Monitoring and early warning system for elderly people living alone based on smart community and multi-dimensional data

Abstract

The invention provides a monitoring and early warning system for elderly people living alone based on a smart community and multi-dimensional data, and relates to the technical field of smart pension, the monitoring and early warning system comprises a personal terminal application, a community management application and a server terminal, and the server terminal comprises a data preprocessing module, a data storage module, a multi-source data integration module and an early warning analysis module. According to the invention, health information and fire-fighting information of elderly people living alone are collected in real time, real-time data are processed and calculated, early warning is carried out according to the real-time data, abstract data are converted into perceivable sound wave frequency, a human instinct response mode is combined, and compared with a general early-warning reminding mode, the method is simpler and clearer, and the early-warning reminding efficiency is improved. And the complex multi-source data is subjected to lightweight processing, so that the problem of algorithm bloating in multi-source data fusion is avoided, and the method can be deployed only by presetting a corresponding item threshold and a frequency parameter.

Description

Technical Field

[0001] The present invention relates to the field of smart elderly care technology, and in particular to a monitoring and early warning system for elderly people living alone based on a smart community and multi-dimensional data. Background Art

[0002] It is a common situation for elderly people to live alone. Due to the deterioration of their physical functions and cognitive decline, they cannot detect some fire and health hazards in time. Moreover, since they live alone, the hazards are very likely to become dangers. Currently, we can only rely on community personnel to visit and investigate frequently to ensure the fire and health safety of elderly people living alone as much as possible, but this is undoubtedly inefficient.

[0003] Smart communities are modern communities that are supported by new-generation information technologies such as the Internet of Things (IoT), big data, artificial intelligence (AI), and cloud computing. They integrate community resources and optimize service processes to achieve intelligent community management, convenient life services, and efficient resident participation. Their goal is to improve residents' quality of life, reduce operating costs, and promote sustainable community development.

[0004] At present, with the development of science and technology, the popularization of smart devices and the development of the Internet of Things, it has become very simple to collect water, electricity, gas, home fire equipment data and health data of elderly people living alone through smart phones, smart bracelets and other devices. By designing APP and computer programs, the elderly and smart communities are connected, and the data interaction in the middle is processed through the server, making it very simple for community service personnel to quickly discover the situation of the elderly.

[0005] However, the current health and fire warning systems for the elderly generally use time series data processing models to process health and fire data and make a certain degree of prediction. Due to the large number of health and fire data items, different collection methods, and different data formats, this type of system requires a large number of algorithms to support data fusion preparation, which makes the system produced in this way bloated, complex, and requires a lot of time to train, and has obvious technical defects. Summary of the invention

[0006] The purpose of the present invention is to solve the shortcomings of the prior art by designing a simpler real-time data processing method and generating specific sound types for early warning reminders, thereby providing a monitoring early warning system for elderly people living alone based on smart communities and multi-dimensional data.

[0007] In order to achieve the above-mentioned purpose, the present invention adopts the following technical scheme: a monitoring and early warning system for elderly people living alone based on smart community and multi-dimensional data, including a personal terminal application, a community management application and a server terminal, wherein the server terminal includes a data preprocessing module, a data storage module, a multi-source data integration module and an early warning analysis module; The personal terminal application: mounted in a smart watch or smart phone, includes a data uploading module for collecting and uploading basic information and environmental data of a personal user, an early warning receiving module for receiving early warning information sent by a server terminal, a service record viewing module for viewing relevant information of community service personnel, and an emergency call module for making emergency calls; The community management application includes an early warning handling and service management module for formulating early warning content and early warning processing content, a data visualization module for visualizing data, a resource scheduling module for scheduling community service resources, and a report generation module for generating periodic reports; The data preprocessing module cleans the noise data of the real-time data and extracts data features; The data storage module is used to store information and data collected by the personal terminal application and data input and generated by the community management application; The multi-source data integration module integrates the data processed by the data preprocessing module, and during the integration, integrates the various information and data of the elderly living alone according to the time sequence relationship; The early warning analysis module includes a fire warning model, a health warning model and a collaborative warning model; The fire warning model analyzes the water, electricity, gas usage information and smoke alarm information, and makes corresponding warnings according to changes in the information; The health warning model analyzes the basic information and medical information of the elderly and makes corresponding warnings according to changes in the information; The collaborative warning model is based on the timeline. When any one of the fire warning and health warning projects is generated, the other warning project is operated at the same time. The change of the warning value is analyzed using the sine function frequency. The corresponding frequency signal can be assigned to the warning value through the sine function. Therefore, when the warning signal is generated, the collaborative warning model can directly generate the corresponding frequency signal and send it through the audio speaker to make a corresponding reminder. Community service personnel can first distinguish the warning level by distinguishing the sound, reduce the time for community service personnel to confirm the signal, and improve the response speed of community service personnel to emergency situations.

