Personnel care method, device, computer device and storage medium

Abstract

Embodiments of the present application disclose a person care method and device, computer equipment and a storage medium. The method comprises: obtaining log data of each door magnetic sensor arranged at a residence of a monitored person to obtain original sequence group data; performing adaptive fuzzy clustering on the original sequence group data to obtain a plurality of sequence group sets; determining a clustering center of each sequence group set and a maximum distance of the clustering center, and setting the maximum distance of the clustering center as a time deviation threshold; obtaining a monitoring signal collected by each door magnetic sensor in real time; determining whether a distance between current monitoring data and any sequence group set is within the corresponding time deviation threshold; if yes, determining that the current monitoring data are matched with the plurality of sequence group sets successfully; determining a behavior category of the monitored person according to the matched sequence group set; and if not, generating a remote reminding information. The method of the embodiments of the present application can improve the safety care efficiency of the monitored person.

Description

Technical Field

[0001] This invention relates to the Internet of Things, and more specifically to methods, devices, computer equipment, and storage media for personnel care. Background Technology

[0002] With the popularization of smart homes, door magnetic sensors can now be connected to the cloud, acquiring data from individual sensors through smart gateways and reporting it to the cloud. However, this creates "information silos," "data silos," and "device silos." The information provided by a single device cannot express a complete meaning and loses its significance. Therefore, how to establish data on the elderly's daily routines through smart homes and back-end data analysis systems, and realize real-time monitoring and early warning of the elderly's living conditions, has become an urgent problem to be solved.

[0003] Existing technology only reports when people go out through door magnetic sensors, and cannot report situations where people do not go out but need assistance in a timely manner. This can easily lead to problems such as elderly people falling or suffering sudden illnesses not being detected and assisted in time, and cannot improve the efficiency of safety care for the monitored people.

[0004] Therefore, it is necessary to design a new method to effectively address the problem of elderly people not being detected and rescued in a timely manner due to falls, sudden illnesses, etc., with personalized, real-time, and accurate monitoring capabilities, thereby improving the efficiency of safety care for those being monitored. Summary of the Invention

[0005] The purpose of this invention is to overcome the shortcomings of the prior art and provide methods, devices, computer equipment and storage media for personnel care.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: a personnel care method, comprising:

[0007] Log data from each door magnetic sensor installed in the residence of the monitored person is acquired to obtain raw sequence group data based on time series.

[0008] Adaptive fuzzy clustering is performed on the original sequence group data to obtain multiple sequence group sets;

[0009] Determine the cluster center and the maximum distance between the cluster centers for each of the sequence groups, and set the maximum distance between the cluster centers as a time deviation threshold;

[0010] The monitoring signals collected by each door magnetic sensor are acquired in real time to obtain the current monitoring data;

[0011] Determine whether the distance between the current monitoring data and any of the sequence sets is within the time deviation threshold of the corresponding sequence set;

[0012] If the distance between the current monitoring data and any of the sequence sets is within the time deviation threshold of the corresponding sequence set, then it is determined that the current monitoring data has successfully matched multiple sequence sets respectively.

[0013] The behavioral category of the monitored personnel is determined based on the set of matched sequence groups.

[0014] If the distance between the current monitoring data and any of the sequence sets is not within the time deviation threshold of the corresponding sequence set, a remote reminder message is generated.

[0015] The further technical solution is as follows: the original sequence group data includes the trajectory data of the monitored personnel within the monitoring area every day.

[0016] The further technical solution is as follows: the sequence set includes behavioral patterns and the time intervals in which the behavioral patterns are generated.

[0017] A further technical solution is as follows: Adaptive fuzzy clustering is performed on the original sequence group data to obtain multiple sequence group sets, including:

[0018] The behavior pattern points obtained by mean shift are used to smooth and filter the original sequence group data, and the original sequence group data that does not meet the requirements are deleted. The original sequence group data belonging to the same category are assigned the sequence value of the corresponding behavior pattern to obtain multiple sequence group sets.

[0019] A further technical solution is as follows: the behavior pattern points obtained by mean shift are used to smooth and filter the original sequence group data, and the original sequence group data that does not meet the requirements are deleted. The original sequence group data belonging to the same category are assigned sequence values ​​corresponding to the behavior pattern to obtain multiple sequence group sets, including:

[0020] Calculate the MeanShift vector for each action sequence point within the original sequence group data;

[0021] Move the behavior pattern point to the next time point according to the MeanShift vector, calculate the MeanShift vector of the next time point, and mark all the behavior sequences that the original sequence group data has passed through. When the passed behavior sequence has been marked, assign the convergence value of the marked behavior sequence to the current behavior sequence.

[0022] Determine whether the MeanShift vector at the next time point is less than the convergence threshold;

[0023] If the MeanShift vector at the next time point is less than the convergence threshold, then the convergence point of the behavior sequence corresponding to the original sequence group data is stored in the sequence group set.

