Sleep quality evaluation method and device, electronic equipment, computer storage medium and program product

Abstract

The invention relates to the technical field of smart home, in particular to a sleep quality evaluation method and device, electronic equipment, a computer storage medium and a program product, the method comprises the steps that action data reflecting a target object is acquired, the action data is derived from multiple pieces of equipment under the same time and space, and the action data comprises action information and time information; determining feature information of a target behavior in a sleep process according to the action data, wherein the feature information of the target behavior comprises at least one of feature information of a normal behavior and feature information of an abnormal behavior; and determining the sleep quality according to the feature information of the target behavior. According to the invention, the accuracy and reliability of sleep quality evaluation can be improved.

Description

Technical Field

[0001] The present application relates to the field of smart home technology, and in particular to a sleep quality assessment method, device, electronic device, computer storage medium and program product. Background Art

[0002] As users' health awareness increases, more and more users collect vital sign data during sleep through vital sign monitoring devices (such as smart pillows, sleep belts, smart bracelets), and report the vital sign data to the server for sleep analysis.

[0003] In the related art, inaccurate recognition of the state of the monitored object is prone to occur, resulting in low accuracy and reliability of the sleep analysis results. Summary of the invention

[0004] The present application provides a sleep quality assessment method, device, electronic device, computer storage medium and program product to at least solve the technical problem of low accuracy and reliability of sleep analysis results.

[0005] According to a first aspect of an embodiment of the present application, a method for evaluating sleep quality is provided, comprising:

[0006] Acquire action data reflecting a target object, the action data originating from a plurality of devices in the same time and space, the action data including action information and time information;

[0007] determining characteristic information of a target behavior during sleep according to the motion data, wherein the characteristic information of the target behavior includes at least one of characteristic information of normal behavior and characteristic information of abnormal behavior;

[0008] The sleep quality is determined according to the characteristic information of the target behavior.

[0009] According to a second aspect of an embodiment of the present application, a sleep quality assessment device is provided, comprising:

[0010] An action data acquisition module, used to acquire action data reflecting a target object, the action data originating from multiple devices in the same time and space, and the action data including action information and time information;

[0011] a characteristic information determination module, configured to determine characteristic information of a target behavior during sleep according to the motion data, wherein the characteristic information of the target behavior includes at least one of characteristic information of a normal behavior and characteristic information of an abnormal behavior;

[0012] The sleep quality assessment module is used to determine the sleep quality according to the characteristic information of the target behavior.

[0013] According to a third aspect of an embodiment of the present application, an electronic device is provided, including a memory and a processor, wherein the memory stores computer instructions, and the processor is used to execute the computer instructions to implement the sleep quality assessment method described in the first aspect of the embodiment of the present application.

[0014] According to a fourth aspect of an embodiment of the present application, a computer-readable storage medium is provided, storing a computer program as described in the first aspect of the embodiment of the present application that can be loaded and executed by a processor.

[0015] According to a fifth aspect of an embodiment of the present application, a computer program product is provided, wherein the computer program product comprises computer instructions. When the computer instructions are executed by a computer or a processor, the steps of the method described in the first aspect of the embodiment of the present application are executed.

[0016] In an embodiment of the present application, motion data reflecting the target object is obtained from multiple devices in the same space and time, and the motion data includes motion information and time information. Thus, more comprehensive data including motion information and time information can be obtained based on multi-source data, providing an objective and comprehensive data basis for subsequent sleep quality assessment. Characteristic information of the target behavior during sleep is determined based on the motion data, and the characteristic information of the target behavior includes at least one of characteristic information of normal behavior and characteristic information of abnormal behavior. Thus, the target behavior of the target object can be analyzed based on the aforementioned objective and comprehensive data to obtain characteristic information that objectively reflects the characteristics of the target behavior, which is conducive to accurately identifying the real motion / behavior of the target object (e.g., human body). The sleep quality is determined based on the characteristic information of the target behavior, so that accurate and reliable sleep quality assessment results can be obtained. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1A is a schematic diagram of the interaction between a server and a terminal in a sleep quality assessment scenario in an embodiment;

[0018] Figure 1B is a schematic diagram of an application scenario of a sleep quality assessment method in an embodiment;

[0019] Figure 2 is a flowchart of a sleep quality assessment method in one embodiment;

[0020] Figure 3 is a flow chart of determining characteristic information of a target behavior during sleep in one embodiment;

[0021] Figure 4 is a flow chart of determining characteristic information of a target behavior during sleep in one embodiment;

[0022] Figure 5Ais a data schematic diagram of the distribution law of actions in an embodiment;

[0023] Figure 5B In one embodiment, the algorithm model is based on Figure 5A A schematic diagram of the output result obtained by the data content shown;

[0024] Figure 5C is a data schematic diagram of the distribution law of actions in an embodiment;

[0025] Figure 5D In one embodiment, the algorithm model is based on Figure 5C A schematic diagram of the output result obtained by the data content shown;

[0026] Figure 6 is a flow chart of determining characteristic information of a target behavior during sleep in one embodiment;

[0027] Figure 7 is a flow chart of a method for determining sleep quality according to characteristic information of a target behavior in an embodiment;

[0028] Figure 8 is a structural block diagram of a sleep quality assessment device in one embodiment;

[0029] Fig. 9 is a structural block diagram of an electronic device in an embodiment. DETAILED DESCRIPTION

[0030] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0031] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0032] According to an embodiment of the present application, an embodiment of a sleep quality assessment method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0033] For ease of understanding, some features of this embodiment are described below:

[0034] Obtain motion data reflecting the target object. The motion data originates from multiple devices in the same time and space, and the motion data includes motion information and time information. The target object refers to the object for which the sleep quality assessment is targeted, such as a user.

[0035] Characteristic information of a target behavior during sleep is determined according to the motion data, where the characteristic information of the target behavior includes at least one of characteristic information of normal behavior and characteristic information of abnormal behavior.

[0036] Determine sleep quality based on characteristic information of target behavior.

[0037] The sleep quality assessment method provided in this application can be applied to Figure 1A In the application environment shown, the application environment may be an environment in which an electronic device interacts with a server, or an environment in which a user interacts with an electronic device, or a multi-terminal interaction, or a multi-server interaction, etc.

[0038] Among them, terminal 001 and terminal 002 communicate with server 003 through the network. Server 003 can obtain the motion data of the target object from terminal 001 and terminal 002. Terminal 001 can be a controlled device, that is, a device operated or controlled by the target object. For example, smart home products such as ventilation equipment (for example, smart doors and windows including door and window sensors), shading equipment (for example, smart curtains), air handling equipment (for example, air conditioning), lighting equipment (for example, smart lamps) and switch equipment (for example, smart physical switches, wireless switches, etc.), or terminal 001 can also be a smart phone, tablet, etc. operated by the user. Terminal 002 can be a monitoring device, that is, a device that monitors the target object. For example, a human body sensor, infrared camera, wearable device (such as a watch), smart sleeping pillow, etc. that detects human body movements. Through terminal 001 and terminal 002, detailed motion data of users can be collected, thereby providing a data basis for more accurately determining the real actions / behaviors of users. Among them, server 003 can be implemented with an independent server or a server cluster composed of multiple servers. Alternatively, the server 003 may also be a smart phone, a personal computer, a laptop computer, a tablet computer, a smart control panel, a portable wearable device, or other electronic devices capable of implementing a network connection.

