CN114283494A - Early warning method, device, equipment and storage medium for user falling - Google Patents
Early warning method, device, equipment and storage medium for user falling Download PDFInfo
- Publication number
- CN114283494A CN114283494A CN202111529641.2A CN202111529641A CN114283494A CN 114283494 A CN114283494 A CN 114283494A CN 202111529641 A CN202111529641 A CN 202111529641A CN 114283494 A CN114283494 A CN 114283494A
- Authority
- CN
- China
- Prior art keywords
- user
- falling
- current
- target
- early warning
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Alarm Systems (AREA)
- Emergency Alarm Devices (AREA)
Abstract
The embodiment of the invention discloses a method, a device, equipment and a storage medium for early warning of falling of a user, wherein the method comprises the following steps: acquiring a current monitoring image of a user; determining the current posture category of the user according to the preset posture classification network model and the current monitoring image; if the current posture category is a falling category, determining target falling threshold information corresponding to the user based on the physiological parameter information of the user; detecting whether a user meets preset falling early warning conditions or not according to target falling threshold information and a target probability value corresponding to the current posture category; and if the preset falling early warning condition is met, generating falling early warning information corresponding to the user. By the technical scheme of the embodiment of the invention, the falling early warning accuracy of the user can be improved.
Description
Technical Field
The embodiment of the invention relates to computer technology, in particular to a method, a device, equipment and a storage medium for early warning of user falling.
Background
With the rapid development of computer technology, whether the user falls can be monitored so as to timely carry out early warning of falling and avoid endangering life. For example, early warning of falling down for elderly users is an important guarantee for the safety of elderly people in a home environment.
At present, fall early warning is generally performed when a user falls down according to user posture information. However, different users have different physical conditions, the processing capability for falling is different, and the emergency degree of falling early warning is also different, so that the falling early warning misjudgment condition can exist only in a falling early warning mode based on user posture information, and the falling early warning accuracy is reduced.
Disclosure of Invention
The embodiment of the invention provides a method, a device, equipment and a storage medium for early warning of user falling, which are used for improving the accuracy of early warning of user falling.
In a first aspect, an embodiment of the present invention provides a method for early warning of a fall of a user, including:
acquiring 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 type is a falling type, determining target falling threshold information corresponding to the user based on the physiological parameter information of the user;
detecting whether the user meets a preset falling early warning condition or not according to the target falling threshold information and a target probability value corresponding to the current posture category;
and if the preset falling early warning condition is met, generating falling early warning information corresponding to the user.
In a second aspect, an embodiment of the present invention further provides a user fall warning apparatus, including:
the current monitoring image acquisition module is used for acquiring a current monitoring image of a user;
the current posture category determining module is used for determining the current posture category of the user according to a preset posture classification network model and the current monitoring image;
a target falling threshold information determining module, configured to determine, if the current posture category is a falling category, target falling threshold information corresponding to the user based on physiological parameter information of the user;
a falling early warning detection module, configured to detect whether the user meets a preset falling early warning condition according to the target falling threshold information and a target probability value corresponding to the current posture category;
and the falling early warning information generating module is used for generating falling early warning information corresponding to the user if the preset falling early warning condition is met.
In a third aspect, an embodiment of the present invention further provides an electronic device, where the electronic device includes:
one or more processors;
a memory for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement a method of fall warning for a user as provided by any of the embodiments of the invention.
In a fourth aspect, embodiments of the present invention also provide a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements a method for fall warning for a user as provided in any of the embodiments of the present invention.
According to the embodiment of the invention, the network model and the current monitoring image of the user are classified according to the preset posture, the current posture type of the user is determined, when the current posture type is a falling type, the target falling threshold information corresponding to the user is determined based on the physiological parameter information of the user, whether the user meets the preset falling early warning condition is detected according to the target falling threshold information and the target probability value corresponding to the current posture type, and if the preset falling early warning condition is met, the falling early warning information corresponding to the user is generated, so that whether the user really needs falling early warning is further determined based on the physiological parameter information of the user, the personalized falling early warning is realized, the condition of misjudgment of the falling early warning is avoided, and the accuracy of the falling early warning is improved.
