Intelligent identification system and method for preventing bed from falling and mattress

Abstract

The invention relates to the technical field of medical care, and discloses an intelligent identification system and method for preventing bed falling and a mattress, and the system comprises an infrared module, a video module, a fusion module and an execution module. The method and the mattress both correspond to the system. According to the invention, the bed falling risk of the patient can be accurately evaluated in multiple dimensions and intervened in time; the infrared module detects abnormal body temperature features, the video module detects anti-bed-falling features, the fusion module combines the abnormal body temperature features and the anti-bed-falling features to correct the bed-falling probability, and the execution module controls the foldable baffle to act and generates alarm information based on the bed-falling probability; therefore, the limitation of a traditional single monitoring mode is changed, the bed falling possibility is comprehensively analyzed from multiple dimensions such as the body temperature and the limb movement, and the judgment on the bed falling risk of the patient is more comprehensive and accurate.

Description

Technical Field

[0001] This application relates to the field of medical care technology, and specifically to an intelligent identification system, method, and mattress for preventing patients from falling out of bed. Background Art

[0002] In the field of medical care, the problem of children falling out of bed after surgery is a safety issue that urgently needs to be solved. Currently, the existing technical means for preventing children from falling out of bed are relatively limited. Commonly, some anti-falling-out-of-bed devices based on a single monitoring method are used. For example, some mattresses only judge whether there is a risk of falling out of bed through pressure sensing. However, the physical condition of children after surgery is complex and changeable, and single pressure monitoring is difficult to comprehensively and accurately evaluate the possibility of their falling out of bed.

[0003] Chinese Patent No. CN117137748A discloses a clinical fall intelligent sensing mattress, a fall warning system, and a fall warning method. This invention relies on the monitoring of pressure sensing electrode sheets and lacks multi-factor fusion analysis. Further, in practical applications, important factors such as abnormal body temperature and limb movement changes in children after surgery are not included in the monitoring and evaluation system. Moreover, it only focuses on fall warning, lacks effective measures for directly preventing falling out of bed, and does not use multiple monitoring methods to comprehensively judge the state of children from multiple dimensions.

[0004] In summary, the existing technology cannot respond in a timely and accurate manner when facing various situations that may occur in children after surgery, and it is difficult to effectively prevent the occurrence of children falling out of bed events, posing a relatively large potential safety hazard. Therefore, there is an urgent need for a new technical solution for intelligent identification of preventing falling out of bed to effectively prevent the occurrence of children falling out of bed events. Summary of the Invention

[0005] The purpose of this application is to provide an intelligent identification system, method, and mattress for preventing falling out of bed to solve the technical problems raised in the above background art.

[0006] To achieve the above purpose, this application discloses the following technical solutions:

[0007] In a first aspect, this application discloses an intelligent identification system for preventing falling out of bed, including:

[0008] An infrared module for detecting the abnormal body temperature characteristics of a patient, and the degree of association between the abnormal body temperature characteristics and the probability of falling out of bed is characterized by an association index;

[0009] A video module for detecting the anti-falling-out-of-bed characteristics of a patient, and the anti-falling-out-of-bed characteristics correspond to the probability of falling out of bed;

[0010] A fusion module for, when detecting the existence of abnormal body temperature characteristics, correcting the probability of falling out of bed corresponding to the anti-falling-out-of-bed characteristics based on the abnormal body temperature characteristics, and the fusion module is communicatively connected to the infrared module and the video module;

[0011] An execution module for controlling the action of a foldable baffle and generating an alarm message based on the probability of falling out of bed, which is communicatively connected to an infrared module, a video module, and a fusion module.

[0012] Preferably, the detection of the abnormal body temperature feature includes:

[0013] Using an infrared sensing element preset in the infrared module to detect the body surface temperature of the patient in real time. Based on a preset normal body temperature range threshold, when the detected real-time body surface temperature of the patient does not belong to this normal body temperature range threshold, it is determined that an abnormal body temperature feature appears.