[0039] In addition, the server 003 can also communicate with the terminal 004 through the network, so that the user can access data through the terminal 004. The terminal 004 can be a smart phone, a personal computer, a laptop, a tablet computer, a smart control panel, a portable wearable device, or other electronic devices that can implement network connection.

[0040] The sleep quality assessment method provided in this application can also be applied to Figure 1B In the application environment shown, the application environment includes a smart device 10 , a gateway 20 , a router 30 , a server 40 and a user terminal 50 .

[0041] Specifically, the user terminal 50, which can also be considered as a user end or terminal, can deploy (also understood as install) the client associated with the smart device 10. This user terminal 50 can be a smart phone, a laptop computer, a personal computer, a tablet computer, a smart control panel or other electronic device that can implement a network connection, which is not limited here.

[0042] Among them, the user terminal 50 is associated with the smart device 10, which essentially means that the user registers an account in the user terminal 50 and configures the smart device 10 in the user terminal 50. For example, the configuration includes adding a device identification to the smart device 10, so that when the user terminal 50 is running, it can provide the user with functions such as device display and device control of the smart device 10. This user terminal 50 can be in the form of an application or a web page. Accordingly, the interface for device display of the user terminal 50 can be in the form of a program window or a web page, which is not limited here.

[0043] The smart device 10 is deployed in the gateway 20, and communicates with the gateway 20 through its own configured communication module, and is then controlled by the gateway 20. It should be understood that the smart device 10 generally refers to one of a plurality of smart devices 10, and the embodiment of the present application only takes the smart device 10 as an example, that is, the embodiment of the present application does not limit the number and device type of the smart devices 10 deployed in the gateway 20. In an application scenario, the smart device 10 accesses the gateway 20 through a local area network, and is thus deployed in the gateway 20. The process of the smart device 10 accessing the gateway 20 through the local area network includes: the gateway 20 first establishes a local area network, and the smart device 10 joins the local area network established by the gateway 20 by connecting to the gateway 20. This local area network includes, but is not limited to: ZIGBEE or Bluetooth. Among them, the smart device 10 can be a smart printer, a smart fax machine, a smart camera, a smart air conditioner, a smart door lock, a smart light, a smart curtain, or a remote control equipped with a communication module, a human body sensor, a door and window sensor, a temperature and humidity sensor, a water immersion sensor, a natural gas alarm, a smoke alarm, a wall switch, a wall socket, a wireless switch, a wireless wall sticker switch, a magic cube controller, a curtain motor and other electronic devices.

[0044] The interaction between the user terminal 50 and the smart device 10 can be achieved through a local area network or a wide area network. In one application scenario, the user terminal 50 establishes a communication connection between the router 30 and the gateway 20 by wired or wireless means, for example, the wired or wireless means include but are not limited to WIFI, so that the user terminal 50 and the gateway 20 are deployed in the same local area network, so that the user terminal 50 can interact with the smart device 10 through the local area network path. In another application scenario, the user terminal 50 establishes a communication connection between the server 40 and the gateway 20 by wired or wireless means, for example, the wired or wireless means include but are not limited to 2G, 3G, 4G, 5G, WIFI, etc., so that the user terminal 50 and the gateway 20 are deployed in the same wide area network, so that the user terminal 50 can interact with the smart device 10 through the wide area network path.

[0045] The server 40 may also be considered as a cloud, a cloud platform, a platform end, a service end, etc. The server 40 may be a single server 40, or a server 40 cluster composed of multiple servers 40, or a cloud computing center composed of multiple servers 40, so as to better provide background services to a large number of user terminals 50. For example, the background service includes a smart device 10 control service.

[0046] In an application scenario, the server 40 or the user terminal 50 obtains the motion data of the target object from the smart device 10, and the target object refers to the object for which the sleep quality assessment is targeted; the server 40 or the user terminal 50 determines the characteristic information of the target behavior during sleep according to the motion data; the server 40 or the user terminal 50 determines the sleep quality according to the characteristic information of the target behavior. If the server 40 performs the above processing, the server 40 can send the determined sleep quality to the user terminal 50 for display. If the user terminal 50 performs the above processing, the user terminal 50 can send the determined sleep quality to the server 40 for storage.

[0047] In such Figure 1A or Figure 1B In the application environment shown, a sleep quality assessment method provided by the embodiment of the present application can be used to accurately identify the real action / behavior of the target object, and then perform sleep quality assessment based on the extracted feature information. Figure 2 As shown, the sleep quality assessment method includes the following processes.

[0048] S100: Acquire motion data reflecting a target object, wherein the target object refers to an object for sleep quality assessment, and specifically, the following description will be made by taking a human body as an example.

[0049] The motion data originates from multiple devices in the same time and space. In other words, in S100, motion data reflecting the human body can be obtained through multiple devices in the same time and space. The motion data includes motion information and time information.

[0050] Exemplarily, the motion data includes the motion type of the human body (i.e., motion information) and the time when the motion occurs (i.e., time information). The motion type of the human body may be turning over, rolling, standing, sitting down, operating a device (e.g., turning on the air conditioner, opening the window, turning off the light), etc.

[0051] Exemplarily, the action data includes the action generated by the human body (i.e., action information) - the time when the action occurs. In this example, the type of the human body's action is not distinguished, and only the fact that "the human body generates an action" is recorded. For example, "1" represents the human body generating an action, and the action data can be presented or recorded as follows: 1-time 1; 1-time 2; 1-time 3... Those skilled in the art should understand that in the above two examples, the latter example can be further obtained from the former example, or the latter example can be directly obtained, which will not be elaborated.

[0052] Reference Figure 1AAs shown, multiple devices in the same time and space can be understood as multiple devices in the same time and space as the human body. The multiple devices can be multiple controlled devices or multiple monitoring devices. In order to fully obtain the motion data of the human body, the controlled devices and monitoring devices can be used at the same time to obtain the motion data.

[0053] S102: Determine characteristic information of a target behavior during sleep according to the motion data. The target behavior is at least one of normal behavior and abnormal behavior. The characteristic information of the target behavior includes at least one of characteristic information of normal behavior and characteristic information of abnormal behavior. For example, the normal behavior may be a sleep behavior, and the abnormal behavior may be a night waking behavior.

[0054] S104: Determine the sleep quality according to the characteristic information of the target behavior.