[0008] As a preferred implementation, when the data preprocessing module preprocesses the real-time data, specifically: First, fill in the missing values: Then normalize the data: Then extract data features based on time series.

[0009] As a preferred implementation, the real-time data of the data upload module is obtained through the smart device carried by the terminal application of the elderly living alone, including but not limited to: voice input, shooting recognition, and the obtained real-time data is reported to the server terminal, and the real-time data items include but are not limited to: basic information of the elderly, medical information of the elderly, water, electricity, gas usage information, and smoke alarm information; the early warning receiving module receives fire warning notifications and health warning notifications, and the notification methods include but are not limited to: voice broadcast, vibration reminder, and screen highlight display; the service record viewing module views the community service content and related personnel information; the call content of the emergency call module is not limited to: one-click calling emergency contacts, community management personnel, emergency calls, and automatic sending of GPS positioning.

[0010] As a preferred implementation, the warning handling and service management module performs targeted processing on the warning content based on the warning information output by the server terminal; the data visualization module displays the distribution of the elderly's location information based on the uploaded real-time data items; the resource scheduling module allocates community service tasks based on the number of elderly people in the community and the number of community managers; the report generation module generates reports on service items within a certain period of time, stores them, and sends them to personal terminal applications.

[0011] As a preferred implementation, the collaborative early warning model presets early warning thresholds for each monitoring item. The fire early warning model analyzes water, electricity, gas usage information and smoke alarm information according to the early warning thresholds in the collaborative early warning model. Similarly, the health early warning model analyzes basic information and medical information of the elderly according to the early warning thresholds in the collaborative early warning model. When any item in the real-time data exceeds the early warning threshold in the collaborative early warning model, the collaborative early warning model processes all data items of the real-time data through a sine function. The specific steps are as follows: First, assume that the real-time data k(t) is the instantaneous frequency of the sine function and generate a frequency modulated signal: Where k(t) is the frequency coefficient that changes with time; Since the real-time data is updated periodically, the corresponding sinusoidal signal is generated according to the real-time data in a single real-time data update cycle. Each signal in the time period is: Then the frequency of each time period can be analyzed by short-time Fourier transform, and the instantaneous frequency can be extracted by Hilbert transform, and finally the frequency analysis result can be matched with the corresponding detection value; The collaborative warning model then generates an electrical signal of the corresponding frequency based on the frequency calculated by the real-time data, and sends it to the community management application and the personal terminal application for playback through the player.

[0012] As a preferred implementation, when the collaborative warning model generates a sine wave signal of a corresponding frequency according to the sine frequency value calculated in real time, it first ensures that the signal amplitude is within the range of [-1, 1], and then based on the periodic update characteristics of real-time data, when converting the sine wave signal of real-time data, a segmented constant frequency signal generation method is adopted, specifically: First define the parameters: sampling rate , duration of each frequency segment , frequency sequence , total duration ; Then the time axis is discretized, and the time point of each signal is defined as: in, is the number of samples per segment; The discrete expression of the i-th segment signal is: Where A is the amplitude scaling factor used to prevent clipping; The complete signal y[n] consists of three signals connected in time sequence: Then, through digital-to-analog conversion, the discrete signal y[n] is converted into a continuous-time signal: in, , the actual sound card outputs through zero-order hold or interpolation filtering.

[0013] As a preferred implementation, the collaborative warning model generates sinusoidal wave signals of different frequencies according to different real-time data, and produces corresponding sounds according to the generated sinusoidal wave signals. Community service personnel are trained to distinguish the sounds produced by sinusoidal wave signals during the training process. Since the frequency of the sinusoidal wave signal changes with the real-time data, community service personnel can quickly identify the urgency of the warning directly through the frequency of the sound generated by the sinusoidal wave signal.