[0014] Preferably, the degree of association between the abnormal body temperature feature and the probability of falling out of bed is characterized by an association index, including:

[0015] Obtaining historical clinical data in which the abnormal body temperature feature is associated with a falling-out-of-bed event, performing statistical analysis based on this data, establishing an association relationship between different abnormal body temperature features and the probability of falling out of bed, and performing regression analysis on this association relationship to obtain the corresponding association index.

[0016] Preferably, the detection of the anti-falling-out-of-bed feature includes:

[0017] Using a camera preset in the video module to capture the limb movements and body position postures of the patient on the mattress in real time, and extracting anti-falling-out-of-bed features based on the results of this real-time capture. The anti-falling-out-of-bed features include the height of sitting up, the amplitude of limb extension, and the distance from the edge of the bed.

[0018] Preferably, the anti-falling-out-of-bed feature corresponds to the probability of falling out of bed, including:

[0019] Obtaining historical clinical data in which the anti-falling-out-of-bed feature is associated with a falling-out-of-bed event, performing statistical analysis based on this data, establishing a corresponding relationship between different anti-falling-out-of-bed features and the probability of falling out of bed, and performing regression analysis on this corresponding relationship to obtain the corresponding probability of falling out of bed; wherein, the corresponding relationship between different anti-falling-out-of-bed features and the probability of falling out of bed is expressed as:

[0020]

[0021] Wherein, GD is the feature value of the height of sitting up for calculating the probability of falling out of bed after normalization, FD is the feature value of the amplitude of limb extension for calculating the probability of falling out of bed after normalization, JL is the feature value of the distance from the edge of the bed for calculating the probability of falling out of bed after normalization, is the degree of deviation of the feature value of the height of sitting up from the preset threshold range of the feature value of the height of sitting up, is the degree of deviation of the feature value of the amplitude of limb extension from the preset threshold range of the feature value of the amplitude of limb extension, The degree of deviation of the bedside proximity eigenvalue from the preset threshold range of the bedside proximity eigenvalue, max() is the maximum value operator, α1, α2, and α3 are preset weight coefficients, and GL is the calculated probability of falling out of bed.

[0022] Preferably, when an abnormal body temperature feature is detected, correcting the probability of falling out of bed corresponding to the fall prevention feature based on the abnormal body temperature feature includes:

[0023] Calculating the probability of falling out of bed corresponding to the fall prevention feature corrected based on the abnormal body temperature feature by using a preset fall probability correction formula, and the fall probability correction formula is:

[0024]

[0025] where GL TW_t is the probability of falling out of bed corresponding to the fall prevention feature corrected by the abnormal body temperature feature at time t, is the degree of deviation of the abnormal body temperature feature at time t from the preset normal body temperature range threshold, GL′ t is the slope value of the probability of falling out of bed with respect to time at time t, GL XZ_t is the calculated probability of falling out of bed corresponding to the fall prevention feature corrected based on the abnormal body temperature feature at time t.

[0026] Preferably, the control of the folding baffle movement includes:

[0027] The execution module sets different intervals of the probability of falling out of bed corresponding to different folding baffle control strategies. When the probability of falling out of bed is in the corresponding interval, the folding baffle is controlled to rise to a preset different height to form a protective enclosure, and when the probability of falling out of bed is in the corresponding interval, the lifting speed of the folding baffle rises to a preset different speed.

[0028] Preferably, the generation of the alarm information includes:

[0029] The execution module presets alarm levels corresponding to different probabilities of falling out of bed. When the probability of falling out of bed reaches the corresponding alarm level, an alarm information is sent to the terminal device of the medical staff through a preset communication device, and the alarm information includes the bed location information and the current risk level of falling out of bed.

[0030] In a second aspect, the present application discloses an intelligent identification method for fall prevention, which is applicable to the intelligent identification system for fall prevention as described above, and includes the following steps:

[0031] S1: Detecting the abnormal body temperature feature of the patient, and the degree of association between the abnormal body temperature feature and the probability of falling out of bed is characterized by an association index;

[0032] S2: Detect the anti-falling bed features of the patient, where the anti-falling bed features correspond to the probability of falling out of bed;

[0033] S3: When an abnormal body temperature feature is detected, correct the probability of falling out of bed corresponding to the anti-falling bed feature based on the abnormal body temperature feature;

[0034] S4: Control the action of the foldable baffle and generate an alarm message based on the probability of falling out of bed.

