Method, device, computer equipment and storage medium for determining IoT device

Abstract

The present application relates to a method, apparatus, computer equipment and storage medium for determining an Internet of Things device. The method comprises: obtaining time series data of the historical environment of a target community; analyzing the risk level of the target community based on the time series data; determining at least one candidate Internet of Things device according to the service needs of the target community; and determining an Internet of Things device suitable for the target community from at least one candidate Internet of Things device according to the risk level of the target community and a preset Internet of Things device screening strategy. The time series data is the environmental data of the target community within a preset historical time period, and the time series data is collected at equal intervals at a preset sampling rate. The present application can determine suitable Internet of Things devices for each community and improve the accuracy of Internet of Things device recommendations.

Description

Technical Field

[0001] The present application relates to the field of Internet of Things monitoring and early warning technology, and in particular to a method, apparatus, computer equipment and storage medium for determining Internet of Things devices. Background Art

[0002] With the development of society and technology, more and more electronic devices are being used in daily life, improving people's living standards. According to relevant surveys, when choosing a retirement plan, 90% of elderly people choose home care, while only about 10% choose to live in a nursing home. Compared with nursing homes, home care is a low-cost and high-economic and socially beneficial option.

[0003] In the related art, home-based elderly care mainly relies on various IoT devices, such as various smart sensors and smart thermometers. However, the cost and maintenance of IoT devices in the process of home-based elderly care are relatively expensive. Therefore, how to recommend effective IoT devices for home-based elderly care has become an urgent problem that needs to be solved. Summary of the Invention

[0004] Based on this, it is necessary to provide an IoT device determination method, apparatus, computer equipment and storage medium that can determine applicable IoT devices for each community based on the risk level of each community to address the above technical problems.

[0005] In a first aspect, the present application provides a method for determining an IoT device, the method comprising:

[0006] Obtaining time series data of the historical environment of the target community. The time series data is the environmental data of the target community within a preset historical time period, and the time series data is collected at equal intervals and according to a preset sampling rate;

[0007] Analyze the risk level of target communities based on time series data;

[0008] Identify at least one candidate IoT device based on the service needs of the target community;

[0009] According to the risk level of the target community and a preset IoT device screening strategy, an IoT device suitable for the target community is determined from at least one candidate IoT device.

[0010] In one embodiment, analyzing the risk level of a target community based on time series data includes:

[0011] Input the time series data into the environmental prediction model, and output the environmental prediction data of the target community through the environmental prediction model. The environmental prediction data represents the environmental changes of the target community in a preset future time period;

[0012] Determine the risk level of the target community based on environmental prediction data.

[0013] In one embodiment, before inputting the time series data into the environmental prediction model, the method further includes:

[0014] Performing stabilization processing on time series data to obtain stable time series data; stabilization processing includes difference operation and smoothing operation;

[0015] Perform non-white noise test on stationary time series data;

[0016] If the stationary time series data is white noise, the step of inputting the stationary time series data into the environmental prediction model is performed.

[0017] In one embodiment, before inputting the time series data into the environmental prediction model, the method further includes:

[0018] Obtain modeling parameters; modeling parameters include autoregressive order, difference order, and moving average order. The difference order is determined based on the number of difference operations, and the autoregressive order and moving average order are determined by a preset order determination method.

[0019] According to the modeling parameters, an autoregressive moving average model is established and used as an environmental prediction model.

[0020] In one embodiment, the preset order determination method includes at least one of the following order determination methods: autocorrelation function and partial autocorrelation function order determination, information criterion order determination, and heat map order determination.

[0021] In one embodiment, the method further comprises:

[0022] According to the IoT devices applicable to the target community, recommendation information of the target IoT devices is sent to the terminal devices of each user in the target community.

[0023] In one embodiment, based on the IoT devices applicable to the target community, recommendation information of the target IoT devices is sent to the terminal devices of each user in the target community, including:

[0024] Obtain the user type of each user in the target community;

[0025] According to the user type, determine the target IoT device corresponding to each user in the target community from the IoT devices applicable to the target community;

[0026] Send recommendation information of target IoT devices to the terminal devices of each user in the target community.

[0027] In one embodiment, obtaining the user type of each user in the target community includes:

[0028] Obtain user data of each user in the target community. User data is data generated when each user uses the community application on a terminal device.

[0029] Clustering the user data to obtain multiple user data sets; each user data set corresponds to a user type;

[0030] The user type of each user in the target community is determined according to the user data set to which each user in the target community belongs.

[0031] In one embodiment, the community application includes a target mode, which includes at least a preset event reminder function and a preset content display interface;

[0032] The method further comprises:

[0033] In response to a mode switching instruction triggered by a user in a target terminal device, the community application in the target terminal device is controlled to switch from a current mode to a target mode.

[0034] In a second aspect, the present application further provides an IoT device determination device, the device comprising:

[0035] The first acquisition module is used to obtain time series data of the historical environment of the target community. The time series data is the environmental data of the target community within a preset historical time period, and the time series data is collected at equal intervals according to a preset sampling rate;

[0036] An analysis module, used to analyze the risk level of the target community based on time series data;

[0037] A first determination module is configured to determine at least one candidate IoT device based on the service needs of the target community;

[0038] The second determination module is used to determine an IoT device suitable for the target community from at least one candidate IoT device based on the risk level of the target community and a preset IoT device screening strategy.

[0039] In one embodiment, the analysis module includes:

[0040] A prediction unit, configured to input the time series data into an environmental prediction model and output environmental prediction data of the target community through the environmental prediction model, wherein the environmental prediction data represents environmental changes of the target community within a preset future time period;

[0041] The first determination unit is used to determine the risk level of the target community based on the environmental prediction data.

[0042] In one embodiment, the apparatus further comprises:

[0043] The processing module is used to perform stabilization processing on the time series data to obtain stable time series data; the stabilization processing includes difference operation and smoothing operation;

[0044] The test module is used to perform non-white noise test on stationary time series data;

[0045] The judgment module is used to execute the step of inputting the stationary time series data into the environmental prediction model if the stationary time series data is white noise.

[0046] In one embodiment, the apparatus further comprises:

[0047] The second acquisition module is used to obtain modeling parameters; the modeling parameters include autoregressive order, difference order and moving average order, the difference order is determined based on the number of difference operations, and the autoregressive order and moving average order are determined by a preset order determination method;

[0048] The modeling module is used to establish an autoregressive moving average model based on modeling parameters and use the autoregressive moving average model as an environmental prediction model.