[0055] The sleep quality assessment method provided in this embodiment, on the one hand, obtains motion data reflecting the target object from multiple devices in the same time and space, and the motion data includes motion information and time information, so that more comprehensive data including motion information and time information can be obtained based on multi-source data, providing an objective and comprehensive data basis for subsequent sleep quality assessment; on the other hand, characteristic information of the target behavior during sleep is determined according to the motion data, and the characteristic information of the target behavior includes at least one of characteristic information of normal behavior and characteristic information of abnormal behavior, so that the target behavior of the target object can be analyzed based on the aforementioned objective and comprehensive data to obtain characteristic information that objectively reflects the characteristics of the target behavior, which is conducive to accurately identifying the real motion / behavior of the target object (for example, the human body); finally, the sleep quality is determined according to the characteristic information of the target behavior, so that accurate and reliable sleep quality assessment results can be obtained.

[0056] In an embodiment of the present application, in S100, the action data reflecting the target object may be acquired in the following manner.

[0057] Method 1: Acquire first action data reflecting the target object from a controlled device, wherein the controlled device includes a device operated by a user, and the first action data includes data of the user operating the controlled device. As mentioned above, the controlled device includes at least one of ventilation equipment, shading equipment, air handling equipment, lighting equipment, and switch equipment, all of which are smart home products. For example, the controlled device includes lighting equipment and / or switch equipment. Through these smart home products, relevant data of user operations on them can be obtained. A simple data form is: time-specific action. For example, 8 o'clock at night-turn on the air conditioner. A more concise data form is: time-action occurs. For example, 8 o'clock at night-there is an action.

[0058] Method 2: Acquire the second motion data reflecting the target object from the monitoring device, the monitoring device includes a device for observing user behavior, and the second motion data includes data reflecting the user's own motion. As mentioned above, the monitoring device can be a device capable of detecting or monitoring human motion, including at least one of a human sensor, an infrared camera, a smart bracelet, a smart watch, and a smart pillow. For example, the monitoring device is set to a human sensor.

[0059] By adopting this embodiment, method one and / or method two can be used to obtain as comprehensive data as possible from multiple devices, providing a multi-dimensional data foundation for subsequent accurate analysis of the behavior of the target object.

[0060] In a specific application of this embodiment, in order to implement the above process S100, the following process is performed.

[0061] (1) First, build the following hardware environment: configure smart devices in the user's bedroom, including controlled devices and monitoring devices. Among them, controlled devices refer to devices that are operated or controlled by users, including at least one of smart home products such as ventilation equipment (for example, smart doors and windows containing door and window sensors), shading equipment (for example, smart curtains), air handling equipment (for example, air conditioners), lighting equipment (for example, smart lamps) and switch equipment (for example, smart physical switches, wireless switches, etc.). For example, the controlled device is a lighting device and / or a switch device. Monitoring equipment refers to equipment that monitors the target object. It includes at least one of a human body sensor that detects human body movements, an infrared camera, a wearable device (for example, a watch), and a smart sleep pillow. For example, the monitoring device is a human body sensor. These smart devices can be connected wirelessly to establish a smart home system, and detailed user movement data can be collected through these smart devices. Controlled devices are devices that are operated or controlled by the target object. For example, smart home products such as ventilation equipment (e.g., smart doors and windows with door and window sensors), shading equipment (e.g., smart curtains), air handling equipment (e.g., air conditioners), lighting equipment (e.g., smart lamps), and switch equipment (e.g., smart physical switches, wireless switches, etc.), or terminal 001 can also be a smart phone, tablet, etc. operated by a user. Terminal 002 can be a monitoring device, that is,

[0062] (2) Determine the room attributes and filter out rooms with bedroom attributes (the sleeping location is not necessarily the bedroom, it may also be the sofa in the living room or the balcony, which can be summarized as: filter out all sleeping rooms). Specifically, first, based on the room bedroom attribute parameters set by the user, filter out all rooms (collectively referred to as bedrooms) that need to count sleep characteristics, and achieve accurate calculation and push of sleep characteristic data.

[0063] (3) Complete the first labeling based on the configuration of smart devices in the bedroom. If necessary, remind the user that they are missing essential equipment. Specifically, in this specific application, in order to collect key data on the user's daily routine, there must be a human body sensor in the bedroom. In addition, in order to ensure the comprehensiveness of the data, at least one of a light or a switch is required. There is no mandatory requirement for the other four types of equipment. According to the device information table, check whether the bedroom is equipped with these three types of essential equipment. Label the bedrooms as follows for different configurations to accurately inform the user which type of essential equipment is missing, and remind the user to add this type of equipment in time, for example, labeling in the following way:

[0064] ① Mark 11 (used to remind users that there are no human sensor devices in the bedroom, but there are switch devices and lighting devices);

[0065] ② Mark 12 (used to remind users that there are no human sensor devices and switch devices in the bedroom, but there are lighting devices);

[0066] ③ Mark 13 (used to remind users that there are no human sensor devices and no lighting devices in the bedroom, but there are switch devices);

[0067] ④ Mark 14 (used to remind users that there are no human sensor devices, switch devices, or lighting devices in the bedroom);

[0068] ⑤ Mark 15 (used to remind users that there are no switch devices and no lighting devices in the bedroom, but there are human body sensor devices);

[0069] ⑥ Mark 16 (used to remind users that there are human body sensor devices, switch devices or lighting devices in the bedroom).

[0070] It is understandable that users can modify and adjust the marking content and reminder content according to their needs.

[0071] (4) Complete the second labeling based on the number of smart device trigger data. If necessary, remind the user that the number of device triggers is too small. Specifically, based on the long-term statistical results of a large number of user sleep habit data, the number of triggers of 7 types of devices (physical switches, wireless switches, curtains, human body sensors, door and window sensors, air conditioners, and lights) in the bedroom from 20:00 yesterday to 10:00 today is counted by default. According to the experience of users' daily routines and algorithm model training sleep data, in this application, 2 types of necessary devices (human body sensors, lights or switches) must all be triggered, that is, the human body sensor and the light are triggered, or the human body sensor and the switch are triggered, or the human body sensor, the light and the switch are all triggered, and the total number of triggers of the 7 types of devices must be at least more than 10 times, which is conducive to training complete and reliable sleep results.

[0072] Therefore, based on the number of times the 7 types of devices are triggered, the bedroom labeled "16" in (3) is marked a second time. The purpose is to inform the user that the reason for no sleep results is that no device is triggered or the number of device triggers is too small. Remind the user that if they want to get sleep results, there must be a sufficient number of device triggers that can represent the user's work and rest. At the same time, remind the user to promptly confirm whether each type of device is in normal working condition. Regarding the above 7 types of devices, focus on the following trigger situations:

[0073] ① Mark 21: None of the 7 types of equipment are triggered;

[0074] ② Mark 22: All the 2 types of essential equipment have triggers, but the total number of triggers for the 7 types of equipment does not exceed 10;

[0075] ③ Mark 23: All the 2 types of essential equipment are not triggered, or the total number of triggering of 7 types of equipment does not exceed 10 times;

[0076] ④ Mark 24: All 2 types of essential equipment are triggered, and the total number of triggers for 7 types of equipment exceeds 10.

