Intelligent bed sleep data tracing method and system

Abstract

The embodiment of the invention provides an intelligent bed sleep data tracing method and system. The method comprises the steps that sleep information is collected; extracting signal features of the original vibration signals, and calculating a first similarity parameter between the signal features and physiological parameters corresponding to the signal features; comparing the physiological parameters among the multiple original vibration signals to generate a second similarity parameter, linearly fusing the first similarity parameter and the second similarity parameter to generate a target evaluation parameter, and judging whether the multiple original vibration signals are homologous or not; when it is judged that the multiple original vibration signals are homologous, signal quality parameters of the original vibration signals are obtained, and a target physiological parameter sequence is generated based on the signal quality parameters; acquiring historical sleep data of the multiple sleep users, comparing the historical sleep data with the target physiological parameter sequence, determining a target user based on a comparison result, and associating the target physiological parameter sequence to the target user.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent beds, and in particular to an intelligent bed sleep data tracing method and system. BACKGROUND

[0002] Existing intelligent beds mostly use non-contact sensors (such as piezoelectric film, optical fiber sensor, etc.) to collect human vibration signals, and realize individual sleep monitoring through unilateral sensors. In a multi-person scenario, such as a double bed scenario, when only one side has a user, the sensors on both sides may trigger data generation at the same time due to the user's turning over, body movement and other actions, causing the system to misjudge as double use, and generate two reports and push them to the bound account, resulting in a decline in user experience.

[0003] However, in the prior art, there is a lack of judgment ability for the above-mentioned scenario, and the data confusion problem when a single user occupies a double bed cannot be effectively solved, and two reports are generated and distributed to different users, resulting in a series of problems such as a decline in user experience. SUMMARY

[0004] In view of the problems in the prior art, the embodiments of the present application provide an intelligent bed sleep data tracing method and system.

[0005] The embodiments of the present application provide an intelligent bed sleep data tracing method, which comprises:

[0006] Collecting sleep information, the sleep information comprising a plurality of original vibration signals of a plurality of sleep users collected by sensors;

[0007] Extracting signal features of the original vibration signals, calculating a first similarity parameter between the signal features, and a physiological parameter corresponding to the signal features;

[0008] Comparing the physiological parameters between the plurality of original vibration signals to generate a second similarity parameter, linearly fusing the first similarity parameter and the second similarity parameter to generate a target evaluation parameter, and determining whether the plurality of original vibration signals are homologous based on the target evaluation parameter;

[0009] When it is determined that the plurality of original vibration signals are homologous, obtaining a signal quality parameter of the original vibration signals, merging the physiological parameters based on the signal quality parameter to generate a target physiological parameter sequence;

[0010] Obtaining historical sleep data of the plurality of sleep users, comparing the target physiological parameter sequence, determining a target user based on the comparison result, and associating the target physiological parameter sequence to the target user.

[0011] In one of the embodiments, the method further comprises:

[0012] Calculate the time domain similarity, the frequency domain similarity and the time-frequency domain similarity between multiple original vibration signals in the same time window, and average the time domain similarity, the frequency domain similarity and the time-frequency domain similarity to obtain a first similarity parameter.

[0013] Compare the similarity parameters corresponding to different physiological parameters between multiple original vibration signals, and average the similarity parameters of multiple physiological parameters to obtain a second similarity parameter.

[0014] Linearly fuse the first similarity parameter and the second similarity parameter to generate a target evaluation parameter.

[0015] In one of the embodiments, the method further comprises:

[0016] Calculate an instantaneous average similarity parameter of the first similarity parameter, and linearly fuse the second similarity parameter, the calculation formula comprising:

[0017]

[0018] wherein, is the target evaluation parameter, S1avg is the instantaneous average similarity parameter, the corresponding weight is a, S2 is the second similarity parameter, and the corresponding weight is b.

[0019] In one of the embodiments, the corresponding weight of the instantaneous average similarity parameter is 0.6, and the corresponding weight of the second similarity parameter is 0.4.

[0020] In one of the embodiments, the method further comprises:

[0021] Compare the signal quality parameter with the quality threshold, select one or more merging strategies to merge the physiological parameters based on the comparison result, and merge the time window corresponding to the original vibration signal to generate a target physiological parameter sequence, the merging strategy comprising:

[0022] Select the physiological parameter with better signal quality parameter, average the physiological parameters, and weight the physiological parameters according to the signal quality parameter.