[0049] In one embodiment, the preset order determination method includes at least one of the following order determination methods: autocorrelation function and partial autocorrelation function order determination, information criterion order determination, and heat map order determination.

[0050] In one embodiment, the apparatus further comprises:

[0051] The recommendation module is used to send recommendation information of target IoT devices to the terminal devices of each user in the target community based on the IoT devices applicable to the target community.

[0052] In one embodiment, the recommendation module includes:

[0053] An acquisition unit, used to acquire the user type of each user in the target community;

[0054] A second determining unit is configured to determine, based on the user type, a target IoT device corresponding to each user in the target community from IoT devices applicable to the target community;

[0055] The sending unit is used to send the recommendation information of the target Internet of Things device to the terminal device of each user in the target community.

[0056] In one embodiment, the acquiring unit includes:

[0057] The acquisition subunit is used to obtain user data of each user in the target community. The user data is the data generated when each user uses the community application in the terminal device;

[0058] A clustering subunit, configured to cluster user data to obtain multiple user data sets; each user data set corresponds to a user type;

[0059] The determination subunit is configured to determine the user type of each user in the target community according to the user data set to which each user in the target community belongs.

[0060] In one embodiment, the community application includes a target mode, which includes at least a preset event reminder function and a preset content display interface;

[0061] The device further comprises:

[0062] The switching control module is used to control the community application in the target terminal device to switch from the current mode to the target mode in response to a mode switching instruction triggered by the user in the target terminal device.

[0063] In a third aspect, the present application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the method provided in any one of the embodiments of the first aspect are implemented.

[0064] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method provided in any one of the embodiments of the first aspect above.

[0065] The aforementioned IoT device determination method, apparatus, computer device, and storage medium obtain time series data of the target community's historical environment; analyze the target community's risk level based on the time series data; determine at least one candidate IoT device based on the target community's service needs; and determine an IoT device suitable for the target community from the at least one candidate IoT device based on the target community's risk level and a preset IoT device screening strategy. The time series data is environmental data of the target community within a preset historical time period, and the time series data is collected at equal intervals at a preset sampling rate. In this method, the risk level of the target community is determined based on future environmental changes in the target community. These future environmental changes are predicted based on analysis of real historical environmental time series data. This ensures that the predicted future environmental changes are more accurately aligned with the actual future environmental conditions, thereby ensuring the accuracy of the determined risk level of the target community. Furthermore, at least one candidate IoT device is determined based on the target community's service needs, and the determined IoT device is compatible with the target community's actual installation environment. Furthermore, based on the target community's risk level, an IoT device suitable for the target community is determined from the candidate IoT devices, ensuring that the determined IoT device accurately meets the target community's environmental anomaly monitoring needs. In this way, the determined applicable IoT devices can be recommended to the corresponding community, which can greatly improve the accuracy of IoT device recommendations; and since the IoT devices determined are suitable for the target devices, there will be no redundant idle situations, which avoids the waste of IoT device resources while also improving the resource utilization of IoT devices. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] Figure 1 A diagram illustrating an application environment of a method for determining an IoT device in one embodiment;

[0067] Figure 2 Schematic diagram of a flow chart of a method for determining an IoT device in one embodiment;

[0068] Figure 3 1 is a flow chart of a method for analyzing the risk level of a target community in one embodiment;

[0069] Figure 4 Schematic diagram of a flow chart of a time series data preprocessing operation in one embodiment;

[0070] Figure 5 A schematic flow chart of a modeling method in one embodiment;

[0071] Figure 6 A schematic flow chart of a method for determining an IoT device in another embodiment;

[0072] Figure 7A schematic flow chart of a method for determining an IoT device in another embodiment;

[0073] Figure 8 1 is a flow chart of a user classification method according to an embodiment;

[0074] Figure 9 A schematic flow chart of a method for determining an IoT device in another embodiment;

[0075] Figure 10 This is a structural block diagram of an IoT device determination apparatus in one embodiment;

[0076] Figure 11 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0077] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0078] Currently, most people prefer home-based care for their elderly. According to relevant research, 90% of seniors choose home-based care, while only about 10% opt for institutional care. At the same time, there are a large number of disabled, elderly, and empty-nest elderly, most of whom live in separate homes. Home-based care may present challenges with daily care, spiritual comfort, and medical care. However, compared to nursing homes, home-based care offers a lower investment and higher economic and social benefits. Furthermore, community applications (APPs) in retirement communities offer convenient, fast, and intuitive operation, providing more online community services for home-based caregivers and generating greater social benefits.

[0079] Home-based elderly care primarily relies on various IoT devices, such as smart sensors, smart home appliances, and smart medical devices, to ensure a high quality of life for those in the care home. Smart sensors include, but are not limited to, smart smoke sensors, smart carbon monoxide sensors, smart liquefied gas sensors, smart temperature and humidity sensors, air quality sensors for volatile organic compounds (VOCs), and smart water leak detection sensors. Smart home appliances include, but are not limited to, smart TVs, projectors, air conditioners, and home robots. Smart medical devices include, but are not limited to, smart blood pressure monitors, smart blood glucose meters, smart thermometers, and smart wristbands.

[0080] When using various IoT devices to achieve home-based elderly care, on the one hand, the cost of IoT devices is high, and the maintenance costs after damage are also relatively expensive. If IoT devices are blindly recommended to users in the community without considering actual needs, some IoT devices will be idle after installation, resulting in a waste of resources. On the other hand, IoT devices are often associated with user terminal devices, requiring users to be able to use the terminal devices normally in order to obtain corresponding monitoring information in a timely manner and enjoy related online community services through the community app installed on the terminal device. However, some users are not familiar with the use and operation of various services in the community app. Payment, repair, etc. cannot be performed online on the community app of the terminal device and need to be handled offline. Therefore, it is necessary to recommend differentiated IoT devices suitable for home-based elderly care to users.

[0081] Based on the above application scenarios, this application proposes a method, device, computer device and storage medium for determining IoT devices, which can determine suitable IoT devices for users in various communities, thereby improving the accuracy of IoT device recommendations during home-based elderly care.

[0082] The method for determining IoT devices provided in this application can be applied to Figure 1 In the application environment shown, the computer devices in the application environment can be, but are not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can be smart speakers, smart TVs, smart air conditioners, smart car devices, etc. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc.

[0083] Among them, the internal structure of the computer device is as follows Figure 1 As shown, the processor in this internal structure is used to provide data calculation and analysis functions. The memory in this internal structure includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database can be used to store historical environmental data and / or user data for each community. The network interface is used to communicate with an external terminal via a network connection. When executed by the processor, the computer program implements a method for identifying an IoT device.