[0024] Determine whether each data point within the original sequence group has converged;

[0025] If every data point within the original sequence set converges, then homogeneous regions are merged, and the sequence set is divided to obtain multiple sequence set sets.

[0026] A further technical solution is as follows: after determining whether each data point within the original sequence group data has converged, the method further includes:

[0027] If not all data points in the original sequence group converge, then the action pattern point is moved to the next time point according to the MeanShift vector, the MeanShift vector of the next time point is calculated, and all action sequences passed through the original sequence group are marked. When the passed action sequence has been marked, the convergence value of the marked action sequence is assigned to the current action sequence.

[0028] The further technical solution is as follows: after determining whether the MeanShift vector at the next time point is less than the convergence threshold, it also includes:

[0029] If the MeanShift vector at the next time point is not less than the convergence threshold, then the action pattern point is moved to the next time point according to the MeanShift vector, the MeanShift vector at the next time point is calculated, and all action sequences passed through the original sequence group data are marked. When the passed action sequence has been marked, the convergence value of the marked action sequence is assigned to the current action sequence.

[0030] The present invention also provides a personnel monitoring device, comprising:

[0031] The log data acquisition unit is used to acquire log data from each door magnetic sensor installed in the residence of the monitored person to obtain raw sequence group data based on time series.

[0032] Clustering unit, used to perform adaptive fuzzy clustering on the original sequence group data to obtain multiple sequence group sets;

[0033] A threshold determination unit is used to determine the cluster center and the maximum distance between the cluster centers of each of the sequence groups, and to set the maximum distance between the cluster centers as a time deviation threshold.

[0034] The signal acquisition unit is used to acquire the monitoring signals collected by each door magnetic sensor in real time to obtain the current monitoring data;

[0035] The judgment unit is used to determine whether the distance between the current monitoring data and any of the sequence groups is within the time deviation threshold of the corresponding sequence group;

[0036] The first determining unit is configured to determine that the current monitoring data is successfully matched with multiple sequence sets if the distance between the current monitoring data and any of the sequence sets is within the time deviation threshold of the corresponding sequence set.

[0037] The second determining unit is used to determine the behavior category of the monitored person based on the set of matched sequence groups.

[0038] The information generation unit is used to generate a remote reminder message if the distance between the current monitoring data and any of the sequence groups is not within the time deviation threshold of the corresponding sequence group.

[0039] The present invention also provides a computer device, the computer device including a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the above-described method.

[0040] The present invention also provides a storage medium storing a computer program that, when executed by a processor, can implement the above-described method.

[0041] The beneficial effects of this invention compared with the prior art are as follows: This invention obtains the original sequence group data by acquiring the log data of the door magnetic sensor, and performs adaptive fuzzy clustering to calculate the maximum distance between the cluster centers. The maximum distance between the cluster centers is set as the time deviation threshold. By using the time deviation threshold in combination with the door magnetic sensor to detect the home status of the monitored person in real time, it can effectively solve the problem of the elderly not being detected and rescued in time due to falls, sudden illnesses, etc. It has personalized, real-time and accurate monitoring capabilities and improves the efficiency of safety care for the monitored person.

[0042] The present invention will be further described below with reference to the accompanying drawings and specific embodiments. Attached Figure Description

[0043] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0044] Figure 1 This is a schematic diagram illustrating an application scenario of the personnel care method provided in an embodiment of the present invention;

[0045] Figure 2 A flowchart illustrating the personnel care method provided in an embodiment of the present invention;

[0046] Figure 3A schematic diagram of a sub-process of the personnel care method provided in an embodiment of the present invention;

[0047] Figure 4 A schematic block diagram of a personnel monitoring device provided in an embodiment of the present invention;

[0048] Figure 5 A schematic block diagram of a clustering unit for a personnel care device provided in an embodiment of the present invention;

[0049] Figure 6 A schematic block diagram of a computer device provided for an embodiment of the present invention. Detailed Implementation

[0050] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0051] It should be understood that, when used in this specification and the appended claims, the terms "comprising" and "including" indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0052] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0053] It should also be further understood that the term "and / or" as used in this specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0054] Please see Figure 1 and Figure 2 , Figure 1 This is a schematic diagram illustrating an application scenario of the personnel care method provided in an embodiment of the present invention. Figure 2This is a schematic flowchart illustrating the personnel monitoring method provided in an embodiment of the present invention. The method is applied in a server. The server is connected to a smart gateway in the monitoring area where each monitored person resides. Each smart gateway is connected to multiple door magnetic sensors in the monitoring area where a monitored person resides. Each door magnetic sensor is installed on each door. The method performs adaptive fuzzy clustering on the original sequence data to obtain multiple sequence set sets; classifies the behavior of the monitored person; matches the current monitoring data with each of the multiple sequence set sets. If the distance between the current monitoring data and any sequence set deviates from a time threshold within that sequence set, a successful match is determined, and the behavior category of the monitored person is determined based on the matched sequence set set; otherwise, a remote reminder message is generated. This enables real-time and accurate monitoring of the monitored person, reduces false alarms, and improves the efficiency of safety monitoring.