[0077] Among them, human body sensor equipment must be included in the two essential equipment categories.

[0078] At this point, based on this specific application, action data reflecting the target object can be obtained.

[0079] In one embodiment of the present application, in S102, if Figure 3 As shown, characteristic information of target behavior during sleep can be determined in the following manner.

[0080] S200: Determine the distribution pattern of the action according to the action data of the target object.

[0081] Among them, optionally, since the action data contains action information and time information, the distribution law of the action may include the time distribution law of the action. For example, the interval time between two adjacent actions, the duration of a continuous action (actions occurring within a set time interval can be defined as continuous actions), the start time and end time of a continuous action, etc. Alternatively, since the action data can originate from multiple devices, the distribution law of the action may also include the device distribution law of the action. For example, the number of times a human body sensor detects human body movements, the number of times a human body operates a physical switch, the number of times a human body operates an air conditioner, etc. Exemplarily, you can refer to Figure 5A As well as the related explanations below, I will not go into details here.

[0082] S202: Determine characteristic information of a target behavior according to a first behavior prediction model that takes the distribution law of the action as input, wherein the first behavior prediction model takes the distribution law of the action as input and takes the characteristic information of the target behavior as output.

[0083] Optionally, the target behavior includes at least one of normal behavior and abnormal behavior. Normal behavior refers to behavior that maintains a normal sleep rhythm, such as sleep behavior itself; abnormal behavior refers to behavior that interrupts or is not conducive to a normal sleep rhythm, such as waking up at night. The characteristic information of the target behavior can adaptively select at least one of the following: the start time, end time, duration, number of times, etc. of the target behavior.

[0084] In this embodiment, the distribution law of the action is determined according to the action data of the target object, and then the distribution law of the action is analyzed using the behavior prediction model to obtain the characteristic information of the target behavior. The entire processing process can be abstracted as: action data → distribution law of action → characteristic information of target behavior. This processing process extracts and analyzes the distribution law of the action to obtain characteristic information that objectively reflects the real behavior of the target object, thereby ensuring the reliability of subsequent sleep quality assessment.

[0085] In a specific implementation, the first behavior prediction model can be a model obtained by training the distribution law of actions based on a Python algorithm model.

[0086] Optionally, in one embodiment of the present application, in S102, as Figure 4 As shown, characteristic information of target behavior during sleep can be determined in the following manner.

[0087] S200: Analyze the motion data of the target object to obtain the distribution law of the motion.

[0088] Among them, optionally, since the action data contains action information and time information, the distribution law of the action may include the time distribution law of the action. For example, the interval time between two adjacent actions, the duration of a continuous action (actions occurring within a set time interval can be defined as continuous actions), the start time and end time of a continuous action, etc. Alternatively, since the action data can originate from multiple devices, the distribution law of the action may also include the device distribution law of the action. For example, the number of times a human body sensor detects human body movements, the number of times a human body operates a physical switch, the number of times a human body operates an air conditioner, etc. Exemplarily, you can refer to Figure 5A As well as the related explanations below, I will not go into details here.

[0089] S302: Determine the time information of the target behavior according to the second behavior prediction model which takes the distribution law of the action as input, wherein the second behavior prediction model takes the distribution law of the action as input and takes the time information of the target behavior as output.

[0090] Wherein, illustratively, the time information of the target behavior includes at least one of the time information of normal behavior and the time information of abnormal behavior. The time information of normal behavior includes the start time and the end time of normal behavior. The time information of abnormal behavior includes the start time and the end time of abnormal behavior.

[0091] S304: Determine characteristic information of the target behavior according to the time information of the target behavior.

[0092] For example: taking the start time of normal behavior as one of the characteristic information of normal behavior; determining the duration of normal behavior based on the start time and end time of normal behavior as one of the characteristic information of normal behavior; determining the duration of abnormal behavior based on the start time and end time of abnormal behavior as one of the characteristic information of abnormal behavior; determining the number of abnormal behaviors based on the number of at least one of the start time and end time of abnormal behavior as one of the characteristic information of abnormal behavior.

[0093] In this embodiment, the distribution law of the action is determined according to the action data of the target object, and then the distribution law of the action is analyzed using the behavior prediction model to obtain the time information of the target behavior, and finally the characteristic information of the target behavior is determined according to the time information of the target behavior. The entire processing process can be abstracted as: action data → distribution law of the action → time information of the target behavior → characteristic information of the target behavior. This processing process obtains the time information of the target behavior by analyzing and mining the distribution law of the action, and then obtains the characteristic information that objectively reflects the real behavior of the target object based on the time information of the target behavior, thereby ensuring the reliability of the subsequent sleep quality assessment.

[0094] In a specific implementation, the second behavior prediction model can be a model obtained by training the distribution law of actions based on a Python algorithm model.

[0095] Optionally, in Figure 3 and Figure 4 In one implementation of the embodiment shown, as Figure 5A As shown, the distribution law of actions includes the time distribution law of actions.

[0096] In these implementations, S200 includes obtaining the time distribution law of the action in the following manner: according to the action data, adjacent actions whose time intervals do not exceed the target time length are divided into the same non-silent time period, thereby obtaining multiple non-silent time periods, and obtaining the start time and end time of each non-silent time period. The time distribution law of the action includes: multiple non-silent time periods, and the start time and end time of each non-silent time period.

[0097] Exemplarily, the time distribution rule of the action also includes any one or more of the following: the duration of each non-silent time period, the first interval time between each non-silent time period and the previous non-silent time period, and the second interval time between each non-silent time period and the next non-silent time period.

[0098] More specifically, refer to Figure 5A As shown, the time distribution rule of the action may include at least "non-silent period start time" and "non-silent period end time". In addition, it may also include one or more of "non-silent period duration", "interval with the previous non-silent period", and "interval with the next non-silent period".

[0099] In this implementation, the temporal distribution of the above-mentioned actions can objectively reflect the real actions of the human body, which is conducive to obtaining the real behavior of the user based on the real action analysis of the human body. Figure 5A As shown, the distribution law of the action also includes the device distribution law of the action. At this time, S200 can obtain the device distribution law of the action in the following way: count the number of actions corresponding to each device in multiple devices in each non-silent time period to obtain the device distribution law of the action.

[0100] For example, refer to Figure 5A As shown, the distribution pattern of actions may include the number of times the human body sensor detects human body movements (2, 3, 42, 3, 3, 9), the number of times the human body operates the physical switch (2, 2, 7, 5, 4, 10), the number of times the human body operates other controlled devices, and the correspondence between these numbers and non-silent periods.