[0014] Compared with the prior art, the advantages and positive effects of the present invention are: The present invention collects health information and fire information of elderly people living alone in real time, processes and calculates the real-time data, makes early warnings based on the real-time data, converts abstract data into perceptible sound wave frequencies, and combines human instinctive reaction patterns. Compared with general early warning reminder methods, it is more concise and clear, and lightweight processing is performed on complex multi-source data, avoiding the problem of bloated algorithms in multi-source data fusion. The present invention can be deployed by simply presetting the corresponding project thresholds and frequency parameters. At the same time, the present invention realizes "cognitive burden-free" early warning through sound, and community service personnel only need to briefly explain the interface to the elderly in advance, avoiding the risk of misreading due to vision and cognitive decline in the elderly. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 A structural schematic diagram of a monitoring and early warning system for elderly people living alone based on a smart community and multi-dimensional data provided by the present invention.

[0016] Figure 2 A half-section schematic diagram of a monitoring and early warning system for elderly people living alone based on a smart community and multi-dimensional data provided by the present invention. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0018] Example 1 like Figure 1 , the present invention provides a technical solution: a monitoring and early warning system for elderly people living alone based on smart communities and multi-dimensional data, including a personal terminal application, a community management application and a server terminal, wherein the server terminal includes a data preprocessing module, a data storage module, a multi-source data integration module and an early warning analysis module; in: The personal terminal application is installed in a smart watch or smart phone, and the interface design content includes but is not limited to: enlarged font, high contrast, voice assistant, simplified interaction process, etc. The personal terminal application includes a data upload module for collecting and uploading basic information and environmental data of personal users, an early warning receiving module for receiving early warning information sent by a server terminal, a service record viewing module for viewing relevant information of community service personnel, and an emergency call module for making emergency calls. Specifically: The real-time data of the data upload module is obtained through the smart device carried by the terminal application of the elderly living alone, including but not limited to: voice input, shooting recognition, and the obtained real-time data is reported to the server terminal. The real-time data items include but are not limited to: basic information of the elderly, medical information of the elderly, water, electricity and gas usage information, and smoke alarm information; the warning receiving module receives fire warning notifications and health warning notifications, and the notification methods are not limited to: voice broadcast, vibration reminder and screen highlight display; the service record viewing module views the community service content and related personnel information; the emergency call module call content includes but is not limited to: one-click calling emergency contacts, community management personnel, emergency phone numbers and automatic sending of GPS positioning; In the above content, the personal terminal application is installed on a smart watch or smart phone, and the interface design takes into account the usage habits of the elderly, such as large fonts, high contrast, voice assistants and simplified interaction processes, to improve the convenience of use for the elderly and avoid problems caused by complex operations. The data upload module collects basic information, medical information, water, electricity, gas usage and smoke alarm data. When implemented, it can access user water, electricity and gas data obtained by smart water systems, power supply company systems, smart gas systems, etc. Based on the smart device environment equipped with the personal terminal application, this method only requires user authorization, or authorization with the help of community service personnel, to obtain the corresponding data. Data related to the user's health can be entered and uploaded through the user's voice input, handwriting input or taking a photo of the medical record, which greatly simplifies the data acquisition process and allows the elderly to easily, conveniently and quickly upload health and fire data. The early warning receiving module can receive fire and health warnings and notify the elderly through voice, vibration and highlight display, which helps to remind the elderly to pay attention to danger in time, especially in emergencies. Multiple notification methods can increase the success rate of information communication. The one-click call and automatic GPS positioning of the emergency call module are key functions, ensuring that the elderly can quickly contact help in an emergency, and community personnel can also quickly locate and shorten the response time.