[0084] Based on the above application scenarios and application environments, the following will specifically explain the technical solutions of the embodiments of the present application and how the technical solutions of the embodiments of the present application solve the above technical problems through embodiments and in conjunction with the accompanying drawings. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments.

[0085] It should be noted that the method for determining an IoT device provided in the embodiments of this application can be executed by a management terminal for managing various retirement communities, a backend server for various community applications, or an IoT device determination device, which can be implemented as part or all of a processor through software, hardware, or a combination of software and hardware. Obviously, the described embodiments are only a portion of the embodiments of this application, not all of them.

[0086] In one embodiment, Figure 2 As shown, a method for determining an IoT device is provided, which is applied to Figure 1 The computer device in the example is used to illustrate the process, including the following steps:

[0087] Step 210: Obtaining time series data of the historical environment of the target community. The time series data is the environmental data of the target community within a preset historical time period.

[0088] The target community can be any residential area. In some scenarios, the target community can also be any retirement community, which is mostly for elderly people who live at home. The community can provide corresponding retirement services for the elderly who live at home.

[0089] In one embodiment, the target community's environmental data includes geographic and cultural environmental data. Geographic environmental data includes information about the target community's climate, temperature, humidity, precipitation, and natural disasters; cultural environmental data includes information about the target community's population changes, economic conditions, and community development. Environmental data can reflect the overall development of the target community.

[0090] In one possible implementation, a historical time period is predefined. Historical environmental data for the target community is then obtained from the official website of the target community's government agency and / or other external systems, such as community management systems. Furthermore, the obtained historical environmental data is arranged by collection time based on data indicators to form time series data.

[0091] As an example, if the preset historical time period is 3 months, then with the current date as the end point, the climate data, temperature data, humidity data, precipitation data, natural disaster data, population fluctuation data, economic data, community development index, etc. of the target community in the past 3 months are obtained from the external system, and then the obtained data are sorted in chronological order to obtain the environmental data corresponding to each time point in the past 3 months of the target community.

[0092] Optionally, before executing the following step 220, the embodiment of the present application may further preprocess the acquired time series data, and the preprocessing may include at least one operation of deduplication, supplementation, screening, sorting and classification.

[0093] Step 220: Analyze the risk level of the target community based on the time series data.

[0094] It's important to note that time series data is a set of random variables ordered by time. It's typically the result of observing an underlying process at a given sampling rate over equally spaced time periods. Essentially, time series data reflects the changing trends of one or more random variables over time. The core of time series forecasting methods is to identify patterns of change in the data and use them to estimate future data.

[0095] In one possible implementation, based on time series data, the changes in the risk level of the target community in a historical time period are determined; based on the changes in the risk level of the target community, the risk level of the target community in a future time period is estimated to obtain the risk level of the target community.

[0096] The historical time period corresponds to the future time period. For example, if the preset historical time period is 3 months, the preset future time period is also 3 months, and the end point of the historical time period and the starting point of the future time period coincide with each other, which is the current time point.

[0097] In another possible implementation, environmental data of the target community in a future time period is predicted based on time series data; the environmental data of the target community in the future time period is analyzed to determine the risk level of the target community.

[0098] As an example, the correspondence between the environmental data fluctuation range and the risk level can be pre-set. Then, after predicting the environmental data of the target community in the future time period, the environmental data fluctuation range can be determined based on the fluctuation between the predicted environmental data and the historical environmental data, and the risk level corresponding to the environmental data fluctuation range can be determined as the risk level of the target community.

[0099] Step 230: Determine at least one candidate IoT device based on the service needs of the target community.

[0100] It should be understood that different IoT devices may be suitable for communities with different risk levels. Therefore, only by recommending IoT devices that are suitable for each community's actual environment can these IoT devices realize their due value and provide convenience to users within the community after installation.

[0101] Therefore, at least one candidate IoT device can be pre-determined from existing IoT devices in the market based on the target community's service needs. Service requirements include, but are not limited to, installation requirements, economic requirements, operational requirements, and lifespan requirements, which are not limited in this embodiment of the present application.

[0102] Step 240: Determine an IoT device suitable for the target community from at least one candidate IoT device based on the risk level of the target community and a preset IoT device screening strategy.

[0103] Among them, the preset IoT device screening strategy includes: the correlation between the risk level and the candidate IoT device is greater than the correlation threshold, or the corresponding relationship between the risk level and the candidate IoT device is determined.

[0104] In one possible implementation, multiple candidate IoT devices that meet community service needs can be pre-determined, and the risk level and correlation between each candidate IoT device can be determined. Once the risk level of the target community is determined, the candidate IoT devices can be screened for those suitable for the target community based on the risk level and the correlation between each candidate IoT device.

[0105] As an example, as shown in Table 1 below, in a correspondence table between risk levels and IoT devices, the correlation between each risk level and each IoT device is different. Therefore, based on the correlation between the risk level and the candidate IoT device, at least one IoT device with a correlation greater than a correlation threshold can be screened out from multiple candidate IoT devices as the IoT device corresponding to the risk level.

[0106] Table 1

[0107]

[0108] In this embodiment of the present application, the number of applicable IoT devices can also be pre-set. Assume that the number of applicable IoT devices is 2. Referring to Table 1, if the risk level of the target community is Level I, IoT device B and IoT device A are determined as IoT devices applicable to the target community. Similarly, if the risk level of the target community is Level V, IoT device C and IoT device A are determined as IoT devices applicable to the target community.

[0109] In another possible implementation, the correspondence between each risk level and candidate IoT devices can be predetermined. In this way, based on the target community's risk level and the correspondence between each risk level and candidate IoT devices, the candidate IoT devices corresponding to that risk level can be directly selected as IoT devices suitable for the target community.

[0110] Optionally, after determining the candidate IoT devices corresponding to the risk level of the target community, further screening may be performed to select at least one IoT device from the candidate IoT devices as an IoT device suitable for the target community. This embodiment of the present application does not limit this.

[0111] As an example, as shown in Table 2 below, in another correspondence table between risk levels and IoT devices, different risk levels correspond to different IoT devices. Therefore, the corresponding candidate IoT devices can be directly determined according to the risk level.

[0112] Table 2

[0113]

[0114]

[0115] Referring to Table 2, if the risk level of the target community is Level I, IoT device A and IoT device B are determined as IoT devices suitable for the target community; similarly, if the risk level of the target community is Level V, IoT device A, IoT device B, IoT device C, IoT device D, and IoT device E are determined as IoT devices suitable for the target community.