[0035] In a third aspect, the present application discloses an intelligent identification mattress for preventing falling out of bed. The mattress includes a foldable baffle, a communication device, and a mattress body. The foldable baffle is disposed on the periphery of the mattress body, and the foldable baffle is connected to the communication device, and the communication device is communicatively connected to the intelligent identification system for preventing falling out of bed as described above. When the foldable baffle and the communication device are operating, the intelligent identification method for preventing falling out of bed as described above is executed.

[0036] Beneficial effects: The intelligent identification system, method, and mattress for preventing falling out of bed of the present application utilize an infrared module, a video module, a fusion module, and an execution module to achieve the function of multi-dimensional and accurate assessment of the patient's risk of falling out of bed and timely intervention; the infrared module detects abnormal body temperature features, the video module detects anti-falling bed features, the fusion module combines the two to correct the probability of falling out of bed, and the execution module controls the action of the foldable baffle and generates an alarm message based on the probability of falling out of bed; thus, through the information interaction and collaborative processing of multiple modules, the limitations of the traditional single monitoring method are changed, and the possibility of falling out of bed is comprehensively analyzed from multiple dimensions such as body temperature and limb movements, making the judgment of the patient's risk of falling out of bed more comprehensive and accurate. When a high risk of falling out of bed is judged, the foldable baffle is raised in time for protection, and the alarm message can also notify the medical staff, effectively reducing the risk of the patient falling out of bed and ensuring the safety of the patient during the medical care process. Description of the Drawings

[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative efforts.

[0038] Figure 1 It is a structural block diagram of the intelligent identification system for preventing falling out of bed provided by the embodiment of the present application;

[0039] Figure 2 It is a flow block diagram of the intelligent identification method for preventing falling out of bed provided by the embodiment of the present application. Detailed Embodiments

[0040] The technical solutions in the embodiments of the present application will be clearly and completely described below. Apparently, the described embodiments are only a part of the embodiments of the present application, rather than all embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the scope of protection of the present application.

[0041] In this article, the term "including" is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or also includes elements inherent in such a process, method, article or device. Without further limitation, the elements defined by the statement "including..." do not exclude the existence of additional identical elements in the process, method, article or device including the said elements.

[0042] The first aspect of this embodiment discloses an intelligent recognition system for preventing patients from falling out of bed as Figure 1 shown, including:

[0043] An infrared module for detecting the abnormal body temperature characteristics of a patient, and the degree of association between the abnormal body temperature characteristics and the probability of falling out of bed is characterized by an association index;

[0044] A video module for detecting the anti-falling-out-of-bed characteristics of a patient, and the anti-falling-out-of-bed characteristics correspond to the probability of falling out of bed;

[0045] A fusion module for, when detecting the existence of abnormal body temperature characteristics, correcting the probability of falling out of bed corresponding to the anti-falling-out-of-bed characteristics based on the abnormal body temperature characteristics, and the fusion module is communicatively connected to the infrared module and the video module;

[0046] An execution module for controlling the action of a foldable baffle and generating an alarm message based on the probability of falling out of bed, and the execution module is communicatively connected to the infrared module, the video module and the fusion module.

[0047] By the above, this embodiment utilizes the infrared module, the video module, the fusion module and the execution module to realize the function of multi-dimensional accurate assessment of the risk of a patient falling out of bed and timely intervention; the infrared module detects abnormal body temperature characteristics, the video module detects anti-falling-out-of-bed characteristics, the fusion module combines the two to correct the probability of falling out of bed, and the execution module controls the action of the foldable baffle and generates an alarm message based on the probability of falling out of bed; thus, through the information interaction and collaborative processing of multiple modules, the limitation of the traditional single monitoring method is changed, and the possibility of falling out of bed is comprehensively analyzed from multiple dimensions such as body temperature and limb movements, making the judgment of the risk of a patient falling out of bed more comprehensive and accurate. When a high risk of falling out of bed is judged, the foldable baffle can be raised in time for protection, and the alarm message can also notify the medical staff, effectively reducing the risk of a patient falling out of bed and ensuring the safety of the patient during the medical care process.

