Smart community comprehensive service method, system, equipment and product

Abstract

The invention discloses a smart community comprehensive service method, system, device and product, and relates to the field of smart community services, and the method comprises the steps: obtaining sensor data in a current community; the sensor data in the current community comprises behavior data, equipment data and environment data of residents; performing data mining and predictive analysis on the sensor data in the current community by using a user behavior analysis model to obtain a future behavior trend; the user behavior analysis model is a deep learning network or a machine learning algorithm; analyzing the future behavior trend by using a machine learning model to obtain a resident demand; the machine learning model is a model which is obtained by training a cloud database and is deployed in an edge computing node. According to the invention, efficient operation of the system and quick response of services can be ensured, intelligent and personalized service recommendation is provided, all-around demands of residents are met, and user experience is improved.

Description

Technical Field

[0001] The present invention relates to the field of smart community services, and in particular to a smart community comprehensive service method, system, equipment and product. Background Art

[0002] With the acceleration of urbanization and the improvement of residents' living standards, community residents' demands for life services are becoming increasingly diversified, personalized and intelligent. The traditional community service model can no longer meet the needs of modern communities. There are several major problems:

[0003] 1. Single service function: Existing smart community projects are mostly focused on a specific service and are unable to provide comprehensive integrated services.

[0004] 2. Slow response: Due to the lack of effective data integration and analysis mechanisms, service response is slow and user experience is poor.

[0005] 3. Inadequate user experience: The existing platform lacks personalized recommendations and service accuracy and cannot meet the personalized needs of residents.

[0006] The existence of the above problems has caused many inconveniences to community residents in their daily lives. Therefore, a new smart community comprehensive service method is needed to solve the deficiencies in the existing technology. Summary of the invention

[0007] The purpose of the present invention is to provide a smart community comprehensive service method, system, equipment and product, which can ensure the efficient operation of the system and the rapid response of the service, while providing intelligent and personalized service recommendations to meet the all-round needs of residents and improve the user experience.

[0008] To achieve the above object, the present invention provides the following solutions:

[0009] In a first aspect, the present invention provides a smart community integrated service method, the smart community integrated service method comprising:

[0010] Acquire sensor data in the current community; the sensor data in the current community includes: resident behavior data, device data and environmental data.

[0011] The user behavior analysis model is used to perform data mining and predictive analysis on the sensor data in the current community to obtain future behavior trends; the user behavior analysis model is a deep learning network or a machine learning algorithm.

[0012] The future behavior trends are analyzed using a machine learning model to obtain residents' needs; the machine learning model is a model trained using a cloud database and deployed in an edge computing node.

[0013] Optionally, the user behavior analysis model is used to perform data mining and predictive analysis on the sensor data in the current community to obtain future behavior trends, specifically including:

[0014] The sensor data in the current community is processed to obtain processed data; the data processing includes: data cleaning, data integration and data storage.

[0015] The processed data is input into a user behavior analysis model to obtain future behavior trends.

[0016] Optionally, the process of determining the user behavior analysis model is:

[0017] The sensor data in the historical community at a number of consecutive moments are obtained; the sensor data in the historical community includes: behavior data of residents, equipment data and environmental data.

[0018] Feature extraction is performed on the sensor data in each of the historical communities to obtain features at several consecutive moments.

[0019] The features at the previous moment are used as input and the features at the next moment are used as output. The deep learning network or machine learning algorithm is trained to obtain a user behavior analysis model.

[0020] Optionally, the process of determining the machine learning model is:

[0021] The sensor data in the historical community at several consecutive moments and the residents' needs corresponding to each moment are obtained; the sensor data in the historical community includes: residents' behavior data, equipment data and environmental data.

[0022] Feature extraction is performed on the sensor data in each of the historical communities to obtain features at several consecutive moments.

[0023] Taking the characteristics at each moment as input and the residents' needs corresponding to the characteristics at each moment as output, the machine learning algorithm is trained to obtain a machine learning model.

[0024] Optionally, the smart community comprehensive service method further includes:

[0025] Information release function: The information release function is used to automatically generate and publish community announcements and event notifications based on the needs of the residents.

[0026] Optionally, the smart community comprehensive service method further includes:

[0027] Information query function: The information query function is used to provide information query function according to the needs of the residents.