Drawings
Fig. 1 is a flowchart of a method for early warning a fall of a user according to an embodiment of the present invention;
fig. 2 is a flowchart of a fall warning method for a user according to a second embodiment of the present invention;
fig. 3 is a schematic structural diagram of a fall warning apparatus for a user according to a third embodiment of the present invention;
fig. 4 is a schematic structural diagram of an electronic device according to a fourth embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
Example one
Fig. 1 is a flowchart of a user fall early warning method according to an embodiment of the present invention, which is applicable to fall monitoring for a user and fall early warning after the user falls, and especially applicable to an application scenario for fall early warning for a household elderly user. The method may be performed by a user fall warning device, which may be implemented in software and/or hardware, integrated in an electronic device. As shown in fig. 1, the method specifically includes the following steps:
and S110, acquiring a current monitoring image of the user.
The user may refer to any user who needs to monitor the early warning of falling. For example, the user may refer to a user having a fall risk such as an elderly user. The current monitoring image may refer to an image including the user acquired at the current time.
Specifically, the current monitoring image of the user can be acquired based on the pre-installed monitoring equipment such as a camera, so that the acquired current monitoring image can be obtained, and the user can be monitored for falling down in real time.
And S120, classifying the network model and the current monitoring image according to the preset posture, and determining the current posture category of the user.
The preset gesture classification network model can be a preset neural network model used for classifying the user gestures. For example, the preset pose classification network model may be, but is not limited to, an inclusion network model. The preset posture classification network model in this embodiment may be obtained by training in advance based on a sample image corresponding to each posture category. The current pose categories may include, but are not limited to: sit, kneel, lie, fall, or normal. Wherein the fall categories may further comprise front falls, back falls and side falls.
Specifically, in this embodiment, the current monitoring image may be input into a trained preset posture classification network model, the preset posture classification network model may extract skeleton features through layer-to-layer convolution operation and a cascade filter, perform posture classification based on the trained optimal convolution kernel parameter, and may directly output the determined current posture category of the user, so that the current posture category of the user may be directly and quickly obtained based on the output of the preset posture classification network model.
Exemplarily, S120 may include: inputting the current monitoring image into a preset posture classification network model for posture classification, and determining the probability value of each posture class of the user; and determining the gesture category corresponding to the maximum probability value as the current gesture category of the user.
Specifically, after the preset posture classification network model performs posture classification based on the current monitoring image, the probability value of the user in each posture category can be output, so that the posture category with the maximum output probability value can be determined as the current posture category of the user.
And S130, if the current posture category is a falling category, determining target falling threshold information corresponding to the user based on the physiological parameter information of the user.
The physiological parameter information may be parameter information for characterizing the physical condition of the user. For example, the physiological parameter information may include parameters such as systolic pressure, diastolic pressure, heart rate and the like associated with heart and brain diseases, and parameters such as dynamic pulse pressure, product of mean arterial pressure and dynamic heart rate and blood pressure may also be used; or parameters of body movement, blood oxygen, respiration, etc. associated with sleep disorders. The target fall threshold information may be threshold information for determining whether the user really needs fall early warning currently. For example, the target fall threshold information may include: a target fall probability value. The target fall probability value may be used to represent a minimum probability value that the user is in a fall posture. The target fall threshold information may further include: the target fall duration. The target fall duration can be used to characterize the shortest duration that the user is in the fall posture.
Specifically, when the current posture type is detected to be the falling type, it is indicated that the current user may have a falling risk, at this time, manually input physiological parameter information of the user may be acquired, the disease information existing in the user may be determined based on the acquired physiological parameter information, and the target falling threshold information corresponding to the user may be determined according to the preset falling threshold information corresponding to each disease and the disease information of the user, so that the personalized falling early warning judgment may be performed based on the physiological parameter information of the user. For example, for a user with heart brain diseases, the target fall probability value and the target fall duration can be set to be smaller; for users with good health, the target falling probability value and the target falling duration can be set to be larger, so that falling early warning judgment can be adjusted in a self-adaptive manner, and the accuracy of falling early warning judgment is ensured.
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 fall risk, and the subsequent fall early warning judgment is not needed, at this time, the step S110 may be returned to continue to monitor the fall of the user.
Exemplarily, the "determining the target fall threshold information corresponding to the user based on the physiological parameter information of the user" in S130 may include: acquiring the collected current physiological parameter information; and inputting the current physiological parameter information into a preset threshold detection network model, and obtaining target falling threshold information corresponding to the user according to the output of the preset threshold detection network model.
