Service method and system based on intelligent bed sleep data abnormity monitoring

Abstract

The embodiment of the invention provides a service method and system based on intelligent bed sleep data abnormity monitoring, and the method comprises the steps: receiving real-time sleep data uploaded by an intelligent bed, comparing the real-time sleep data with an abnormal value interval, and detecting whether the real-time sleep data has data abnormity or not. When the real-time sleep data is not abnormal, determining a corresponding historical data set based on a transmission source of the sleep data, inputting the historical data set and bound user information into a time sequence algorithm model for training, and outputting a normal numerical interval of the user; when the numerical value of the real-time sleep data is abnormal, the abnormal type of the numerical value abnormality is judged. When the exception type is equipment exception, a corresponding exception maintenance node is matched based on the exception type, and the intelligent bed number and the exception type are sent to the exception maintenance node; and when the abnormality type is a non-equipment abnormality, generating a corresponding user health early warning scheme based on the abnormality deviation degree of the numerical value abnormality and the abnormality deviation degree.

Description

Technical Field

[0001] The present invention relates to the technical field of smart beds, and in particular to a service method and system based on abnormal monitoring of sleep data of smart beds. Background Art

[0002] With the popularity of smart home systems, smart beds are an important smart home device. The sleep data generated during their use is of great significance for users' health monitoring. At the same time, customer service systems are also constantly developing. Online customer service consultation portals and work order systems are common customer service methods. The data processing system is responsible for collecting, processing and analyzing large amounts of data to provide efficient and accurate decision support.

[0003] However, in the existing technical solutions, there are some problems in the practical application of smart beds. The existing automatic work order generation system is usually based on preset rules, lacking intelligence and flexibility, and may not accurately assign the user's problem to the most appropriate service personnel, thus affecting the efficiency of problem solving. In addition, the existing system is usually unable to monitor the user's sleep data in real time. Customer service intervention is only triggered when the user actively consults or an abnormal situation occurs, which may cause some potential problems to be ignored, thus affecting the user's health and experience. Summary of the invention

[0004] In view of the problems existing in the prior art, an embodiment of the present invention provides a service method and system based on abnormal monitoring of sleep data of a smart bed.

[0005] An embodiment of the present invention provides a service method based on abnormal sleep data monitoring of a smart bed, the method comprising: Receiving real-time sleep data uploaded by the smart bed, and detecting whether the real-time sleep data has data anomalies; When there is no data anomaly in the real-time sleep data, a corresponding historical data set is determined based on the transmission source of the sleep data, the historical data set and the bound user information are input into a time series algorithm model for training, and an abnormal numerical interval of the user is output; Comparing the real-time sleep data with the abnormal numerical value interval to detect whether there is a numerical abnormality, and when the real-time sleep data has a numerical abnormality, determining the abnormality type of the numerical abnormality; When the abnormality type is a non-human abnormality, the corresponding abnormal maintenance node is matched based on the abnormality type, and the smart bed number and abnormality type are sent to the abnormal maintenance node; When the abnormality type is a man-made abnormality, based on the abnormal deviation degree of the numerical abnormality, a corresponding user health warning plan is generated based on the abnormal deviation degree.

[0006] In one embodiment, the method further comprises: Obtaining a timeline of historical sleep data in the historical data set, inputting the timeline of historical sleep data and bound user information into a timing algorithm model for training, and outputting a trained user sleep time baseline; Based on the user's sleep time baseline and in combination with statistical data, an abnormal value interval of the user's time axis is determined.

[0007] In one embodiment, the method further comprises: The real-time sleep data is compared item by item with the abnormal value interval of the time axis at the corresponding moment, and whether there is data abnormality is determined based on the comparison result, and the item by item data includes single item data and combined data.

[0008] In one embodiment, the method further comprises: When there is an abnormal value in the real-time sleep data, the bound user information is transmitted to a customer service node.

[0009] In one embodiment, the method further comprises: The real-time sleep data includes user vital sign data and smart bed usage data; The user's vital signs data include heart rate, respiratory rate, body movement and snoring; The smart bed usage data includes changes in mattress pressure distribution and equipment operating status.