[0028] Optionally, the smart community comprehensive service method further includes:

[0029] Online service function: The online service function is used to provide online services according to the needs of the residents.

[0030] In a second aspect, the present invention provides a smart community integrated service system, the smart community integrated service system comprising:

[0031] The data acquisition module is used to obtain sensor data in the current community; the sensor data in the current community includes: resident behavior data, equipment data and environmental data.

[0032] The user behavior analysis module is used to perform data mining and predictive analysis on the sensor data in the current community using a user behavior analysis model to obtain future behavior trends; the user behavior analysis model is a deep learning network or a machine learning algorithm.

[0033] The resident demand analysis module is used to analyze the future behavioral trends using a machine learning model to obtain resident needs; the machine learning model is a model trained using a cloud database and deployed in an edge computing node.

[0034] In a third aspect, the present invention provides a computer device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement any one of the smart community comprehensive service methods described above.

[0035] In a fourth aspect, the present invention provides a computer program product, including a computer program, which, when executed by a processor, implements any of the smart community comprehensive service methods described above.

[0036] According to the specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0037] The present invention provides a smart community comprehensive service method, system, device and product, which obtains sensor data in the current community, uses a user behavior analysis model to perform data mining and predictive analysis on the sensor data in the current community, obtains future behavior trends, and can provide intelligent and personalized service recommendations to improve user experience; at the same time, edge computing technology is used to ensure efficient operation of the system and rapid response of services; finally, a machine learning model is used to analyze the future behavior trends, which can meet the all-round needs of residents. Compared with the existing technology, the present invention can bring many conveniences to community residents in their daily lives. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0039] Figure 1 This is an application environment diagram of a smart community comprehensive service method in one embodiment of the present invention.

[0040] Figure 2 A flowchart of a smart community comprehensive service method provided by one embodiment of the present invention.

[0041] Figure 3 A schematic diagram of the functional modules of a smart community comprehensive service system provided in one embodiment of the present invention.

[0042] Figure 4 A schematic diagram of the workflow of a data acquisition module provided in one embodiment of the present invention.

[0043] Figure 5 A schematic diagram of the workflow of a data processing unit provided in one embodiment of the present invention.

[0044] Figure 6 A schematic diagram of the workflow of a user behavior analysis module provided in one embodiment of the present invention.

[0045] Figure 7 A schematic diagram of the workflow of an edge computing platform provided for one embodiment of the present invention.

[0046] Figure 8 A schematic diagram of the digital + smart community comprehensive service system architecture provided in one embodiment of the present invention.

[0047] Fig. 9 A schematic diagram of the structure of a computer device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0048] 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.

[0049] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and understandable, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0050] The smart community comprehensive service method provided by the embodiment of the present invention can be applied to Figure 1 In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be set up separately, integrated on the server 104, or placed on the cloud or other servers. The terminal 102 can send the acquired sensor data in the current community to the server 104. After the server 104 receives the sensor data, for the sensor data, the server 104 uses the user behavior analysis model to perform data mining and predictive analysis on the sensor data in the current community to obtain future behavior trends; the user behavior analysis model is a deep learning network or a machine learning algorithm; the machine learning model is used to analyze the future behavior trends to obtain residents' needs; the machine learning model is a model trained using a cloud database and deployed in an edge computing node. The server 104 can feedback the obtained resident needs to the terminal 102. In addition, in some embodiments, the smart community comprehensive service method can also be implemented independently by the server 104 or the terminal 102. For example, the terminal 102 can directly analyze the sensor data obtained in the current community, or the server 104 can obtain the sensor data in the current community from the data storage system and analyze the obtained sensor data in the current community.

[0051] The terminal 102 may be, but is not limited to, various desktop computers, laptop computers, smart phones, tablet computers, IoT devices, and portable wearable devices. The IoT devices may be smart speakers, smart TVs, smart air conditioners, smart vehicle-mounted devices, etc. The portable wearable devices may be smart watches, smart bracelets, head-mounted devices, etc. The server 104 may be implemented as an independent server or a server cluster consisting of multiple servers, or may be a cloud server.

[0052] In an exemplary embodiment, Figure 2 As shown, a smart community comprehensive service method is provided. The method is executed by a computer device, and can be executed by a computer device such as a terminal or a server alone, or by a terminal and a server together. In an embodiment of the present invention, the method is applied to Figure 1 The server 104 in the example is used as an example to illustrate the method, which includes the following steps S1 to S3. Among them:

[0053] S1: Acquire sensor data in the current community; the sensor data in the current community includes: resident behavior data, device data and environmental data.