The preset threshold detection network model may be a network model that is preset and used 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, an svm (support Vector machine) support Vector machine model. The preset threshold detection network model in this embodiment may be obtained by training in advance based on historical physiological parameter information.
Specifically, the present embodiment can acquire the current physiological parameter information of the user in real time based on the health monitoring device (such as a bracelet, etc.) worn by the user, and can input the current physiological parameter information into the preset threshold detection network model to determine the target falling threshold information corresponding to the current physiological parameter information, thereby dynamically determining the target falling threshold information according with the current body condition of the user, and further ensuring the accuracy of the falling early warning judgment.
And S140, detecting whether the user meets preset falling early warning conditions or not according to the target falling threshold information and the target probability value corresponding to the current posture category.
The preset falling early warning condition can be preset, and the user really needs the condition met when falling early warning is needed.
Specifically, when the target fall threshold information is the target fall probability value, S140 may include: and if the target probability value corresponding to the current posture category is greater than or equal to the target falling probability value, determining that the user meets the preset falling early warning condition. Through the self-adaptive adjustment of the target falling probability value based on the physiological parameter information of the user, the personalized falling early warning can be realized, the condition of misjudgment of the falling early warning is avoided, and the accuracy of the falling early warning is further improved.
And S150, if the preset falling early warning condition is met, generating falling early warning information corresponding to the user.
Specifically, when it is detected that the current user meets the preset fall early warning condition, the generated fall early warning information can be sent to the associated personal device of the user, such as a mobile phone of a user relative, or a rescue call is directly dialed, so that the user can be rescued in time, and the safety of the user is ensured.
According to the technical scheme, the current posture category of the user is determined according to the preset posture classification network model and the current monitoring image of the user, when the current posture category is the falling category, the target falling threshold information corresponding to the user is determined based on the physiological parameter information of the user, whether the user meets the preset falling early warning condition or not is detected according to the target falling threshold information and the target probability value corresponding to the current posture category, and if the preset falling early warning condition is met, falling early warning information corresponding to the user is generated, so that whether the user really needs falling early warning or not can be further determined based on the physiological parameter information of the user, personalized falling early warning is achieved, the condition of misjudgment of falling early warning is avoided, and the accuracy of falling early warning is improved.
On the basis of the above technical solution, before step S120, the method may further include: detecting whether the user is a wheelchair user or not based on the user category corresponding to the user; if the wheelchair user is the wheelchair user, acquiring a preset posture classification network model obtained in advance based on sample image training of the wheelchair user; and if the wheelchair is not the user, acquiring a preset posture classification network model obtained in advance based on sample image training of the wheelchair user.
In particular, the user categories may be configured based on the user's actual situation. For example, if the user is a wheelchair-dependent user, the user category may be configured as a wheelchair user, otherwise a non-wheelchair user is configured. According to the embodiment, the preset posture classification network model can be trained in advance based on the sample image of the wheelchair user, so that the wheelchair user can be subjected to posture classification more accurately based on the trained preset posture classification network model, and the accuracy of falling early warning is further improved.
On the basis of the above technical solutions, the method may further include: and acquiring the current position information of the user. Accordingly, step S120 may include: and determining the current posture category of the user according to the current monitoring image and the current position information based on the preset posture classification network model.
Specifically, the user may be positioned based on the received rssi (received Signal Strength indication) Signal Strength at each node position in the monitored space, so as to obtain the current position information of the user, and the current monitored image and the current position information may be input into the preset posture classification network model, so that the preset posture classification network model may convert the user size information in the current monitored image based on the current position information, so as to obtain the accurate actual size information of the user, and further ensure the accuracy of posture classification.
Example two
Fig. 2 is a flowchart of a user fall early warning method according to a second embodiment of the present invention, and in this embodiment, based on the above embodiment, further optimization is performed on the step of detecting whether the user meets the preset fall early warning condition according to the target fall threshold information and the target probability value corresponding to the current posture category. Wherein explanations of the same or corresponding terms as those of the above-described embodiments are omitted.
Referring to fig. 2, the early warning method for user fall provided by the embodiment specifically includes the following steps:
and S210, acquiring a current monitoring image of the user.