[0023] In one of the embodiments, the method further comprises:

[0024] Obtain a historical modal matrix constructed by multiple sleep users based on historical sleep data, compare the modal matrix converted by the target physiological parameter sequence with the historical modal matrix, calculate the modal closeness in the comparison result, and select the user corresponding to the historical modal matrix with the closest modal closeness as the target user.

[0025] The embodiment of the present application provides a kind of intelligent bed sleep data traceability system, the system comprises:

[0026] The acquisition module is configured to acquire sleep information, wherein the sleep information comprises a plurality of original vibration signals of a plurality of sleep users collected by a sensor;

[0027] The first parameter module is configured to extract signal features of the original vibration signals, calculate first similarity parameters between the signal features, and calculate physiological parameters corresponding to the signal features.

[0028] The second parameter module is configured to compare the physiological parameters between the plurality of original vibration signals to generate second similarity parameters, linearly fuse the first similarity parameters and the second similarity parameters to generate target evaluation parameters, and determine whether the plurality of original vibration signals are homologous based on the target evaluation parameters.

[0029] The merging module is configured to, when it is determined that the plurality of original vibration signals are homologous, acquire signal quality parameters of the original vibration signals, merge the physiological parameters based on the signal quality parameters to generate a target physiological parameter sequence.

[0030] The user module is configured to acquire historical sleep data of the plurality of sleep users, compare the target physiological parameter sequence with the historical sleep data, determine a target user based on a comparison result, and associate the target physiological parameter sequence to the target user.

[0031] In one of the embodiments, the system further comprises:

[0032] The first calculation module is configured to calculate time domain similarity, frequency domain similarity, and time-frequency domain similarity between the plurality of original vibration signals in the same time window, and perform average calculation on the time domain similarity, the frequency domain similarity, and the time-frequency domain similarity to obtain the first similarity parameters.

[0033] The second calculation module is configured to compare similarity parameters corresponding to different physiological parameters between the plurality of original vibration signals, and perform average calculation on the similarity parameters of the plurality of physiological parameters to obtain the second similarity parameters.

[0034] The linear fusion module is configured to linearly fuse the first similarity parameters and the second similarity parameters to generate target evaluation parameters.

[0035] An electronic device is provided in an embodiment of the application, comprising a processor and a memory.

[0036] The processor is connected to the memory.

[0037] The memory is configured to store executable program codes.

[0038] The processor runs a program corresponding to the executable program codes by reading the executable program codes stored in the memory, so as to execute the method described in one or more embodiments.

[0039] An embodiment of the present application provides a non-transitory computer-readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement steps of the intelligent bed sleep data tracing method.

[0040] In view of the above, in one or more embodiments of the present specification, sleep information is collected, the sleep information including a plurality of original vibration signals of a plurality of sleep users collected by a sensor; signal features of the original vibration signals are extracted, a first similarity parameter between the signal features is calculated, and physiological parameters corresponding to the signal features are calculated; physiological parameters between the plurality of original vibration signals are compared, a second similarity parameter is generated, the first similarity parameter and the second similarity parameter are linearly fused to generate a target evaluation parameter, and whether the plurality of original vibration signals are homologous is determined based on the target evaluation parameter; when it is determined that the plurality of original vibration signals are homologous, a signal quality parameter of the original vibration signal is obtained, the physiological parameters are merged based on the signal quality parameter to generate a target physiological parameter sequence; historical sleep data of the plurality of sleep users is obtained, compared with the target physiological parameter sequence, a target user is determined based on a comparison result, and the target physiological parameter sequence is associated to the target user. In this way, homologous determination can be performed by comprehensively considering the similarity of signal layer and physiological layer, the reliability of homologous determination decision is improved, the data quality is improved by fusion, the data attribution is ensured to be accurate by historical comparison, the data confusion problem is finally solved, and the user experience is improved. BRIEF DESCRIPTION OF DRAWINGS

[0041] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor.

[0042] Figure 1 is a flowchart of an intelligent bed sleep data tracing method provided by one embodiment of the present specification.

[0043] Figure 2 is a flowchart of determining whether a plurality of original vibration signals are homologous provided by one embodiment of the present specification.

[0044] Figure 3 is a flowchart of physiological parameter merging / selection provided by one embodiment of the present specification.