[0101] In this implementation, by combining the time distribution law and device distribution law of the above-mentioned actions, the real actions of the human body can be reflected more objectively based on multi-dimensional data, which is conducive to obtaining the real behavior of the user based on the real action analysis of the human body.

[0102] exist Figure 3 In a specific application of the illustrated embodiment, in order to implement S200 and S202 , the following method may be used.

[0103] First, the trigger data of the 7 types of devices mentioned above are regularized, and all trigger operations with a trigger time interval of no more than 15 minutes are merged into one non-silent period, and key information such as the number of triggers of the 7 types of devices in each non-silent period, start time, end time, duration, and time interval with adjacent non-silent periods are counted. That is, based on this, the time distribution law of the action and the device distribution law of the action are obtained.

[0104] Then, the non-silent period data is processed by, for example, a Python algorithm model to obtain the sleep result. Figure 5A Only with complete work and rest routine data can we train the following Figure 5B The effective sleep results shown include sleep start time, sleep end time, sleep duration, night wake-up time or night wake-up times (not shown), etc. Figure 5B In contrast, Figure 5C The so-called work and rest regularity means that no matter whether the user goes to bed early or late, the user has at least a long period of sleep, that is, a quiet period, such as Figure 5A 21:09-21:12, 21:56-22:01, 22:48-23:19, 23:44-23:49 are active, 05:23-05:28 get up at night, 06:58-07:13 get up, 23:49-06:58 is the complete sleep period. In sharp contrast, Figure 5C These are all short non-silent periods. The longest silent period is 23:59-00:54, which is a total of 55 minutes. It is impossible for a user to move all night and sleep for only 55 minutes, so it is impossible to predict the sleep results. Figure 5C The data shown can be obtained as follows Figure 5D In the invalid sleep results shown, the sleep start time, sleep end time, sleep duration, and nighttime waking time are all unpredictable.

[0105] Afterwards, the bedroom labeled “24” in (4) above can be labeled for the third time according to the sleep results output by the algorithm model (i.e., the characteristic information of the target behavior), as follows:

[0106] ① Mark 31: The data during non-quiet periods do not have a regular work and rest pattern, and effective sleep results cannot be obtained;

[0107] ② Mark 32: The data during non-quiet periods have a regular work and rest schedule, and effective sleep results are obtained.

[0108] In this specific application, the characteristic information of the target behavior is directly determined based on the behavior prediction model. Figure 4 In the specific implementation of the embodiment shown, the time information of the target behavior, such as the start time of sleep, the end time of sleep, and the time of getting up at night, can also be obtained according to the behavior prediction model. Then, the characteristic information of the target behavior is determined according to the time information of the target behavior. This will not be described in detail.

[0109] In one embodiment of the present application, in S102, as Figure 6 As shown, characteristic information of target behavior during sleep can be determined in the following manner.

[0110] S500: Determine time information of a target behavior during sleep according to the motion data.

[0111] S502: Determine characteristic information of the target behavior according to time information of the target behavior.

[0112] Optionally, S500 can be implemented in the following manner: determine the time difference between two adjacent actions according to the time information of two adjacent actions in the action data; determine the behavior composed of two adjacent actions whose time difference meets the first duration requirement as normal behavior, and determine the time corresponding to the two adjacent actions as the time information of normal behavior, and / or, determine the behavior composed of two adjacent actions whose time difference meets the second duration requirement as abnormal behavior, and determine the time corresponding to the two adjacent actions as the time information of abnormal behavior, wherein the first duration is greater than the second duration, and the abnormal behavior occurs between two normal behaviors. This implementation method fully considers the action characteristics of normal behavior and abnormal behavior, and accurately determines the real behavior of the target object by analyzing the time corresponding to two adjacent actions. In other words, this embodiment does not necessarily rely on the algorithm model, but can determine the characteristic information of the target behavior through data analysis.

[0113] Exemplarily, the first duration requirement may be "greater than 80 minutes". That is, if the time interval between adjacent actions 1 and 2 is greater than 80 minutes, it is determined that actions 1 and 2 constitute normal behavior A (for example, sleep behavior A), the time of action 1 is the start time of normal behavior A, and the time of action 2 is the end time of normal behavior A. The second duration requirement may be "less than 10 minutes". That is, if it is to be determined as abnormal behavior (for example, waking up at night), the interval between two adjacent actions needs to be less than 10 minutes. Those skilled in the art should understand that the first duration requirement and the second duration requirement can be set as needed or based on experience, and this application does not limit their specific values.

[0114] More specifically, refer to Figure 5A and 5B, the end time of the non-silent period "6.19 23:49" corresponds to action 1, and the start time of the non-silent period "6.20 5:23" corresponds to action 2; the end time of the non-silent period "6.205:28" corresponds to action 3, the start time of the non-silent period "6.20 6:58" corresponds to action 4, and the end time of the non-silent period "6.20 7:13" corresponds to action 5. Since the interval between action 1 and action 2 is 334 minutes, and the interval between action 3 and action 4 is 90 minutes, both meet the first duration requirement, so action 1 and action 2 form the first sleep behavior A, and action 3 and action 4 form the second sleep behavior B; since the interval between action 2 and action 3 is 5 minutes, which meets the second duration requirement, and the behavior composed of action 2 and action 3 is between the first sleep behavior A and the second sleep behavior B, so action 2 and action 3 form the night-time behavior.

[0115] In general, the complete sleep behavior includes the first sleep behavior A and the second sleep behavior B. The start time of the sleep behavior is the time corresponding to action 1, and the end time of the sleep behavior is the time corresponding to action 4; the start time of the night-time behavior is the time corresponding to action 2, and the end time of the night-time behavior is the time corresponding to action 3. In one example, the sleep duration can be based on the time difference between action 4 and action 1. In another example, the sleep duration can be obtained by subtracting the duration of the night-time behavior from the time difference between action 4 and action 1.

[0116] From another perspective, the complete sleep behavior can also be understood as including the first sleep behavior A, the behavior of getting up at night, and the second sleep behavior B. This does not affect the confirmation of the start time and end time of the complete sleep behavior. In one example, the sleep duration can be based on the time difference between action 4 and action 1. In another example, the sleep duration can be obtained by subtracting the duration of the behavior of getting up at night from the time difference between action 4 and action 1.

[0117] In other examples, there may be multiple waking up behaviors, and correspondingly, the sleep behavior may include multiple sleep behaviors, such as the aforementioned first sleep behavior A and the second sleep behavior B. In other examples, there may be 0 waking up behaviors, and correspondingly, the sleep behavior has only one sleep behavior. Optionally, the time information of the target behavior includes at least one of the time information of normal behavior and the time information of abnormal behavior; the time information of normal behavior includes the start time and the end time of normal behavior; the time information of abnormal behavior includes the start time and the end time of abnormal behavior.