S220, classifying the network model and the current monitoring image according to the preset posture, and determining the current posture category of the user.
And S230, if the current posture category is a falling category, determining a target falling probability value and a target falling duration corresponding to the user based on the physiological parameter information of the user.
Specifically, when the current posture category is a falling category, the target falling probability value and the target falling duration corresponding to the user can be determined based on manually input physiological parameter information of the user or automatically acquired current physiological parameter information in real time, so that falling early warning judgment can be adaptively adjusted, and the accuracy of falling early warning judgment is further ensured.
And S240, if the current posture types obtained in the target falling duration each time are falling types and the target probability values corresponding to the current posture types are all larger than or equal to the corresponding target falling probability values, determining that the user meets the preset falling early warning conditions.
Specifically, the embodiment can perform the user fall judgment in real time, and also can perform the user fall judgment at intervals. When the current posture types detected in the target falling time length each time are falling types and the target probability values corresponding to the current posture types each time are larger than or equal to the corresponding target falling probability values, it is indicated that the falling duration time of the user reaches the target falling time length, and at this time, it can be determined that the current user really needs falling early warning, that is, it is determined that the user meets preset falling early warning conditions, so that falling early warning information is generated. The embodiment can further avoid the false judgment of the fall early warning caused by the fact that the user bends down to pick up objects and the like by judging the fall of the user based on the target fall duration, so that the accuracy of the fall early warning is further improved.
And S250, if the preset falling early warning condition is met, generating falling early warning information corresponding to the user.
According to the technical scheme of the embodiment, when the current posture categories obtained each time in the target falling time are falling categories and the target probability values corresponding to the current posture categories are greater than or equal to the corresponding target falling probability values, falling early warning information corresponding to the user is generated, so that the condition of false judgment of falling early warning can be further avoided, and the accuracy of falling early warning is further improved.
The following is an embodiment of the user fall early warning device provided in the embodiment of the present invention, the device and the user fall early warning method in the embodiments described above belong to the same inventive concept, and details that are not described in detail in the embodiment of the user fall early warning device may refer to the embodiment of the user fall early warning method described above.
EXAMPLE III
Fig. 3 is a schematic structural diagram of a user fall early warning device according to a third embodiment of the present invention, which is applicable to fall monitoring of a user and fall early warning after the user falls, and especially applicable to an application scenario of fall early warning for a household elderly user, and specifically includes: the system comprises a current monitoring image acquisition module 310, a current posture category determination module 320, a target fall threshold information determination module 330, a fall early warning detection module 340 and a fall early warning information generation module 350.
The current monitoring image obtaining module 310 is configured to obtain a current monitoring image of a user; a current posture category determining module 320, configured to determine a current posture category of the user according to the preset posture classification network model and the current monitoring image; a target falling threshold information determining module 330, configured to determine, if the current posture category is a falling category, target falling threshold information corresponding to the user based on physiological parameter information of the user; a falling early warning detection module 340, configured to detect whether the user meets a preset falling early warning condition according to the target falling threshold information and the target probability value corresponding to the current posture category; and a fall early warning information generating module 350, configured to generate fall early warning information corresponding to the user if a preset fall early warning condition is met.
Optionally, the target fall threshold information determining module 330 is specifically configured to: acquiring the collected current physiological parameter information; and inputting the current physiological parameter information into a preset threshold detection network model, and obtaining target falling threshold information corresponding to the user according to the output of the preset threshold detection network model.
Optionally, the target fall threshold information comprises: a target fall probability value;
the fall early warning detection module 340 is specifically configured to: and if the target probability value corresponding to the current posture category is greater than or equal to the target falling probability value, determining that the user meets the preset falling early warning condition.
Optionally, the target fall threshold information further comprises: a target fall duration;
the fall early warning detection module 340 is specifically configured to: and if the current posture types obtained in the target falling duration each time are falling types and the target probability values corresponding to the current posture types are all larger than or equal to the corresponding target falling probability values, determining that the user meets the preset falling early warning conditions.
Optionally, the current posture category determining module 320 is specifically configured to: inputting the current monitoring image into a preset posture classification network model for posture classification, and determining the probability value of each posture class of the user; and determining the gesture category corresponding to the maximum probability value as the current gesture category of the user.