[0010] An embodiment of the present invention provides a service system based on abnormal sleep data monitoring of a smart bed, the system comprising: A receiving module, used to receive real-time sleep data uploaded by the smart bed, and detect whether the real-time sleep data has data anomalies, wherein the real-time sleep data includes user vital sign data and smart bed usage data; A training module, for determining a corresponding historical data set based on a transmission source of the sleep data when there is no data anomaly in the real-time sleep data, inputting the historical data set and bound user information into a time series algorithm model for training, and outputting an abnormal numerical interval of the user; A comparison module, used for comparing the real-time sleep data with the abnormal value interval, detecting whether there is a numerical abnormality, and when the real-time sleep data has a numerical abnormality, determining the abnormality type of the numerical abnormality; A maintenance module, for, when the abnormality type is a non-human abnormality, matching a corresponding abnormal maintenance node based on the abnormality type, and sending the smart bed number and abnormality type to the abnormal maintenance node; The early warning module is used to generate a corresponding user health early warning plan based on the abnormal deviation degree of the numerical abnormality when the abnormality type is a man-made abnormality.

[0011] In one embodiment, the system further comprises: A timeline module, used to obtain a timeline of historical sleep data in the historical data set, input the timeline of historical sleep data and bound user information into a timing algorithm model for training, and output a trained user sleep time baseline; The determination module is used to determine the abnormal value interval of the user's time axis based on the user's sleep time baseline in combination with statistical data.

[0012] In one embodiment, the system further comprises: The abnormal module is used to compare the real-time sleep data with the abnormal value interval of the time axis at the corresponding moment item by item, and determine whether there is data abnormality based on the comparison result, wherein the item by item data includes single item data and combined data.

[0013] An embodiment of the present invention provides an electronic device, including 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 by reading the executable program code stored in the memory, so as to execute the method described in one or more embodiments.

[0014] An embodiment of the present invention provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the above-mentioned service method based on abnormal monitoring of sleep data of a smart bed are implemented.

[0015] In view of the above, in one or more embodiments of the present specification, the real-time sleep data uploaded by the smart bed is received, and the real-time sleep data is detected to see if there is data anomaly; when there is no data anomaly in the real-time sleep data, the corresponding historical data set is determined based on the transmission source of the sleep data, and the historical data set and the bound user information are input into the time series algorithm model for training, and the abnormal numerical interval of the user is output; the real-time sleep data is compared with the abnormal numerical interval to detect whether there is a numerical anomaly, and when there is a numerical anomaly in the real-time sleep data, the abnormal type of the numerical anomaly is determined; when the abnormal type is non-human abnormality, the corresponding abnormal maintenance node is matched based on the abnormal type, and the smart bed number and abnormal type are sent to the abnormal maintenance node; when the abnormal type is human abnormality, based on the abnormal deviation degree of the numerical abnormality, the corresponding user health warning scheme is generated based on the abnormal deviation degree. In this way, by real-time monitoring of the user's sleep data, it is possible to timely determine whether there is an abnormal situation, and automatically generate a work order, assign it to the service personnel, and realize the active contact of the service personnel, so as to handle the problem for the user in the first time, improve the timeliness and efficiency of customer service, and reduce the waiting time of the user, and improve the customer experience. On the other hand, for the user's health problems, it is also possible to provide more targeted and timely health warnings in terms of sleep, further improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 This is a flowchart of a service method based on abnormal sleep data monitoring of a smart bed provided by an embodiment of this specification.

[0018] Figure 2 It is a structural diagram of a service system based on abnormal sleep data monitoring of a smart bed provided by an embodiment of this specification.

[0019] Figure 3 It is a structural schematic diagram of an electronic device provided by an embodiment of this specification. DETAILED DESCRIPTION

[0020] The subject matter described herein will now be discussed with reference to example embodiments. It should be understood that the discussion of these embodiments is only to enable those skilled in the art to better understand and implement the subject matter described herein, and is not a limitation of the scope of protection, applicability or examples set forth in the claims. The functions and arrangements of the elements discussed can be changed without departing from the scope of protection of the contents of this specification. Various examples can omit, replace or add various processes or components as needed. For example, the described method can be performed in an order different from the described order, and various steps can be added, omitted or combined. In addition, the features described relative to some examples can also be combined in other examples.