[0019] The community management application is installed in the computer of the community service center, including an early warning handling and service management module for formulating early warning content and early warning processing content, a data visualization module for visualizing data, a resource scheduling module for scheduling community service resources, and a report generation module for generating periodic reports, specifically: The warning handling and service management module performs targeted processing on the warning content according to the warning information output by the server terminal; the data visualization module displays the distribution of the elderly's location information according to the uploaded real-time data items; the resource scheduling module allocates community service tasks according to the number of elderly people in the community and the number of community managers; the report generation module generates reports for service items within a certain period of time, stores them, and sends them to personal terminal applications; The data preprocessing module cleans the noise data of the real-time data and extracts data features, specifically: First, fill in the missing values: Then normalize the data: Then extract data features based on time series; The data storage module is used to store information and data collected by the personal terminal application and data input and generated by the community management application; The multi-source data integration module integrates the data processed by the data preprocessing module, and during the integration, integrates the various information and data of the elderly living alone according to the time sequence relationship; The early warning analysis module includes a fire warning model, a health warning model and a collaborative warning model; The fire warning model analyzes the water, electricity, gas usage information and smoke alarm information, and makes corresponding warnings according to changes in the information; The health warning model analyzes the basic information and medical information of the elderly and makes corresponding warnings according to changes in the information; The collaborative warning model is based on the timeline. When any one of the fire warning and health warning projects is generated, the other warning project is operated at the same time. The change of the warning value is analyzed using the sine function frequency. The corresponding frequency signal can be assigned to the warning value through the sine function. Therefore, when the warning signal is generated, the collaborative warning model can directly generate the corresponding frequency signal and send it through the audio speaker to make a corresponding reminder. Community service personnel can first distinguish the warning level by distinguishing the sound, reduce the time for community service personnel to confirm the signal, and improve the response speed of community service personnel to emergency situations.

[0020] In this embodiment, the present invention realizes closed-loop management from risk monitoring to emergency response through multi-terminal collaboration, multi-source data fusion and intelligent early warning models, thereby improving the safety of elderly people living alone while optimizing community service efficiency.

[0021] Example 2 like Figure 2As shown, the collaborative early warning model presets the early warning threshold of each monitoring item. The fire early warning model analyzes the water, electricity, gas usage information and smoke alarm information according to the early warning threshold in the collaborative early warning model. Similarly, the health early warning model analyzes the basic information and medical information of the elderly according to the early warning threshold in the collaborative early warning model. When any item in the real-time data exceeds the early warning threshold in the collaborative early warning model, the collaborative early warning model processes all data items of the real-time data through a sine function. The specific steps are as follows: First, assume that the real-time data k(t) is the instantaneous frequency of the sine function and generate a frequency modulated signal: Where k(t) is the frequency coefficient that changes with time; Since the real-time data is updated periodically, the corresponding sinusoidal signal is generated according to the real-time data in a single real-time data update cycle. Each signal in the time period is: Then the frequency of each time period can be analyzed by short-time Fourier transform, and the instantaneous frequency can be extracted by Hilbert transform, and finally the frequency analysis result can be matched with the corresponding detection value; Then the collaborative warning model generates an electrical signal of the corresponding frequency based on the frequency calculated by the real-time data, and sends it to the community management application and the personal terminal application for playback through the player; Among them, since the value of real-time data actually has only two situations: lower than the threshold and higher than the threshold, but the difference between the real-time data and the threshold is an important indicator reflecting the urgency of the situation, in general, complex algorithm conversion and step-by-step definition are required to reflect the difference, which requires a lot of preliminary preparation and calculation, and the step-by-step division is also prone to inaccurate numerical expression. In the present invention, the early warning of multi-source data will further increase the workload in the early stage and reduce the accuracy, but the real-time data is converted into a sound of the corresponding frequency through a sine function to remind, which can greatly simplify the workload of the early preparation, and each value corresponds to a sine wave information. Although the user cannot accurately distinguish it at the first time, it can be further distinguished with the help of data visualization. Compared with the general early warning level division, this method is obviously faster, more accurate and convenient to construct; In this embodiment, the general expression of the sine function is: , where A is the amplitude, B affects the frequency and period, C is the phase displacement, and D is the longitudinal displacement. The waveform of the sine function is the same as that of the sound wave, and sound is a common means of warning and reminder. Normal people are not sensitive to the amplitude of sound, so using real-time data as B in the sine function can directly affect the frequency of the sine function. Combined with the characteristics that the waveform of the sine function is the same as that of the sound wave, the sine wave information of the sine function is converted into an electrical signal of the output sound wave. The real-time data that exceeds the threshold can be directly played out in the form of sound to directly remind the user. In addition, the user can also quickly make a preliminary judgment on the warning level according to the frequency of the sound, so as to facilitate the timely formulation or implementation of the warning response plan.