Optionally, the apparatus further comprises:
the preset posture classification network model acquisition module is used for: before classifying the network model and the current monitoring image according to the preset posture and determining the current posture category of the user, detecting whether the user is a wheelchair user or not based on the user category corresponding to the user; if the wheelchair user is the wheelchair user, acquiring a preset posture classification network model obtained in advance based on sample image training of the wheelchair user; and if the wheelchair is not the user, acquiring a preset posture classification network model obtained in advance based on sample image training of the wheelchair user.
Optionally, the apparatus further comprises:
the current position information acquisition module is used for acquiring the current position information of the user;
the current posture category determining module 320 is specifically configured to: and determining the current posture category of the user according to the current monitoring image and the current position information based on the preset posture classification network model.
The user fall early warning device provided by the embodiment of the invention can execute the user fall early warning method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of executing the user fall early warning method.
It should be noted that, in the embodiment of the user fall warning device, the units and modules included in the embodiment are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be implemented; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention.
Example four
Fig. 4 is a schematic structural diagram of an electronic device according to a fourth embodiment of the present invention. FIG. 4 illustrates a block diagram of an exemplary electronic device 12 suitable for use in implementing embodiments of the present invention. The electronic device 12 shown in fig. 4 is only an example and should not bring any limitation to the function and the scope of use of the embodiment of the present invention.
As shown in FIG. 4, electronic device 12 is embodied in the form of a general purpose computing device. The components of 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 couples various system components including the system memory 28 and the processing unit 16.
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/nonvolatile computer system storage media. By way of example only, storage system 34 may be used to read from and write to non-removable, nonvolatile magnetic media (not shown in FIG. 4, and commonly referred to as a "hard drive"). Although not shown in FIG. 4, a magnetic disk drive for reading from and writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 18 by one or more data media interfaces. 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 carry out the functions of embodiments of the invention.
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 examples or some combination thereof may comprise an implementation of a network environment. Program modules 42 generally carry out the functions and/or methodologies of the described embodiments of the invention.
The processing unit 16 executes various functional applications and data processing by executing programs stored in the system memory 28, for example, to implement the steps of a fall warning method for a user provided by the embodiment of the present invention, the method including:
acquiring a current monitoring image of a user;
determining the current posture category of the user according to the preset posture classification network model and the current monitoring image;
if the current posture category is a falling category, determining target falling threshold information corresponding to the user based on the physiological parameter information of the user;
detecting whether a user meets preset falling early warning conditions or not according to target falling threshold information and a target probability value corresponding to the current posture category;
and if the preset falling early warning condition is met, generating falling early warning information corresponding to the user.
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 in any embodiment of the present invention.
EXAMPLE five
The present embodiment provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of a method for fall warning of a user as provided by any of the embodiments of the invention, the method comprising:
acquiring a current monitoring image of a user;
determining the current posture category of the user according to the preset posture classification network model and the current monitoring image;
if the current posture category is a falling category, determining target falling threshold information corresponding to the user based on the physiological parameter information of the user;
detecting whether a user meets preset falling early warning conditions or not according to target falling threshold information and a target probability value corresponding to the current posture category;
and if the preset falling early warning condition is met, generating falling early warning information corresponding to the user.
Computer storage media for embodiments of the invention may employ any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. The computer-readable storage medium may be, for example but not limited to: an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the 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 the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
It will be understood by those skilled in the art that the modules or steps of the invention described above may be implemented by a general purpose computing device, they may be centralized on a single computing device or distributed across a network of computing devices, and optionally they may be implemented by program code executable by a computing device, such that it may be stored in a memory device and executed by a computing device, or it may be separately fabricated into various integrated circuit modules, or it may be fabricated by fabricating a plurality of modules or steps thereof into a single integrated circuit module. Thus, the present invention is not limited to any specific combination of hardware and software.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (10)
1. A user fall warning method, comprising:
acquiring 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 type is a falling type, determining target falling threshold information corresponding to the user based on the physiological parameter information of the user;
detecting whether the user meets a preset falling early warning condition or not according to the target falling threshold information and a target probability value corresponding to the current posture category;
and if the preset falling early warning condition is met, generating falling early warning information corresponding to the user.