[0021] As used herein, the term "including" and its variations represent open terms, meaning "including but not limited to". The term "based on" means "based at least in part on". The terms "one embodiment" and "an embodiment" mean "at least one embodiment". The term "another embodiment" means "at least one other embodiment". The terms "first", "second", etc. may refer to different or the same objects. Other definitions may be included below, whether explicit or implicit. Unless the context clearly indicates otherwise, the definition of a term is consistent throughout the specification.

[0022] like Figure 1 As shown, an embodiment of the present invention provides a service method based on abnormal sleep data monitoring of a smart bed, comprising: Step S102, receiving real-time sleep data uploaded by the smart bed, and detecting whether there is data anomaly in the real-time sleep data, wherein the real-time sleep data includes user vital sign data and smart bed usage data.

[0023] Specifically, when the user rests on the smart bed, the various sensors equipped on the smart bed can monitor the user's sleep status. The sensors can capture vital signs such as heart rate, breathing rate, body movement, snoring, etc., and also record the use of the device itself, such as changes in mattress pressure distribution, device operating status and other data. After the smart bed collects the data, it can connect to the service system through cloud services or local servers to transmit the user's real-time sleep data.

[0024] Furthermore, after receiving the real-time sleep data, the service system may first pre-process the real-time sleep data, such as performing preliminary cleaning to remove obvious noise points or error values. For example, extreme abnormal values ​​caused by sensor failure or external interference should be identified and excluded. It may also include smoothing the real-time sleep data and the time series data (such as heart rate, respiratory rate) generated at the corresponding time, so as to better reflect the real physiological trend of the user when sleeping. Further, after pre-processing the real-time sleep data, the service system first detects whether there is data anomaly in the real-time sleep data, wherein the data anomaly refers to whether the user's valid data reaches the normal threshold, and the situation of insufficient valid data, such as from the user's vital sign data: the device is offline, the vital sign data received by the cloud is less than a certain length of time, such as less than 2 hours, then the real-time sleep data of that night will not be issued; there is too much body movement, and the real-time sleep data received has more than 50% body movement signals, then it is determined that the device has too much body movement that night, and the real-time sleep data of that night will not be issued. From the use data of the smart bed: for example, the device has not responded for a long time, the sensor reading is unstable for more than a certain length of time, etc.

[0025] In addition, the normal threshold range of the user can be determined by comprehensive analysis based on the collected data of the user's heart rate, breathing rate, body movement and snoring, combined with normal medical indicators, and training with the user's own characteristic data (such as the user's weight, height, etc.), and further analysis can be performed to determine the user's normal interval data in four aspects: sleep quality, heart, breathing, and nervous system. The specific process can be to establish a user model through user characteristic data, and then train and determine it in combination with medical indicators.

[0026] Step S104, when there is no data anomaly in the real-time sleep data, a corresponding historical data set is determined based on the transmission source of the sleep data, the historical data set and the bound user information are input into a time series algorithm model for training, and the abnormal numerical range of the user is output.

[0027] Specifically, when there is no data anomaly in the real-time sleep data, that is, when the valid data of the real-time sleep data reaches the normal threshold, subsequent services can be further performed based on the real-time sleep data. Find the corresponding user account according to the source of the real-time sleep data (that is, the specific smart bed device). Each smart bed device should be bound to a user account to ensure that it can be accurately associated with the historical data of a specific user. Extract all available historical sleep data records for the user from the database. These data can include long-term accumulated vital sign data (such as heart rate, respiratory rate, etc.) and usage habits (such as bedtime, waking up time, etc.). In order to improve the accuracy of the model, try to obtain as much data as possible within the time span.

[0028] Furthermore, before subsequent model training based on historical sleep data records, bound user information can also be obtained, such as age, gender, living habits, sleep duration, sleep time, and other personal information. This information can help build a more comprehensive user portrait, thereby improving the accuracy of model prediction.