[0022] Example 3 When the collaborative warning model generates a sine wave signal of the corresponding frequency according to the sine frequency value calculated in real time, it first ensures that the signal amplitude is within the range of [-1, 1]. Then, based on the periodic update characteristics of real-time data, a segmented constant frequency signal generation method is adopted when converting the sine wave signal of real-time data. Specifically: First define the parameters: sampling rate , duration of each frequency segment , frequency sequence , total duration ; Then the time axis is discretized, and the time point of each signal is defined as: in, is the number of samples per segment; The discrete expression of the i-th segment signal is: Where A is the amplitude scaling factor used to prevent clipping; The complete signal y[n] consists of three signals connected in time sequence: Then, through digital-to-analog conversion, the discrete signal y[n] is converted into a continuous-time signal: in, , the actual sound card outputs through zero-order hold or interpolation filtering; Furthermore, the collaborative warning model generates sinusoidal wave signals of different frequencies according to different real-time data, and produces corresponding sounds according to the generated sinusoidal wave signals. Community service personnel are trained to distinguish the sounds produced by sinusoidal wave signals during the training process. Since the frequency of the sinusoidal wave signal changes with the real-time data, community service personnel can quickly identify the urgency of the warning directly through the frequency of the sound generated by the sinusoidal wave signal.

[0023] Example 4 like Figure 2 As shown, when the collaborative early warning model is in operation, the health early warning model and the fire early warning model first compare the data of the corresponding items in the real-time data. The health early warning model and the fire early warning model pre-set the comparison thresholds of each item in the real-time data and the collaborative early warning model. The setting of the threshold is formulated according to the specific physical health and living habits of the elderly. The construction of the health early warning model and the fire early warning model can be based on the technical construction of health early warning and fire early warning in the existing technology, as long as the comparison of real-time data with the threshold is completed; When any data in the real-time data exceeds the threshold, all data items in the real-time data are processed by a sine function to generate a sine wave signal, and a sound for early warning reminder is produced based on the sine wave. The elderly and community service personnel can judge the urgency of the early warning situation through sounds of different frequencies. When the sound is generated, the corresponding project voice can be inserted into it, which is also convenient for users to distinguish. A switching function can also be added to facilitate users to quickly switch the early warning sounds of different projects, making it more convenient for community service personnel to judge the early warning situation.

[0024] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A monitoring and early warning system for elderly people living alone based on smart communities and multi-dimensional data, characterized in that: It includes a personal terminal application, a community management application and a server terminal, wherein the server terminal includes a data preprocessing module, a data storage module, a multi-source data integration module and an early warning analysis module; The personal terminal application: mounted in a smart watch or smart phone, includes a data uploading module for collecting and uploading basic information and environmental data of a personal user, an early warning receiving module for receiving early warning information sent by a server terminal, a service record viewing module for viewing relevant information of community service personnel, and an emergency call module for making emergency calls; The community management application includes an early warning handling and service management module for formulating early warning content and early warning processing content, a data visualization module for visualizing data, a resource scheduling module for scheduling community service resources, and a report generation module for generating periodic reports; The data preprocessing module cleans the noise data of the real-time data and extracts data features; The data storage module is used to store information and data collected by the personal terminal application and data input and generated by the community management application; The multi-source data integration module integrates the data processed by the data preprocessing module, and during the integration, integrates the various information and data of the elderly living alone according to the time sequence relationship; The early warning analysis module includes a fire warning model, a health warning model and a collaborative warning model; The fire warning model analyzes the water, electricity, gas usage information and smoke alarm information, and makes corresponding warnings according to changes in the information; The health warning model analyzes the basic information and medical information of the elderly and makes corresponding warnings according to changes in the information; The collaborative warning model is based on the timeline. When any one of the fire warning and health warning projects is generated, the other warning project is operated at the same time. The change of the warning value is analyzed using the sine function frequency. The corresponding frequency signal can be assigned to the warning value through the sine function. Therefore, when the warning signal is generated, the collaborative warning model can directly generate the corresponding frequency signal and send it through the audio speaker to make a corresponding reminder. Community service personnel can first distinguish the warning level by distinguishing the sound, reduce the time for community service personnel to confirm the signal, and improve the response speed of community service personnel to emergency situations.