[0045] Figure 4 is a structural schematic diagram of an intelligent bed sleep data tracing system provided by one embodiment of the present specification.

[0046] Figure 5Fig. 1 is a structural schematic diagram of an electronic device according to an embodiment of the present specification. DETAILED DESCRIPTION

[0047] The subject matter described herein will now be discussed with reference to example implementations. It should be understood that these implementations are discussed in order to enable those with skill in the art to better understand and implement the subject matter described herein, and are not to be considered limitations on the scope of protection, applicability, or examples set forth in the claims. Changes in the function and arrangement of elements discussed can be made without departing from the scope of the subject matter of the present specification. Various examples can omit, substitute, or add various procedures or components as appropriate. For instance, the methods described can be performed in an order different than that described, and in various examples, various steps can be added, omitted, or combined. Also, features described with respect to some examples can be combined in other examples.

[0048] As used herein, the term “includes” and its variants are meant to be interpreted broadly. The term “based on” means “based, at least in part, on.” The terms “one embodiment,” “an embodiment,” “some embodiments,” and “other embodiments” mean “at least one embodiment.” The terms “a first,” “a second,” “the first,” “the second,” “the third,” “the fourth,” etc. mean “at least one,” and are not necessarily used in a reflective context. The terms “plurality” and “a plurality” mean “two or more.” The term “another” means “at least one,” and the term “another” used in a context implies at least one, and the context requires a single instance with at least one including the instance. The term “another” used in a context implies at least one, and the context requires a plurality of instances with at least one including the instance. The context will make clear to those of skill in the art the intended meaning of the term “another.” The term “comprising” means “including, but not limited to.” The term “based on” means “based, at least in part, on.” The term “one embodiment” and “an embodiment” means “at least one embodiment.” The term “another embodiment” means “at least one other embodiment.” The terms “first,” “second,” etc. can refer to different or the same objects. Other definitions can be found in the following sections. The definitions are not meant to be limiting unless otherwise explicitly stated.

[0049] As Figure 1 As shown in the figure, the embodiment of the present application provides a smart bed sleep data traceability method, comprising:

[0050] Step S102, collecting sleep information, the sleep information comprising a plurality of original vibration signals of a plurality of sleep users collected by sensors.

[0051] Specifically, when there are multiple sleep users on the smart bed, the smart bed can collect sleep information through non-contact sensors deployed at multiple places of the smart bed. Taking a double-bed smart bed as an example, non-contact sensors are usually deployed under the left and right mattresses of the smart bed. The sensors continuously collect the weak mechanical vibrations of the human body (produced by heartbeat, breathing, body movement, etc.) of multiple users, convert them into analog electrical signals, and then into corresponding original vibration signals.

[0052] Step S104, extracting signal features of the original vibration signals, calculating a first similarity parameter between the signal features, and a physiological parameter corresponding to the signal features.

[0053] Specifically, after obtaining the original vibration signal, in order to ensure the quality of the data, the original vibration signal needs to be preprocessed, such as noise reduction and enhancement. The preprocessing steps can include but are not limited to: removing low-frequency baseline drift caused by mattress deformation and environmental slow vibration through high-pass filtering; removing high-frequency electronic noise and environmental sudden peak interference through low-pass filtering; retaining the most useful frequency band for human physiological signals through band-pass filtering; and signal gain amplification, etc.

[0054] Further, for the preprocessed vibration signal, a plurality of signal features are extracted and calculated, including but not limited to: signal peak value, frequency, root mean square, etc. Then, the first similarity parameter (S1) between the signal features from the sensors at different positions of the smart bed is compared. In this example, taking the original vibration signals collected by the left and right non-contact sensors of the smart bed as an example, the calculation process of S1 between the left and right signals in the same time window can further include:

[0055] Calculate the time domain similarity c1: that is, calculate the Pearson correlation coefficient of the left and right signals. c1 reflects the synchronicity of the waveform shape;

[0056] Calculate the frequency domain similarity c2: that is, calculate the power spectral density of the left and right signals, and then calculate the correlation coefficient of the two PSD curves. c2 reflects the consistency of the frequency distribution;

[0057] Calculate the time-frequency domain similarity c3: that is, perform short-time Fourier transform on the left and right signals to obtain a time-frequency spectrum, and then calculate the correlation coefficient of the two time-frequency matrices. c3 reflects the synchronicity of the signal change with time and frequency.