[0029] Furthermore, for analyzing the user's sleep data, a machine learning or deep learning model suitable for processing time series data can be selected, such as a long short-term memory network (LSTM), a gated recurrent unit (GRU), an ARIMA model, etc. The above model is suitable for analyzing the changing trend of sleep patterns, such as the relationship between the user's sleep data and time during 8 hours of sleep. The selected time series algorithm model is trained using the above historical data set and user information as input. During the training process, pay attention to adjusting the hyperparameters to optimize the model performance. After training, the model can establish a normal sleep behavior baseline based on the user's historical sleep data. This baseline reflects the typical sign value distribution related to the sleep time point under the user's daily sleep state. Based on the baseline, a reasonable abnormal value interval can be set for each sign indicator at each sleep time. Usually, these thresholds can be determined by statistical methods (such as confidence intervals, standard deviation multiples) or by the experience of domain experts. Once the real-time monitored data exceeds this interval, it is considered that there may be an abnormal situation. Output the user's abnormal value interval, and the abnormal value interval is associated with the user's sleep time axis.

[0030] Step S106 , comparing the real-time sleep data with the abnormal numerical value interval to detect whether there is a numerical abnormality, and when the real-time sleep data has a numerical abnormality, determining the abnormality type of the numerical abnormality.

[0031] Specifically, the latest real-time sleep data (such as heart rate, respiratory rate, body movement, snoring, etc.) is automatically compared with the abnormal value range output by the training model. In addition, when comparing, it is not only a comparison of a single indicator, but the system also needs to comprehensively consider the relationship between multiple related vital signs. For example, the simultaneous changes in heart rate and respiratory rate may be related to the user's sleep condition, not just independent events of the two data.

[0032] In addition, when comparing abnormal value ranges with real-time sleep data, the sleep timeline should also be considered. For example, starting from the timeline when the user falls asleep, a comparison should be performed item by item at each time point. When the vital sign data exceeds the preset abnormal value range, the system will immediately mark an alarm mechanism.

[0033] In addition, considering the influence of individual differences and environmental factors, the abnormal value range should have a certain degree of flexibility to allow appropriate adjustments based on the user's daily activity patterns. For example, in a short period of time after a user performs strenuous exercise, their heart rate and breathing rate may be higher than normal.

[0034] Furthermore, in order to accurately determine the specific type of numerical anomaly, classification rules corresponding to the abnormal data can be pre-set, wherein the classification rules can roughly correspond to two types of situations, namely, erroneous readings caused by equipment failure or indeed reflecting changes in the user's health status.

[0035] Step S108, when the abnormality type is a non-human abnormality, the corresponding abnormal maintenance node is matched based on the abnormality type, and the smart bed number and abnormality type are sent to the abnormal maintenance node.

[0036] Specifically, when the system needs to confirm that the detected anomaly is indeed not caused by the user's normal activities or external factors (such as ambient temperature changes, temporary physical discomfort, etc.), it ensures that there will be no false alarms that disturb the user or waste maintenance resources. Then the machine learning model is used to further analyze the time series characteristics of the abnormal data to determine whether it meets the equipment failure mode. After determining it as a failure mode, the type of anomaly (such as sensor failure, communication interruption, hardware damage, etc.) is determined based on the abnormal data.

[0037] Furthermore, a mapping table from exception types to maintenance nodes is established, which lists in detail which specific maintenance nodes should handle different types of exceptions. For example, software problems may be handled by the technical support team, while hardware failures can be repaired by on-site engineers. After the corresponding maintenance node is determined, the system will automatically generate a detailed maintenance work order. The work order should contain all necessary information, such as the unique number of the smart bed (for quick location of the device), a specific description of the exception (to help technicians prepare solutions in advance), and any relevant background information (such as recent usage records or previous maintenance history). Send the maintenance work order to the corresponding abnormal maintenance node.

[0038] Step S110, when the abnormality type is a man-made abnormality, based on the abnormal deviation degree of the numerical abnormality, a corresponding user health warning plan is generated based on the abnormal deviation degree.