2. According to claim 1, a monitoring and early warning system for elderly people living alone based on smart community and multi-dimensional data is characterized by: When the data preprocessing module preprocesses the real-time data, specifically: First, fill in the missing values: Then normalize the data: Then extract data features based on time series.

3. According to claim 1, a monitoring and early warning system for elderly people living alone based on smart community and multi-dimensional data is characterized by: In the personal terminal application, the real-time data of the data upload module is obtained through the smart device carried by the terminal application of the elderly living alone, including but not limited to: voice input, shooting recognition, and the obtained real-time data is reported to the server terminal. The real-time data items are not limited to: basic information of the elderly, medical information of the elderly, water, electricity and gas usage information, and smoke alarm information; The warning receiving module receives fire warning notifications and health warning notifications, and the notification methods include but are not limited to: voice broadcast, vibration reminder and screen highlight display; the service record viewing module views community service content and related personnel information; the emergency call module call content includes but is not limited to: one-click calling emergency contacts, community managers, emergency calls and automatic sending of GPS positioning.

4. According to claim 1, a monitoring and early warning system for elderly people living alone based on smart community and multi-dimensional data is characterized by: In the community management application, the warning handling and service management module performs targeted processing on the warning content according to the warning information output by the server terminal; The data visualization module displays the distribution of the elderly's location information according to the uploaded real-time data items; the resource scheduling module allocates community service tasks according to the number of elderly people in the community and the number of community managers; The report generation module generates reports of service items within a certain period of time, stores them, and sends them to the personal terminal application.

5. According to claim 1, a monitoring and early warning system for elderly people living alone based on smart community and multi-dimensional data is characterized by: The collaborative early warning model presets the early warning threshold of each monitoring item. The fire early warning model analyzes the water, electricity, gas usage information and smoke alarm information according to the early warning threshold in the collaborative early warning model. Similarly, the health early warning model analyzes the basic information and medical information of the elderly according to the early warning threshold in the collaborative early warning model. When any item in the real-time data exceeds the early warning threshold in the collaborative early warning model, the collaborative early warning model processes all data items of the real-time data through a sine function. The specific steps are as follows: First, assume that the real-time data k(t) is the instantaneous frequency of the sine function and generate a frequency modulated signal: Where k(t) is the frequency coefficient that changes with time; Since the real-time data is updated periodically, the corresponding sinusoidal signal is generated according to the real-time data in a single real-time data update cycle. Each signal in the time period is: Then the frequency of each time period can be analyzed by short-time Fourier transform, and the instantaneous frequency can be extracted by Hilbert transform, and finally the frequency analysis result can be matched with the corresponding detection value; The collaborative warning model then generates an electrical signal of the corresponding frequency based on the frequency calculated by the real-time data, and sends it to the community management application and personal terminal application for playback through the player.

6. The monitoring and early warning system for elderly people living alone based on smart community and multi-dimensional data according to claim 5 is characterized by: When the collaborative warning model generates a sine wave signal of the corresponding frequency according to the sine frequency value calculated in real time, it first ensures that the signal amplitude is within the range of [-1, 1]. Then, based on the periodic update characteristics of real-time data, a segmented constant frequency signal generation method is adopted when converting the sine wave signal of real-time data. Specifically: First define the parameters: sampling rate , duration of each frequency segment , frequency sequence Total duration ; Then the time axis is discretized, and the time point of each signal is defined as: in, is the number of samples per segment; The discrete expression of the i-th segment signal is: Where A is the amplitude scaling factor used to prevent clipping; The complete signal y[n] consists of three signals connected in time sequence: Then, through digital-to-analog conversion, the discrete signal y[n] is converted into a continuous-time signal: in, , the actual sound card outputs through zero-order hold or interpolation filtering.

7. The monitoring and early warning system for elderly people living alone based on smart community and multi-dimensional data according to claim 6 is characterized by: The collaborative early warning model generates sinusoidal wave signals of different frequencies according to different real-time data, and produces corresponding sounds according to the generated sinusoidal wave signals. Community service personnel are trained to distinguish the sounds produced by sinusoidal wave signals during the training process. Since the frequency of the sinusoidal wave signal changes with the real-time data, community service personnel can quickly identify the urgency of the warning directly through the frequency of the sound generated by the sinusoidal wave signal.

Images