[0055] Figure 2 This is a flowchart illustrating the personnel care method provided in an embodiment of the present invention. Figure 2 As shown, the method includes the following steps S110 to S180.

[0056] S110. Obtain log data from each door magnetic sensor installed in the residence of the monitored person to obtain raw sequence group data based on time series.

[0057] In this embodiment, the raw sequence group data includes the trajectory data of the monitored personnel within the monitoring area each day.

[0058] By analyzing the log data from each door magnetic sensor, we can obtain the activity areas of the monitored individuals within the monitored area, the time spent in each activity area, and the time of entry into each activity area. This yields the daily trajectory data of the monitored individuals within the residential monitoring area, indicating when they entered a particular activity area, how long they stayed in that area, and when they entered another activity area. Based on the log data, we can generate daily activity pattern data for the monitored individuals according to a timeline.

[0059] S120. Perform adaptive fuzzy clustering on the original sequence group data to obtain multiple sequence group sets.

[0060] In this embodiment, the sequence set includes behavioral patterns and time intervals in which the behavioral patterns are generated.

[0061] Each sequence set corresponds to a behavioral pattern and the time interval in which that behavioral pattern occurred, thereby enabling the classification of the behavior of the monitored personnel.

[0062] Specifically, the behavior pattern points obtained by mean shift are used to smooth and filter the original sequence group data, and the original sequence group data that does not meet the requirements are deleted. The original sequence group data belonging to the same category are assigned the sequence value of the corresponding behavior pattern to obtain multiple sequence group sets.

[0063] In one embodiment, please refer to Figure 3 The above-mentioned step S120 may include steps S121 to S126.

[0064] S121. Calculate the MeanShift vector for each action sequence point within the original sequence group data;

[0065] S122. Move the behavior pattern point to the next time point according to the MeanShift vector, calculate the MeanShift vector of the next time point, and mark all the behavior sequences that the original sequence group data has passed through. When the passed behavior sequence has been marked, assign the convergence value of the marked behavior sequence to the current behavior sequence.

[0066] S123. Determine whether the MeanShift vector at the next time point is less than the convergence threshold;

[0067] S124. If the MeanShift vector at the next time point is less than the convergence threshold, then the convergence point of the behavior sequence corresponding to the original sequence group data is stored in the sequence group set.

[0068] S125. Determine whether each data point in the original sequence group data has converged;

[0069] S126. If each data point in the original sequence group data converges, then the homogeneous regions are merged and the sequence group set is divided to obtain multiple sequence group sets.

[0070] If not all data points within the original sequence group converge, then step S122 is executed.

[0071] If the MeanShift vector at the next time point is not less than the convergence threshold, then proceed to step S122.

[0072] It is derived by using the gradient of the probability density function of the sequence points of the behavior sequence. Through iterative operation, it converges to the maximum value of the probability density function, thereby realizing behavior pattern localization and tracking. The sequence group segmentation principle based on the mean moving algorithm means that each behavior sequence in the sequence group moves in the direction of its increasing gradient and finally reaches the density maximum point, thereby realizing the optimization of the sequence group.

[0073] Specifically, the behavioral pattern points obtained by mean shift are used to smooth the sequence group, and then the behavioral sequence points with fewer numbers are deleted, thereby achieving noise reduction of the sequence group. Sequence groups belonging to the same category are assigned sequence values ​​corresponding to the behavioral patterns. Only those behavioral patterns with more behavioral sequence points and larger spatial scales are retained, while small-scale noise is effectively filtered out.

[0074] Each access control point corresponds to a behavior pattern; for example, the access control data for the bedroom represents sleeping, the access control data for the living room represents relaxing, the access control data for the dining room represents eating, and the access control data for the bathroom represents using the toilet.

[0075] The original sequence formed by the detection time points of each access control system over multiple consecutive days is denoted as X. j The entire department is prohibited from generating raw sequence data at multiple consecutive testing time points, denoted as set S;

[0076] Let set S = {X1, X2, ..., X} n} represents the original sequence data, T = {y1, y2, ..., y} n Let {l1, l2, ..., l} be the convergence point of the data, and L = {l1, l2, ..., l} n} is a classification set, ε is the convergence threshold, the kernel function used is the unit uniform kernel function, and the behavior sequence X is... ij The basic form of the MeanShift vector is defined as follows: Among them, s h Let s be a set of high-dimensional spheres with radius h, and the set of y-points satisfying the following relation: h (x) = {y:(yx)} T (yx)≤h 2}; k represents the original sequence X j Of the m sample points xi, k points fall into s. K In the collection.

