User fall warning method, device, equipment and storage medium

Abstract

The embodiment of the present invention discloses a user fall warning method, device, equipment and storage medium, the method comprising: obtaining a current monitoring image of a user; determining the current posture category of the user according to a preset posture classification network model and the current monitoring image; if the current posture category is a fall category, determining the target fall threshold information corresponding to the user based on the physiological parameter information of the user; detecting whether the user meets the preset fall warning condition according to the target fall threshold information and the target probability value corresponding to the current posture category; if the preset fall warning condition is met, generating the fall warning information corresponding to the user. Through the technical solution of the embodiment of the present invention, the accuracy of the user fall warning can be improved.

Description

Technical Field

[0001] The embodiments of the present invention relate to computer technology, and more particularly to a method, device, equipment and storage medium for early warning of a user falling. Background Art

[0002] With the rapid development of computer technology, it is possible to monitor whether a user has fallen, so as to provide a timely warning of a fall and avoid endangering life. For example, providing a warning of a fall for an elderly user is an important guarantee for the safety of the elderly in a home environment.

[0003] At present, fall warning is usually carried out when the user falls based on the user's posture information. However, since different users have different physical conditions, different abilities to deal with falls, and different urgency of fall warning, the fall warning method based only on the user's posture information may lead to misjudgment of fall warning, thus reducing the accuracy of fall warning. Summary of the invention

[0004] Embodiments of the present invention provide a method, device, equipment and storage medium for early warning of a user falling, so as to improve the accuracy of early warning of a user falling.

[0005] In a first aspect, an embodiment of the present invention provides a user fall warning method, comprising:

[0006] Get the user's current monitoring image;

[0007] Determining the current posture category of the user according to a preset posture classification network model and the current monitoring image;

[0008] If the current posture category is a fall category, determining target fall threshold information corresponding to the user based on the physiological parameter information of the user;

[0009] Detecting whether the user meets a preset fall warning condition according to the target fall threshold information and the target probability value corresponding to the current posture category;

[0010] If the preset fall warning condition is met, fall warning information corresponding to the user is generated.

[0011] In a second aspect, an embodiment of the present invention further provides a user fall warning device, comprising:

[0012] The current monitoring image acquisition module is used to obtain the current monitoring image of the user;

[0013] A current posture category determination module, used to determine the current posture category of the user according to a preset posture classification network model and the current monitoring image;

[0014] a target fall threshold information determination module, configured to determine the target fall threshold information corresponding to the user based on the physiological parameter information of the user if the current posture category is a fall category;

[0015] A fall warning detection module, used to detect whether the user meets a preset fall warning condition according to the target fall threshold information and the target probability value corresponding to the current posture category;

[0016] The fall warning information generating module is used to generate the fall warning information corresponding to the user if the preset fall warning condition is met.

[0017] In a third aspect, an embodiment of the present invention further provides an electronic device, the electronic device comprising:

[0018] one or more processors;

[0019] A memory for storing one or more programs;

[0020] When the one or more programs are executed by the one or more processors, the one or more processors implement the user fall warning method provided by any embodiment of the present invention.

[0021] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a user fall warning method as provided in any embodiment of the present invention.

[0022] The embodiment of the present invention determines the current posture category of the user according to a preset posture classification network model and the current monitoring image of the user, and when the current posture category is a fall category, determines the target fall threshold information corresponding to the user based on the physiological parameter information of the user, and detects whether the user meets the preset fall warning conditions according to the target fall threshold information and the target probability value corresponding to the current posture category. If the preset fall warning conditions are met, the fall warning information corresponding to the user is generated, so that it can be further determined based on the physiological parameter information of the user whether the user really needs a fall warning, thereby realizing personalized fall warning, avoiding the misjudgment of fall warning, and thus improving the accuracy of fall warning. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 is a flow chart of a user fall warning method provided by Embodiment 1 of the present invention;

[0024] Figure 2 is a flow chart of a user fall warning method provided by Embodiment 2 of the present invention;

[0025] Figure 3It is a structural schematic diagram of a user fall warning device provided by Embodiment 3 of the present invention;

[0026] Figure 4 It is a structural schematic diagram of an electronic device provided in Embodiment 4 of the present invention. DETAILED DESCRIPTION

[0027] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only parts related to the present invention, rather than all structures, are shown in the accompanying drawings.