2. The method of claim 1, wherein the determining the target fall threshold information corresponding to the user based on the physiological parameter information of the user comprises:
acquiring the collected current physiological parameter information;
and inputting the current physiological parameter information into a preset threshold detection network model, and obtaining target falling threshold information corresponding to the user according to the output of the preset threshold detection network model.
3. The method of claim 1, wherein the target fall threshold information comprises: a target fall probability value;
the detecting whether the user meets a preset falling early warning condition or not according to the target falling threshold information and the target probability value corresponding to the current posture category includes:
and if the target probability value corresponding to the current posture category is greater than or equal to the target falling probability value, determining that the user meets a preset falling early warning condition.
4. The method of claim 3, wherein the target fall threshold information further comprises: a target fall duration;
the detecting whether the user meets a preset falling early warning condition or not according to the target falling threshold information and the target probability value corresponding to the current posture category includes:
and if the current posture types obtained each time in the target falling duration are falling types and the target probability values corresponding to the current posture types are all larger than or equal to the corresponding target falling probability values, determining that the user meets preset falling early warning conditions.
5. The method of claim 1, wherein classifying the network model and the current monitoring image according to a preset pose and determining the current pose category of the user comprises:
inputting the current monitoring image into a preset posture classification network model for posture classification, and determining the probability value of the user in each posture class;
and determining the gesture category corresponding to the maximum probability value as the current gesture category of the user.
6. The method of claim 1, further comprising, prior to classifying a network model and the current monitoring image according to a preset pose and determining a current pose category of the user:
detecting whether the user is a wheelchair user or not based on the user category corresponding to the user;
if the wheelchair user is the wheelchair user, acquiring a preset posture classification network model obtained in advance based on sample image training of the wheelchair user;
and if the wheelchair is not the user, acquiring a preset posture classification network model obtained in advance based on sample image training of the wheelchair user.
7. The method according to any one of claims 1-6, further comprising:
acquiring current position information of the user;
classifying the network model and the current monitoring image according to a preset posture, and determining the current posture category of the user, wherein the step of classifying the network model and the current monitoring image according to the preset posture comprises the following steps:
and determining the current posture category of the user according to the current monitoring image and the current position information based on a preset posture classification network model.
8. A user fall warning device, comprising:
the current monitoring image acquisition module is used for acquiring a current monitoring image of a user;
the current posture category determining module is used for determining the current posture category of the user according to a preset posture classification network model and the current monitoring image;
a target falling threshold information determining module, configured to determine, if the current posture category is a falling category, target falling threshold information corresponding to the user based on physiological parameter information of the user;
a falling early warning detection module, configured to detect whether the user meets a preset falling early warning condition according to the target falling threshold information and a target probability value corresponding to the current posture category;
and the falling early warning information generating module is used for generating falling early warning information corresponding to the user if the preset falling early warning condition is met.
9. An electronic device, characterized in that the electronic device comprises:
one or more processors;
a memory for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement a user fall warning method as claimed in any one of claims 1-7.
10. A computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, is adapted to carry out a method for fall warning of a user as claimed in any one of the claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111529641.2A CN114283494A (en) | 2021-12-14 | 2021-12-14 | Early warning method, device, equipment and storage medium for user falling |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111529641.2A CN114283494A (en) | 2021-12-14 | 2021-12-14 | Early warning method, device, equipment and storage medium for user falling |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114283494A true CN114283494A (en) | 2022-04-05 |