[0116] Based on the above optional implementation methods, the embodiments of the present application do not limit the number and types of IoT devices applicable to the target community. During specific deployment and installation, the applicable IoT devices can be further screened in combination with other influencing factors, and the present application does not impose any restrictions on this.

[0117] In addition, it should be noted that the method for determining IoT devices provided in the embodiments of the present application is not limited to retirement communities, but can also be used for any other community.

[0118] In the above-mentioned IoT device determination method, time series data of the target community's historical environment is obtained; the target community's risk level is analyzed based on the time series data; at least one candidate IoT device is determined based on the target community's service needs; and an IoT device suitable for the target community is determined from the at least one candidate IoT device based on the target community's risk level and a preset IoT device screening strategy. The time series data is environmental data of the target community within a preset historical time period, and the time series data is collected at equal intervals at a preset sampling rate. In this method, the risk level of the target community is determined based on future environmental changes in the target community. These future environmental changes are predicted based on analysis of real historical environmental time series data. This ensures that the predicted future environmental changes are more accurately aligned with the actual future environmental conditions, thereby ensuring the accuracy of the determined risk level of the target community. Furthermore, at least one candidate IoT device is determined based on the target community's service needs, and the determined IoT device is compatible with the target community's actual installation environment. Furthermore, based on the target community's risk level, an IoT device suitable for the target community is determined from the candidate IoT devices, ensuring that the determined IoT device accurately meets the target community's environmental anomaly monitoring needs. In this way, the determined applicable IoT devices can be recommended to the corresponding community, which can greatly improve the accuracy of IoT device recommendations; and since the IoT devices determined are suitable for the target devices, there will be no redundant idle situations, which avoids the waste of IoT device resources while also improving the resource utilization of IoT devices.

[0119] Based on the above embodiment, based on time series data, relevant algorithms can be used to process time series data to determine the risk level of the target community; or based on human experience, the risk level of the target community can be determined according to the changing characteristics of the time series data. This application does not impose any restrictions on this.

[0120] In one embodiment, the present application provides a method for analyzing the risk level of a target community, such as Figure 3 As shown, the method is the same as the execution subject in the above embodiment, and is described using a computer device as an example. The method includes the following steps:

[0121] Step 310: Input the time series data into the environmental prediction model, and output the environmental prediction data of the target community through the environmental prediction model. The environmental prediction data represents the environmental changes of the target community in a preset future time period.

[0122] The environmental prediction model can be a trained neural network model or a specific mathematical statistical model, and the embodiments of the present application do not limit this. In this step, the environmental prediction model can analyze the changing characteristics of the input time series data and analyze the environmental changes of the target community in the future time period to predict the environmental data of the target community in the future time period.

[0123] It should be noted that the time series data input into the environmental prediction model can be the acquired original data or the processed data, and the embodiments of the present application do not impose any restrictions on this.

[0124] In one embodiment, before executing the above step 310, the acquired time series data may be preprocessed, such as Figure 4 As shown in Figure 2, the preprocessing of time series data includes the following steps:

[0125] Step 410: performing a stabilization process on the time series data to obtain a stationary time series data; the stabilization process includes a difference operation and a smoothing operation;

[0126] Stationarization requires that the fitted curve derived from time series data continue to follow its existing shape "inertia" for a period of time into the future. In other words, stationarity requires that the mean, variance, and covariance of the time series data are constant, independent of time t. Only such a series can serve as a basis for predicting future data based on historical data.

[0127] Stationary series include strictly stationary and weakly stationary. Strictly stationary means that the distribution does not change over time, such as white noise. Weakly stationary means that the distribution's expectation and correlation coefficient (dependence) remain unchanged, but the value at a certain moment in the future depends on its past information. In some embodiments, as long as the low-order moments of the time series are stationary (second order), the time series data can be guaranteed to be approximately stationary.

[0128] However, most of the time series data actually obtained are weakly stationary data. Therefore, it is necessary to perform stabilization processing on the data to make it stationary.

[0129] In one possible implementation, the difference method and smoothing method (rolling mean and rolling standard deviation) are used to achieve the stabilization of time series data, so that the non-stationary time series data is converted into stationary time series data after d-order difference operation and smoothing.

[0130] It should be noted that in some cases, first-order differencing (d = 1) of time series data can achieve sequence stationarity. However, for some more complex time series data, second-order differencing (d = 2) may be required depending on the complexity. This application does not limit the order of differencing, which can be determined based on the actual data being processed.

[0131] Step 420: Perform a non-white noise test on the stationary time series data;

[0132] It should be understood that after the time series data is stabilized, the resulting stationary time series data should be white noise, without any non-white noise. Therefore, in order to verify the effectiveness of the stabilization process and to determine whether the time series data ultimately input into the environmental prediction model is a stationary series, it is necessary to perform a non-white noise test on the stationary time series data obtained in step 410 above.

[0133] As an example, the Ljung-Box test can be used to test stationary time series data for non-white noise. If the stationary time series data is a random sequence, it meets the stationary requirements. If the stationary time series data is not a random sequence, further stabilization processing is required.

[0134] Step 430: If the stationary time series data is white noise, then the step of inputting the stationary time series data into the environmental prediction model is executed.

[0135] That is, if the stationary time series data is white noise, then execute the above step 310, input the stationary time series data into the environmental prediction model, and output the environmental prediction data of the target community through the environmental prediction model.

[0136] Step 320: Determine the risk level of the target community based on the environmental prediction data.

[0137] Since environmental prediction data represents the environmental changes of the target community within a preset future time period, the development, safety and possible natural disasters of the target community can be predicted based on the environmental changes in the future time period, and the risk level of the target community can be determined based on the prediction results.

[0138] In some scenarios, if the distance between communities is within a preset distance range, or if multiple communities belong to the same geographical area, the risk level of one community can be used as the risk level of several surrounding communities to reduce the number of times the community risk level is determined.

[0139] It should be understood that different communities may have the same or different risk levels. For communities with the same risk level, the applicable IoT devices are the same.

[0140] In this way, after determining the risk levels and applicable IoT devices for a certain number of communities, for other communities, after determining the risk level of the community, the IoT devices applicable to any community with the same risk level can be used as the IoT devices applicable to that community.

[0141] For example, if the risk level of the first community is III, the applicable IoT devices include IoT device A, IoT device B, IoT device C, and IoT device D. Therefore, if the risk level of the second community is also determined to be III, the IoT devices applicable to the first community can be used as the IoT devices applicable to the second community. In other words, the IoT devices applicable to the first and second communities are the same.