[0028] Embodiment 1

[0029] Figure 1 This is a flow chart of a user fall warning method provided in Embodiment 1 of the present invention. This embodiment can be applied to the case of monitoring a user's fall and providing a fall warning after the user falls, especially in the application scenario of providing a fall warning for elderly users at home. This method can be executed by a user fall warning device, which can be implemented by software and / or hardware and integrated into an electronic device. Figure 1 As shown, the method specifically comprises the following steps:

[0030] S110: Acquire the current monitoring image of the user.

[0031] The user may refer to any user who needs to monitor the fall warning. For example, the user may refer to a user who is at risk of falling, such as an elderly user. The current monitoring image may refer to an image containing the user collected at the current moment.

[0032] Specifically, the current monitoring image of the user can be collected based on monitoring equipment such as pre-installed cameras, so that the collected current monitoring image can be obtained to perform real-time fall monitoring on the user.

[0033] S120: Determine the current posture category of the user according to a preset posture classification network model and the current monitoring image.

[0034] Among them, the preset posture classification network model can be a pre-set neural network model for classifying user postures. For example, the preset posture classification network model can be but is not limited to an Inception network model. The preset posture classification network model in this embodiment can be obtained by pre-training based on sample images corresponding to each posture category. The current posture category may include but is not limited to: sitting, kneeling, lying, falling or normal. Among them, the fall category can also include front fall, back fall and side fall.

[0035] Specifically, this embodiment can input the current monitoring image into a trained preset posture classification network model. The preset posture classification network model can extract skeleton features through layer-by-layer convolution operations and cascade filters, perform posture classification based on the trained optimal convolution kernel parameters, and directly output the determined current posture category of the user. Therefore, based on the output of the preset posture classification network model, the user's current posture category can be directly and quickly obtained.

[0036] Exemplarily, S120 may include: inputting the current monitoring image into a preset posture classification network model for posture classification, determining the probability value of the user being in each posture category; and determining the posture category corresponding to the maximum probability value as the current posture category of the user.

[0037] Specifically, after the preset posture classification network model performs posture classification based on the current monitoring image, the probability value of the user being in each posture category can be output, so that the posture category with the largest output probability value can be determined as the user's current posture category.

[0038] S130: If the current posture category is a fall category, determine the target fall threshold information corresponding to the user based on the user's physiological parameter information.

[0039] Among them, the physiological parameter information can be parameter information used to characterize the user's physical condition. For example, the physiological parameter information can include parameters such as systolic blood pressure, diastolic blood pressure, heart rate, etc. associated with cardiovascular and cerebrovascular diseases, and parameters such as dynamic pulse pressure, mean arterial pressure and dynamic heart rate and blood pressure product can also be used; or, parameters such as body movement, blood oxygen, and respiration associated with sleep disorders. The target fall threshold information can be threshold information used to determine whether the user really needs a fall warning at present. For example, the target fall threshold information can include: a target fall probability value. The target fall probability value can be used to characterize the minimum probability value of the user being in a fall posture. The target fall threshold information can also include: a target fall duration. The target fall duration can be used to characterize the shortest duration that the user is in a fall posture.

[0040] Specifically, when the current posture category is detected as a fall category, it indicates that the current user may be at risk of falling. At this time, the manually input user's physiological parameter information can be obtained, and the user's disease information can be determined based on the obtained physiological parameter information. According to the pre-set fall threshold information corresponding to each disease and the user's disease information, the target fall threshold information corresponding to the user is determined, so that personalized fall warning judgment can be made based on the user's physiological parameter information. For example, for users with cardiovascular and cerebrovascular diseases, the target fall probability value and target fall duration can be set smaller; for users in good health, the target fall probability value and target fall duration can be set larger, so that the fall warning judgment can be adaptively adjusted to ensure the accuracy of the fall warning judgment.

[0041] It should be noted that if the current posture category is a non-fall category, such as sitting, kneeling, lying or normal, it indicates that the current user does not have a risk of falling, and there is no need for subsequent fall warning judgment. At this time, the process can return to step S110 to continue monitoring the user for falls.