[0048] Specifically, the detection of the abnormal body temperature feature includes:

[0049] The infrared sensing element preset in the infrared module is used to detect the body surface temperature of the patient in real time. Based on the preset normal body temperature range threshold, when the detected real-time body surface temperature of the patient does not belong to this normal body temperature range threshold, it is determined that an abnormal body temperature feature appears.

[0050] Through the above, this embodiment uses any existing infrared sensing element, which is preset in the infrared module, and combines with the normal body temperature range threshold to achieve accurate detection of the abnormal body temperature feature of the patient. The infrared sensing element detects the patient's body surface temperature in real time. Once the detected value exceeds the preset normal body temperature range threshold, it can quickly determine that an abnormal body temperature feature appears. This simple and efficient detection method provides key data for subsequent analysis of the risk of falling out of bed.

[0051] Specifically, the degree of association between the abnormal body temperature feature and the probability of falling out of bed is characterized by an association index, including:

[0052] Obtain historical clinical data in which the abnormal body temperature feature is associated with the event of falling out of bed. Based on this data, conduct statistical analysis, establish the association relationship between different abnormal body temperature features and the probability of falling out of bed, and conduct regression analysis on this association relationship to obtain the corresponding association index.

[0053] Through the above, this embodiment uses existing statistical analysis techniques and regression analysis techniques to achieve statistical analysis and regression analysis of historical clinical data, thereby quantifying the degree of association between the abnormal body temperature feature and the probability of falling out of bed, providing a scientific basis for the fusion module to correct the probability of falling out of bed, avoiding subjective judgment, making the system more objective and accurate when evaluating the risk of falling out of bed, and thus being able to formulate more reasonable anti-falling-out-of-bed measures and improving the system's ability to prevent falling out of bed.

[0054] Specifically, the detection of the anti-falling-out-of-bed feature includes:

[0055] The camera preset in the video module is used to capture the limb movements and body position postures of the patient on the mattress in real time. Based on the results of this real-time capture, anti-falling-out-of-bed features are extracted, and the anti-falling-out-of-bed features include the height of sitting up, the amplitude of limb extension, and the distance from the edge of the bed.

[0056] Through the above, this embodiment uses any existing camera preset in the video module to achieve real-time capture of the patient's limb movements and body position postures, and effectively extracts the anti-falling-out-of-bed features. The camera monitors the patient's activities on the mattress in all directions, and extracts key features such as the height of sitting up, the amplitude of limb extension, and the distance from the edge of the bed, thereby directly reflecting the relationship between the patient's activity state and the risk of falling out of bed, and providing rich data support for subsequent calculation of the probability of falling out of bed.

[0057] Specifically, the anti-falling bed features correspond to the probability of falling out of bed, including:

[0058] Obtain historical clinical data in which the anti-falling bed features are associated with falling-out-of-bed events, conduct statistical analysis based on this data, establish the corresponding relationship between different anti-falling bed features and the probability of falling out of bed, and conduct regression analysis on this corresponding relationship to obtain the corresponding probability of falling out of bed; among them, the corresponding relationship between different anti-falling bed features and the probability of falling out of bed is expressed as:

[0059]

[0060] Among them, GD is the eigenvalue of the body sitting-up height feature for calculating the probability of falling out of bed after normalization, FD is the eigenvalue of the limb stretching amplitude feature for calculating the probability of falling out of bed after normalization, JL is the eigenvalue of the distance from the edge of the bed for calculating the probability of falling out of bed after normalization, is the degree of deviation of the body sitting-up height eigenvalue from the preset threshold range of the body sitting-up height eigenvalue, is the degree of deviation of the limb stretching amplitude eigenvalue from the preset threshold range of the limb stretching amplitude eigenvalue, is the degree of deviation of the distance from the edge of the bed eigenvalue from the preset threshold range of the distance from the edge of the bed eigenvalue, max() is the maximum value calculation operator, α1, α2, and α3 are preset weight coefficients, and GL is the calculated probability of falling out of bed.