[0054] S2: Use a user behavior analysis model to perform data mining and predictive analysis on the sensor data in the current community to obtain future behavior trends; the user behavior analysis model is a deep learning network or a machine learning algorithm.

[0055] S3: Use a machine learning model to analyze the future behavioral trends and obtain residents' needs; the machine learning model is a model trained using a cloud database and deployed in an edge computing node.

[0056] The implementation of the above steps S1 to S3 can ensure the efficient operation of the system and the rapid response of services, while providing intelligent and personalized service recommendations to meet the all-round needs of residents and enhance user experience.

[0057] In another exemplary embodiment of the present invention, in step S1, the behavior data, device data and environmental data of residents in the community are collected using IoT devices and sensors.

[0058] IoT devices include:

[0059] 1. Environmental sensors: temperature sensor, humidity sensor, light sensor, sound sensor, air quality sensor (PM2.5).

[0060] 2. Position sensor: GPS module (Global Positioning System), RFID tag (Radio Frequency Identification).

[0061] 3. Image and video sensors: cameras and surveillance equipment, image sensors (used for image recognition and analysis).

[0062] 4. Power sensors: current sensor, voltage sensor, power sensor.

[0063] 5. Biosensors: heart rate sensor, blood pressure sensor, blood sugar sensor.

[0064] 6. Motion sensors: accelerometer, gyroscope, magnetometer (for direction and position detection).

[0065] Combined with the sensors mentioned above, the collected data can be broken down into the following categories:

[0066] 1. Residents’ behavioral data:

[0067] (1) Activity participation:

[0068] The amount and type of residents' activities (e.g., walking, running, cycling, etc.) are recorded through motion sensors (e.g., accelerometers, gyroscope sensors).

[0069] Track residents’ activity paths within the community and the frequency of their participation in community activities through location sensors (such as GPS modules and RFID tags).

[0070] (2) Shopping behavior:

[0071] Understand residents’ shopping locations and frequency through location sensors (such as GPS modules) and social sensors (such as shopping app records).

[0072] Analyze residents' purchasing behavior and commodity types through payment system data (such as credit card and mobile payment records).

[0073] 2. Equipment data:

[0074] (1) Payment records:

[0075] Residents’ energy consumption and payment are recorded through smart electricity meters, water meters, gas meters, etc. These devices usually have built-in current sensors, voltage sensors, and flow sensors for accurate measurement.

[0076] Residents’ payment time and amount are recorded through an online payment system (such as a smart payment terminal).

[0077] 3. Environmental data:

[0078] Temperature: Collect indoor and outdoor temperature data through temperature sensors.

[0079] Humidity: The humidity level in the air is measured by a humidity sensor.

[0080] Light intensity: Light sensors are used to record the light intensity in the environment and analyze the use of natural light and artificial lighting.

[0081] Air quality: Air quality sensors (such as PM2.5 sensors and carbon dioxide sensors) are used to detect the concentration of particles and gases in the air.

[0082] Noise Level: Use sound sensors to record the noise level in the environment and understand the noise pollution.

[0083] Gas concentration: Monitor the concentration of different gases in the air through gas sensors (such as carbon monoxide sensors, carbon dioxide sensors).

[0084] Through the data collected by the above sensors and devices, the community can fully understand the residents' behavioral habits, equipment usage and environmental quality, so as to make more accurate and scientific management decisions.

[0085] In another exemplary embodiment of the present invention, in step S2, specifically including:

[0086] S21: Processing the sensor data in the current community to obtain processed data; the data processing includes: data cleaning, data integration and data storage;

[0087] S22: Input the processed data into a user behavior analysis model to obtain future behavior trends.

[0088] The collected data is cleaned, integrated and stored, and user behavior analysis technology is used for mining and prediction.

[0089] 1. Data cleaning:

[0090] Data deduplication: Remove duplicate data records.

[0091] Missing value handling: Fill in or remove missing data points. For example, you can use the mean, median, or interpolation to fill in missing values.

[0092] Outlier detection and processing: Identify and process outliers, which may be caused by sensor failure or data entry errors.

[0093] Data standardization and normalization: Convert data to the same scale to facilitate subsequent analysis and modeling.