[0042] Exemplarily, "determining the target fall threshold information corresponding to the user based on the user's physiological parameter information" in S130 may include: obtaining the collected current physiological parameter information; inputting the current physiological parameter information into a preset threshold detection network model, and obtaining the target fall threshold information corresponding to the user according to the output of the preset threshold detection network model.

[0043] The preset threshold detection network model may be a pre-set network model for determining the target fall threshold information of the user. For example, the preset threshold detection network model may be, but is not limited to, a SVM (Support Vector Machine) support vector machine model. The preset threshold detection network model in this embodiment may be obtained by training based on historical physiological parameter information in advance.

[0044] Specifically, this embodiment can collect the user's current physiological parameter information in real time based on the health monitoring device worn by the user (such as a bracelet, etc.), and can input the current physiological parameter information into a preset threshold detection network model to determine the target fall threshold information corresponding to the current physiological parameter information, thereby dynamically determining the target fall threshold information that meets the user's current physical condition, further ensuring the accuracy of the fall warning judgment.

[0045] S140. Detect whether the user meets a preset fall warning condition according to the target fall threshold information and the target probability value corresponding to the current posture category.

[0046] Among them, the preset fall warning condition can be a pre-set condition that is met when the user really needs a fall warning.

[0047] Specifically, when the target fall threshold information is a target fall probability value, S140 may include: if the target probability value corresponding to the current posture category is greater than or equal to the target fall probability value, determining that the user meets the preset fall warning condition. By adaptively adjusting the target fall probability value based on the user's physiological parameter information, a personalized fall warning can be achieved, avoiding the misjudgment of the fall warning, thereby improving the accuracy of the fall warning.

[0048] S150: If the preset fall warning condition is met, generate fall warning information corresponding to the user.

[0049] Specifically, when it is detected that the current user meets the preset fall warning conditions, the generated fall warning information can be sent to the user's associated device, such as the user's relative's mobile phone, or a rescue call can be made directly to provide timely rescue to the user and ensure the user's safety.

[0050] The technical solution of this embodiment determines the current posture category of the user according to a preset posture classification network model and the current monitoring image of the user, and when the current posture category is a fall category, determines the target fall threshold information corresponding to the user based on the user's physiological parameter information, and detects whether the user meets the preset fall warning conditions according to the target fall threshold information and the target probability value corresponding to the current posture category. If the preset fall warning conditions are met, the fall warning information corresponding to the user is generated, so that it can be further determined based on the user's physiological parameter information whether the user really needs a fall warning, thereby realizing personalized fall warning, avoiding the misjudgment of fall warning, and thus improving the accuracy of fall warning.

[0051] On the basis of the above technical solution, before step S120, it may also include: based on the user category corresponding to the user, detecting whether the user is a wheelchair user; if the user is a wheelchair user, obtaining a preset posture classification network model pre-trained based on sample images of wheelchair users; if the user is not a wheelchair user, obtaining a preset posture classification network model pre-trained based on sample images of non-wheelchair users.

[0052] Specifically, the user category can be configured based on the actual situation of the user. For example, if the user is a wheelchair user, the user category can be configured as a wheelchair user, otherwise it can be configured as a non-wheelchair user. In this embodiment, the preset posture classification network model can be trained in advance based on sample images of wheelchair users, so that the posture of the wheelchair user can be more accurately classified based on the trained preset posture classification network model, further improving the accuracy of the fall warning.

[0053] Based on the above technical solutions, the method may further include: obtaining the current location information of the user. Accordingly, step S120 may include: determining the current posture category of the user based on the preset posture classification network model, according to the current monitoring image and the current location information.

[0054] Specifically, the user can be located based on the RSSI (Received Signal Strength Indication) signal strength received at each node position in the monitoring space to obtain the user's current location information, and the current monitoring image and the current location information can be input into the preset posture classification network model, so that the preset posture classification network model can convert the user size information in the current monitoring image based on the current location information to obtain the user's accurate actual size information, thereby ensuring the accuracy of posture classification.

[0055] Embodiment 2

[0056] Figure 2 This is a flow chart of a user fall warning method provided in Embodiment 2 of the present invention. Based on the above embodiment, this embodiment further optimizes the step of "detecting whether the user meets the preset fall warning condition according to the target fall threshold information and the target probability value corresponding to the current posture category". The explanations of the terms that are the same or corresponding to the above embodiment are not repeated here.