[0061] In the actual application of this embodiment, the corresponding weight coefficients α1 + α2 + α3 = 1 can be set through regression analysis. Further, on the basis of fixed weight coefficients, based on the calculation realizes the capture of the most influential feature among the three features of the body sitting-up height, limb stretching amplitude, and distance from the edge of the bed.

[0062] Through the above, this embodiment realizes the accurate calculation of the probability of falling out of bed corresponding to the anti-falling bed features. By quantifying the relationship between different anti-falling bed features and the probability of falling out of bed, comprehensively considering the body sitting-up height, limb stretching amplitude, distance from the edge of the bed and their degree of deviation from the threshold, and combining with the preset weight coefficients, the probability of falling out of bed is accurately calculated, providing accurate data support for the execution module to take corresponding measures, and improving the pertinence and effectiveness of the system in preventing falling out of bed.

[0063] Specifically, when an abnormal body temperature feature is detected, based on this abnormal body temperature feature, the probability of falling out of bed corresponding to the anti-falling bed feature is corrected, including:

[0064] Use the preset probability of falling out of bed correction formula to calculate the probability of falling out of bed corresponding to the anti-falling bed feature corrected based on the abnormal body temperature feature. The probability of falling out of bed correction formula is:

[0065]

[0066] Among them, GL TW_t is the probability of falling out of bed corresponding to the fall prevention feature corrected by the abnormal body temperature feature at time t, is the degree of deviation between the abnormal body temperature feature at time t and the preset normal body temperature range threshold, GL′ t is the slope value of the probability of falling out of bed with respect to time at time t, GL XZ_t is the calculated probability of falling out of bed corresponding to the fall prevention feature corrected based on the abnormal body temperature feature at time t.

[0067] By the above, this embodiment realizes more accurate calculation of the probability of falling out of bed by using the fall probability correction formula. When an abnormal body temperature feature is detected, the degree of deviation between the abnormal body temperature feature and the normal body temperature range threshold and the slope value of the probability of falling out of bed with respect to time are comprehensively considered, and the probability of falling out of bed calculated based on the fall prevention feature is corrected. Thus, not only the current state features are considered, but also the influence of abnormal body temperature and the change trend (i.e., the slope value) of the probability of falling out of bed are taken into account, further improving the accuracy of the fall risk assessment and providing a more reliable basis for timely and appropriate fall prevention intervention.

[0068] Specifically, the control of the folding baffle movement includes:

[0069] The execution module sets different intervals of the probability of falling out of bed corresponding to different folding baffle control strategies. When the probability of falling out of bed is in the corresponding interval, the execution module controls the folding baffle to rise to different preset heights to form a protective enclosure, and when the probability of falling out of bed is in the corresponding interval, the lifting speed of the folding baffle rises to different preset speeds.

[0070] By the above, this embodiment realizes the intelligent control of the folding baffle by using different control strategies set by the execution module according to the probability of falling out of bed. The execution module controls the folding baffle to rise to different heights and adjusts the lifting speed for different intervals of the probability of falling out of bed. When the probability of falling out of bed is relatively high, the baffle quickly rises to a relatively high position to form an effective protective enclosure, and vice versa, relatively lower protective measures are taken. This control method of dynamically adjusting according to the risk level not only ensures timely and effective prevention of falling out of bed in high-risk situations, but also reasonably utilizes resources in low-risk situations, improving the practicability and safety of the fall prevention device.

[0071] Specifically, the generation of the alarm information includes:

[0072] In the execution module, different alarm levels corresponding to different fall-out-of-bed probabilities are preset. When the fall-out-of-bed probability reaches the corresponding alarm level, an alarm message is sent to the terminal device of the medical staff through a preset communication device. The alarm message includes the bed location information and the current fall risk level.