[0118] Furthermore, S502 may include at least one of the following processing methods:

[0119] The start time of the normal behavior is used as one of the characteristic information of the normal behavior;

[0120] According to the start time and end time of the normal behavior, the duration of the normal behavior is determined as one of the characteristic information of the normal behavior;

[0121] According to the start time and end time of the abnormal behavior, the duration of the abnormal behavior is determined as one of the characteristic information of the abnormal behavior;

[0122] The number of times of the abnormal behavior is determined according to the number of at least one of the start time and the end time of the abnormal behavior, as one of the characteristic information of the abnormal behavior.

[0123] So far, combined with Figure 2-Figure 6 , an exemplary explanation is given on how to determine the characteristic information of target behavior during sleep based on motion data.

[0124] Figure 7 FIG. 1 is a flow chart of a method for determining sleep quality based on characteristic information of a target behavior according to an embodiment of the present application. Figure 7 , including the following processing.

[0125] S600: Determine a single score for each item of feature information according to a scoring strategy corresponding to each item of feature information in the feature information of the target behavior.

[0126] S602: Perform weighted calculation based on the individual scores of each feature information to obtain a total score representing the sleep quality.

[0127] In this embodiment, since each feature information has a corresponding scoring strategy according to its impact on sleep quality, a single score for each feature information can be achieved based on a single feature information, and the granularity of the score is more detailed. Furthermore, by weighted calculation of a single score for a feature information, the single scores of all feature information can be combined to obtain a total score that objectively expresses sleep quality, thereby improving the objectivity and reliability of sleep quality assessment.

[0128] Optionally, in this embodiment, in the scoring strategy, the closer the characteristic information of normal behavior is to the target value (or ideal value, which can be set manually), the higher the single score of the characteristic information of normal behavior is, and the greater the abnormal degree of abnormal behavior represented by the characteristic information of abnormal behavior is, the lower the single score of the characteristic information of abnormal behavior is. Such a scoring strategy can fully reflect the favorable effects of normal behavior on sleep quality and the unfavorable effects of abnormal behavior on sleep quality, which conforms to objective laws and natural laws of the human body, and is conducive to ensuring the reliability and objectivity of the scoring results.

[0129] In this embodiment, exemplarily, the scoring strategy corresponding to each feature information includes at least one of the following.

[0130] The characteristic information of normal behavior includes the start time of sleep behavior (or sleep start time). The scoring strategy for the start time of sleep behavior includes: determining the corresponding single score according to the time period to which the start time of sleep behavior belongs and the difference with the benchmark time in the time period to which it belongs. Among them, the closer the start time of sleep behavior is to the target time period, or the greater the difference between the start time of sleep behavior and the benchmark time in the time period to which it belongs, the greater the corresponding single score. In the scoring strategy for the characteristic information of sleep start time, the impact of starting sleep in different time periods on sleep quality is fully and carefully considered, the granularity of sleep quality assessment is further refined, and the scoring method is more scientific.

[0131] The characteristic information of normal behavior includes the duration of sleep behavior (or sleep duration). The scoring strategy for the duration of sleep behavior is: determine the corresponding single score according to the difference between the duration of sleep behavior and the target duration. Among them, the closer the duration of sleep behavior is to the target duration, the greater the corresponding single score. In the scoring strategy for the characteristic information of sleep duration, the sleep duration is not purely considered, but the sleep duration is compared with the target duration, so that the scoring result is more in line with the natural law of human sleep, and the scoring method is more scientific.

[0132] The characteristic information of abnormal behavior includes the number of times of getting up at night (or the number of times of getting up at night). The scoring strategy for the number of times of getting up at night is: determine the corresponding single score according to the number of times of getting up at night. Among them, the greater the number of times of getting up at night, the smaller the corresponding single score. In the scoring strategy for the characteristic information of the number of times of getting up at night, the adverse effects of the number of times of getting up at night on sleep quality are fully considered, making the scoring results more scientific.

[0133] The characteristic information of abnormal behavior includes the duration of getting up at night. The scoring strategy for the duration of getting up at night is: determine the corresponding single score according to the duration of getting up at night. Among them, the longer the duration of getting up at night, the smaller the corresponding single score. In the scoring strategy for the characteristic information of the duration of getting up at night, the adverse effects of the duration of getting up at night on sleep quality are fully considered, making the scoring results more scientific.

[0134] Optionally, in S602 of this embodiment, the total score is calculated using the following formula: s=s1·a1+s2·a2+s3·a3…+sn·an.

[0135] Among them, n is a positive integer, indicating the number of feature information items, s1 to sn respectively represent the individual scores of the 1st to nth feature information items, a1 to an respectively represent the weights of the 1st to nth feature information items, s represents the total score, a1+a2+a3+…+an=1.

[0136] Among them, when the characteristic information of the target behavior includes the characteristic information of normal behavior and the characteristic information of abnormal behavior, and the characteristic information of normal behavior includes the start time s3 of the sleep behavior and the duration s1 of the sleep behavior, and the characteristic information of abnormal behavior includes the number of times s2 of getting up at night, a1 > a2 > a3. Exemplarily, a1 = 50%, a2 = 30%, a3 = 20%.

[0137] In a specific application of this embodiment, the sleep score and labeling are completed based on the sleep scoring criteria, intuitively displaying the sleep quality score and providing sleep suggestions. Specifically, according to the authoritative international scientific sleep standard, combining the three parameters of sleep duration d, sleep start time st, and the number of times of getting up at night w in the effective sleep result of the bedroom with the "label 32" in the previous text, combining Figure 5A In room_111, the sleep duration is 7.1h, the sleep start time is 23:49, and the getting up time is [05:23, 05:28]. The corresponding parameters are d = 7.1, st = 23.49, w = 1. The following sleep scoring criteria are formulated:

[0138] ① Sleep duration score, that is, the scoring strategy corresponding to the characteristic information of sleep duration is:

[0139] s1 = 100 - |8 - d| * 10. Among them, d represents the sleep duration, and 8 represents the target duration (or target value) of the sleep duration. The closer the sleep duration is to the target duration, the larger the single score S1 corresponding to the sleep duration.

[0140] ② Number of times of getting up at night score, that is, the scoring strategy corresponding to the characteristic information of the number of times of getting up at night is:

[0141] s2 = 100 - w * 10; where w represents the number of times of getting up at night. The more times of getting up at night, the smaller the single score S2 corresponding.