[0057] See also Figure 2 The user fall warning method provided in this embodiment specifically includes the following steps:

[0058] S210: Obtain the current monitoring image of the user.

[0059] S220: Determine the current posture category of the user according to a preset posture classification network model and the current monitoring image.

[0060] S230: If the current posture category is a fall category, determine a target fall probability value and a target fall duration corresponding to the user based on the user's physiological parameter information.

[0061] Specifically, when the current posture category is a fall category, the target fall probability value and target fall duration corresponding to the user can be determined based on the manually input physiological parameter information of the user or the current physiological parameter information automatically collected in real time, so that the fall warning judgment can be adaptively adjusted to further ensure the accuracy of the fall warning judgment.

[0062] S240: If the current posture category obtained each time within the target fall duration is a fall category, and the target probability value corresponding to the current posture category is greater than or equal to the corresponding target fall probability value, it is determined that the user meets the preset fall warning condition.

[0063] Specifically, this embodiment can make a fall judgment in real time, or it can make a fall judgment at regular intervals. When the current posture category detected each time within the target fall duration is a fall category, and the target probability value corresponding to each current posture category is greater than or equal to the corresponding target fall probability value, it indicates that the duration of the user's fall reaches the target fall duration. At this time, it can be determined that the current user really needs a fall warning, that is, it can be determined that the user meets the preset fall warning conditions, so as to generate fall warning information. This embodiment can further avoid the misjudgment of the fall warning caused by the user bending over to pick up something, etc., by making a fall judgment based on the target fall duration, thereby further improving the accuracy of the fall warning.

[0064] S250: If the preset fall warning condition is met, generate fall warning information corresponding to the user.

[0065] The technical solution of this embodiment generates fall warning information corresponding to the user when the current posture category obtained each time within the target fall duration is a fall category and the target probability value corresponding to the current posture category is greater than or equal to the corresponding target fall probability value, thereby further avoiding the misjudgment of the fall warning and further improving the accuracy of the fall warning.

[0066] The following is an embodiment of a user fall warning device provided by an embodiment of the present invention. The device and the user fall warning method of the above embodiments belong to the same inventive concept. For details not described in detail in the embodiment of the user fall warning device, reference can be made to the embodiment of the above user fall warning method.

[0067] Embodiment 3

[0068] Figure 3 This is a structural schematic diagram of a user fall warning device provided in Example 3 of the present invention. This embodiment can be applied to situations where user falls are monitored and fall warnings are issued after the user falls, especially in application scenarios where fall warnings are issued to elderly users at home. The device specifically includes: a current monitoring image acquisition module 310, a current posture category determination module 320, a target fall threshold information determination module 330, a fall warning detection module 340 and a fall warning information generation module 350.

[0069] Among them, the current monitoring image acquisition module 310 is used to obtain the current monitoring image of the user; the current posture category determination module 320 is used to determine the current posture category of the user according to the preset posture classification network model and the current monitoring image; the target fall threshold information determination module 330 is used to determine the target fall threshold information corresponding to the user based on the user's physiological parameter information if the current posture category is a fall category; the fall warning detection module 340 is used to detect whether the user meets the preset fall warning conditions based on the target fall threshold information and the target probability value corresponding to the current posture category; the fall warning information generation module 350 is used to generate the fall warning information corresponding to the user if the preset fall warning conditions are met.

[0070] Optionally, the target fall threshold information determination module 330 is specifically used to: obtain the collected current physiological parameter information; input the current physiological parameter information into a preset threshold detection network model, and obtain the target fall threshold information corresponding to the user according to the output of the preset threshold detection network model.

[0071] Optionally, the target fall threshold information includes: a target fall probability value;

[0072] The fall warning detection module 340 is specifically used to: if the target probability value corresponding to the current posture category is greater than or equal to the target fall probability value, determine that the user meets the preset fall warning condition.

[0073] Optionally, the target fall threshold information also includes: target fall duration;

[0074] The fall warning detection module 340 is specifically used to: if the current posture category obtained each time within the target fall duration is a fall category, and the target probability value corresponding to the current posture category is greater than or equal to the corresponding target fall probability value, it is determined that the user meets the preset fall warning condition.