[0039] Specifically, when it is determined based on the abnormal data that the abnormal type is caused by physiological or behavioral changes in the user rather than a problem with the device itself, the specific degree of deviation is calculated based on the difference between the real-time sleep data and the user's normal value range. The calculation of the degree of deviation can be a simple difference calculation, or it can be measured by statistical methods (such as standard deviation, confidence interval, etc.). The degree of abnormal deviation can be divided into different levels, such as mild, moderate and severe. Each level corresponds to a different level of health risk. Corresponding to different degrees of abnormal deviation of different data, the user's health level can be divided into different levels, such as mild, moderate and severe. Each level corresponds to a different level of health risk.

[0040] Furthermore, for minor deviations, some information on improving lifestyle can be sent to the user's bound terminal; for more serious deviations, the user will be notified to seek professional medical help according to the type of deviation value, and the warning information will be notified to the health manager for further service. For example, when there is a minor deviation, a gentle reminder message is pushed, such as "Your heart rate increased slightly during sleep last night. It is recommended that you go to bed early tonight." When there is a moderate deviation, a health reminder with specific guidance can be sent, such as "Your breathing rate has fluctuated greatly in the past few days, which may be caused by stress or environmental factors. Please try relaxation exercises and keep the indoor air circulating." When there is a serious deviation, the emergency notification mechanism is triggered to inform the user that there may be health risks and strongly recommend that he or she consult a doctor as soon as possible. "Your nighttime heart rate is detected to be abnormally low, and there may be a risk of heart problems. Please contact a medical professional immediately." At the same time, the health manager will also receive a work order for the corresponding health changes, and the health manager will further communicate and handle with the user through telephone and other means.

[0041] The embodiment of the present invention provides a service method based on abnormal monitoring of sleep data of a smart bed, which receives real-time sleep data uploaded by the smart bed, detects whether the real-time sleep data has data abnormalities; when the real-time sleep data does not have data abnormalities, determines the corresponding historical data set based on the transmission source of the sleep data, inputs the historical data set and the bound user information into the time series algorithm model for training, and outputs the abnormal numerical interval of the user; compares the real-time sleep data with the abnormal numerical interval, detects whether there is a numerical abnormality, and when there is a numerical abnormality in the real-time sleep data, determines the abnormal type of the numerical abnormality; when the abnormal type is non-human abnormality, matches the corresponding abnormal maintenance node based on the abnormal type, and sends the smart bed number and the abnormal type to the abnormal maintenance node; when the abnormal type is human abnormality, based on the abnormal deviation degree of the numerical abnormality, generates the corresponding user health warning scheme based on the abnormal deviation degree. In this way, by real-time monitoring of the user's sleep data, it can timely determine whether there is an abnormal situation, and automatically generate a work order, which is assigned to the service personnel, so as to realize the active contact of the service personnel, thereby handling the problem for the user in the first time, improving the timeliness and efficiency of customer service, while reducing the waiting time of the user and improving the customer experience. On the other hand, for the health problems of the user, it can also provide health warnings in sleep in a more targeted and timely manner, further improving the user experience.

[0042] See also Figure 2 , Figure 2 Schematic diagram of a service system based on abnormal sleep data monitoring of smart beds provided in an embodiment of the present application. Figure 2 As shown, the system comprises: The receiving module S202 is used to receive the real-time sleep data uploaded by the smart bed and detect whether there is data anomaly in the real-time sleep data, wherein the real-time sleep data includes user vital sign data and smart bed usage data; The training module S204 is used to determine the corresponding historical data set based on the transmission source of the sleep data when there is no data anomaly in the real-time sleep data, input the historical data set and the bound user information into the time series algorithm model for training, and output the abnormal numerical interval of the user; A comparison module S206 is used to compare the real-time sleep data with the abnormal value interval to detect whether there is a numerical abnormality, and when the real-time sleep data has a numerical abnormality, determine the abnormality type of the numerical abnormality; Maintenance module S208, for, when the abnormality type is a non-human abnormality, matching a corresponding abnormal maintenance node based on the abnormality type, and sending the smart bed number and abnormality type to the abnormal maintenance node; The early warning module S210 is used to generate a corresponding user health early warning plan based on the abnormal deviation degree of the numerical abnormality when the abnormality type is a man-made abnormality.