[0073] Through the above, in this embodiment, the timely and accurate alarm function is realized by using the alarm levels preset in the execution module and the communication device. The execution module sets corresponding alarm levels according to different fall-out-of-bed probabilities. When the fall-out-of-bed probability reaches the corresponding level, an alarm message including the bed location information and the fall risk level is sent to the medical staff terminal through the communication device. This enables the medical staff to quickly understand the specific situation of the patient, take corresponding measures in a timely manner, shortens the response time, improves the efficiency and safety of medical care, and effectively reduces the possible harm caused by the patient falling out of bed.

[0074] The second aspect of this embodiment discloses an intelligent identification method for preventing falling out of bed as Figure 2 shown. This method is applicable to the intelligent identification system for preventing falling out of bed as described above, and includes the following steps:

[0075] S1: Detect the abnormal body temperature characteristics of the patient. The degree of association between the abnormal body temperature characteristics and the fall-out-of-bed probability is characterized by an association index;

[0076] S2: Detect the fall-prevention characteristics of the patient. The fall-prevention characteristics correspond to the fall-out-of-bed probability;

[0077] S3: When an abnormal body temperature characteristic is detected, correct the fall-out-of-bed probability corresponding to the fall-prevention characteristics based on the abnormal body temperature characteristic;

[0078] S4: Control the action of the foldable baffle and generate an alarm message based on the fall-out-of-bed probability.

[0079] It should be noted that the intelligent identification method for preventing falling out of bed in this embodiment corresponds to the aforementioned intelligent identification system for preventing falling out of bed. Therefore, for the content not specifically described in the intelligent identification method for preventing falling out of bed in this embodiment, it can, but is not limited to, function definitions, working principles, technical effects, etc., and can refer to the aforementioned intelligent identification method for preventing falling out of bed. This text will not elaborate here.

[0080] In the third aspect of this embodiment, an intelligent recognition mattress for preventing patients from falling out of bed is disclosed. The mattress includes a foldable baffle, a communication device, and a mattress body. The foldable baffle is disposed on the periphery of the mattress body, and the foldable baffle is connected to the communication device. The communication device is communicatively connected to the intelligent recognition system for preventing patients from falling out of bed as described above. When the foldable baffle and the communication device are operating, the intelligent recognition method for preventing patients from falling out of bed as described above is executed. Preferably, in this embodiment, the number of foldable baffles is four, and the four foldable baffles are respectively installed at the four sides of the mattress body. The communication device can be any one in the prior art, such as a wireless communication device or a communication data line.

[0081] Similarly, it should be noted that the intelligent recognition mattress for preventing patients from falling out of bed in this embodiment corresponds to the intelligent recognition system for preventing patients from falling out of bed described above. Therefore, for the content not specifically described in the intelligent recognition mattress for preventing patients from falling out of bed in this embodiment, it can, but is not limited to, function definitions, working principles, technical effects, etc., and can refer to the intelligent recognition mattress for preventing patients from falling out of bed described above. This text will not elaborate here.

[0082] In summary, the intelligent recognition system, method, and mattress for preventing patients from falling out of bed in this embodiment utilize an infrared module, a video module, a fusion module, and an execution module to achieve the function of multi-dimensional accurate assessment of the risk of patients falling out of bed and timely intervention. The infrared module detects abnormal body temperature characteristics, the video module detects the characteristics of preventing patients from falling out of bed, the fusion module combines the two to correct the probability of falling out of bed, and the execution module controls the action of the foldable baffle and generates an alarm message based on the probability of falling out of bed. Therefore, through the information interaction and collaborative processing of multiple modules, the limitations of the traditional single monitoring method are changed, and the possibility of falling out of bed is comprehensively analyzed from multiple dimensions such as body temperature and limb movements, making the judgment of the risk of patients falling out of bed more comprehensive and accurate. When a high risk of falling out of bed is judged, the foldable baffle is raised in time for protection, and the alarm message can also notify medical staff, effectively reducing the risk of patients falling out of bed and ensuring the safety of patients during medical care.