[0075] Optionally, the current posture category determination module 320 is specifically used to: input the current monitoring image into a preset posture classification network model for posture classification, determine the probability value of the user being in each posture category; and determine the posture category corresponding to the maximum probability value as the user's current posture category.

[0076] Optionally, the device further comprises:

[0077] The preset posture classification network model acquisition module is used to: before determining the user's current posture category based on the preset posture classification network model and the current monitoring image, detect whether the user is a wheelchair user based on the user category corresponding to the user; if the user is a wheelchair user, obtain the preset posture classification network model pre-trained based on the sample images of wheelchair users; if the user is not a wheelchair user, obtain the preset posture classification network model pre-trained based on the sample images of non-wheelchair users.

[0078] Optionally, the device further comprises:

[0079] Current location information acquisition module, used to obtain the user's current location information;

[0080] The current posture category determination module 320 is specifically used to determine the user's current posture category based on a preset posture classification network model, according to the current monitoring image and current location information.

[0081] The user fall warning device provided in the embodiment of the present invention can execute the user fall warning method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of executing the user fall warning method.

[0082] It is worth noting that in the embodiment of the above-mentioned user fall warning device, the various units and modules included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0083] Embodiment 4

[0084] Figure 4 A schematic diagram of the structure of an electronic device provided in Embodiment 4 of the present invention. Figure 4 A block diagram of an exemplary electronic device 12 suitable for use in implementing embodiments of the present invention is shown. Figure 4 The electronic device 12 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0085] like Figure 4 As shown, the electronic device 12 is in the form of a general purpose computing device. The components of the electronic device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that connects various system components (including the system memory 28 and the processing unit 16).

[0086] Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. By way of example, these architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MAC) bus, an Enhanced ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

[0087] The electronic device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the electronic device 12, including volatile and non-volatile media, removable and non-removable media.

[0088] The system memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. The electronic device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 34 may be used to read and write non-removable, non-volatile magnetic media ( Figure 4 not shown, usually called a "hard drive"). Although Figure 4 Not shown in the figure, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 18 via one or more data medium interfaces. The system memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present invention.

[0089] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in system memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. Program modules 42 generally perform the functions and / or methods of the embodiments described herein.

[0090] The electronic device 12 may also communicate with one or more external devices 14 (e.g., keyboards, pointing devices, displays 24, etc.), may communicate with one or more devices that enable a user to interact with the electronic device 12, and / or may communicate with any device that enables the electronic device 12 to communicate with one or more other computing devices (e.g., network cards, modems, etc.). Such communication may be performed via an input / output (I / O) interface 22. Furthermore, the electronic device 12 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter 20. As shown, the network adapter 20 communicates with other modules of the electronic device 12 via a bus 18. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0091] The processing unit 16 executes various functional applications and data processing by running the program stored in the system memory 28, for example, implementing a user fall warning method provided by the embodiment of the present invention, the method comprising:

[0092] Get the user's current monitoring image;

[0093] Determine the user's current posture category based on a preset posture classification network model and the current monitoring image;

[0094] If the current posture category is a fall category, determining the target fall threshold information corresponding to the user based on the user's physiological parameter information;

[0095] According to the target fall threshold information and the target probability value corresponding to the current posture category, detect whether the user meets the preset fall warning conditions;

[0096] If the preset fall warning conditions are met, the corresponding fall warning information for the user is generated.

[0097] Of course, those skilled in the art can understand that the processor can also implement the technical solution of the user fall warning method provided by any embodiment of the present invention.

[0098] Embodiment 5

[0099] This embodiment provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the steps of the user fall warning method provided in any embodiment of the present invention are implemented. The method includes:

[0100] Get the user's current monitoring image;

[0101] Determine the user's current posture category based on a preset posture classification network model and the current monitoring image;

[0102] If the current posture category is a fall category, determining the target fall threshold information corresponding to the user based on the user's physiological parameter information;

[0103] According to the target fall threshold information and the target probability value corresponding to the current posture category, detect whether the user meets the preset fall warning conditions;

[0104] If the preset fall warning conditions are met, the corresponding fall warning information for the user is generated.