[0058] Then, the average of c1, c2, and c3 is calculated to determine the first similarity parameter in the current time window. Among them, the Pearson correlation coefficient can effectively capture the synchronicity and consistency of the fluctuation of the waveforms on both sides; the power spectral density correlation coefficient analyzes the similarity from the frequency perspective, and the heartbeat, breathing, and snoring of the human body have their own main frequency characteristics; the time-frequency matrix generated by the short-time Fourier transform can not only see the frequency distribution, but also see the change of these frequency components over time. For the first similarity parameter, the feature similarity can be accurately analyzed in real time.

[0059] Further, the physiological parameters corresponding to the signal features are calculated, including but not limited to:

[0060] Heart rate: first separate the heartbeat component from the vibration signal through filtering or blind source separation (BSS) technology, and then perform peak detection or autocorrelation analysis to calculate the heart rate.

[0061] Respiratory rate: the peak value of the 0.1-0.5Hz frequency band signal can be detected to calculate the number of breaths per minute. Or use FFT spectrum analysis to find the main frequency in this frequency band and convert it to respiratory rate.

[0062] Body motion index: the energy integration of the signal in 1-20Hz band, or the root mean square (RMS) of the whole signal window, can be calculated. The larger the value, the more intense the body motion.

[0063] In / out of bed status determination: the variance or energy of the signal window is calculated. If it is lower than a certain preset in-bed threshold for a period of time, it is determined as “out of bed”; otherwise, it is “in bed”.

[0064] Turn-over / snoring event: when the signal amplitude or the energy of a certain frequency band exceeds the corresponding turn-over / snoring threshold, it is determined that a turn-over or snoring event has occurred, and the number and intensity thereof are recorded.

[0065] Thus, the continuous original vibration signal is converted into discrete, quantized, and clear physiological parameter, greatly compressing the data volume.

[0066] In step S106, the physiological parameters between the multiple original vibration signals are compared to generate a second similarity parameter, the first similarity parameter and the second similarity parameter are linearly fused to generate a target evaluation parameter, and whether the multiple original vibration signals are homologous is determined based on the target evaluation parameter.

[0067] Specifically, after S1 is calculated by comparing the specific morphology of the original vibration signal, the physiological state represented thereby is compared, and a second similarity parameter (S2) is calculated. That is, the correlation between the physiological parameters is determined by comparing the physiological parameters between the multiple original vibration signals, such as the physiological parameters (heart rate, respiration rate, body motion index, etc.) corresponding to the left and right vibration signals. Similarly, the corresponding similarity is calculated, and the calculation process can be, for example: calculating the heart rate sequence similarity w1: the Pearson correlation coefficient of the two-sided heart rate sequence; calculating the respiration rate sequence similarity w2: the Pearson correlation coefficient of the two-sided respiration rate sequence; calculating the body motion index sequence similarity w3: the Pearson correlation coefficient of the two-sided body motion index sequence. After the correlation w1, w2, w3 of the physiological parameters is determined, the average value thereof is calculated to obtain the second similarity parameter. Compared with the first similarity parameter focusing on real-time feature analysis, the second similarity parameter focuses more on global index evaluation. In the actual sleep process, the first similarity parameter may be deceived (misjudged as homologous) by a certain accidental and large-scale coordinated action, but the second similarity parameter denies this possibility from the whole night physiological rhythm, and vice versa.

[0068] Further, as Figure 2As shown, before linear fusion of S1 and S2, the instantaneous S1 sequence can be globalized, such as calculating the average value of N time windows S1 of a single night to obtain the instantaneous average similarity parameter S1avg. That is, a stable index similar to the signal morphology similarity of the whole night is generated, so as to avoid the excessive influence of noise or abnormal fluctuations of a single time window on the overall judgment.

[0069] Then linear fusion is performed on S1avg and S2, and the fusion strategy can include:

[0070]

[0071] Wherein, the weights a, b can be set by the user as required. The weights can also be set to 0.6 and 0.4 respectively, and the weight of the first similarity parameter is slightly greater than that of the second similarity parameter. Because S1 is the similarity of signal morphology, it is more direct and lower level evidence. S2 is higher level and time-delayed supplementary evidence, and the weight is slightly lower but crucial.