[0094] 2. Data Integration:

[0095] Data merging: Merge data from different sensors and devices into a unified data table.

[0096] Time synchronization: Ensure that the timestamps of all data points are aligned to facilitate time series analysis.

[0097] Data association: Associating different types of data based on specific rules (such as time window, geographic location, etc.).

[0098] 3. Data storage:

[0099] Database management system: Use a relational database (such as MySQL, PostgreSQL) or a NoSQL database (such as MongoDB, Cassandra) to store cleaned and integrated data.

[0100] Data warehouse: Build a data warehouse (using Alibaba Cloud services to save costs and facilitate subsequent operation and maintenance) to facilitate large-scale data analysis.

[0101] Data backup and recovery: Back up data regularly to ensure data security and recoverability.

[0102] Among them, data storage includes: edge computing nodes and cloud databases.

[0103] The relationship between edge computing and cloud computing is a cooperative relationship. Since edge computing devices have very small computing power and storage, they are only suitable for processing some simple algorithms with low resource consumption, so as to respond to user needs and improve user experience in a more real-time manner. More complex and large calculations are calculated on cloud servers.

[0104] The relationship between edge computing nodes, cloud databases, and machine learning algorithms is as follows:

[0105] (1) Edge computing nodes:

[0106] Function:

[0107] Data collection: Collecting behavioral data of residents.

[0108] Preprocessing: cleaning and preliminary analysis of data.

[0109] Real-time prediction: Run pre-trained machine learning models for real-time analysis.

[0110] Advantages: fast response, reduced latency, and improved data security.

[0111] (2) Cloud database:

[0112] Function:

[0113] Data storage: Storing and managing large-scale data.

[0114] Data integration: Merge data from different edge nodes.

[0115] Model training: Use large-scale data to train machine learning models.

[0116] Advantages: Powerful computing power, capable of handling complex analysis tasks.

[0117] (3) Machine Learning Algorithms:

[0118] Function:

[0119] Model training: Train models with large-scale data in cloud databases.

[0120] Model deployment: Deploy the model to edge computing nodes.

[0121] Prediction and optimization: Predict residents’ needs and optimize service recommendations.

[0122] Advantages: Improve prediction accuracy and provide personalized services.

[0123] (4) The workflow is as follows:

[0124] a. Data collection and preprocessing: Edge computing nodes collect and clean data.

[0125] b. Data transmission and integration: Upload the pre-processed data to the cloud database for integration.

[0126] c. Model training and deployment: The cloud database trains the model and deploys it to the edge computing node.

[0127] d. Real-time prediction and optimization: Edge computing nodes use models to make real-time predictions and optimize services.

[0128] (5) The advantages are as follows:

[0129] Real-time: Edge computing nodes respond quickly and reduce latency.

[0130] Security: Process sensitive data locally to improve security.

[0131] Efficiency: Cloud databases handle complex tasks, making the overall system more efficient.

[0132] 4. User behavior analysis technology:

[0133] Data Mining: Use data mining techniques to extract useful information and patterns from data.

[0134] Cluster analysis: such as K-means clustering, used to discover group patterns of user behavior.

[0135] Association rule analysis: such as the Apriori algorithm, which is used to discover association rules between user behaviors (such as shopping basket analysis).

[0136] Frequent pattern mining: Identifying patterns that occur frequently in user behavior.

[0137] Predictive analytics include:

[0138] Time series analysis: such as ARIMA and LSTM, used to predict future user behavior trends (such as electricity consumption and shopping frequency).

[0139] Regression analysis: such as linear regression and decision tree regression, used to predict numerical results (such as consumption amount).

[0140] Classification analysis: such as logistic regression, random forest, and SVM, used to predict classification results (such as whether to participate in an activity).

[0141] Deep learning: such as convolutional neural networks (CNN) and recurrent neural networks (RNN), which are used for complex pattern recognition and prediction.

[0142] 5. Specific mining and prediction steps:

[0143] Feature engineering: extract useful features from raw data, such as statistical features (mean, variance), time features (time period, season), etc.

[0144] Model training: Use the training dataset to train the selected machine learning or deep learning model and adjust the model parameters to optimize performance.

[0145] Model evaluation: Use the validation data set to evaluate the prediction accuracy and generalization ability of the model. Common indicators include accuracy, precision, recall, F1 value, mean square error, etc.