[0105] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to: an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0106] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0107] The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0108] Computer program code for performing the operations of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0109] It should be understood by those skilled in the art that the modules or steps of the present invention described above can be implemented by a general-purpose computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, optionally, they can be implemented by a program code executable by a computer device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0110] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A user fall warning method, characterized in that: include: Get the user's current monitoring image; Determining the current posture category of the user according to a preset posture classification network model and the current monitoring image; If the current posture category is a fall category, then based on the physiological parameter information of the user, the target fall threshold information corresponding to the user is determined; wherein the target fall threshold information is threshold information used to determine whether the user currently really needs a fall warning; Detecting whether the user meets a preset fall warning condition according to the target fall threshold information and the target probability value corresponding to the current posture category; If the preset fall warning condition is met, generating fall warning information corresponding to the user; The determining, based on the physiological parameter information of the user, target fall threshold information corresponding to the user includes: Obtain the collected current physiological parameter information; Inputting the current physiological parameter information into a preset threshold detection network model, and obtaining the target fall threshold information corresponding to the user according to the output of the preset threshold detection network model, wherein the preset threshold detection network model is obtained by training based on historical physiological parameter information in advance; The target fall threshold information includes: a target fall probability value and a target fall duration; The detecting, according to the target fall threshold information and the target probability value corresponding to the current posture category, whether the user meets the preset fall warning condition includes: If the current posture category obtained each time within the target fall duration is a fall category, and the target probability value corresponding to the current posture category is greater than or equal to the corresponding target fall probability value, it is determined that the user meets the preset fall warning condition.

2. The method according to claim 1, characterized in that The step of determining the current posture category of the user according to the preset posture classification network model and the current monitoring image includes: Inputting the current monitoring image into a preset posture classification network model for posture classification, and determining the probability value of the user being in each posture category; The posture category corresponding to the largest probability value is determined as the current posture category of the user.

3. The method according to claim 1, characterized in that Before determining the current posture category of the user according to the preset posture classification network model and the current monitoring image, the method further includes: Based on the user category corresponding to the user, detecting whether the user is a wheelchair user; If the user is in a wheelchair, a preset posture classification network model pre-trained based on sample images of the user is obtained; If the user is not a wheelchair user, a preset posture classification network model pre-trained based on sample images of non-wheelchair users is obtained.

4. The method according to any one of claims 1 to 3, characterized in that: The method further comprises: Obtaining the current location information of the user; The step of determining the current posture category of the user according to the preset posture classification network model and the current monitoring image includes: Based on a preset posture classification network model, the current posture category of the user is determined according to the current monitoring image and the current position information.

5. A user fall warning device, characterized in that: include: The current monitoring image acquisition module is used to obtain the current monitoring image of the user; A current posture category determination module, used to determine the current posture category of the user according to a preset posture classification network model and the current monitoring image; A target fall threshold information determination module, for determining the target fall threshold information corresponding to the user based on the physiological parameter information of the user if the current posture category is a fall category; wherein the target fall threshold information is threshold information for determining whether the user currently really needs a fall warning; A fall warning detection module, used to detect whether the user meets a preset fall warning condition according to the target fall threshold information and the target probability value corresponding to the current posture category; A fall warning information generating module, configured to generate fall warning information corresponding to the user if the preset fall warning condition is met; The target fall threshold information determination module is specifically used to: Acquire the collected current physiological parameter information; input the current physiological parameter information into a preset threshold detection network model, and obtain the target fall threshold information corresponding to the user according to the output of the preset threshold detection network model, wherein the preset threshold detection network model is obtained by pre-training based on historical physiological parameter information; The target fall threshold information includes: a target fall probability value and a target fall duration; The fall warning detection module is specifically used for: If the current posture category obtained each time within the target fall duration is a fall category, and the target probability value corresponding to the current posture category is greater than or equal to the corresponding target fall probability value, it is determined that the user meets the preset fall warning condition.

6. An electronic device, characterized in that: The electronic device comprises: one or more processors; A memory for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the user fall warning method as described in any one of claims 1-4.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the user fall warning method as described in any one of claims 1 to 4 is implemented.

Images