[0072] The target evaluation parameter is calculated as Then, the target evaluation parameter is compared with a preset decision threshold, and the decision threshold can be set by the user as required. When the user prefers to reduce false positives, a high threshold can be set, such as 0.8 or 0.9, and vice versa. In the comparison result, if the target evaluation parameter is higher than the threshold, it is determined that the signals on both sides in the time window are homologous; otherwise, they are not homologous (i.e. signals generated by two independent activities of a person).

[0073] In step S108, when it is determined that the multiple original vibration signals are homologous, a signal quality parameter of the original vibration signal is obtained, the physiological parameter is merged based on the signal quality parameter, and a target physiological parameter sequence is generated.

[0074] Specifically, when it is determined that the multiple original vibration signals are homologous, it indicates that the source of the collected original vibration signals is the same user. Then the multiple preprocessed original vibration signals can be merged to improve the data accuracy and reliability. That is, the signal quality parameter of the original vibration signal is obtained. The basis of the signal quality parameter can include but is not limited to signal-to-noise ratio, signal strength, frequency of abnormal values, etc. The above basis is fused to generate a corresponding scalar value q, and the range of q is in the range of [0, 1], q = 1 represents perfect quality, and q = 0 represents unusable data.

[0075] Further, after determining the signal quality parameter, the physiological parameters are combined according to the specific value of the signal quality parameter, such as comparing the signal quality with a quality threshold, and selecting one or more combination strategies according to the comparison result, such as weighted average or selection combination of the physiological parameters. For example, the data of the side with better signal quality is selected as the output; or the signal quality is used as the weight to perform weighted average on the physiological parameters of both sides to obtain a more accurate estimated value. As shown in Figure 3 , in Figure 3 , lq represents the signal quality parameter corresponding to the left vibration signal, and rq represents the signal quality parameter corresponding to the right vibration signal. When both are greater than or equal to 0.9, the average of the physiological parameters of both is calculated; when one of them is less than 0.9, the physiological parameter of the other one which is greater than or equal to 0.9 is taken as the standard; when both are less than 0.9, it is indicated that both data are unreliable, and the average of both sides can be calculated to improve the fault tolerance and control the error range.

[0076] Further, the above combination process is performed for each independent time window (such as 10 seconds), and then a plurality of time windows are combined to generate a feature vector composed of physiological parameters in a period of time (such as 5 minutes), that is, the target physiological parameter sequence.

[0077] Step S110, historical sleep data of a plurality of sleep users is acquired, and the target physiological parameter sequence is compared with the historical sleep data to determine a target user based on the comparison result, and the target physiological parameter sequence is associated with the target user.

[0078] Specifically, historical sleep data of a plurality of sleep users using a smart bed is acquired, wherein the historical sleep data can be a historical modal matrix generated according to the vibration signals collected in the historical sleep of each user. Then, the target physiological parameter sequence is converted into a modal matrix, which is compared with the historical modal matrix of each user, and according to the comparison result, it is determined that the user whose historical modal matrix is closer to the modal matrix is the target user. Taking user AB as an example.

[0079]

[0080]

[0081] wherein, Δ A is the modal closeness between the modal matrix corresponding to the original vibration signal and the modal matrix of user A, and Δ B is the modal closeness between the modal matrix corresponding to the original vibration signal and the modal matrix of user B.

[0082] H A , H B are the historical modal matrices of users A and B. n is the number of days, d is the feature dimension, and R represents the real number set.

[0083] The modal matrix corresponding to the target physiological parameter sequence includes, but is not limited to: sleep time, wake-up time, heart rate mode, heart rate variability, mean heart rate, respiratory rate mode, respiratory variability, mean respiratory rate, snoring severity, body movement distribution, and turning-over frequency.

[0084] μ(.) is the historical modal matrix mean, is the Mahalanobis distance (Σ is the covariance matrix).

[0085] After determining the target user, the target physiological parameter sequence is associated to the target user, such as generating the latest sleep quality report based on the target physiological parameter and sending it to the binding user terminal of the target user.