[0142] In this embodiment, the acquired time series data is stabilized to obtain stationary time series data. This stationary time series data is then input into an environmental prediction model, which is then used to determine the target community's environmental prediction data. The use of the environmental prediction model not only increases data processing speed but also improves the accuracy of the target community's environmental data prediction. Furthermore, by determining the target community's risk level based on future environmental data rather than historical data, the determined risk level is more consistent with the target community's development and is more accurate.

[0143] In addition, in one embodiment, the present application also provides a modeling method for establishing the environmental prediction model in the embodiment of the present application. Figure 5 As shown, the modeling method includes the following steps:

[0144] Step 510: Obtain modeling parameters; the modeling parameters include autoregressive order, differential order and moving average order, the differential order is determined based on the number of differential operations, and the autoregressive order and moving average order are determined by a preset order determination method.

[0145] In one possible implementation, the Autoregressive Integrated Moving Average (ARIMA) model is one of the time series forecasting analysis methods. The modeling parameters of the ARIMA model are (p, d, q).

[0146] Where P is the autoregressive order, representing the number of lags of the time series data used in the ARIMA model, also known as the autoregressive (AR) term. d is the differencing order, representing the number of differencing steps required for the time series data to stabilize, also known as the integrated term. q is the moving average order, representing the number of lags of the forecast error used in the ARIMA model, also known as the moving average (MA) term.

[0147] The order of difference can be determined by the number of difference operations during the stationary process. That is, if the time series data is converted to a stationary time series after a first-order difference operation, the order of difference is 1; if the time series data is converted to a stationary time series after a second-order difference operation, the order of difference is 2.

[0148] The above-mentioned autoregressive order and moving average order are determined by a preset order determination method, and the preset order determination method includes at least one of the following order determination methods: autocorrelation function (ACF) and partial autocorrelation function (PACF), information criterion order determination, and heat map order determination.

[0149] As an example, the autocorrelation function describes the linear correlation between a time series observation and its past observations; the partial autocorrelation function describes the linear correlation between the expected past observations of a time series observation, given an intermediate observation. If the autocorrelation and partial autocorrelation functions are used to determine the order, the autoregressive order of an autoregressive process depends primarily on the order at which the autocorrelation coefficient is truncated. For example, if the autocorrelation coefficient is truncated at order 4, the autoregressive order is P = 4. The moving average order of a moving average process depends primarily on whether the partial autocorrelation coefficient decays rapidly. If not, the process is considered low-order, with a moving average order of q = 1 or q = 0.

[0150] As another example, if the information criterion is used to determine the order, the commonly used information criterion functions include the Akaike Information Criterion (AIC), the Bayesian Information Criterion (BIC) and the Hannan-Quinn Information Criterion (HQIC), and this application does not impose any restrictions on this.

[0151] Step 520: Establish an autoregressive moving average model based on the modeling parameters, and use the autoregressive moving average model as the environment prediction model.

[0152] In a possible implementation, if the order is determined using the autocorrelation function and the partial autocorrelation function, an autoregressive moving average model can be established according to the type of the autocorrelation function and the type of the partial autocorrelation function.

[0153] When the partial autocorrelation function is of the truncated type and the autocorrelation function is of the tailing type, an environmental prediction AR model is established based on the time series data, and the autoregressive moving average model is determined based on the AR model; when the partial autocorrelation function is of the tailing type and the autocorrelation function is of the truncated type, an environmental prediction MA model is established based on the time series data, and the autoregressive moving average model is determined based on the MA model; when the partial autocorrelation function is of the tailing type and the autocorrelation function is of the tailing type, an environmental prediction autoregressive moving average model is established based on the time series data.

[0154] In this embodiment, an autoregressive moving average model is pre-established and used in the embodiments of this application as an environmental prediction model. This environmental prediction model can better analyze the input time series data and accurately predict environmental changes in the target community within a preset future time period.

[0155] Based on the above embodiments, the IoT device determination method provided in this application can determine applicable IoT devices for each community. In this scenario, after determining the IoT devices applicable to each community, the IoT devices applicable to each community can also be recommended to users in the community.

[0156] Furthermore, after determining the IoT devices suitable for each community, the computer device can further accurately recommend suitable target IoT devices for each user within each community. Specifically, after executing step 230 and determining the IoT devices suitable for the target community based on the risk level of the target community, the computer device can also determine, from among the IoT devices suitable for the target community, the target IoT devices suitable for each user within the target community.

[0157] In one embodiment, Figure 6 As shown, this application also provides another method for determining an IoT device, which is applied to Figure 1 The computer device in the example is used to illustrate the process, including the following steps:

[0158] Step 610: Obtain time series data of the historical environment of the target community. The time series data is the environmental data of the target community within a preset historical time period, and the time series data is collected at equal intervals according to a preset sampling rate.

[0159] Step 620: Analyze the risk level of the target community based on the time series data.

[0160] Step 630: Determine at least one candidate IoT device based on the service needs of the target community.

[0161] Step 640: Determine an IoT device suitable for the target community from at least one candidate IoT device based on the risk level of the target community and a preset IoT device screening policy.

[0162] It should be noted that the implementation process of the above steps 610 to 640 can refer to the IoT device determination method shown in any of the above embodiments. Its implementation principle and technical effects are similar to those of the above method embodiments and will not be repeated here.

[0163] Step 650: Based on the IoT devices applicable to the target community, recommendation information of the target IoT devices is sent to the terminal devices of each user in the target community.

[0164] In a possible implementation, step 650 may be implemented by taking an IoT device applicable to the target community as the target IoT device, and sending recommendation information of the target IoT device to a terminal device of each user in the target community.

[0165] In this implementation process, the target IoT devices are IoT devices suitable for the target community. That is, after determining the IoT devices suitable for the target community, the IoT devices suitable for the target community are directly recommended to every user in the target community.

[0166] In another possible implementation, step 650 may be implemented as follows: after determining the IoT devices applicable to the target community, the IoT devices corresponding to the user types of the users in the target community are determined from the IoT devices applicable to the target community. Then, different IoT devices are recommended for different users based on their user types.

[0167] In this implementation, the target IoT devices can be all IoT devices applicable to the target community, or can be some IoT devices applicable to the target community. That is, when recommending target IoT devices to each user, they can be filtered from the IoT devices applicable to the target community.

[0168] In one embodiment, Figure 7 As shown, the implementation process of sending the target IoT device recommendation information to the terminal device of each user in the target community based on the IoT devices applicable to the target community may include the following steps:

[0169] Step 710: Obtain the user type of each user in the target community.