[0146] Model deployment: Deploy the trained model to the production environment to process and predict user behavior in real time.

[0147] Continuous optimization: Regularly retrain the model and update feature engineering methods to ensure that the model remains efficient in new data environments.

[0148] Through the above steps, community managers can deeply understand the behavioral patterns of residents, predict future behavioral trends, and then formulate more scientific and humane management strategies.

[0149] In another exemplary embodiment of the present invention, the process of determining the user behavior analysis model is as follows:

[0150] A1: Acquire sensor data in a historical community at a number of consecutive moments; the sensor data in the historical community includes: behavior data of residents, equipment data, and environmental data.

[0151] A2: Extract features from the sensor data in each of the historical communities to obtain features at several consecutive moments.

[0152] A3: Use the features of the previous moment as input and the features of the next moment as output to train the deep learning network or machine learning algorithm to obtain a user behavior analysis model.

[0153] In another exemplary embodiment of the present invention, the process of determining the machine learning model is:

[0154] B1: Obtain sensor data in a historical community at several consecutive moments and the residents' needs corresponding to each moment; the sensor data in the historical community includes: residents' behavior data, equipment data and environmental data.

[0155] B2: Extract features from the sensor data in each of the historical communities to obtain features at several consecutive moments.

[0156] B3: Take the characteristics at each moment as input and the residents’ needs corresponding to the characteristics at each moment as output, train the machine learning algorithm and obtain a machine learning model.

[0157] Use machine learning algorithms to analyze residents’ behavioral data, predict residents’ needs, and optimize service recommendations.

[0158] 1. Specific analysis steps:

[0159] 1. Data collection and preprocessing:

[0160] Collect data: Collect data from IoT devices and sensors, including activity participation, shopping behavior, payment records, environmental data, etc.

[0161] Data cleaning: handle missing values, outliers, duplicate data, and standardize data.

[0162] Feature engineering: extracting and creating useful features, such as statistical features, time features, behavioral pattern features, etc.

[0163] 2. Feature selection and extraction:

[0164] Feature selection: Select highly relevant features to reduce dimensionality, such as using correlation analysis, principal component analysis (PCA), etc.

[0165] Feature extraction: Extract new features from raw data, such as user behavior frequency, shopping basket analysis, etc.

[0166] 3. Build a machine learning model:

[0167] Choose an algorithm: Choose an appropriate machine learning algorithm based on the problem type, such as linear regression, decision tree, random forest, support vector machine (SVM), neural network, etc.

[0168] Define inputs and outputs: Define the inputs and outputs of the model based on the prediction target.

[0169] 4. Model training and evaluation:

[0170] Data splitting: Divide the data into training set, validation set and test set.

[0171] Model training: Train the model using the training set and tune the hyperparameters through cross-validation.

[0172] Model evaluation: Use the validation set to evaluate the model performance and select appropriate evaluation indicators, such as accuracy, precision, recall, mean square error, etc.

[0173] 2. Specific Analysis and Prediction Process

[0174] 1. Take residents’ demand forecast as an example:

[0175] Input: Residents’ historical behavior data, such as past shopping records, activity participation, payment records, environmental data, etc.

[0176] Output: Forecasted resident needs, such as services or goods that may be needed in the future (shopping lists, activity suggestions, etc.).

[0177] 2. Algorithm example:

[0178] Linear Regression:

[0179] Input: Feature vector of historical behavior data.

[0180] Output: predicted numerical demand, such as the amount of consumption in the future.

[0181] Loss function: Mean Squared Error (MSE).

[0182] Classification algorithm (SVM):

[0183] Input: Feature vector of historical behavior data.

[0184] Output: Predicted classification results, such as whether a resident will attend an event.

[0185] Loss function: Cross entropy loss (for classification problems).

[0186] Time Series Analysis (LSTM Neural Network):

[0187] Input: Historical behavior data in the form of time series.

[0188] Output: Demand forecast for a period of time in the future.

[0189] Loss function: Mean squared error (MSE) or root mean square error (RMSE).

[0190] 3. Optimize service recommendations

[0191] 1. Data preprocessing: clean and integrate residents’ historical behavior data and extract useful features.

[0192] 2. Build a recommendation system:

[0193] Collaborative filtering: recommending services or products based on the behavioral similarities of residents.

