponding relationship between the core body temperature value of the subject to be analyzed and the time; Determining, according to the baseline circadian rhythm information, the time when the core body temperature value is minimum as the target time of the object to be analyzed; The initial sleep time period is determined according to the target time and the sleep duration information, and the target sleep time period is determined according to the initial sleep time period, the initial working time period and the target working time period.

6. The method according to any one of claims 1 to 5, characterized in that: After adjusting the light of the illumination device corresponding to the object to be analyzed according to the predicted illumination parameters to obtain the illumination device after light adjustment, the method further includes: Acquire a second EEG signal of the object to be analyzed under the predicted illumination parameters; Preprocessing the second EEG signal to obtain a preprocessed EEG signal; Performing continuous wavelet transform processing on the preprocessed EEG signal to obtain a time-frequency diagram corresponding to the second EEG signal; Inputting the time-frequency graph into the trained sleep staging model to obtain the sleep staging result of the subject to be analyzed; the sleep staging result is used to indicate the proportion of the duration of the subject to be analyzed in different sleep stages; The sleep quality of the subject to be analyzed is determined according to the sleep staging result.

7. A light adjustment device for an illumination device, characterized in that: The device comprises: A signal acquisition module, used to acquire a first EEG signal of an object to be analyzed under different light intensity environments; A signal processing module, used for filtering the electrooculogram signal in the first electroencephalogram signal to obtain a filtered electroencephalogram signal; A model prediction module, used for inputting the filtered EEG signal into the trained light sensitivity prediction model to obtain the predicted light sensitivity of the object to be analyzed; a parameter prediction module, used to obtain the initial sleep time period, target sleep time period, individual characteristic information of the object to be analyzed, and the meteorological information of the location where the object to be analyzed is located, and input the predicted light sensitivity, the initial sleep time period, the target sleep time period, the individual characteristic information and the meteorological information into the trained illumination parameter prediction model to obtain the predicted illumination parameters corresponding to the object to be analyzed; The light adjustment module is used to adjust the light of the lighting device corresponding to the object to be analyzed according to the predicted lighting parameters to obtain the lighting device after light adjustment.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. 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 method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images