[0170] The user type of each user in the target community can be directly obtained from the management system of the target community, or can be determined through data generated by the user using the community application of the target community. This embodiment of the application does not limit this.

[0171] In this step, users in the target community are pre-classified into at least one type, with each type corresponding to at least one user. This allows recommendations for target IoT devices suitable for different users based on their user types.

[0172] As an example, users in the target community can be divided into the following four types:

[0173] High-value users: These users are receptive to home-based elderly care services provided by community applications, are familiar with terminal device operations, and are more likely to accept various home-based elderly care IoT devices, thus improving their quality of life.

[0174] Medium-value users: These users are willing to accept home-based elderly care services provided by community applications, but are still accustomed to paying bills and reporting repairs offline. They can accept some IoT devices for home-based elderly care, but are less willing to accept IoT devices that can replace other offline behaviors.

[0175] Potential users: Although they are interested in the online services, activities, and businesses provided by community applications, they are hesitant to use the home care functions provided by community applications due to various reasons (e.g., financial problems, health conditions, installation methods), and are also hesitant to use IoT devices that match home care.

[0176] Low-value users: These users do not like to operate terminal devices, are unwilling to use the home-based elderly care functions provided by community applications, and do not accept any IoT devices that assist in home-based elderly care.

[0177] Step 720: Determine, based on the user type, a target IoT device corresponding to each user in the target community from the IoT devices applicable to the target community.

[0178] In this step, based on the user type, all or part of the IoT devices applicable to the target community are determined as target IoT devices corresponding to users of the user type.

[0179] As an example, assume that the target community has 10 IoT devices. If user A is a high-value user, all IoT devices applicable to the target community can be recommended to user A, that is, the target IoT devices determined for user A are 10. If user B is a potential user, a small number of IoT devices applicable to the target community can be recommended to user B, for example, the target IoT devices determined for user B can be 1, 2, or 4. If user C is a low-value user, no IoT devices are recommended to him or her, that is, the target IoT devices determined for user C are 0.

[0180] Step 730: Send recommendation information of the target IoT device to the terminal device of each user in the target community.

[0181] The recommendation information at least includes the device details and usage instructions of the target IoT device, so that the user can clearly understand the specific functions of the target IoT device based on the recommendation information, and then determine whether the target IoT device needs to be installed according to their own needs.

[0182] In this embodiment, after determining the IoT devices suitable for the target community, the target IoT devices suitable for each user in the target community can be recommended based on their user type. In other words, the IoT device recommendation solution can be specific to each user, achieving personalized and precise recommendations.

[0183] Based on the above embodiment, before obtaining user types, users in the target community can be pre-categorized based on their habits in using the community application. It should be noted that the categories are not limited to the four types listed in the above embodiment, and can also be more or fewer types. The embodiment of this application is intended to illustrate the classification process and does not limit the number of user types after classification.

[0184] In one embodiment, Figure 8 As shown, the present application provides a user classification method that can be applied in the above step 710 to obtain the user type of each user in the target community. The method includes the following steps:

[0185] Step 810: Obtain user data of each user in the target community. The user data is data generated when each user uses a community application in a terminal device.

[0186] Among them, user data may include user information such as age, height, weight, medical history, preferences, etc. filled in by users when registering in the community application, and may also include behavioral trajectory data such as the services accessed, services handled, payment data, maintenance data, etc. during the use of the community application.

[0187] In a possible implementation, user data of each user in the target community may be obtained from a backend server of a community application through a user identifier (eg, user name, registration account, etc.).

[0188] Step 820: Cluster the user data to obtain multiple user data sets; each user data set corresponds to a user type.

[0189] Among them, user data can be clustered using at least one of K-means clustering, mean shift clustering, density-based spatial clustering of applications with noise (DBSCAN), maximum expectation clustering using Gaussian mixture model (GMM), agglomerative hierarchical clustering, and graph community detection (GCD).

[0190] As an example, when using K-Means clustering, first, a number of clusters are selected and the center point of each cluster is randomly initialized. The center point is a position with the same length as the vector of each data point. Then, the distance from each data point to the center point is calculated, and the data point is assigned to the cluster to which the center point is closest. Furthermore, the center point of each cluster is calculated and used as the new center point. These three steps are repeated until the center point of each cluster changes within a preset range after each iteration, thus completing the clustering. In this process, the center points can also be randomly initialized multiple times, and the final cluster center with the best performance is selected.

[0191] In this way, after clustering the user data, multiple user data sets are obtained. Each user data set includes user data of at least one user, and each data set corresponds to a type of user.

[0192] Step 830: Determine the user type of each user in the target community based on the user data set to which each user in the target community belongs.

[0193] In this step, since one user data set corresponds to one user type, the user type of each user is determined according to the user data set to which the user data of each user belongs and the correspondence between the user data set and the user type.

[0194] In this embodiment, user data generated by each user in the target community when using the community application is collected and clustered. Based on the clustering results, the users in the target community are divided into multiple user types, and the user type of each user is determined. This allows for recommendations of suitable target IoT devices for each user based on their user type, improving the efficiency of IoT device recommendations.

[0195] Furthermore, in the above embodiments, the community application mentioned in the embodiments of the present application includes a target mode, and the target mode at least includes a preset event reminder function and a preset content display interface; in the case of adding a target mode, the IoT device determination method shown in the embodiments of the present application may also include: in response to a mode switching instruction triggered by the user in the target terminal device, controlling the community application in the target terminal device to switch from the current mode to the target mode.

[0196] The target device terminal is any terminal device of any user, and can run the community application normally.

[0197] As an example, event reminders include, but are not limited to, reminders for medication and physical examinations. They can also include reminders for prolonged periods of sitting, prompting users to move around more and exercise more. The default content display interface features large fonts and simple, clear content, making it easier for home-based elderly care residents to clearly and accurately access the online services provided by the community application on their devices.

[0198] Furthermore, after the community application in the target terminal device is controlled to switch from the current mode to the target mode, if no new mode switching instruction is received, the community application in the terminal device runs and displays according to the target mode.

[0199] In this embodiment, the community application is provided with a target mode. Users can switch the community application to the target mode according to their own needs, which can meet the needs of elderly users and provide them with a better experience. In this way, the community application can provide better online services for home-based elderly people.

[0200] Additionally, in one embodiment, Figure 9 As shown, the embodiment of the present application also provides another method for determining an IoT device, which is applied to Figure 1 Taking the computer device in FIG. 1 as an example, the method includes the following steps:

[0201] Step 901: Obtain time series data of the historical environment of the target community. The time series data is the environmental data of the target community within a preset historical time period, and the time series data is collected at equal intervals according to a preset sampling rate.