[0043] In another embodiment, a service system based on abnormal sleep data monitoring of a smart bed further includes: A division module, used for dividing the model corresponding to the preset algorithm into models of different levels of sensitivity when it is detected that the number of users is greater than 1; The selection module is used to select a sensitivity model of a corresponding level to detect the user's sleep vibration signal based on the snoring level selected by the user, and trigger a preset intervention action when snoring is detected.

[0044] In another embodiment, a service system based on abnormal sleep data monitoring of a smart bed further includes: A timeline module, used to obtain a timeline of historical sleep data in the historical data set, input the timeline of historical sleep data and bound user information into a timing algorithm model for training, and output a trained user sleep time baseline; The determination module is used to determine the abnormal value interval of the user's time axis based on the user's sleep time baseline in combination with statistical data.

[0045] In another embodiment, a service system based on abnormal sleep data monitoring of a smart bed further includes: The abnormal module is used to compare the real-time sleep data with the abnormal value interval of the time axis at the corresponding moment item by item, and determine whether there is data abnormality based on the comparison result, wherein the item by item data includes single item data and combined data.

[0046] Those skilled in the art can clearly understand that the technical solutions of the embodiments of the present application can be implemented with the help of software and / or hardware. The "unit" and "module" in this specification refer to software and / or hardware that can independently complete or cooperate with other components to complete specific functions, where the hardware can be, for example, a field programmable gate array (FPGA), an integrated circuit (IC), etc.

[0047] Each processing unit and / or module of the embodiments of the present application may be implemented by an analog circuit that implements the functions described in the embodiments of the present application, or may be implemented by software that executes the functions described in the embodiments of the present application.

[0048] See also Figure 3 , which shows a schematic diagram of the structure of an electronic device involved in an embodiment of the present application, the electronic device can be used to implement Figure 1 The method in the embodiment shown. Figure 3As shown, the electronic device 300 may include: at least one processor 301 , at least one network interface 304 , a user interface 303 , a memory 305 , and at least one communication bus 302 .

[0049] The communication bus 302 is used to realize the connection and communication between these components.

[0050] The user interface 303 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 303 may also include a standard wired interface and a wireless interface.

[0051] The network interface 304 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0052] Among them, the processor 301 may include one or more processing cores. The processor 301 uses various interfaces and lines to connect various parts of the entire electronic device 300, and executes various functions and processes data of the electronic device 300 by running or executing instructions, programs, code sets or instruction sets stored in the memory 305, and calling data stored in the memory 305. Optionally, the processor 301 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 301 can integrate one or a combination of a processor (Central Processing Unit, CPU), an image processor (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; and the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 301, but implemented separately through a chip.

[0053] Among them, the memory 305 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 305 may also be optionally at least one storage device located away from the aforementioned processor 301. As Figure 3 As shown, the memory 305 as a computer storage medium may include an operating system, a network communication module, a user interface module, and program instructions.

[0054] exist Figure 3 In the electronic device 300 shown, the user interface 303 is mainly used to provide an input interface for the user and obtain the data input by the user; and the processor 301 can be used to call the interactive application based on image generation stored in the memory 305, and perform the following operations: receive the real-time sleep data uploaded by the smart bed, and detect whether there is data anomaly in the real-time sleep data; when there is no data anomaly in the real-time sleep data, determine the corresponding historical data set based on the transmission source of the sleep data, input the historical data set and the bound user information into the timing algorithm model for training, and output the user's abnormal numerical range; compare the real-time sleep data with the abnormal numerical range, detect whether there is a numerical anomaly, and when there is a numerical anomaly in the real-time sleep data, determine the abnormal type of the numerical anomaly; when the abnormal type is non-human abnormality, match the corresponding abnormal maintenance node based on the abnormal type, and send the smart bed number and abnormal type to the abnormal maintenance node; when the abnormal type is human abnormality, based on the abnormal deviation degree of the numerical abnormality, generate a corresponding user health warning plan based on the abnormal deviation degree.

[0055] The present application also provides a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, the steps of the above method are implemented. The computer-readable storage medium may 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, and 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.

[0056] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0057] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0058] In the several embodiments provided in the present application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0059] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0060] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0061] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM), random access memory (RAM), mobile hard disk, disk or optical disk and other media that can store program codes.