[0086] The intelligent bed sleep data tracing method provided by the embodiment of the application collects sleep information, the sleep information including multiple original vibration signals of multiple sleep users collected by a sensor; signal features of the original vibration signals are extracted, a first similarity parameter between the signal features and physiological parameters corresponding to the signal features are calculated; physiological parameters between the multiple original vibration signals are compared, a second similarity parameter is generated, the first similarity parameter and the second similarity parameter are linearly fused to generate a target evaluation parameter, and whether the multiple original vibration signals are homologous is determined based on the target evaluation parameter; when it is determined that the multiple original vibration signals are homologous, signal quality parameters of the original vibration signals are obtained, the physiological parameters are merged based on the signal quality parameters to generate a target physiological parameter sequence; historical sleep data of the multiple sleep users are obtained, compared with the target physiological parameter sequence, a target user is determined based on a comparison result, and the target physiological parameter sequence is associated to the target user. In this way, homologous determination can be performed by comprehensively considering the similarity of the signal layer and the physiological layer, the reliability of the homologous determination decision is improved, the data quality is improved through fusion, the data attribution is ensured to be accurate through historical comparison, the data confusion problem is finally solved, and the user experience is improved.

[0087] Please refer to Figure 4 , Figure 4 is a structural schematic diagram of an intelligent bed sleep data tracing system provided by the embodiment of the application. As Figure 4 indicated, the system includes:

[0088] The acquisition module S402 is configured to acquire sleep information, and the sleep information includes multiple original vibration signals of multiple sleep users collected by a sensor.

[0089] The first parameter module S404 is configured to extract signal features of the original vibration signals, calculate a first similarity parameter between the signal features, and calculate physiological parameters corresponding to the signal features.

[0090] The second parameter module S406 is configured to compare physiological parameters between the multiple original vibration signals to generate a second similarity parameter, linearly fuse the first similarity parameter and the second similarity parameter to generate a target evaluation parameter, and determine whether the multiple original vibration signals are homologous based on the target evaluation parameter.

[0091] The merging module S408 is configured to, when it is determined that the multiple original vibration signals are homologous, acquire a signal quality parameter of the original vibration signal, merge the physiological parameters based on the signal quality parameter to generate a target physiological parameter sequence.

[0092] The user module S410 is configured to acquire historical sleep data of multiple sleep users, compare the historical sleep data with the target physiological parameter sequence, determine a target user based on a comparison result, and associate the target physiological parameter sequence to the target user.

[0093] In another embodiment, an intelligent bed sleep data tracing system further includes:

[0094] The first calculation module is configured to calculate time domain similarity, frequency domain similarity and time-frequency domain similarity between the multiple original vibration signals in the same time window, and perform average calculation on the time domain similarity, the frequency domain similarity and the time-frequency domain similarity to obtain a first similarity parameter.

[0095] The second calculation module is configured to compare similarity parameters corresponding to different physiological parameters between the multiple original vibration signals, and perform average calculation on the similarity parameters of the multiple physiological parameters to obtain a second similarity parameter.

[0096] The linear fusion module is configured to linearly fuse the first similarity parameter and the second similarity parameter to generate a target evaluation parameter.

[0097] Those skilled in the art can clearly understand that the technical solutions of the embodiments of the present application can be implemented by means of software and / or hardware. The "unit" and "module" in the specification refer to software and / or hardware that can independently complete or cooperate with other components to complete a specific function, and the hardware may, for example, be a field programmable gate array (FPGA), an integrated circuit (IC), and the like.

[0098] The various processing units and / or modules of the embodiments of the present application can be implemented by means of analog circuits that implement the functions described in the embodiments of the present application, or can be implemented by means of software that implements the functions described in the embodiments of the present application.

[0099] Referring to Figure 5Fig. 1 shows a structural schematic diagram of an electronic device according to an embodiment of the present application, which can be used to implement the method in the embodiments shown in the present application. Figure 1 As shown in the embodiments shown in the present application, the electronic device 500 can include at least one processor 501, at least one network interface 504, a user interface 503, a memory 505, and at least one communication bus 502. Figure 5

[0100] The communication bus 502 is used to realize the connection and communication between the components.

[0101] The user interface 503 can include a display, a camera, and optionally a standard wired interface and a wireless interface.

[0102] The network interface 504 can optionally include a standard wired interface and a wireless interface (such as a WI-FI interface).

[0103] The processor 501 can include one or more processing cores. The processor 501 connects various parts in the electronic device 500 through various interfaces and lines, executes various functions of the electronic device 500 and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 505, and calling data stored in the memory 505. Optionally, the processor 501 can be realized in at least one of the hardware forms of a digital signal processing (DSP), a field-programmable gate array (FPGA), and a programmable logic array (PLA). The processor 501 can be a combination of one or more of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. The CPU is mainly used to process the operating system, user interface, and application programs; the GPU is used to render and draw the content to be displayed on the display; and the modem is used to process wireless communication. It can be understood that the above-mentioned modem can also not be integrated into the processor 501, but can be realized by a separate chip.