[0142] ③ Sleep start time score, that is, the scoring strategy corresponding to the characteristic information of the sleep start time is

[0143] 1) When 20 ≤ st < 24, s3 = 100 - |22 - st| * 10;

[0144] 2) When 0 ≤ st ≤ 1, s3 = 70 + (1 - st) * 10;

[0145] 3) When 1 < st ≤ 2, s3 = 50 + (2 - st) * 10;

[0146] 4) When 2 < st ≤ 3, s3 = 40 + (3 - st) * 10;

[0147] 5) When st > 3, s3 = 40;

[0148] Different sleep start time periods have different corresponding sleep start time score calculation formulas. Among them, st represents the sleep start time, and 1) to 5) represent the scoring methods in 5 different time periods respectively. According to 1) to 5), it can be found that it is necessary to determine the single score corresponding to the sleep start time according to the time period to which the sleep start time belongs, based on the difference between the sleep start time and the reference time in the time period to which it belongs. Referring to 1) to 5), for example, when 20≤st<24, the reference time is 22, and when 0≤st≤1, the reference time is 1.

[0149] ④ Sleep score s = s1*50% + s2*30% + s3*20%. Based on this, the total score of sleep quality can be obtained.

[0150] Finally, mark the sleep score results and give sleep suggestions:

[0151] ① Excellent (85-100 points); Sleep advice: The sleep quality is very good, please keep it up!

[0152] ②Good (60-85 points); Sleep advice: The sleep is slightly insufficient, it is recommended to go to bed early!

[0153] ③ Poor (0-60 points); Sleep advice: Severe lack of sleep, please pay attention to sleep health!

[0154] The above is a detailed description of a sleep quality assessment method or its steps according to an embodiment of the present application. The present application also provides a sleep quality assessment device, such as Figure 8 As shown, the sleep quality assessment device includes a motion data acquisition module 70, a feature information determination module 72 and a sleep quality assessment module 74. The details are described below.

[0155] In this embodiment, the motion data acquisition module 70 is used to acquire motion data reflecting the target object. The motion data originates from multiple devices in the same time and space, and the motion data includes motion information and time information.

[0156] The characteristic information determination module 72 is used to determine characteristic information of a target behavior during sleep according to the motion data, where the characteristic information of the target behavior includes at least one of characteristic information of a normal behavior and characteristic information of an abnormal behavior.

[0157] The sleep quality assessment module 74 is used to determine the sleep quality according to the characteristic information of the target behavior.

[0158] In various implementations of this embodiment, for a detailed description of the action data acquisition module 70, please refer to the description of S100 in the above method embodiment; for a detailed description of the feature information determination module 72, please refer to the description of S102, S200-S202 ( Figure 3 )、S200-S304( Figure 4 )、S500-S502( Figure 6 ) description; For a detailed description of the sleep quality assessment module 74, please refer to the above method embodiment for S104, S600-S602 ( Figure 7 ) is described in detail here and will not be repeated again.

[0159] The sleep quality assessment device provided in this embodiment, on the one hand, obtains motion data reflecting the target object from multiple devices in the same time and space, and the motion data includes motion information and time information, so that more comprehensive data including motion information and time information can be obtained based on multi-source data, providing an objective and comprehensive data basis for subsequent sleep quality assessment; on the other hand, characteristic information of the target behavior during sleep is determined according to the motion data, and the characteristic information of the target behavior includes at least one of characteristic information of normal behavior and characteristic information of abnormal behavior, so that the target behavior of the target object can be analyzed based on the aforementioned objective and comprehensive data to obtain characteristic information that objectively reflects the characteristics of the target behavior, which is conducive to accurately identifying the real motion / behavior of the target object (for example, the human body); finally, the sleep quality is determined according to the characteristic information of the target behavior, so that accurate and reliable sleep quality assessment results can be obtained.

[0160] An embodiment of the present application also provides an electronic device, including a memory and a processor, wherein the memory stores computer instructions, and the processor is used to implement the above-mentioned sleep quality assessment method when executing the computer instructions.

[0161] Specifically, Fig. 9 As shown, the electronic device includes a processor 80, at least one communication bus 82, a user interface 83, at least one external communication interface 84 and a memory 85. The communication bus 82 is configured to realize connection and communication between these components. The user interface 83 may include a display screen, and the external communication interface 84 may include a standard wired interface and a wireless interface. The memory 85 stores a sleep quality assessment method. The processor 80 is used to adopt the above method when executing the sleep quality assessment method stored in the memory 85.

[0162] An embodiment of the present application also provides a computer-readable storage medium storing a computer program that can be loaded by a processor and execute the above sleep quality assessment method.

[0163] The embodiment of the present application also provides a computer program product, which includes computer instructions. When the computer instructions are executed by a computer or a processor, the steps of the above sleep quality assessment method are executed.

[0164] The above descriptions of the electronic device, computer-readable storage medium, and computer program product embodiments are similar to the descriptions of the above method embodiments, and have similar beneficial effects as the method embodiments. For technical details not disclosed in the electronic device and storage medium embodiments of the present application, please refer to the descriptions of the method embodiments of the present application for understanding.

[0165] Overall, this application realizes sleep quality assessment based on big data analysis of smart devices. It can accurately assess the user's sleep quality through smart device configuration analysis, device log data analysis, algorithm model training, and sleep quality scoring, and provide personalized sleep suggestions to help users improve their sleep quality and improve their quality of life.

[0166] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0167] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0168] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, 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 interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0169] 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 units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0170] 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.

[0171] 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 storage medium. Based on this understanding, the technical solution of the present application, in essence, 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, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0172] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for evaluating sleep quality, characterized in that: The method comprises: Acquire action data reflecting a target object, the action data originating from a plurality of devices in the same time and space, the action data including action information and time information; determining characteristic information of a target behavior during sleep according to the motion data, wherein the characteristic information of the target behavior includes at least one of characteristic information of normal behavior and characteristic information of abnormal behavior; The sleep quality is determined according to the characteristic information of the target behavior.

2. The sleep quality assessment method according to claim 1, characterized in that: The obtaining of action data reflecting the target object includes: Acquiring first action data reflecting a target object from a controlled device, wherein the controlled device includes a device operated by a user, and the first action data includes data of the user operating the controlled device; and / or, Second action data reflecting the target object is acquired from a monitoring device, wherein the monitoring device includes a device for observing user behavior, and the second action data includes data reflecting the user's own actions.

3. The sleep quality assessment method according to claim 2, characterized in that: The controlled equipment includes at least one of ventilation equipment, shading equipment, air handling equipment, lighting equipment and switch equipment, Or, the controlled device includes at least one of a lighting device and a switch device; The monitoring device includes at least one of a human body sensor and an infrared camera.

4. The sleep quality assessment method according to claim 1, characterized in that: The determining characteristic information of the target behavior during sleep according to the motion data includes: Determining a distribution law of actions according to the action data; The characteristic information of the target behavior is determined according to a first behavior prediction model that takes the distribution law of the action as input, wherein the first behavior prediction model takes the distribution law of the action as input and takes the characteristic information of the target behavior as output.

5. The sleep quality assessment method according to claim 1, characterized in that: The determining characteristic information of the target behavior during sleep according to the motion data includes: Obtaining a distribution law of actions according to the action data analysis; determining the time information of the target behavior according to a second behavior prediction model that takes the distribution law of the action as input, wherein the second behavior prediction model takes the distribution law of the action as input and takes the time information of the target behavior as output; The characteristic information of the target behavior is determined according to the time information of the target behavior.