[0077] Specifically, determine the behavioral sequence X j Calculate each behavioral sequence point X separately. ij The MeanShift vector Mh(x) represents the direction and time distance that the action sequence needs to move in one step;

[0078] Behavioral sequence point X ij This represents the original sequence formed by the j-th access control on day i at the detection time point; the sequence formed by the j-th access control over multiple consecutive days at the detection time points is denoted as the behavior sequence X. j The entire department is prohibited from generating raw sequence data at multiple consecutive testing time points, denoted as set S.

[0079] Move the behavior pattern point to the next time point based on the value of Mh(x), and calculate Mh(x) for that point; where the behavior pattern point is the center of the time interval of the behavior pattern.

[0080] Repeat the process of "moving the behavior pattern point to the next time point based on the value of Mh(x) and calculating Mh(x) for that point" until Mh(x) < ε, which means that the cluster center has been found and no further movement is needed. Store the convergence point in the set T.

[0081] While performing mean shift, all the behavior sequences that the set S passes through are marked. If a behavior sequence has already been marked, the mean shift stops. The convergence point of the behavior sequence is the same as the convergence point of the marked behavior sequence, and the convergence value is directly assigned to that point.

[0082] Repeat steps two through four above until all data points converge;

[0083] By merging homogeneous regions, the sequence set is divided into multiple sequence sets, each corresponding to a behavior pattern.

[0084] In this embodiment, homogeneous regions refer to behavioral sequences with the same cluster center. By merging behavioral sequences with the same cluster center, the original sequence group data is divided into multiple sequence group sets, each corresponding to a behavioral pattern.

[0085] S130. Determine the cluster center and the maximum distance between the cluster centers of each sequence group set, and set the maximum distance between the cluster centers as the time deviation threshold.

[0086] S140. Real-time acquisition of monitoring signals collected by each door magnetic sensor to obtain current monitoring data.

[0087] In this embodiment, the current monitoring data refers to the monitoring signal of each door magnetic sensor.

[0088] S150. Determine whether the distance between the current monitoring data and any of the sequence sets is within the time deviation threshold of the corresponding sequence set;

[0089] S160. If the distance between the current monitoring data and any of the sequence sets is within the time deviation threshold of the corresponding sequence set, then it is determined that the current monitoring data has successfully matched multiple sequence sets respectively.

[0090] S170. Determine the behavioral category of the monitored personnel based on the set of matched sequence groups;

[0091] S180. If the distance between the current monitoring data and any of the sequence sets is not within the time deviation threshold of the corresponding sequence set, a remote reminder message is generated.

[0092] In this embodiment, the current monitoring data is matched with multiple sequence sets. If the current monitoring data deviates from the time threshold of any sequence set, the match is considered successful. The behavior category of the monitored person is determined based on the matched sequence set. Otherwise, a remote reminder is generated. This enables real-time and accurate monitoring of the monitored person, reduces false alarms, and improves the efficiency of safety monitoring.

[0093] In this embodiment, the method automatically generates time-series-based classification rules by acquiring log data from each door magnetic sensor in real time, eliminating the need for manual setting of matching templates and alarm triggering time deviation thresholds. It utilizes door magnetic sensing combined with internet technology to monitor the home status of elderly people living alone in real time, making caregiving more convenient and efficient. Furthermore, by combining the historical daily routines of elderly people living alone with a clustering algorithm, time-series alarm rules are established to achieve real-time and accurate care, reducing false alarms and improving the efficiency of safe care for elderly people living alone.

[0094] The aforementioned personnel monitoring method obtains raw sequence data by acquiring log data from door magnetic sensors and performs adaptive fuzzy clustering to calculate the maximum distance between cluster centers. The maximum distance between cluster centers is then set as a time deviation threshold. By combining the time deviation threshold with door magnetic sensors, the home status of the monitored personnel can be detected in real time. This effectively solves the problem of elderly people not being detected and rescued in time due to falls, sudden illnesses, etc. It has personalized, real-time, and accurate monitoring capabilities, and improves the efficiency of safety monitoring for the monitored personnel.

[0095] Figure 4 This is a schematic block diagram of a personnel monitoring device 300 provided in an embodiment of the present invention. Figure 4 As shown, corresponding to the above-described personnel care method, the present invention also provides a personnel care device 300. This personnel care device 300 includes a unit for performing the above-described personnel care method, and the device can be configured in a server. Specifically, please refer to... Figure 4 The personnel monitoring device 300 includes a log data acquisition unit 301, a clustering unit 302, a threshold determination unit 303, a signal acquisition unit 304, a judgment unit 305, a first determination unit 306, a second determination unit 307, and an information generation unit 308.