[0083] In the embodiments provided in the present application, it should be understood that the embodiments described herein can be implemented in hardware, software, firmware, middleware, code, or any suitable combination thereof. For hardware implementation, the processor can be implemented in one or more of the following units: application specific integrated circuit (ASIC), digital signal processor (DSP), digital signal processing device (DSPD), programmable logic device (PLD), field programmable gate array (FPGA), processor, controller, microcontroller, microprocessor, other electronic units designed to implement the functions described herein, or a combination thereof. For software implementation, part or all of the processes of the embodiments can be completed by instructing the relevant hardware through a computer program. When implemented, the above program can be stored in a computer-readable storage medium or transmitted as one or more instructions or codes on a computer-readable storage medium. The computer-readable storage medium includes computer storage media and communication media, where the communication media includes any medium that facilitates the transmission of a computer program from one place to another. The storage media can be any available medium that can be accessed by a computer. The computer-readable storage medium can include, but is not limited to, RAM, ROM, EEPROM, CD-ROM, or other optical disc storage, magnetic disk storage media, or other magnetic storage devices, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer.

[0084] Finally, it should be noted that the above are only the preferred embodiments of the present application and are not used to limit the present application. Although the present application has been described in detail with reference to the foregoing embodiments, for those skilled in the art, they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. An intelligent recognition system for preventing falling out of bed, characterized in that, Comprising: An infrared module for detecting abnormal body temperature characteristics of a patient, and the degree of association between the abnormal body temperature characteristics and the probability of falling out of bed is characterized by an association index; A video module for detecting the anti-falling-out-of-bed characteristics of a patient, and the anti-falling-out-of-bed characteristics correspond to the probability of falling out of bed; A fusion module for, when detecting the existence of abnormal body temperature characteristics, correcting the probability of falling out of bed corresponding to the anti-falling-out-of-bed characteristics based on the abnormal body temperature characteristics, and the fusion module is communicatively connected to the infrared module and the video module; An execution module for controlling the action of a foldable baffle and generating an alarm message based on the probability of falling out of bed, and the execution module is communicatively connected to the infrared module, the video module and the fusion module.

2. The intelligent identification system for preventing a patient from falling out of bed according to claim 1, wherein The detection of the abnormal body temperature characteristics includes: Using an infrared sensing element preset in the infrared module to perform real-time detection on the body surface temperature of the patient, and based on a preset normal body temperature range threshold, when the detected real-time body surface temperature of the patient does not belong to the normal body temperature range threshold, it is determined that abnormal body temperature characteristics occur.

3. The intelligent identification system for preventing falling out of bed according to claim 2, characterized in that, The degree of association between the abnormal body temperature characteristics and the probability of falling out of bed is characterized by an association index, including: Obtaining historical clinical data in which the abnormal body temperature characteristics are associated with falling-out-of-bed events, performing statistical analysis based on the data, establishing an association relationship between different abnormal body temperature characteristics and the probability of falling out of bed, and performing regression analysis on the association relationship to obtain a corresponding association index.

4. The intelligent identification system for preventing a patient from falling out of bed according to claim 1, characterized in that, The detection of the anti-falling-out-of-bed characteristics includes: Using a camera preset in the video module to perform real-time capture of the limb movements and body position postures of the patient on the mattress, and extracting anti-falling-out-of-bed characteristics based on the results of the real-time capture, and the anti-falling-out-of-bed characteristics include the height of sitting up of the body, the amplitude of limb extension, and the distance from the edge of the bed.