[0202] Step 902: Performing a stabilization process on the time series data to obtain stationary time series data; the stabilization process includes a difference operation and a smoothing operation.

[0203] Step 903: Perform a non-white noise test on the stationary time series data.

[0204] Step 904: If the stationary time series data is white noise, the stationary time series data is input into the environmental prediction model, and the environmental prediction data of the target community is output through the environmental prediction model.

[0205] Among them, environmental prediction data represents the environmental changes of the target community within a preset future time period.

[0206] Step 905: Determine the risk level of the target community based on the environmental prediction data.

[0207] Step 906: Determine at least one candidate IoT device based on the service needs of the target community.

[0208] Step 907: Determine an IoT device suitable for the target community from at least one candidate IoT device based on the risk level of the target community and a preset IoT device screening strategy.

[0209] Step 908: Obtain the user type of each user in the target community.

[0210] Step 909: Determine, based on the user type, a target IoT device corresponding to each user in the target community from the IoT devices applicable to the target community.

[0211] Step 910: Send recommendation information of the target IoT device to the terminal device of each user in the target community.

[0212] The implementation principles and technical effects of each implementation step in the method for determining an IoT device provided in this embodiment are similar to those in the previous method embodiments and will not be repeated here.

[0213] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0214] Based on the same inventive concept, embodiments of the present application also provide an IoT device identification apparatus for implementing the IoT device identification method described above. The solution provided by this apparatus is similar to the solution described in the method described above. Therefore, the specific limitations in one or more IoT device identification apparatus embodiments provided below can be found in the limitations of the IoT device identification method described above and will not be further elaborated here.

[0215] In one embodiment, Figure 10 As shown, an IoT device determination device is provided. The device 1000 includes: a first acquisition module 1010, an analysis module 1020, a first determination module 1030, and a second determination module 1040, wherein:

[0216] The first acquisition module 1010 is used to obtain time series data of the historical environment of the target community. The time series data is the environmental data of the target community within a preset historical time period, and the time series data is collected at equal intervals according to a preset sampling rate;

[0217] An analysis module 1020 is used to analyze the risk level of the target community based on the time series data;

[0218] A first determination module 1030 is configured to determine at least one candidate IoT device based on the service needs of the target community;

[0219] The second determining module 1040 is configured to determine an IoT device applicable to the target community from at least one candidate IoT device according to the risk level of the target community and a preset IoT device screening strategy.

[0220] In one embodiment, the analysis module 1020 includes:

[0221] A prediction unit, configured to input the time series data into an environmental prediction model and output environmental prediction data of the target community through the environmental prediction model, wherein the environmental prediction data represents environmental changes of the target community within a preset future time period;

[0222] The first determination unit is used to determine the risk level of the target community based on the environmental prediction data.

[0223] In one embodiment, the apparatus 1000 further includes:

[0224] The processing module is used to perform stabilization processing on the time series data to obtain stable time series data; the stabilization processing includes difference operation and smoothing operation;

[0225] The test module is used to perform non-white noise test on stationary time series data;

[0226] The judgment module is used to execute the step of inputting the stationary time series data into the environmental prediction model if the stationary time series data is white noise.

[0227] In one embodiment, the apparatus 1000 further includes:

[0228] The second acquisition module is used to obtain modeling parameters; the modeling parameters include autoregressive order, difference order and moving average order, the difference order is determined based on the number of difference operations, and the autoregressive order and moving average order are determined by a preset order determination method;

[0229] The modeling module is used to establish an autoregressive moving average model based on modeling parameters and use the autoregressive moving average model as an environmental prediction model.

[0230] In one embodiment, the preset order determination method includes at least one of the following order determination methods: autocorrelation function and partial autocorrelation function order determination, information criterion order determination, and heat map order determination.

[0231] In one embodiment, the apparatus 1000 further includes:

[0232] The recommendation module is used to send recommendation information of target IoT devices to the terminal devices of each user in the target community based on the IoT devices applicable to the target community.

[0233] In one embodiment, the recommendation module includes:

[0234] An acquisition unit, used to acquire the user type of each user in the target community;

[0235] A second determining unit is configured to determine, based on the user type, a target IoT device corresponding to each user in the target community from IoT devices applicable to the target community;

[0236] The sending unit is used to send the recommendation information of the target Internet of Things device to the terminal device of each user in the target community.

[0237] In one embodiment, the acquiring unit includes:

[0238] The acquisition subunit is used to obtain user data of each user in the target community. The user data is the data generated when each user uses the community application in the terminal device;

[0239] A clustering subunit, configured to cluster user data to obtain multiple user data sets; each user data set corresponds to a user type;

[0240] The determination subunit is configured to determine the user type of each user in the target community according to the user data set to which each user in the target community belongs.

[0241] In one embodiment, the community application includes a target mode, which includes at least a preset event reminder function and a preset content display interface;

[0242] Then the device 1000 further includes:

[0243] The switching control module is used to control the community application in the target terminal device to switch from the current mode to the target mode in response to a mode switching instruction triggered by the user in the target terminal device.

[0244] Each module in the aforementioned IoT device identification apparatus may be implemented in whole or in part through software, hardware, or a combination thereof. Each module may be embedded in or independent of a processor in a computer device in hardware form, or may be stored in a computer device memory in software form, so that the processor can call and execute the corresponding operations of each module.

[0245] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 11 As shown. The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a method for determining an Internet of Things device is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad provided on the computer device housing, or an external keyboard, touchpad or mouse.

[0246] Those skilled in the art will understand that Figure 11 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0247] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0248] Obtaining time series data of the historical environment of the target community. The time series data is the environmental data of the target community within a preset historical time period, and the time series data is collected at equal intervals and according to a preset sampling rate;

[0249] Analyze the risk level of target communities based on time series data;

[0250] Identify at least one candidate IoT device based on the service needs of the target community;

[0251] According to the risk level of the target community and a preset IoT device screening strategy, an IoT device suitable for the target community is determined from at least one candidate IoT device.

[0252] When the computer device provided in this embodiment implements the above steps, its implementation principle and technical effects are similar to those of the above method embodiment, and will not be repeated here.

[0253] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0254] Obtaining time series data of the historical environment of the target community. The time series data is the environmental data of the target community within a preset historical time period, and the time series data is collected at equal intervals and according to a preset sampling rate;

[0255] Analyze the risk level of target communities based on time series data;

[0256] Identify at least one candidate IoT device based on the service needs of the target community;

[0257] According to the risk level of the target community and a preset IoT device screening strategy, an IoT device suitable for the target community is determined from at least one candidate IoT device.