[0104] ​The memory 505 can include a random access memory (RAM) and a read-only memory (ROM). Optionally, the memory 505 includes a non-transitory computer-readable storage medium. The memory 505 can be used to store instructions, programs, codes, code sets, or instruction sets. The memory 505 can include a program storage area and a data storage area, where the program storage area can store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playing function, an image playing function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; and the data storage area can store data involved in the above-mentioned various method embodiments, etc. The memory 505 can also be at least one storage device located away from the processor 501. As shown in Figure 5 The memory 505 as a computer storage medium can include an operating system, a network communication module, a user interface module, and program instructions.

[0105] In the electronic device 500 shown in Figure 5 The user interface 503 is mainly used to provide an interface for user input and obtain user input data; and the processor 501 can be used to call an interactive application program based on images stored in the memory 505 and specifically perform the following operations: collecting sleep information, where the sleep information includes a plurality of original vibration signals of a plurality of sleep users collected by a sensor; extracting signal features of the original vibration signals, calculating a first similarity parameter between the signal features, and a physiological parameter corresponding to the signal features; comparing the physiological parameters between the plurality of original vibration signals, generating a second similarity parameter, linearly fusing the first similarity parameter and the second similarity parameter, generating a target evaluation parameter, and determining whether the plurality of original vibration signals are homologous based on the target evaluation parameter; when it is determined that the plurality of original vibration signals are homologous, obtaining a signal quality parameter of the original vibration signal, merging the physiological parameters based on the signal quality parameter, and generating a target physiological parameter sequence; obtaining historical sleep data of the plurality of sleep users, comparing the target physiological parameter sequence, determining a target user based on a comparison result, and associating the target physiological parameter sequence to the target user.

[0106] The application further provides a computer readable storage medium, which stores a computer program. The computer program is executed by a processor to implement the steps of the method. The computer readable storage medium can include, but is not limited to, any type of disk, including a floppy disk, an optical disk, a DVD, a CD-ROM, a micro drive, a magneto-optical disk, a ROM, a RAM, an EPROM, an EEPROM, a DRAM, a VRAM, a flash memory device, a magnetic card or an optical card, a nanosystem (including a molecular memory IC), or any type of medium or device suitable for storing instructions and / or data.

[0107] It should be noted that, for the foregoing method embodiments, in order to simply describe, they are all described as a series of action combinations, but those skilled in the art should know that the present application is not limited to the order of the actions described, because according to the present application, certain steps can be performed in other order or simultaneously. Secondly, those skilled in the art should know that the embodiments described in the specification all belong to preferred embodiments, and the actions and modules involved are not necessarily necessary for the present application.

[0108] In the above embodiments, the description of each embodiment is focused on, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0109] In several embodiments provided by the present application, it should be understood that the disclosed device can be implemented by other means. For example, the device embodiments described above are only illustrative, and the division of the units is only a logical function division, and actual implementation can have another division manner, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some service interface, device or unit, which can be electrical or other forms.

[0110] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0111] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0112] The integrated unit, if implemented in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable memory. Based on such understanding, the technical solutions of the present application, essentially or in other words, the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a memory and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned memory includes: a U disk, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and various media that can store program codes.

[0113] A person of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be executed by a program instructing relevant hardware, and the program can be stored in a computer readable memory, which can include a flash disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0114] The above describes specific embodiments of the present specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be executed in an order different from that in the embodiments and still achieve the desired result. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are possible or can be advantageous.

Claims

1. A method for tracing sleep data of a smart bed, the method comprising: Collect sleep information, which includes multiple raw vibration signals from multiple sleep users collected by sensors; Extract the signal features of the original vibration signal, calculate the first similarity parameter between the signal features, and the physiological parameters corresponding to the signal features; By comparing the physiological parameters among multiple original vibration signals, a second similarity parameter is generated. The first similarity parameter and the second similarity parameter are linearly fused to generate a target evaluation parameter. Based on the target evaluation parameter, it is determined whether multiple original vibration signals are from the same source. When multiple original vibration signals are determined to be from the same source, the signal quality parameters of the original vibration signals are obtained, and the physiological parameters are merged based on the signal quality parameters to generate a target physiological parameter sequence. Historical sleep data of multiple sleep users are obtained and compared with the target physiological parameter sequence. Based on the comparison results, the target user is determined and the target physiological parameter sequence is associated with the target user.