[0062] A person skilled in the art may understand that all or part of the steps in the various methods of the above embodiments may be completed by entering a program to instruct related hardware, and the program may be stored in a computer-readable memory, which may include a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0063] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A service method based on abnormal sleep data monitoring of a smart bed, the method comprising: Receiving real-time sleep data uploaded by the smart bed, and detecting whether the real-time sleep data has data anomalies; When there is no data anomaly in the real-time sleep data, a corresponding historical data set is determined based on the transmission source of the sleep data, the historical data set and the bound user information are input into a time series algorithm model for training, and an abnormal numerical interval of the user is output; Comparing the real-time sleep data with the abnormal numerical value interval to detect whether there is a numerical abnormality, and when the real-time sleep data has a numerical abnormality, determining the abnormality type of the numerical abnormality; When the abnormality type is a non-human abnormality, the corresponding abnormal maintenance node is matched based on the abnormality type, and the smart bed number and abnormality type are sent to the abnormal maintenance node; When the abnormality type is a man-made abnormality, based on the abnormal deviation degree of the numerical abnormality, a corresponding user health warning plan is generated based on the abnormal deviation degree.

2. The method according to claim 1, characterized in that The historical data set and bound user information are input into a time series algorithm model for training, and the abnormal numerical range of the user is output, including: Obtaining a timeline of historical sleep data in the historical data set, inputting the timeline of historical sleep data and bound user information into a timing algorithm model for training, and outputting a trained user sleep time baseline; Based on the user's sleep time baseline and in combination with statistical data, an abnormal value interval of the user's time axis is determined.

3. The method according to claim 2, characterized in that The comparing the real-time sleep data with the abnormal value interval to detect whether there is an abnormal value includes: The real-time sleep data is compared item by item with the abnormal value interval of the time axis at the corresponding moment, and whether there is data abnormality is determined based on the comparison result, and the item by item data includes single item data and combined data.

4. The method according to claim 1, characterized in that The method further comprises: When there is an abnormal value in the real-time sleep data, the bound user information is transmitted to a customer service node.

5. The method according to claim 1, characterized in that The method further comprises: The real-time sleep data includes user vital sign data and smart bed usage data; The user's vital signs data include heart rate, respiratory rate, body movement and snoring; The smart bed usage data includes changes in mattress pressure distribution and equipment operating status.

6. A service system based on abnormal sleep data monitoring of smart beds, characterized in that: The system comprises: A receiving module, used to receive real-time sleep data uploaded by the smart bed, and detect whether the real-time sleep data has data anomalies, wherein the real-time sleep data includes user vital sign data and smart bed usage data; A training module, for determining a corresponding historical data set based on a transmission source of the sleep data when there is no data anomaly in the real-time sleep data, inputting the historical data set and bound user information into a time series algorithm model for training, and outputting an abnormal numerical interval of the user; A comparison module, used for comparing the real-time sleep data with the abnormal value interval, detecting whether there is a numerical abnormality, and when the real-time sleep data has a numerical abnormality, determining the abnormality type of the numerical abnormality; A maintenance module, for, when the abnormality type is a non-human abnormality, matching a corresponding abnormal maintenance node based on the abnormality type, and sending the smart bed number and abnormality type to the abnormal maintenance node; The early warning module is used to generate a corresponding user health early warning plan based on the abnormal deviation degree of the numerical abnormality when the abnormality type is a man-made abnormality.

7. The system according to claim 6, characterized in that The system further comprises: A timeline module, used to obtain a timeline of historical sleep data in the historical data set, input the timeline of historical sleep data and bound user information into a timing algorithm model for training, and output a trained user sleep time baseline; The determination module is used to determine the abnormal value interval of the user's time axis based on the user's sleep time baseline in combination with statistical data.

8. The system according to claim 7, characterized in that The system further comprises: The abnormal module is used to compare the real-time sleep data with the abnormal value interval of the time axis at the corresponding moment item by item, and determine whether there is data abnormality based on the comparison result, wherein the item by item data includes single item data and combined data.

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 by reading the executable program code stored in the memory, so as to execute the method according to any one of claims 1 to 5.

10. A computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the method according to any one of claims 1 to 5.

Images