5. The intelligent recognition system for preventing a patient from falling out of bed according to claim 4, characterized in that, The anti-falling-out-of-bed characteristics corresponding to the probability of falling out of bed include: Obtaining historical clinical data in which the anti-falling-out-of-bed characteristics are associated with falling-out-of-bed events, performing statistical analysis based on the data, establishing a corresponding relationship between different anti-falling-out-of-bed characteristics and the probability of falling out of bed, and performing regression analysis on the corresponding relationship to obtain a corresponding probability of falling out of bed; wherein, the corresponding relationship between the different anti-falling-out-of-bed characteristics and the probability of falling out of bed is expressed as: Among them, GD is the eigenvalue of the body sitting-up height for calculating the probability of falling out of bed after normalization, FD is the eigenvalue of the limb stretching amplitude for calculating the probability of falling out of bed after normalization, and JL is the eigenvalue of the distance from the edge of the bed for calculating the probability of falling out of bed after normalization. is the degree of deviation of the eigenvalue of the body sitting-up height from the preset threshold range of the eigenvalue of the body sitting-up height. is the degree of deviation of the eigenvalue of the limb stretching amplitude from the preset threshold range of the eigenvalue of the limb stretching amplitude. is the degree of deviation of the eigenvalue of the distance from the edge of the bed from the preset threshold range of the eigenvalue of the distance from the edge of the bed, max( ) is the maximum value calculation operator, α1, α2, and α3 are preset weight coefficients, and GL is the calculated probability of falling out of bed.

6. The intelligent recognition system for preventing a patient from falling out of bed according to claim 1, characterized in that, The method for, when detecting the existence of abnormal body temperature characteristics, correcting the probability of falling out of bed corresponding to the anti-falling-out-of-bed characteristics based on the abnormal body temperature characteristics includes: Calculating the probability of falling out of bed corresponding to the anti-falling-out-of-bed characteristics corrected based on the abnormal body temperature characteristics by using a preset probability-of-falling-out-of-bed correction formula, and the probability-of-falling-out-of-bed correction formula is: Among them, GL TW_t is the probability of falling out of bed corresponding to the fall prevention feature corrected by the abnormal body temperature feature at time t, is the degree of deviation between the abnormal body temperature feature at time t and the preset normal body temperature range threshold, GL′ t is the slope value of the probability of falling out of bed with respect to time at time t, GL XZ_t is the calculated probability of falling out of bed corresponding to the fall prevention feature corrected based on the abnormal body temperature feature at time t.

7. The intelligent recognition system for preventing a patient from falling out of bed according to claim 1, wherein, The control of the action of the foldable baffle includes: The execution module sets different intervals of the probability of falling out of bed corresponding to different foldable baffle control strategies, and when the probability of falling out of bed is in the corresponding interval, the foldable baffle is controlled to rise to different preset heights to form a protective enclosure, and when the probability of falling out of bed is in the corresponding interval, the lifting speed of the foldable baffle rises to different preset speeds.

8. The intelligent identification system for preventing a patient from falling out of bed according to claim 1, characterized in that, The generation of the alarm message includes: In the execution module, different alarm levels corresponding to different falling-out-of-bed probabilities are preset. When the falling-out-of-bed probability reaches the corresponding alarm level, an alarm message is sent to the terminal device of the medical staff through a preset communication device. The alarm message includes the information of the bed location and the current falling-out-of-bed risk level.

9. An intelligent recognition method for preventing falling out of bed, which is applicable to the intelligent recognition system for preventing falling out of bed as described in any one of claims 1-8, characterized in that, It includes the following steps: S1: Detect the abnormal body temperature characteristics of the patient, and the degree of association between the abnormal body temperature characteristics and the falling-out-of-bed probability is characterized by an association index; S2: Detect the anti-falling-out-of-bed characteristics of the patient, and the anti-falling-out-of-bed characteristics correspond to the falling-out-of-bed probability; S3: When an abnormal body temperature characteristic is detected, correct the falling-out-of-bed probability corresponding to the anti-falling-out-of-bed characteristic based on the abnormal body temperature characteristic; S4: Control the action of the foldable baffle and generate an alarm message based on the falling-out-of-bed probability.

10. An intelligent recognition mattress for preventing falling out of bed, characterized in that, The mattress includes a foldable baffle, a communication device and a mattress body. The foldable baffle is arranged on the periphery of the mattress body, and the foldable baffle is connected to the communication device. The communication device is communicatively connected to the intelligent identification system for anti-falling-out-of-bed according to any one of claims 1-8. When the foldable baffle and the communication device are operating, the intelligent identification method for anti-falling-out-of-bed according to claim 9 is executed.

Images