2. The method according to claim 1, characterized in that, The process of generating target evaluation parameters includes: Calculate the time-domain similarity, frequency-domain similarity, and time-frequency-domain similarity among multiple original vibration signals within the same time window, and average the time-domain similarity, frequency-domain similarity, and time-frequency-domain similarity to obtain the first similarity parameter; By comparing the similarity parameters corresponding to different physiological parameters among multiple original vibration signals, and averaging the similarity parameters of multiple physiological parameters, a second similarity parameter is obtained. The first similarity parameter and the second similarity parameter are linearly fused to generate the target evaluation parameters.

3. The method according to claim 2, characterized in that, The linear fusion process includes: Calculate the instantaneous average similarity parameter of the first similarity parameter, and linearly fuse it with the second similarity parameter. The calculation formula includes: ， in, S1avg is the target evaluation parameter, S2 is the instantaneous average similarity parameter with a corresponding weight of α, and S2 is the second similarity parameter with a corresponding weight of β.

4. The method according to claim 3, characterized in that, The weight corresponding to the instantaneous average similarity parameter is 0.6, and the weight corresponding to the second similarity parameter is 0.

4.

5. The method according to claim 1, characterized in that, The step of merging the physiological parameters based on the signal quality parameters to generate a target physiological parameter sequence includes: By comparing signal quality parameters with quality thresholds, one or more merging strategies are selected based on the comparison results to merge physiological parameters, and the time windows corresponding to the original vibration signals are merged to generate a target physiological parameter sequence. The merging strategies include: Physiological parameters with good signal quality are selected, physiological parameters are calculated by average, and physiological parameters are calculated by weighting the signal quality parameters.

6. The method according to claim 1, characterized in that, The step of acquiring historical sleep data from multiple sleep users, comparing it with the target physiological parameter sequence, and determining the target user based on the comparison results includes: A historical modality matrix is ​​constructed based on historical sleep data from multiple sleep users. The modality matrix converted from the target physiological parameter sequence is compared with the historical modality matrix. The modality similarity in the comparison results is calculated, and the user corresponding to the historical modality matrix with the closest modality similarity is selected as the target user.

7. A smart bed sleep data tracing system, characterized in that, The system includes; The acquisition module is used to acquire sleep information, which includes multiple raw vibration signals from multiple sleep users acquired by sensors. The first parameter module is used to extract the signal features of the original vibration signal, calculate the first similarity parameter between the signal features, and the physiological parameters corresponding to the signal features; The second parameter module is used to compare the physiological parameters between multiple original vibration signals, generate a second similarity parameter, linearly fuse the first similarity parameter and the second similarity parameter to generate a target evaluation parameter, and determine whether multiple original vibration signals are from the same source based on the target evaluation parameter. The merging module is used to obtain the signal quality parameters of the original vibration signals when it is determined that multiple original vibration signals are from the same source, and to merge the physiological parameters based on the signal quality parameters to generate a target physiological parameter sequence. The user module is used to acquire historical sleep data of multiple sleep users, compare it with the target physiological parameter sequence, determine the target user based on the comparison results, and associate the target physiological parameter sequence with the target user.

8. The system according to claim 7, characterized in that, The system also includes: The first calculation module is used to calculate the time-domain similarity, frequency-domain similarity, and time-frequency-domain similarity among multiple original vibration signals within the same time window, and to average the time-domain similarity, frequency-domain similarity, and time-frequency-domain similarity to obtain the first similarity parameter. The second calculation module is used to compare the similarity parameters corresponding to different physiological parameters among multiple original vibration signals, and to calculate the average of the similarity parameters of multiple physiological parameters to obtain the second similarity parameter. The linear fusion module is used to linearly fuse the first similarity parameter and the second similarity parameter to generate target evaluation parameters.

9. An electronic device, comprising a processor and a memory; The processor is connected to the memory; The memory is used to store executable program code; The processor runs a program corresponding to the executable program code stored in the memory to perform the method as described in any one of claims 1-6.

10. A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method as described in any one of claims 1-6.

Images