[0096] The log data acquisition unit 301 is used to acquire log data from each door magnetic sensor installed in the residence of the monitored person to obtain raw sequence group data based on time series; the clustering unit 302 is used to perform adaptive fuzzy clustering on the raw sequence group data to obtain multiple sequence group sets; the threshold determination unit 303 is used to determine the cluster center and the maximum distance between the cluster centers of each sequence group set, and set the maximum distance between the cluster centers as the time deviation threshold; the signal acquisition unit 304 is used to acquire the monitoring signal collected by each door magnetic sensor in real time to obtain the current monitoring data; the judgment unit 305 is used to judge the current monitoring data. The system determines whether the distance between the current monitoring data and any of the sequence sets is within the time deviation threshold of the corresponding sequence set; a first determining unit 306 is used to determine if the current monitoring data is successfully matched with multiple sequence sets if the distance between the current monitoring data and any of the sequence sets is within the time deviation threshold of the corresponding sequence set; a second determining unit 307 is used to determine the behavior category of the monitored person based on the matched sequence sets; and an information generating unit 308 is used to generate a remote reminder message if the distance between the current monitoring data and any of the sequence sets is not within the time deviation threshold of the corresponding sequence set.

[0097] In one embodiment, the clustering unit 302 is used to smooth and filter the original sequence group data using behavioral pattern points obtained by mean shift, delete the original sequence group data that does not meet the requirements, and assign the original sequence group data belonging to the same category with the sequence value of the corresponding behavioral pattern, so as to obtain multiple sequence group sets.

[0098] In one embodiment, such as Figure 5 As shown, the clustering unit 302 includes a vector calculation subunit 3021, a drift subunit 3022, a vector judgment subunit 3023, a storage subunit 3024, a convergence judgment subunit 3025, and a segmentation subunit 3026.

[0099] Vector calculation subunit 3021 is used to calculate the MeanShift vector of each behavior sequence point within the original sequence group data; drift subunit 3022 is used to move the behavior pattern point to the next time point according to the MeanShift vector, calculate the MeanShift vector of the next time point, and mark all behavior sequences traversed by the original sequence group data. When a traversed behavior sequence has been marked, the convergence value of the marked behavior sequence is assigned to the current behavior sequence; vector judgment subunit 3023 is used to determine whether the MeanShift vector of the next time point is less than the convergence threshold. If the MeanShift vector of the next time point is not less than the convergence threshold, the following steps are performed: moving the behavior pattern point to the next time point according to the MeanShift vector, calculating the MeanShift vector of the next time point, and marking all behavior sequences traversed by the original sequence group data. When a traversed behavior sequence has been marked, the convergence value of the marked behavior sequence is assigned to the current behavior sequence. Storage subunit 3024 is used to store the convergence point of the behavior sequence corresponding to the original sequence group data into the sequence group set if the MeanShift vector at the next time point is less than the convergence threshold. Convergence judgment subunit 3025 is used to determine whether each data point in the original sequence group data has converged. If each data point in the original sequence group data has not converged, the behavior pattern point is moved to the next time point according to the MeanShift vector, the MeanShift vector at the next time point is calculated, and all behavior sequences traversed by the original sequence group data are marked. When a traversed behavior sequence has been marked, the convergence value of the marked behavior sequence is assigned to the current behavior sequence. Segmentation subunit 3026 is used to merge homogeneous regions and segment the sequence group set to obtain multiple sequence group sets if each data point in the original sequence group data has converged.

[0100] It should be noted that those skilled in the art can clearly understand that the specific implementation process of the above-mentioned personnel care device 300 and each unit can be referred to the corresponding description in the foregoing method embodiments. For the sake of convenience and brevity, it will not be repeated here.

[0101] The aforementioned personnel monitoring device 300 can be implemented as a computer program, which can, for example... Figure 6 It runs on the computer device shown.

[0102] Please see Figure 6 , Figure 6 This is a schematic block diagram of a computer device provided in an embodiment of this application. The computer device 500 can be a server, wherein the server can be a standalone server or a server cluster composed of multiple servers.

[0103] See Figure 6 The computer device 500 includes a processor 502, a memory, and a network interface 505 connected via a system bus 501. The memory may include a non-volatile storage medium 503 and internal memory 504.

[0104] The non-volatile storage medium 503 may store an operating system 5031 and a computer program 5032. The computer program 5032 includes program instructions that, when executed, cause the processor 502 to perform a human care method.

[0105] The processor 502 provides computing and control capabilities to support the operation of the entire computer device 500.

[0106] The internal memory 504 provides an environment for the operation of the computer program 5032 in the non-volatile storage medium 503. When the computer program 5032 is executed by the processor 502, the processor 502 can perform a personnel care method.