[0258] When the computer-readable storage medium provided in this embodiment implements the above steps, its implementation principle and technical effects are similar to those of the above method embodiment, and will not be repeated here.

[0259] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0260] The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0261] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art could make various modifications and improvements without departing from the spirit of the present application, all of which fall within the scope of protection of the present application. Therefore, the scope of protection of the present patent application shall be determined by the appended claims.

Claims

1. A method for determining an Internet of Things device, characterized in that: The method comprises: Obtaining time series data of the historical environment of the target community, wherein the time series data is environmental data of the target community within a preset historical time period, and the time series data is collected at equal intervals and according to a preset sampling rate; Analyzing the risk level of the target community based on the time series data; determining at least one candidate IoT device based on the service needs of the target community; Determining an IoT device suitable for the target community from the at least one candidate IoT device according to the risk level of the target community and a preset IoT device screening strategy; According to the user type of each user in the target community, the target IoT device corresponding to each user in the target community is determined from the IoT devices applicable to the target community, and recommendation information of the target IoT device is sent to the terminal device of each user in the target community, so as to determine whether to install the target IoT device based on the recommendation information of the target IoT device.

2. The method according to claim 1, characterized in that Analyzing the risk level of the target community based on the time series data includes: Inputting the time series data into an environmental prediction model, and outputting environmental prediction data of the target community through the environmental prediction model, wherein the environmental prediction data represents environmental changes of the target community within a preset future time period; The risk level of the target community is determined based on the environmental prediction data.

3. The method according to claim 2, characterized in that Before inputting the time series data into the environmental prediction model, the method further includes: Performing a stabilization process on the time series data to obtain stable time series data; the stabilization process includes a difference operation and a smoothing operation; Performing a non-white noise test on the stationary time series data; If the stationary time series data is white noise, the step of inputting the stationary time series data into the environmental prediction model is performed.

4. The method according to claim 2 or 3, characterized in that Before inputting the time series data into the environmental prediction model, the method further includes: Obtaining modeling parameters; the modeling parameters include an autoregressive order, a difference order, and a moving average order, the difference order being determined based on the number of difference operations, and the autoregressive order and the moving average order being determined by a preset order determination method; An autoregressive moving average model is established according to the modeling parameters, and the autoregressive moving average model is used as the environmental prediction model.

5. The method according to claim 4, characterized in that The preset order determination method includes at least one of the following order determination methods: autocorrelation function and partial autocorrelation function order determination, information criterion order determination, and heat map order determination.

6. The method according to any one of claims 1 to 3, characterized in that Before determining, based on the user type of each user in the target community, the target IoT device corresponding to each user in the target community from IoT devices applicable to the target community, the method further includes: Obtain the user type of each user in the target community.

7. The method according to claim 6, characterized in that The obtaining of the user type of each user in the target community includes: Acquire user data of each user in the target community, wherein the user data is data generated when each user uses a community application on the terminal device; Clustering the user data to obtain multiple user data sets, each user data set corresponding to a user type; The user type of each user in the target community is determined according to the user data set to which each user in the target community belongs.

8. The method according to claim 7, characterized in that The community application includes a target mode, which includes at least a preset event reminder function and a preset content display interface; The method further comprises: In response to a mode switching instruction triggered by a user in a target terminal device, the community application in the target terminal device is controlled to switch from a current mode to the target mode.

9. An IoT device identification device, characterized in that: The device comprises: A first acquisition module is configured to acquire time series data of the historical environment of a target community, wherein the time series data is environmental data of the target community within a preset historical time period, and the time series data is collected at equal intervals and at a preset sampling rate; An analysis module, configured to analyze the risk level of the target community based on the time series data; A first determination module is configured to determine at least one candidate IoT device based on the service needs of the target community; a second determining module, configured to determine an IoT device applicable to the target community from the at least one candidate IoT device based on the risk level of the target community and a preset IoT device screening strategy; The recommendation module is used to determine the target IoT device corresponding to each user in the target community from the IoT devices applicable to the target community based on the user type of each user in the target community, and send recommendation information of the target IoT device to the terminal device of each user in the target community, so as to determine whether to install the target IoT device based on the recommendation information of the target IoT device.

10. The device according to claim 9, characterized in that The analysis module includes: A prediction unit, configured to input the time series data into an environmental prediction model, and output environmental prediction data of the target community through the environmental prediction model, wherein the environmental prediction data represents environmental changes of the target community within a preset future time period; The first determining unit is configured to determine a risk level of the target community according to the environmental prediction data.

11. The device according to claim 10, characterized in that The device further comprises: A processing module, configured to perform a stabilization process on the time series data to obtain stable time series data; the stabilization process includes a difference operation and a smoothing operation; A testing module, configured to perform a non-white noise test on the stationary time series data; The judgment module is used to execute the step of inputting the stationary time series data into the environmental prediction model if the stationary time series data is white noise.

12. The device according to claim 10 or 11, characterized in that The device further comprises: a second acquisition module, configured to acquire modeling parameters; the modeling parameters including an autoregressive order, a differencing order, and a moving average order, wherein the differencing order is determined based on the number of differencing operations, and the autoregressive order and the moving average order are determined by a preset order determination method; The modeling module is used to establish an autoregressive moving average model according to the modeling parameters, and use the autoregressive moving average model as the environmental prediction model.

13. The device according to claim 12, characterized in that The preset order determination method includes at least one of the following order determination methods: autocorrelation function and partial autocorrelation function order determination, information criterion order determination, and heat map order determination.

14. The device according to any one of claims 9 to 11, characterized in that The recommendation module includes: The acquiring unit is configured to acquire the user type of each user in the target community.

15. The device according to claim 14, characterized in that The acquisition unit includes: an acquisition subunit, configured to acquire user data of each user in the target community, wherein the user data is data generated when each user uses a community application on the terminal device; a clustering subunit, configured to cluster the user data to obtain a plurality of user data sets, each of which corresponds to a user type; The determination subunit is configured to determine the user type of each user in the target community according to the user data set to which each user in the target community belongs.

16. The device according to claim 15, characterized in that The community application includes a target mode, which includes at least a preset event reminder function and a preset content display interface; Then the device further comprises: The switching control module is used to control the community application in the target terminal device to switch from the current mode to the target mode in response to a mode switching instruction triggered by the user in the target terminal device.

17. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

18. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images