6. The sleep quality assessment method according to claim 4 or 5, characterized in that: The distribution law of the actions includes: the time distribution law of the actions; The obtaining of the distribution law of the action according to the action data analysis includes obtaining the time distribution law of the action in the following manner: According to the action data, adjacent actions whose time intervals do not exceed the target time length are divided into the same non-silent time period, thereby obtaining multiple non-silent time periods, and obtaining the start time and end time of each of the non-silent time periods; The time distribution rule of the action includes: the multiple non-silent time periods, and the start time and end time of each of the non-silent time periods.

7. The sleep quality assessment method according to claim 6, characterized in that: The distribution law of the actions also includes: the device distribution law of the actions; The obtaining of the distribution law of the action according to the action data analysis includes obtaining the device distribution law of the action in the following manner: The number of actions corresponding to each device in the multiple devices in each of the non-silent time periods is counted to obtain a device distribution rule of the actions.

8. The sleep quality assessment method according to claim 6, characterized in that: The time distribution rule of the action also includes any one or more of the following: The duration of each non-silent time period, the first interval between each non-silent time period and the previous non-silent time period, and the second interval between each non-silent time period and the next non-silent time period.

9. The sleep quality assessment method according to claim 1, characterized in that: The determining characteristic information of the target behavior during sleep according to the motion data includes: Determining time information of the target behavior during sleep according to the motion data; The characteristic information of the target behavior is determined according to the time information of the target behavior.

10. The method according to claim 9, characterized in that The step of determining the time information of the target behavior during sleep according to the motion data includes: Determine the time difference between two adjacent actions according to the time information of the two adjacent actions in the action data; Determine a behavior consisting of two adjacent actions whose time difference meets the first duration requirement as the normal behavior, determine the time corresponding to the two adjacent actions as the time information of the normal behavior, and / or, A behavior consisting of two adjacent actions whose time difference meets the second duration requirement is determined as the abnormal behavior, and the time corresponding to the two adjacent actions is the time information of the abnormal behavior, wherein the first duration is greater than the second duration, and the abnormal behavior occurs between the two normal behaviors.

11. The sleep quality assessment method according to claim 5, 9 or 10, characterized in that: The time information of the target behavior includes at least one of the time information of the normal behavior and the time information of the abnormal behavior; The time information of the normal behavior includes the start time and the end time of the normal behavior; The time information of the abnormal behavior includes the start time and the end time of the abnormal behavior.

12. The sleep quality assessment method according to claim 11, characterized in that: The determining the characteristic information of the target behavior according to the time information of the target behavior includes at least one of the following: Using the start time of the normal behavior as one of the characteristic information of the normal behavior; Determine, according to the start time and end time of the normal behavior, the duration of the normal behavior as one of the characteristic information of the normal behavior; Determine the duration of the abnormal behavior according to the start time and end time of the abnormal behavior as one of the characteristic information of the abnormal behavior; The number of times of the abnormal behavior is determined according to the number of at least one of the start time and the end time of the abnormal behavior as one of the characteristic information of the abnormal behavior.

13. The sleep quality assessment method according to claim 1, characterized in that: The determining the sleep quality according to the characteristic information of the target behavior includes: Determine a single score for each item of feature information according to a scoring strategy corresponding to each item of feature information in the feature information of the target behavior; A weighted calculation is performed based on the individual scores of each item of feature information to obtain a total score representing the sleep quality.

14. The sleep quality assessment method according to claim 13, characterized in that: The scoring strategy corresponding to each feature information includes at least one of the following: The characteristic information of the normal behavior includes the start time of the sleep behavior, and the scoring strategy of the start time of the sleep behavior includes: determining the corresponding single score according to the time period to which the start time of the sleep behavior belongs and the difference between the start time of the sleep behavior and the reference time in the time period to which it belongs, wherein the closer the start time of the sleep behavior is to the target time period, or the greater the difference between the start time of the sleep behavior and the reference time in the time period to which it belongs, the greater the corresponding single score. The characteristic information of the normal behavior includes the duration of the sleep behavior. The scoring strategy of the duration of the sleep behavior is: determining the corresponding single score according to the difference between the duration of the sleep behavior and the target duration, wherein the closer the duration of the sleep behavior is to the target duration, the larger the corresponding single score is. The characteristic information of the abnormal behavior includes the number of times of getting up at night. The scoring strategy of the number of times of getting up at night is: determining the corresponding single score according to the number of times of getting up at night, wherein the greater the number of times of getting up at night, the smaller the corresponding single score. The characteristic information of the abnormal behavior includes the duration of the behavior of getting up at night. The scoring strategy for the duration of the behavior of getting up at night is: determine the corresponding single score according to the duration of the behavior of getting up at night, wherein the longer the duration of the behavior of getting up at night, the smaller the corresponding single score.

15. The sleep quality assessment method according to claim 13, characterized in that: The weighted calculation is performed based on the individual scores of each feature information to obtain a total score representing the sleep quality, including: The total score is calculated using the following formula: s = s1·a1+s2·a2+s3·a3…+sn·an; Wherein, n is a positive integer, indicating the number of feature information, s1 to sn respectively indicate the individual scores of the 1st to nth feature information, a1 to an respectively indicate the weights of the 1st to nth feature information, and s indicates the total score; Among them, a1+a2+a3+…+an=1; Among them, when the characteristic information of the target behavior includes the characteristic information of the normal behavior and the characteristic information of the abnormal behavior, and the characteristic information of the normal behavior includes the start time s3 of the sleep behavior and the duration s1 of the sleep behavior, and the characteristic information of the abnormal behavior includes the number of times of getting up at night s2, a1>a2>a3.

16. A sleep quality assessment device, characterized in that: The sleep quality assessment device comprises: An action data acquisition module, used to acquire action data reflecting a target object, the action data originating from multiple devices in the same time and space, and the action data including action information and time information; a characteristic information determination module, configured to determine characteristic information of a target behavior during sleep according to the motion data, wherein the characteristic information of the target behavior includes at least one of characteristic information of a normal behavior and characteristic information of an abnormal behavior; The sleep quality assessment module is used to determine the sleep quality according to the characteristic information of the target behavior.

17. An electronic device, characterized in that: The electronic device comprises a memory and a processor, wherein the memory stores computer instructions, and the processor is configured to execute the computer instructions to implement the sleep quality assessment method according to any one of claims 1 to 15.

18. A computer-readable storage medium, characterized in that: A computer program according to any one of claims 1 to 15 is stored and can be loaded and executed by a processor.

19. A computer program product, characterized in that The computer program product comprises computer instructions, which, when executed by a computer or a processor, cause the steps of the method according to any one of claims 1 to 15 to be performed.

Images