[0107] This network interface 505 is used for network communication with other devices. Those skilled in the art will understand that... Figure 6 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device 500 to which the present application is applied. The specific computer device 500 may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0108] The processor 502 is used to run a computer program 5032 stored in the memory to perform the following steps:

[0109] Log data from each door magnetic sensor installed in the residence of the monitored person is acquired to obtain raw sequence group data based on time series; adaptive fuzzy clustering is performed on the raw sequence group data to obtain multiple sequence group sets; the cluster center and maximum distance between the cluster centers of each sequence group set are determined, and the maximum distance between the cluster centers is set as a time deviation threshold; the monitoring signal collected by each door magnetic sensor is acquired in real time to obtain current monitoring data; it is determined whether the distance between the current monitoring data and any of the sequence group sets is within the time deviation threshold of the corresponding sequence group set; if the distance between the current monitoring data and any of the sequence group sets is within the time deviation threshold of the corresponding sequence group set, it is determined that the current monitoring data has successfully matched multiple sequence group sets; the behavior category of the monitored person is determined based on the matched sequence group sets; if the distance between the current monitoring data and any of the sequence group sets is not within the time deviation threshold of the corresponding sequence group set, a remote reminder message is generated.

[0110] The original sequence data includes the daily trajectory data of the monitored personnel within the monitoring area.

[0111] The set of sequence groups includes behavioral patterns and the time intervals in which the behavioral patterns are generated.

[0112] In one embodiment, when the processor 502 performs adaptive fuzzy clustering on the original sequence group data to obtain a set of multiple sequence groups, it specifically implements the following steps:

[0113] The behavior pattern points obtained by mean shift are used to smooth and filter the original sequence group data, and the original sequence group data that does not meet the requirements are deleted. The original sequence group data belonging to the same category are assigned the sequence value of the corresponding behavior pattern to obtain multiple sequence group sets.

[0114] In one embodiment, when the processor 502 performs the step of smoothing and filtering the original sequence group data using the behavioral pattern points obtained by mean shift, deleting the original sequence group data that does not meet the requirements, and assigning the original sequence group data of the same type with the sequence value of the corresponding behavioral pattern to obtain a set of multiple sequence groups, the processor 502 specifically implements the following steps:

[0115] Calculate the MeanShift vector for each behavior sequence point within the original sequence group data; move the behavior pattern point to the next time point based on the MeanShift vector, calculate the MeanShift vector for the next time point, and mark all behavior sequences traversed by the original sequence group data. When a traversed behavior sequence has been marked, assign the convergence value of the marked behavior sequence to the current behavior sequence; determine whether the MeanShift vector at the next time point is less than the convergence threshold; if the MeanShift vector at the next time point is less than the convergence threshold, store the convergence point of the behavior sequence corresponding to the original sequence group data in the sequence group set; determine whether each data point within the original sequence group data has converged; if each data point within the original sequence group data has converged, merge homogeneous regions and split the sequence group set to obtain multiple sequence group sets.

[0116] In one embodiment, after implementing the step of determining whether each data point in the original sequence group data has converged, the processor 502 further implements the following steps:

[0117] If not all data points in the original sequence group converge, then the action pattern point is moved to the next time point according to the MeanShift vector, the MeanShift vector of the next time point is calculated, and all action sequences passed through the original sequence group are marked. When the passed action sequence has been marked, the convergence value of the marked action sequence is assigned to the current action sequence.

[0118] In one embodiment, after performing the step of determining whether the MeanShift vector at the next time point is less than the convergence threshold, the processor 502 further performs the following steps:

[0119] If the MeanShift vector at the next time point is not less than the convergence threshold, then the action pattern point is moved to the next time point according to the MeanShift vector, the MeanShift vector at the next time point is calculated, and all action sequences passed through the original sequence group data are marked. When the passed action sequence has been marked, the convergence value of the marked action sequence is assigned to the current action sequence.

[0120] It should be understood that in the embodiments of this application, the processor 502 may be a central processing unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0121] It will be understood by those skilled in the art that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program includes program instructions and can be stored in a storage medium, which is a computer-readable storage medium. The program instructions are executed by at least one processor in the computer system to implement the process steps of the embodiments of the above methods.

[0122] Therefore, the present invention also provides a storage medium. This storage medium can be a computer-readable storage medium. The storage medium stores a computer program, wherein when executed by a processor, the computer program causes the processor to perform the following steps:

[0123] Log data from each door magnetic sensor installed in the residence of the monitored person is acquired to obtain raw sequence group data based on time series; adaptive fuzzy clustering is performed on the raw sequence group data to obtain multiple sequence group sets; the cluster center and maximum distance between the cluster centers of each sequence group set are determined, and the maximum distance between the cluster centers is set as a time deviation threshold; the monitoring signal collected by each door magnetic sensor is acquired in real time to obtain current monitoring data; it is determined whether the distance between the current monitoring data and any of the sequence group sets is within the time deviation threshold of the corresponding sequence group set; if the distance between the current monitoring data and any of the sequence group sets is within the time deviation threshold of the corresponding sequence group set, it is determined that the current monitoring data has successfully matched multiple sequence group sets; the behavior category of the monitored person is determined based on the matched sequence group sets; if the distance between the current monitoring data and any of the sequence group sets is not within the time deviation threshold of the corresponding sequence group set, a remote reminder message is generated.

[0124] The original sequence data includes the daily trajectory data of the monitored personnel within the monitoring area.

[0125] The set of sequence groups includes behavioral patterns and the time intervals in which the behavioral patterns are generated.

[0126] In one embodiment, when the processor executes the computer program to perform adaptive fuzzy clustering on the original sequence group data to obtain a set of multiple sequence groups, it specifically implements the following steps:

[0127] The behavior pattern points obtained by mean shift are used to smooth and filter the original sequence group data, and the original sequence group data that does not meet the requirements are deleted. The original sequence group data belonging to the same category are assigned the sequence value of the corresponding behavior pattern to obtain multiple sequence group sets.

[0128] In one embodiment, when the processor executes the computer program to perform the steps of smoothing and filtering the original sequence group data using the behavioral pattern points obtained by mean shift, deleting the original sequence group data that does not meet the requirements, and assigning the original sequence group data of the same type with the sequence value of the corresponding behavioral pattern to obtain multiple sequence group sets, the specific implementation is as follows:

[0129] Calculate the MeanShift vector for each behavior sequence point within the original sequence group data; move the behavior pattern point to the next time point based on the MeanShift vector, calculate the MeanShift vector for the next time point, and mark all behavior sequences traversed by the original sequence group data. When a traversed behavior sequence has been marked, assign the convergence value of the marked behavior sequence to the current behavior sequence; determine whether the MeanShift vector at the next time point is less than the convergence threshold; if the MeanShift vector at the next time point is less than the convergence threshold, store the convergence point of the behavior sequence corresponding to the original sequence group data in the sequence group set; determine whether each data point within the original sequence group data has converged; if each data point within the original sequence group data has converged, merge homogeneous regions and split the sequence group set to obtain multiple sequence group sets.

[0130] In one embodiment, after executing the computer program to implement the step of determining whether each data point in the original sequence group data has converged, the processor further implements the following steps:

[0131] If not all data points in the original sequence group converge, then the action pattern point is moved to the next time point according to the MeanShift vector, the MeanShift vector of the next time point is calculated, and all action sequences passed through the original sequence group are marked. When the passed action sequence has been marked, the convergence value of the marked action sequence is assigned to the current action sequence.

[0132] In one embodiment, after executing the computer program to perform the step of determining whether the MeanShift vector at the next time point is less than the convergence threshold, the processor further performs the following steps:

[0133] If the MeanShift vector at the next time point is not less than the convergence threshold, then the action pattern point is moved to the next time point according to the MeanShift vector, the MeanShift vector at the next time point is calculated, and all action sequences passed through the original sequence group data are marked. When the passed action sequence has been marked, the convergence value of the marked action sequence is assigned to the current action sequence.

[0134] The storage medium can be any computer-readable storage medium capable of storing program code, such as a USB flash drive, portable hard drive, read-only memory (ROM), magnetic disk, or optical disk.

[0135] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0136] In the several embodiments provided by this invention, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For example, the division of each unit is merely a logical functional division, and there may be other division methods in actual implementation. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed.

[0137] The steps in the method of this invention can be adjusted, merged, or reduced in order according to actual needs. The units in the device of this invention can be merged, divided, or reduced according to actual needs. Furthermore, the functional units in the various embodiments of this invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0138] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, a terminal, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention.

[0139] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and these modifications or substitutions should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for personnel care, characterized in that, include: Log data from each door magnetic sensor installed in the residence of the monitored person is acquired to obtain raw sequence group data based on time series. Adaptive fuzzy clustering is performed on the original sequence group data to obtain multiple sequence group sets; Determine the cluster center and the maximum distance between the cluster centers for each of the sequence groups, and set the maximum distance between the cluster centers as a time deviation threshold; The monitoring signals collected by each door magnetic sensor are acquired in real time to obtain the current monitoring data; Determine whether the distance between the current monitoring data and any of the sequence sets is within the time deviation threshold of the corresponding sequence set; If the distance between the current monitoring data and any of the sequence sets is within the time deviation threshold of the corresponding sequence set, then it is determined that the current monitoring data has successfully matched multiple sequence sets respectively. The behavioral category of the monitored personnel is determined based on the set of matched sequence groups. If the distance between the current monitoring data and any of the sequence sets is not within the time deviation threshold of the corresponding sequence set, a remote reminder message is generated; Specifically, the behavior pattern points obtained by mean shift are used to smooth and filter the original sequence group data, and the original sequence group data that does not meet the requirements are deleted. At the same time, the original sequence group data belonging to the same category are assigned the sequence value of the corresponding behavior pattern to obtain multiple sequence group sets.

2. The personnel care method according to claim 1, characterized in that, The raw sequence data includes the daily trajectory data of the monitored personnel within the monitored area.

3. The personnel care method according to claim 1, characterized in that, The set of sequence groups includes behavioral patterns and the time intervals in which the behavioral patterns are generated.

4. The method for personnel care according to claim 1, characterized in that, The adaptive fuzzy clustering of the original sequence group data to obtain multiple sequence group sets includes: The behavior pattern points obtained by mean shift are used to smooth and filter the original sequence group data, and the original sequence group data that does not meet the requirements are deleted. The original sequence group data belonging to the same category are assigned the sequence value of the corresponding behavior pattern to obtain multiple sequence group sets.

5. The personnel care method according to claim 4, characterized in that, The original sequence group data is smoothed and filtered using the behavioral pattern points obtained by mean shift, and the original sequence group data that does not meet the requirements is deleted. The original sequence group data belonging to the same category are assigned sequence values ​​corresponding to the behavioral patterns to obtain multiple sequence group sets, including: Calculate the MeanShift vector for each action sequence point within the original sequence group data; Move the behavior pattern point to the next time point according to the MeanShift vector, calculate the MeanShift vector of the next time point, and mark all the behavior sequences that the original sequence group data has passed through. When the passed behavior sequence has been marked, assign the convergence value of the marked behavior sequence to the current behavior sequence. Determine whether the MeanShift vector at the next time point is less than the convergence threshold; If the MeanShift vector at the next time point is less than the convergence threshold, then the convergence point of the behavior sequence corresponding to the original sequence group data is stored in the sequence group set. Determine whether each data point within the original sequence group has converged; If every data point within the original sequence group converges, then homogeneous regions are merged, and the sequence group set is divided to obtain multiple sequence group sets.

6. The method for personnel care according to claim 5, characterized in that, After determining whether each data point within the original sequence group has converged, the method further includes: If not all data points in the original sequence group converge, then the action pattern point is moved to the next time point according to the MeanShift vector, the MeanShift vector of the next time point is calculated, and all action sequences passed through the original sequence group are marked. When the passed action sequence has been marked, the convergence value of the marked action sequence is assigned to the current action sequence.

7. The method for personnel care according to claim 5, characterized in that, After determining whether the MeanShift vector at the next time point is less than the convergence threshold, the method further includes: If the MeanShift vector at the next time point is not less than the convergence threshold, then the action pattern point is moved to the next time point according to the MeanShift vector, the MeanShift vector at the next time point is calculated, and all action sequences passed through the original sequence group data are marked. When the passed action sequence has been marked, the convergence value of the marked action sequence is assigned to the current action sequence.

8. A personnel monitoring device, characterized in that, include: The log data acquisition unit is used to acquire log data from each door magnetic sensor installed in the residence of the monitored person to obtain raw sequence group data based on time series. Clustering unit, used to perform adaptive fuzzy clustering on the original sequence group data to obtain multiple sequence group sets; A threshold determination unit is used to determine the cluster center and the maximum distance between the cluster centers of each of the sequence groups, and to set the maximum distance between the cluster centers as a time deviation threshold. The signal acquisition unit is used to acquire the monitoring signals collected by each door magnetic sensor in real time to obtain the current monitoring data; The judgment unit is used to determine whether the distance between the current monitoring data and any of the sequence groups is within the time deviation threshold of the corresponding sequence group; The first determining unit is configured to determine that the current monitoring data is successfully matched with multiple sequence sets if the distance between the current monitoring data and any of the sequence sets is within the time deviation threshold of the corresponding sequence set. The second determining unit is used to determine the behavior category of the monitored person based on the set of matched sequence groups. An information generation unit is used to generate a remote reminder message if the distance between the current monitoring data and any of the sequence groups is not within the time deviation threshold of the corresponding sequence group. Specifically, the behavior pattern points obtained by mean shift are used to smooth and filter the original sequence group data, and the original sequence group data that does not meet the requirements are deleted. At the same time, the original sequence group data belonging to the same category are assigned the sequence value of the corresponding behavior pattern to obtain multiple sequence group sets.

9. A computer device, characterized in that, The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the method as described in any one of claims 1 to 7.

10. A storage medium, characterized in that, The storage medium stores a computer program that, when executed by a processor, can implement the method as described in any one of claims 1 to 7.

Images