[0194] Content recommendation: Recommend relevant services or products based on residents’ historical behaviors and characteristics.

[0195] 3. Training and evaluation:

[0196] Train recommendation model: Use training data to train the recommendation system.

[0197] Evaluate recommendation results: Use the validation set to evaluate the accuracy and satisfaction of recommendations. Common indicators include accuracy, recall, F1 value, etc.

[0198] 4. Continuous optimization: Continuously update and optimize the recommendation system based on resident feedback and new data.

[0199] 4. Practical application process

[0200] 1. Data preparation:

[0201] Collect and clean residents’ behavioral data.

[0202] Extract and select features.

[0203] 2. Model training:

[0204] Train the selected model using the training data.

[0205] Tune hyperparameters to optimize model performance.

[0206] 3. Model evaluation:

[0207] The prediction accuracy of the model was evaluated using the validation set.

[0208] Select the best performing model for deployment.

[0209] 4. Prediction and recommendation:

[0210] Use the trained model to make predictions on new data.

[0211] Generate personalized service or product recommendations based on the prediction results.

[0212] Through the above steps, communities can use machine learning technology to accurately predict residents’ needs, provide personalized service recommendations, and improve residents’ satisfaction and community management efficiency.

[0213] In another exemplary embodiment of the present invention, the smart community comprehensive service method further includes:

[0214] Information release function: The information release function is used to automatically generate and publish community announcements and event notifications based on the needs of the residents.

[0215] In another exemplary embodiment of the present invention, the smart community comprehensive service method further includes:

[0216] Information query function: The information query function is used to provide information query function according to the needs of the residents, allowing residents to query community information, policies and regulations, service guidelines and other content through mobile applications or web pages.

[0217] In another exemplary embodiment of the present invention, the smart community comprehensive service method further includes:

[0218] Online service function: The online service function is used to provide online services according to the needs of the residents.

[0219] Among them, online service functions include:

[0220] The online shopping module supports residents in group purchasing of fresh food, shopping of daily necessities, etc.

[0221] The online payment module supports residents in paying for living expenses such as water, electricity, gas, and property fees.

[0222] The community activity module publishes information about community cultural activities and supports residents to register online.

[0223] The cultural reading module provides resources such as e-books, newspapers and magazines.

[0224] The smart community comprehensive service method of the present invention has the following beneficial effects:

[0225] 1. Timeliness and accuracy of information release and query: Ensure timely release and accurate query of information through real-time data collection and analysis.

[0226] 2. Diversity and comprehensiveness of service functions: The system provides comprehensive community services, including online shopping, payment, event registration, cultural reading, etc., to meet the all-round needs of residents.

[0227] 3. Intelligent and personalized services: Through user behavior analysis and machine learning algorithms, we provide intelligent and personalized service recommendations to enhance user experience.

[0228] 4. Efficiency of data processing and service response: Use edge computing technology to ensure efficient operation of the system and rapid response of services.

[0229] The present invention also provides an application scenario, which applies the above-mentioned smart community comprehensive service method. Specifically: The smart community comprehensive service method provided in this embodiment can be applied in the smart community comprehensive service scenario. The smart community comprehensive service scenario includes a data acquisition link, a data analysis link, and a demand prediction link; the acquired data enters the data analysis link, and through data mining and predictive analysis of the user behavior analysis model, the future behavior trend is obtained, and then enters the demand prediction link, and after analysis by the machine learning model, the residents' needs are obtained.

[0230] Based on the same inventive concept, the embodiment of the present invention also provides a smart community integrated service system for implementing the smart community integrated service method involved above. The implementation scheme for solving the problem provided by the system is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more smart community integrated service system embodiments provided below can refer to the limitations of the smart community integrated service method above, and will not be repeated here.

[0231] In an exemplary embodiment, Figure 3 As shown, a smart community comprehensive service system is provided, including:

[0232] The data acquisition module M1 is used to obtain sensor data in the current community; the sensor data in the current community includes: resident behavior data, equipment data and environmental data.

[0233] The workflow of the data acquisition module is as follows: Figure 4 As shown, with the development of cities, the population size of residential areas has expanded, and the traditional information collection management system has problems such as traditional information collection methods, backward equipment, incomplete types, cumbersome operations, low quality of collected data, scattered equipment, and decentralized platforms. In response to the above problems, the present invention proposes an intelligent collection method that integrates collection equipment and auxiliary equipment to complete the standardization of data collection. The data collection module mainly includes: resident information, face recognition access control, license plate recognition, smart cameras, smart express cabinets, charging piles, identity elevator control (controlling elevators through identity authentication methods such as swiping cards), online shopping malls, community group purchases, catering service industry settlement, and property work orders.

[0234] (1) Terminal devices refer to various terminal IoT devices, such as cameras, access control cards, etc.

[0235] (2) Storage devices refer to small storage devices that are paired with terminal devices and are used to cache small amounts of data collected by the terminal. When enough data is accumulated (configurable), it is compressed and uploaded to the big data platform. The big data platform can also actively send data reporting commands to the storage device as needed. At this time, the storage device needs to upload all the cached data even if it has not accumulated enough data.

[0236] (3) Big Data Platform: It is a control management platform and data forwarder used to configure various commands and rules. When receiving data reported by the terminal, it forwards the data packet to the data processing unit for standardized processing.

[0237] (4) The data processing unit is a data processing, cleaning, and verification device that processes the data forwarded by the big data platform in a standardized manner according to the configured rules and algorithms. After the processing is completed, the data is uploaded to the data warehouse for storage. Figure 5 shown.

[0238] (5) Data warehouse: stores all data.

[0239] The user behavior analysis module M2 is used to perform data mining and predictive analysis on the sensor data in the current community using a user behavior analysis model to obtain future behavior trends; the user behavior analysis model is a deep learning network or a machine learning algorithm.

[0240] The workflow of the user behavior analysis module is as follows: Figure 6 As shown, by mining, analyzing and processing user behaviors, the community service platform is connected with community user terminals to form a closed loop of smart community services.

[0241] The resident demand analysis module M3 is used to analyze the future behavior trends using a machine learning model to obtain resident needs; the machine learning model is a model trained using a cloud database and deployed in an edge computing node.

[0242] In addition, the smart community comprehensive service system also includes:

[0243] Edge computing platform:

[0244] Deploy edge computing nodes within the community to provide real-time data processing and analysis, reduce cloud computing pressure, and improve system response speed.

[0245] Use edge computing technology to achieve local data processing and instant response.

[0246] The workflow of the edge computing platform is as follows: Figure 7 As shown in the figure, edge nodes have computing, network, and storage resources. The edge computing platform uses resources in two ways:

[0247] (1) Computing, network, and storage resources are directly encapsulated to provide a calling interface. The edge manager uses edge node resources through code download, network policy configuration, and database management.

[0248] (2) The resources of edge nodes are encapsulated into functional modules according to functional fields. The edge manager combines and calls functional modules through model-driven business orchestration to achieve integrated development and agile deployment of edge computing services.

[0249] like Figure 7 As shown in the figure, the commonly used industrial control protocol parsing module is composed of a set of dedicated hardware, firmware, device drivers and API interfaces. It provides protocol, interface conversion and gateway functions for edge devices.

[0250] Edge management module: It is an edge device controller that provides resource scheduling, system launch, configuration, software / firmware updates, application management, business orchestration, execution strategies, and other system lifecycle management capabilities for edge node devices.

[0251] Policy execution module: responsible for translating policies into device commands and scheduling execution locally. It supports both pushing policies from the controller and actively requesting policies from the controller. Policies can focus only on high-level business needs without fine-grained control of edge nodes, thereby ensuring the autonomy of edge computing nodes and the real-time nature of event response processing. At the same time, it allows direct operation or calling of corresponding resources through code management, network configuration, database operations, etc. to complete corresponding management tasks. Code management includes operations such as storage, update, retrieval, addition, deletion, and version control of functional modules or codes.

[0252] Database: A small cache database at the edge, used to cache data collected by edge devices.

[0253] Data processing module: includes data preprocessing (filtering, clarifying, aggregating, quality optimization and semantic analysis of collected data), data distribution and policy execution (based on predefined rules and data processing results, execute policies locally and forward data to the cloud or other edge nodes for processing).

[0254] As an optional implementation, the smart community comprehensive service system also includes: a service interface module and a user interaction module.

[0255] Among them, the service interface module: provides processed data to various application modules through the API interface. Supports multiple terminal devices (such as mobile phones and computers) to access system services.

[0256] User interaction module: Provides mobile applications and web pages, through which residents can search for information, shop online, pay bills online, sign up for community activities, read cultural books, etc. Provides personalized services and information recommendations based on the user's historical behavior and preferences.

[0257] In an exemplary embodiment, the digital + smart community integrated service system architecture diagram is as follows Figure 8 shown.

[0258] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Fig. 9As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, 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, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store sensor data in the community. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a smart community comprehensive service method is implemented.

[0259] Those skilled in the art will understand that Fig. 9 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present invention, and does not constitute a limitation on the computer device to which the solution of the present invention is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0260] In an exemplary embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the above-mentioned method embodiments are implemented when the processor executes the computer program.

[0261] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the above-mentioned method embodiments are implemented.

[0262] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the above-mentioned method embodiments are implemented.

[0263] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in the present invention are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0264] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be completed 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 the memory, database or other medium used in the embodiments provided by the present invention can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0265] The database involved in each embodiment provided by the present invention may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided by the present invention may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0266] The technical features of the above embodiments may be combined arbitrarily. 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.

[0267] The principles and implementation methods of the present invention are described in this article using specific examples. The description of the above embodiments is only used to help understand the method and core idea of ​​the present invention. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A smart community comprehensive service method, characterized in that: The smart community comprehensive service method comprises: Acquire sensor data in the current community; the sensor data in the current community includes: resident behavior data, device data and environmental data; Using a user behavior analysis model to perform data mining and predictive analysis on sensor data in the current community to obtain future behavior trends; the user behavior analysis model is a deep learning network or a machine learning algorithm; The future behavior trends are analyzed using a machine learning model to obtain residents' needs; the machine learning model is a model trained using a cloud database and deployed in an edge computing node.

2. The smart community comprehensive service method according to claim 1, characterized in that: The user behavior analysis model is used to perform data mining and predictive analysis on the sensor data in the current community to obtain future behavior trends, including: Processing the sensor data in the current community to obtain processed data; the data processing includes: data cleaning, data integration and data storage; The processed data is input into a user behavior analysis model to obtain future behavior trends.

3. The smart community comprehensive service method according to claim 1, characterized in that: The determination process of the user behavior analysis model is as follows: Obtain sensor data within a historical community at several consecutive moments; The sensor data in the historical community includes: behavior data, equipment data and environmental data of residents; Extracting features from sensor data in each of the historical communities to obtain features at a number of consecutive moments; The features at the previous moment are used as input and the features at the next moment are used as output. The deep learning network or machine learning algorithm is trained to obtain a user behavior analysis model.

4. The smart community comprehensive service method according to claim 1, characterized in that: The determination process of the machine learning model is: Acquire sensor data in a historical community at a number of consecutive moments and residents' needs corresponding to each moment; the sensor data in the historical community includes: residents' behavior data, equipment data and environmental data; Extracting features from sensor data in each of the historical communities to obtain features at a number of consecutive moments; Taking the characteristics at each moment as input and the residents' needs corresponding to the characteristics at each moment as output, the machine learning algorithm is trained to obtain a machine learning model.

5. The smart community comprehensive service method according to claim 1, characterized in that: The smart community comprehensive service method also includes: Information release function: The information release function is used to automatically generate and publish community announcements and event notifications based on the needs of the residents.

6. The smart community comprehensive service method according to claim 5, characterized in that: The smart community comprehensive service method also includes: Information query function: The information query function is used to provide information query function according to the needs of the residents.

7. The smart community comprehensive service method according to claim 6, characterized in that: The smart community comprehensive service method also includes: Online service function: The online service function is used to provide online services according to the needs of the residents.

8. A smart community comprehensive service system, characterized in that: The smart community comprehensive service system includes: A data acquisition module is used to obtain sensor data in the current community; the sensor data in the current community includes: resident behavior data, equipment data and environmental data; A user behavior analysis module, which is used to perform data mining and predictive analysis on the sensor data in the current community using a user behavior analysis model to obtain future behavior trends; the user behavior analysis model is a deep learning network or a machine learning algorithm; The resident demand analysis module is used to analyze the future behavioral trends using a machine learning model to obtain resident needs; the machine learning model is a model trained using a cloud database and deployed in an edge computing node.

9. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the smart community comprehensive service method described in any one of claims 1 to 7.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, it implements the smart community comprehensive service method described in any one of claims 1-7.

Images