Family
ID=80872192
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111529641.2A Pending CN114283494A (en) | 2021-12-14 | 2021-12-14 | Early warning method, device, equipment and storage medium for user falling |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114283494A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115180059A (en) * | 2022-07-05 | 2022-10-14 | 苏州万佳电器有限公司 | Fall warning device and method, two-wheel vehicle and storage medium |
| CN115868966A (en) * | 2022-12-12 | 2023-03-31 | 北京顺源辰辰科技发展有限公司 | Intelligent action assisting system and intelligent action assisting method |
| CN115969356A (en) * | 2022-12-12 | 2023-04-18 | 北京顺源辰辰科技发展有限公司 | Multimode behavior monitoring method and device based on intelligent sliding rail |
| CN116035564A (en) * | 2022-12-06 | 2023-05-02 | 北京顺源辰辰科技发展有限公司 | Dysphagia and aspiration intelligent detection method and device and electronic equipment |
| CN116269355A (en) * | 2023-05-11 | 2023-06-23 | 江西珉轩智能科技有限公司 | Safety monitoring system based on figure gesture recognition |
| CN116687394A (en) * | 2023-08-04 | 2023-09-05 | 亿慧云智能科技（深圳）股份有限公司 | Tumble detection method, device, equipment and storage medium based on millimeter wave radar |
| WO2024077550A1 (en) * | 2022-10-13 | 2024-04-18 | 深圳市锐明技术股份有限公司 | Alarm method, alarm apparatus, control device and storage medium |
-
2021
- 2021-12-14 CN CN202111529641.2A patent/CN114283494A/en active Pending
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115180059A (en) * | 2022-07-05 | 2022-10-14 | 苏州万佳电器有限公司 | Fall warning device and method, two-wheel vehicle and storage medium |
| WO2024077550A1 (en) * | 2022-10-13 | 2024-04-18 | 深圳市锐明技术股份有限公司 | Alarm method, alarm apparatus, control device and storage medium |
| CN116035564A (en) * | 2022-12-06 | 2023-05-02 | 北京顺源辰辰科技发展有限公司 | Dysphagia and aspiration intelligent detection method and device and electronic equipment |
| CN115868966A (en) * | 2022-12-12 | 2023-03-31 | 北京顺源辰辰科技发展有限公司 | Intelligent action assisting system and intelligent action assisting method |
| CN115969356A (en) * | 2022-12-12 | 2023-04-18 | 北京顺源辰辰科技发展有限公司 | Multimode behavior monitoring method and device based on intelligent sliding rail |
| CN116269355A (en) * | 2023-05-11 | 2023-06-23 | 江西珉轩智能科技有限公司 | Safety monitoring system based on figure gesture recognition |
| CN116687394A (en) * | 2023-08-04 | 2023-09-05 | 亿慧云智能科技（深圳）股份有限公司 | Tumble detection method, device, equipment and storage medium based on millimeter wave radar |
| CN116687394B (en) * | 2023-08-04 | 2023-10-20 | 亿慧云智能科技（深圳）股份有限公司 | Tumble detection method, device, equipment and storage medium based on millimeter wave radar |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114283494A (en) | Early warning method, device, equipment and storage medium for user falling | |
| CN109452935B (en) | Non-invasive method and system for estimating blood pressure from a vascular plethysmogram using statistical post-processing | |
| CN107595259A (en) | A kind of alarm method, device, wearable device and storage medium | |
| JP6310476B2 (en) | Method and system for reducing the load caused by harmful alarms in clinical settings | |
| TW201510917A (en) | Automated quality assessment of physiological signals | |
| US10206593B2 (en) | Method and system of detecting arrhythmia using photoplethysmogram signal | |
| CN113287175A (en) | Interactive health status evaluation method and system thereof | |
| US10978209B2 (en) | Method of an interactive health status assessment and system thereof | |
| US11432778B2 (en) | Methods and systems for patient monitoring | |
| US11596764B2 (en) | Electronic device and method for providing information for stress relief by same | |
| US20190326020A1 (en) | Video Conferencing and Virtual Appointments | |
| CN110755047B (en) | Cardiovascular and cerebrovascular disease prevention method, device, terminal and storage medium | |
| Nazário et al. | Quality of context evaluating approach in AAL environment using IoT technology | |
| US20220254241A1 (en) | Ai-based video tagging for alarm management | |
| Khan et al. | Severe analysis of cardiac disease detection using the wearable device by artificial intelligence | |
| CN113040757B (en) | Head posture monitoring method and device, head intelligent wearable device and storage medium | |
| CN116013548A (en) | Intelligent ward monitoring method and device based on computer vision | |
| CN115177263A (en) | Heart detection method and system based on dynamic and static combination and readable storage medium | |
| CN108837271A (en) | The output method and Related product of electronic device, prompt information | |
| CN113208609A (en) | Electrocardio information management system | |
| WO2016051379A1 (en) | User state classification | |
| US20240194359A1 (en) | Methods and systems for transmitting medical information according to prioritization criteria | |
| CN109620156A (en) | A kind of sleep detection method and device | |
| TW202022891A (en) | System and method of interactive health assessment | |
| US11657701B2 (en) | Systems and methods for emergency alert and call regarding driver condition |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |