Remote home health status multi-dimensional monitoring system and method

Abstract

The application provides a remote home health state multi-dimensional monitoring system and method, and belongs to the technical field of remote communication and health monitoring. The system comprises a data acquisition layer, a data control layer, a data analysis layer and a data output layer. The data control layer comprises a first data queue corresponding to an image sensor and a second data queue corresponding to a sound sensor. The data analysis layer analyzes at least part of the sensing data stored in the first data queue and / or the second data queue. The data output layer receives the analysis result of the data analysis layer, outputs the remote home health state of a target person, and sends a feedback instruction to the wearable device worn by the target person when the remote home health state of the target person meets the preset standard. The method is realized based on the system. The application can comprehensively determine and monitor the remote home health state based on multi-dimensional data, different dimensions are mutually complementary and activated, and the accuracy can be ensured while reducing the energy consumption of the sensor data.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of remote communication and health monitoring, and particularly relates to a remote home health state multi-dimensional monitoring system and method, a computer readable storage medium for implementing the method, a computer program product, and an electronic device. BACKGROUND

[0002] With the acceleration of population aging in China, remote home health services have become a hot topic, and traditional family service models have been unable to meet the needs of family users. By applying communication technology, information technology, Internet of Things technology, artificial intelligence, etc. to the home health service environment, an intelligent and personalized service system is constructed, thereby providing a comfortable, convenient, safe, and controllable home health service environment for family users, which becomes a new direction for the development of remote home health.

[0003] Remote home health care services integrate medical equipment and communication technology and apply them to health, medical care, and related services to reduce the need for human care. Chinese invention patent CN113034850B provides an intelligent home health management device that can control and interact with health-related factors and the surrounding environment, allowing patients to be in a good health management state at home. Chinese invention patent CN113113145B discloses a smart home care service management integrated intelligent platform based on remote monitoring and video processing, which monitors the real-time online health status of all old people in the community, improves the home care service management level and the quality of care services, and enhances the overall care experience of the elderly.

[0004] However, in actual application, it is found that the remote home health care solutions of the prior art are mostly based on single-dimensional data for limited threshold judgment and warning, and the monitoring accuracy is not high enough. If more types / numbers of physical sensors are arranged to improve the comprehensiveness of the data, the hardware cost and data energy consumption are increased. Moreover, in the monitoring solutions of the prior art involving multiple types of sensors, different dimensional data are not linked, the data processing dimension is single, and the processing method of each dimension is complex, which cannot reduce the data processing cost. SUMMARY

[0005] To solve the above technical problems, the present application provides a remote home health state multi-dimensional monitoring system and method, a computer readable storage medium for implementing the method, a computer program product, and an electronic device.

[0006] In a first aspect of the present application, a remote home health state multi-dimensional monitoring system is provided, which comprises a data acquisition layer, a data control layer, a data analysis layer, and a data output layer.

[0007] The data acquisition layer includes image sensors, sound sensors, and wearable devices;

[0008] The image sensors are used to collect image frames of a target person in N monitoring areas;

[0009] The sound sensors are used to collect voiceprint signals existing in the N monitoring areas;

[0010] The target person wears the wearable devices and moves in the N monitoring areas; N≥2;

[0011] The data control layer includes a first data queue corresponding to the image sensors and a second data queue corresponding to the sound sensors;

[0012] The data analysis layer analyzes at least part of the sensing data stored in the first data queue and / or the second data queue based on the control instructions generated by the data control layer;

[0013] The data output layer receives the analysis results of the data analysis layer, outputs the remote home health status of the target person, and sends feedback instructions to the wearable devices worn by the target person when the remote home health status of the target person meets the preset standards.

[0014] The first data queue is a ring queue with a size of N; one image sensor is configured for each monitoring area;

[0015] Every preset period, the image frames corresponding to each monitoring area collected by each image sensor are stored in the ring queue;

[0016] When the ring queue is full, the data analysis layer generates the control instructions to detect and analyze all sensing data stored in the first data queue.

[0017] Every preset period, the image frames corresponding to each monitoring area collected by each image sensor are stored in the ring queue, specifically including:

[0018] Every preset period, N image frames corresponding to N monitoring areas collected by N image sensors are randomly stored in the ring queue;

[0019] When the ring queue is full, the data analysis layer generates the control instructions to detect and analyze all sensing data stored in the first data queue, specifically including:

[0020] Detecting whether the target person appears in the N image frames.

[0021] Each monitoring area is configured with one of the sound sensors; every preset period, the voiceprint signal corresponding to each monitoring area collected by each sound sensor is stored into the second data queue;

[0022] And the i-th monitoring area corresponds to a voiceprint signal Vi and an image frame F i; the second data queue includes N storage locations, and the voiceprint signal Vi is stored into the i-th storage location of the second data queue; i = 1, 2, …, N;

[0023] When the ring queue is full, the data analysis layer detects N image frames stored in the ring queue;

[0024] When none of the N image frames detects the target person, at least part of the sensing data stored in the second data queue is analyzed, and the analysis includes detecting whether the voiceprint signal stored in the second data queue is continuous.

[0025] The remote home health status of the target person includes one of the following:

[0026] (1) The target person is not in any monitoring area;

[0027] (2) The target person is in one of the monitoring areas, and is in a relatively static state for a long time and is located outside the monitoring range;

[0028] (3) The target person is in multiple monitoring areas and normally active.

[0029] When the remote home health status of the target person meets the preset standard, a feedback indication is sent to the wearable device worn by the target person, specifically including:

[0030] When the analysis result represents that the target person is in a relatively static state for a long time and is located outside the monitoring range, a feedback indication is sent to the wearable device worn by the target person, and the feedback indication requires the target person to make a feedback action or submit a voice reply.

[0031] In a second aspect of the present application, a remote home health status multi-dimensional monitoring method is provided.

[0032] The embodiments of the home health status multi-dimensional monitoring method mentioned in this part can be implemented on an electronic device or system configured with a memory and a processor through a computer program. The electronic device or system can be a physical machine, a virtual machine, a server, a cluster, or any combination thereof.

[0033] The specific form of the electronic device can also be a human-computer interaction terminal, which can be a desktop terminal, a smart handheld terminal, a mobile terminal, etc. with a human-computer interaction interface.

[0034] The method comprises the following steps:

[0035] S710: Collecting N image frames of a target person in N monitoring areas and N sets of voiceprint signals existing in the N monitoring areas; N≥2;

[0036] S720: Storing the N image frames into a first ring queue and storing the N sets of voiceprint signals into a second normal queue;

[0037] S730: When the first ring queue is full, analyzing at least part of the sensing data stored in the first ring queue and / or the second normal queue;

[0038] S740: Based on the analysis result, outputting a remote home health status of the target person;

[0039] And when the remote home health status of the target person meets a preset standard, sending a feedback indication to the target person, the feedback indication requiring the target person to make a feedback action or submit a voice reply.

[0040] Further, the step S710 and the step S720 are repeatedly executed every preset period;

[0041] And the step 720 stores the N image frames into the first ring queue in different orders in different periods;

[0042] The step 720 stores the N sets of voiceprint signals into the second normal queue in the same order in different periods.

[0043] When the first ring queue is full, detecting whether the target person appears in the N image frames of the first ring queue;

[0044] When the target person is not detected in the N image frames, analyzing at least part of the sensing data stored in the second normal queue, and the analysis comprises detecting whether the voiceprint signals stored in the second normal queue are continuous.

[0045] The aforementioned remote home health status multi-dimensional monitoring method can be realized automatically through various forms of electronic devices and computer program instructions; the computer program instructions can be stored in different forms of storage media and loaded into a computer electronic device for execution.

[0046] Therefore, in the third aspect of the present application, a computer readable storage medium for storing computer instructions is also provided, when the computer instructions run on an electronic device, the electronic device executes all or part of the steps of the aforementioned remote home health status multi-dimensional monitoring method.

[0047] In a fourth aspect of the present application, a computer device is also proposed, comprising a processor and a memory, the memory being configured to store instructions, and the processor being configured to invoke the instructions in the memory so that the computer device performs the aforementioned remote home health status multi-dimensional monitoring method.

[0048] In a fifth aspect of the present application, a computer program product is also proposed, comprising a computer program, when the computer program is executed, all or part of the steps of the aforementioned remote home health status multi-dimensional monitoring method are implemented.

[0049] The technical scheme of the present application, through the data acquisition layer composed of image sensors, sound sensors and wearable devices, the data control layer composed of the first data queue corresponding to the image sensors and the second data queue corresponding to the sound sensors respectively performs data acquisition and storage, the data analysis layer analyzes at least part of the sensor data stored in the first data queue and / or the second data queue based on the control instructions generated by the data control layer; the data output layer receives the analysis results of the data analysis layer, outputs the remote home health status of the target person, and when the remote home health status of the target person meets the preset standard, sends feedback instructions to the wearable device worn by the target person, which can perform remote home health status comprehensive judgment and monitoring based on multi-dimensional data, different dimensions complement and activate each other, which can ensure accuracy while reducing sensor data energy consumption.

[0050] The further advantages of the present application will be further embodied in detail in the specific embodiment part combined with the drawings of the specification. BRIEF DESCRIPTION OF DRAWINGS

[0051] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed in the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0052] Figure 1 is a remote home health status multi-dimensional monitoring system architecture level schematic diagram of an embodiment of the present application;

[0053] Figure 2 is a part of the data interaction principle schematic diagram of the remote home health status multi-dimensional monitoring system of the present application;

[0054] Figure 3 is a layout schematic diagram of the target monitoring area and the data acquisition sensor in the technical scheme of the present application;

[0055] Figure 4 is a flowchart of a remote home health status multi-dimensional monitoring method according to an embodiment of the present application; DETAILED DESCRIPTION

[0056] Firstly, referring to Figure 1 , Figure 1 From the perspective of system architecture level, the present application introduces a remote home health status multi-dimensional monitoring system architecture level diagram.

[0057] Figure 1 The remote home health status multi-dimensional monitoring system includes a data acquisition layer, a data control layer, a data analysis layer and a data output layer.

[0058] The data acquisition layer includes an image sensor, a sound sensor and a wearable device;

[0059] The image sensor is used to collect image frames of a target person in N monitoring areas;

[0060] The sound sensor is used to collect voiceprint signals existing in the N monitoring areas;

[0061] The target person wears the wearable device to move in the N monitoring areas; N≥2;

[0062] The data control layer includes a first data queue corresponding to the image sensor and a second data queue corresponding to the sound sensor;

[0063] The data analysis layer analyzes at least part of the sensing data stored in the first data queue and / or the second data queue based on the control instructions generated by the data control layer;

[0064] The data output layer receives the analysis results of the data analysis layer, outputs the remote home health status of the target person, and sends feedback instructions to the wearable device worn by the target person when the remote home health status of the target person meets the preset standard.

[0065] Next, combined with Figure 2 and Figure 3 , the function implementation of the above different levels of architecture is further introduced.

[0066] In Figure 2The diagram illustrates a data acquisition layer consisting of an image sensor, a sound sensor, and a wearable device; a data control layer consisting of a first data queue corresponding to the image sensor and a second data queue corresponding to the sound sensor, which respectively acquire and store data; a data analysis layer including at least one data analysis engine, which analyzes at least a portion of the sensor data stored in the first data queue and / or the second data queue based on control commands generated by the data control layer; and a data output layer receiving the analysis results from the data analysis layer, outputting the remote home health status of the target person, and sending a feedback instruction to the wearable device worn by the target person when the remote home health status of the target person meets the preset standard.

[0067] In the data control layer, the first data queue is a circular queue of size N, and the second data queue is a regular queue of size N that operates on a first-in, first-out basis. Here, the value of N equals the number of target monitoring areas.

[0068] by Figure 3 The diagram shown illustrates the layout of the target monitoring area and data acquisition sensors. Figure 3 The image shows a home monitoring environment, which is roughly divided into the living room (where image sensor F1 and sound sensor V1 are installed) and rooms (living room, kitchen and bathroom, etc.) 1-4 (where image sensors F2-F5 and sound sensors V2-V5 are installed respectively).

[0069] For ease of description, in the following embodiments, the data (image frames) collected by image sensors F1-F5 are also described as F1-F5; the data (voiceprint sequences) collected by sound sensors V1-V5 are also described as V1-V5.

[0070] As the first advantage of the present invention, Figure 3 In the five monitoring areas shown (N=5), each monitoring area is equipped with one image sensor and one sound sensor. That is, the technical solution of this invention first requires the acquisition of sensor data in two dimensions (image dimension and sound dimension).

[0071] However, instead of simply combining, storing, and processing the sensor data from the two dimensions (image dimension and sound dimension), this application makes the following improvements.

[0072] First, at preset intervals, image frames corresponding to each monitoring area collected by each image sensor are stored in the circular queue; when the circular queue is full, the data analysis layer generates the control command to detect and analyze all sensor data stored in the first data queue.

[0073] The inventor notices that when performing remote home health status monitoring, the focus is on identifying abnormal states, but abnormal states are actually in the minority in the overall monitoring period. However, uninterrupted data collection is still required. Although the data collection process cannot be avoided, not every data collection is of analytical value, so the invention makes the above improvements. First, the data storage method uses a ring queue, which avoids data overflow while ensuring that the latest data is analyzed each time. Second, analysis is only performed when the queue is full, avoiding frequent data analysis processes.

[0074] Second, in order to reflect the linkage of the above two processes, during actual storage, every N image frames corresponding to N monitoring areas collected by N image sensors are randomly stored in the ring queue every preset period. In other words, the N image frames are stored in the first ring queue in different orders in different periods.

[0075] Next, the above process will be described with an illustrative example.

[0076] Suppose the preset period is 30s, N = 5, t = 0s is the starting point, and the ring queue storage size is 5 (all values are only examples, and actual values may be different).

[0077] Although the ring queue does not have a factual starting point and end point (cyclic coverage storage, which will not overflow), in order to facilitate description, it is assumed that a certain storage area R1 is the starting point and storage area R5 is the end point (R1 and R5 are connected end to end, i.e. R1-R2-R3-R4-R5-R1-…);

[0078] t = 0: the data (image frames) collected by image sensors F1-F5 are also described as F1-F5 accordingly;

[0079] F1 is stored in R1, F2 is stored in R3, F3 is stored in R2, F4 is stored in R5, and F5 is stored in R4.

[0080] t = 30: the data (image frames) collected by image sensors F1-F5 are also described as F'1-F'5 accordingly;

[0081] F'1 is stored in R3, F'2 is stored in R5, F'3 is stored in R'2, F'4 is stored in R4, and F'5 is stored in R1.

[0082] The focus of the above example is that the N image frames are randomly stored in different orders in different cycles to the first ring queue, and the purpose of randomness is to break the storage order each time, because the subsequent analysis also needs to consider the different order each time to improve accuracy, which also conforms to the randomness of the target person's activities between different monitoring areas. The prior art does not consider this feature and gives the corresponding data storage and processing method, which is one of the important improvements of the application.

[0083] Corresponding to this, when the ring queue is full, the data analysis layer generates the control instruction to detect and analyze all the sensing data stored in the first data queue, specifically including:

[0084] Detect whether the target person appears in the N image frames.

[0085] Preferably, considering the randomness of the storage order of the ring queue each time, when the ring queue is full, the data analysis layer detects the N image frames stored in the ring queue;

[0086] When the target person is not detected in the consecutive N image frames, analyze at least part of the sensing data stored in the second data queue.

[0087] If the target person is not detected in the consecutive N image frames after a certain data collection and random order storage, there are two possibilities: one is that the target person goes out and is not in any monitoring area; one is that the target person happens to be in the monitoring blind area and does not move for a long time. There are many reasons for this situation. Due to the limitation of house type structure, under the limitation of limited sensors, no matter how to set the sensor position, there will always be some monitoring blind areas, although these blind areas are exactly the necessary passageway connecting different areas, but the target person usually does not stay for a long time, therefore, considering the limited value of monitoring sensors, it will not be specially set for this purpose.

[0088] However, if the N image frames do not detect the target person, it is very likely that there is an abnormality.

[0089] It can be seen that since the ring queue has been used for N image frame storage before, and the storage order is random in different cycles, the speed of the detection process of "consecutive N image frames do not detect the target person" is optimal as a whole, and there is no error accumulation in extreme cases, thereby reducing the data calculation amount while ensuring compliance with the actual situation.

[0090] For the first kind of exception, supplementary monitoring and maintenance can be carried out based on the positioning attribute of the wearable device worn by the target person; however, for the second case, further analysis is required, that is, when the target person is not detected in the N image frames, at least part of the sensing data stored in the second data queue is analyzed, and the analysis includes detecting whether the voiceprint signal stored in the second data queue is continuous.

[0091] Preferably, one sound sensor is configured for each monitoring area; every preset period, the voiceprint signal corresponding to each monitoring area collected by each sound sensor is stored in the second data queue;

[0092] And the voiceprint signal Vi corresponding to the i-th monitoring area and the image frame F i; the second data queue includes N storage locations, and the voiceprint signal Vi is stored in the i-th storage location of the second data queue; i = 1, 2, …, N;

[0093] When the ring queue is full, the data analysis layer detects the N image frames stored in the ring queue;

[0094] When the target person is not detected in the N image frames, at least part of the sensing data stored in the second data queue is analyzed, and the analysis includes detecting whether the voiceprint signal stored in the second data queue is continuous.

[0095] It can be seen that the data analysis in the second dimension is entered at this time.

[0096] Unlike the storage method of the image frame data in the first dimension, the voiceprint signal in the second dimension is stored in a fixed order to facilitate subsequent continuity analysis.

[0097] Continue the previous example, as follows:

[0098] Assume that the preset period is 30s, N = 5, t = 0s is the starting point, and the second data queue storage size is 5 (all values are examples, actual situations are different).

[0099] The second data queue is a first-in-first-out linked list storage queue, and the storage locations are L1-L2-L3-L4-L5 in turn; when 5 elements are stored, if there is a 6th element to be enqueued, the element stored first is dequeued.

[0100] t = 0: The data (voiceprint signal sequence) collected by the sound sensors F1-F5 is also described as V1-V5 accordingly;

[0101] V1 is stored in L1, V2 is stored in L2, V3 is stored in L3, V4 is stored in L4, and V5 is stored in L5.

[0102] t=30: The data (image frames) collected by sound sensors F1-F5 are also described as F'1-F'5 accordingly;

[0103] Then store V'1 in L1, V'2 in L2, V'3 in L3, V'4 in L4, and V'5 in L5.

[0104] At this time, when the target person is not detected in any of the N image frames, at least a portion of the sensor data stored in the second data queue is analyzed, and the analysis includes detecting whether the voiceprint signal stored in the second data queue is continuous.

[0105] In other words, when the target person is not detected in any of the N image frames, it is only a preliminary judgment that there may be some abnormal status, but it is still necessary to further confirm it through voiceprint signals.

[0106] Specifically, since voiceprint signals are stored in the second data queue in a fixed order, if the voiceprint signals are discontinuous, it means that the target person has not passed through two consecutive different areas. That is, the target person may be in one of the monitoring areas and has been in a relatively static state for a long time and is outside the monitoring range.

[0107] Preferably, the N storage areas included in the second data queue correspond to the N monitoring areas.

[0108] by Figure 3 For example, preferably, L1 corresponds to V1, L2 corresponds to V2, L3 corresponds to V4, L4 corresponds to V5, and L5 corresponds to V3.

[0109] In other words, the continuity relationship of the N storage areas included in the second data queue is determined based on the continuity (adjacent) relationship of the N monitoring areas.

[0110] For example, if there is no voiceprint signal in L1, a voiceprint signal in L2, and then no voiceprint signal in L3, it may mean that the target person is in a blind spot between regions V2 and V4. Figure 3 (Abnormal stop in the passageway)

[0111] Of course, the above examples of continuity or regional adjacency are merely illustrative, and those skilled in the art can set the continuity relationship according to the actual layout of the target area and their experience.

[0112] The key improvement of the above embodiment is that, based on the continuity relationship, for voiceprint signals, a chain queue storage is used and the health status judgment of the monitoring area is based on the continuity relationship (i.e., at least two storage areas), thus avoiding the impact of data loss in a single storage area.

[0113] The above monitoring analysis is performed by Figure 3 The data analysis engine of the data analysis layer, and the analysis result is output by the data output layer.

[0114] Therefore, as a general example, the remote home health status of the target person includes one of the following:

[0115] (1) The target person is not in any monitoring area;

[0116] (2) The target person is in one of the monitoring areas, and is in a relatively static state for a long time and is located outside the monitoring range;

[0117] (3) The target person is normally active in multiple monitoring areas.

[0118] When the remote home health status of the target person meets the preset standard, a feedback instruction is issued to the wearable device worn by the target person, specifically including:

[0119] When the analysis result represents that the target person is in a relatively static state for a long time and is located outside the monitoring range, a feedback instruction is issued to the wearable device worn by the target person, and the feedback instruction requires the target person to take feedback action or submit a voice reply.

[0120] Optionally, when the target person does not take feedback action or submit a voice reply, it is judged that the target person has an abnormality, and relevant measures such as remote distress call need to be taken.

[0121] Preferably, when the remote home health status of the target person meets the preset standard, a feedback instruction is issued to the wearable device worn by the target person, specifically including:

[0122] When the analysis result represents that the target person is not in any monitoring area, it is determined through the wearable device worn by the target person whether the target person goes out, and if so, a feedback instruction is issued to the wearable device worn by the target person, and the feedback instruction requires the target person to take feedback action or submit a voice reply.

[0123] Preferably, when the remote home health status of the target person is that the target person is normally active in multiple monitoring areas, the preset period is increased, which can further realize the data acquisition energy consumption of the data sensor and the subsequent processing energy consumption.

[0124] In Figures 1-3 Based on the system embodiment shown, Figure 4 The flowchart of the remote home health status multi-dimensional monitoring method of one embodiment of the present application is shown.

[0125] In Figure 4 The method can be implemented on an electronic device or system configured with a memory and a processor via a computer program, and the electronic device or system can be in the form of a physical machine, a virtual machine, a server, a cluster, or any combination thereof.

[0126] The electronic device can also be in the form of a human-computer interaction terminal, which can be a desktop terminal, a smart handheld terminal, a mobile terminal, or the like with a human-computer interaction interface.

[0127] The method comprises the following steps:

[0128] S710: Collecting N image frames of a target person in N monitoring areas and N sets of voiceprint signals existing in the N monitoring areas; N≥2;

[0129] S720: Storing the N image frames in a first ring queue and storing the N sets of voiceprint signals in a second normal queue;

[0130] S730: When the first ring queue is full, analyzing at least part of the sensing data stored in the first ring queue and / or the second normal queue;

[0131] S740: Based on the analysis result, outputting a remote home health status of the target person;

[0132] And when the remote home health status of the target person meets a preset standard, sending a feedback instruction to the target person, the feedback instruction requiring the target person to make a feedback action or submit a voice reply.

[0133] Further, the step S710 and the step S720 are repeatedly executed every preset period.

[0134] And the step 720 stores the N image frames in the first ring queue in different orders in different periods.

[0135] The step 720 stores the N sets of voiceprint signals in the second normal queue in the same order in different periods.

[0136] When the first ring queue is full, detecting whether the target person appears in the N image frames of the first ring queue.

[0137] When the N image frames do not detect the target person, analyzing at least part of the sensing data stored in the second normal queue, and the analysis includes detecting whether the voiceprint signals stored in the second normal queue are continuous.

[0138] It can be understood that the method embodiments and the system embodiments correspond to each other in the execution process, the execution principle, the corresponding function modules and the method steps, and therefore will not be repeated here.

[0139] Other technologies, principles, algorithms or models not detailed in the present application can be referred to the prior art.

[0140] In the foregoing embodiment section, the present application gives a plurality of embodiments, each of which can constitute an independent technical solution and can contribute to the prior art and solve the corresponding technical problems.

[0141] However, it should be pointed out that different embodiments can be combined with each other without violating the logic; at the same time, each embodiment can solve at least one technical problem, but it does not require each individual embodiment to solve multiple or all technical problems.

[0142] At the same time, in the specific embodiments of the present application, if user-related data is involved, when the embodiments of the present application are applied to specific products or technologies, the user's permission or consent needs to be obtained, and the collection, use and processing of related data need to comply with relevant laws, regulations and standards of the country and region.

[0143] The technical solution of the present application, through the data acquisition layer composed of image sensors, sound sensors and wearable devices, the data control layer composed of the first data queue corresponding to the image sensor and the second data queue corresponding to the sound sensor respectively carries out data acquisition and storage, the data analysis layer generates control instructions based on the data control layer, and analyzes at least part of the sensor data stored in the first data queue and / or second data queue; the data output layer receives the analysis result of the data analysis layer, and outputs the remote home health status of the target person;

[0144] At the same time, the first data queue adopts a ring queue, and the second data queue adopts a normal queue, which meets the data generation characteristics of the actual home environment and the subsequent data analysis needs;

[0145] Finally, when the remote home health status of the target person meets the preset standard, a feedback instruction is sent to the wearable device worn by the target person, which can comprehensively determine and monitor the remote home health status based on multi-dimensional data, different dimensions complement and activate each other, and can ensure accuracy while reducing sensor data energy consumption.

[0146] The foregoing has shown and described the method embodiments and systems of the present application, but for those skilled in the art, it can be understood that various changes, modifications, replacements and variations can be made to these embodiments without departing from the principles and spirits of the present application, and the scope of the present application is defined by the appended claims and their equivalents.

Claims

1. A remote home health status multi-dimensional monitoring system, the system comprising a data acquisition layer, a data control layer, a data analysis layer and a data output layer; characterized in that: the data acquisition layer comprises image sensors, sound sensors and wearable devices; the image sensors are used to acquire image frames of a target person in N monitoring areas, and every preset period, N sets of image frames corresponding to N monitoring areas acquired by N image sensors are randomly stored into a first ring queue, and the N sets of image frames are stored into the first ring queue in different orders in different periods; the sound sensors are used to acquire voiceprint signals existing in the N monitoring areas, and every preset period, the voiceprint signal corresponding to each monitoring area acquired by each sound sensor is stored into a second data queue, the second data queue is a first-in-first-out ordinary queue with a size of N, the i-th monitoring area corresponds to a voiceprint signal Vi and an image frame Fi; the second data queue comprises N storage locations, and the voiceprint signal Vi is stored into the i-th storage location of the second data queue; i = 1, 2, …, N; the target person wears the wearable devices to move in the N monitoring areas; N ≥ 2; the data control layer comprises the first ring queue corresponding to the image sensors and the second data queue corresponding to the sound sensors; the data analysis layer analyzes at least part of the sensing data stored in the first ring queue and / or the second data queue based on the control instruction generated by the data control layer; when the first ring queue is full, the data analysis layer detects N sets of image frames stored in the first ring queue; when the target person is not detected in the N sets of image frames, at least part of the sensing data stored in the second data queue is analyzed, and the analysis includes detecting whether the voiceprint signals stored in the second data queue are continuous; the data output layer receives the analysis result of the data analysis layer, outputs the remote home health status of the target person, and sends a feedback instruction to the wearable device worn by the target person when the remote home health status of the target person meets the preset standard.

2. The multi-dimensional monitoring system for remote home health status according to claim 1, wherein, Each monitoring area is configured with one image sensor; Every preset period, the image frames corresponding to each monitoring area acquired by each image sensor are stored into the first ring queue; When the first ring queue is full, the data analysis layer generates the control instruction to detect and analyze all sensing data stored in the first ring queue.

3. The remote home health status multi-dimensional monitoring system of claim 2, wherein, Wherein, Every preset period, the image frames corresponding to each monitoring area acquired by each image sensor are stored into the first ring queue, specifically including: Every preset period, N sets of image frames corresponding to N monitoring areas acquired by N image sensors are randomly stored into the first ring queue; When the first ring queue is full, the data analysis layer generates the control instruction to detect and analyze all sensing data stored in the first ring queue, specifically including: detecting whether the target person appears in the N sets of image frames.

4. The remote home health status multi-dimensional monitoring system of claim 2, wherein, Each monitoring area is configured with one of the sound sensors; and every preset period, the voiceprint signals corresponding to each monitoring area collected by each sound sensor are stored into the second data queue; And the voiceprint signal Vi corresponding to the i-th monitoring area and the image frame Fi; The second data queue includes N storage locations, and the voiceprint signal Vi is stored into the i-th storage location of the second data queue; i = 1, 2, …, N.

5. The multi-dimensional monitoring system for remote home health status according to claim 3 or 4, wherein, Characterized in that: The remote home health status of the target person includes one of the following: (1) The target person is not in any monitoring area; (2) The target person is in one of the monitoring areas and is in a relatively static state for a long time and is located outside the monitoring range; (3) The target person is normally active in multiple monitoring areas.

6. The multi-dimensional monitoring system for remote home health status according to claim 3 or 4, wherein, Characterized in that: When the remote home health status of the target person meets the preset standard, a feedback instruction is sent to the wearable device worn by the target person, specifically including: When the analysis result represents that the target person is in a relatively static state for a long time and is located outside the monitoring range, a feedback instruction is sent to the wearable device worn by the target person, and the feedback instruction requires the target person to take feedback action or submit a voice reply.

7. A method for multi-dimensional monitoring of remote home health status, characterized in that, The method includes the following steps: S710: Collecting N groups of image frames of a target person in N monitoring areas and N groups of voiceprint signals existing in the N monitoring areas; N ≥ 2; S720: Storing the N groups of image frames into a first ring queue and storing the N groups of voiceprint signals into a second data queue, the second data queue being a first-in-first-out ordinary queue with a size of N; S730: When the first ring queue is full, analyzing at least part of the sensing data stored in the first ring queue and / or the second data queue; S740: Based on the analysis result, outputting the remote home health status of the target person; And when the remote home health status of the target person meets the preset standard, a feedback instruction is sent to the target person, and the feedback instruction requires the target person to take feedback action or submit a voice reply; Every preset period, the steps S710 and S720 are repeatedly executed; Every preset period, N groups of image frames corresponding to N monitoring areas collected by N image sensors are randomly stored into the first ring queue; In different periods, the step 720 stores the N groups of image frames into the first ring queue in different orders; In different periods, the step 720 stores the N groups of voiceprint signals into the second data queue in the same order, and the second data queue is a first-in-first-out ordinary queue with a size of N; When the first ring queue is full, detecting whether the target person appears in the N groups of image frames in the first ring queue; When the target person is not detected in the N groups of image frames, analyzing at least part of the sensing data stored in the second data queue, and the analysis includes detecting whether the voiceprint signals stored in the second data queue are continuous.

8. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer executable instructions, and the computer executable instructions are executed by the processor to implement the steps of the remote home health state multi-dimensional monitoring method in claim 7.

Images