Intelligent property multi-source data fusion and collaborative management method and system

Abstract

This invention discloses a method and system for multi-source data fusion and collaborative management in smart property management. The method includes: constructing a trusted data space infrastructure comprising identity management, usage right control, and auditing modules; reliably accessing heterogeneous data from multiple sources within the property, such as security, energy, equipment, and customer service, into the data space through standardized connectors and performing standardized descriptions; performing fusion analysis and processing of authorized data in a secure computing environment based on predefined data usage contracts; and automatically matching and triggering cross-system collaborative management instructions by a collaborative strategy engine based on the fusion analysis results, achieving intelligent event linkage and business closed-loop. By combining trusted data space technology with smart property management business, and under the premise of ensuring data sovereignty and security, this invention breaks down data silos, achieves trusted fusion and intelligent collaborative management of multi-source data, and significantly improves property management efficiency and service levels.

Description

Technical Field

[0001] This invention relates to the field of smart city management platform technology, and in particular to a method and system for multi-source data fusion and collaborative management of smart properties. Background Technology

[0002] With the development of IoT, big data, and AI technologies, smart property management systems have been widely applied in modern building and community management. These systems typically integrate multiple independent subsystems such as security monitoring, access control, energy metering, equipment operation and maintenance, parking management, and customer service work orders, generating massive amounts of heterogeneous multi-source data.

[0003] However, current smart property management systems face serious challenges at the data level: The problem of data silos is serious: each subsystem is built by different vendors, with different data formats, standards, and storage methods, and lacks an effective interconnection mechanism, which prevents the full release of data value.

[0004] High risks of data security and privacy breaches: Property data contains a large amount of sensitive data such as owners' personal information, behavioral patterns, and property information. Under the traditional centralized data pool fusion model, there are risks of unclear sovereignty, uncontrolled access, and vulnerability to attacks and leaks after data aggregation.

[0005] Low efficiency of collaborative management: Due to the inability to effectively integrate data, cross-system event linkage (such as fire alarm linkage with video, access control and elevator control) is mostly hard-coded or simply triggered, making it difficult to achieve proactive and predictive collaborative management based on intelligent analysis of global data.

[0006] Trusted data sharing is difficult to achieve: multiple stakeholders, such as property management companies, owners, merchants, and government regulatory departments (such as street offices and fire departments), need to collaborate on data, but lack a mutually trusting, controllable, and auditable data exchange environment.

[0007] In recent years, the concept of a trusted data space has emerged as an new data exchange and collaboration infrastructure. Based on a distributed architecture, it ensures data flow under the premise of being "usable but invisible, controllable and measurable" through standardized connectors, identity authentication, access control, and audit logs. However, a mature and systematic solution is currently lacking for how to deeply integrate this architecture with specific smart property scenarios and design a complete approach from data access and fusion processing to collaborative applications.

[0008] Therefore, there is an urgent need for a method that can break down data silos, safeguard data sovereignty and security, and improve the efficiency of cross-business collaborative management of properties. Summary of the Invention

[0009] To address the challenges of multi-source data fusion, high security risks, and unintelligent collaborative management in existing smart property management systems, this invention provides a method and system for multi-source data fusion and collaborative management in smart property management. This method, while ensuring the data sovereignty and security of all participating parties, enables the reliable fusion and intelligent collaborative application of property data, thereby improving property management efficiency, service levels, and emergency response capabilities.

[0010] According to one aspect of this disclosure, a method for multi-source data fusion and collaborative management of smart properties is provided, the method comprising: Step 1: Build and initialize the trusted data space infrastructure; Step 2: Trusted access and standardized description of multi-source data; Step 3: Secure integration and analysis processing based on data usage rights; Step 4: Trigger cross-system collaborative management strategies and responses; Step 5: Full-process audit and continuous optimization.

[0011] In one possible implementation, the trusted data space infrastructure is constructed and initialized, including: Deploy core components of a trusted data space, including identity and access management, a data usage rights control engine, and a global audit module, on the property cloud platform or edge nodes, and configure standardized data connectors for various data source systems within the property and external stakeholders. The data connector supports multiple network and data protocols and has functions such as encrypted data transmission, format conversion, and edge preprocessing.

[0012] In one possible implementation, trusted access to and standardized description of multi-source data are as follows: Through the data connector, heterogeneous data from security, access control, equipment maintenance, energy metering, and customer service work order subsystems are connected to the trusted data space in real time or on a timed basis, and metadata descriptions and data source identity identifiers based on a unified model are added to the connected data.

[0013] In one possible implementation, secure fusion and analysis processing based on data usage rights includes: The data consumer initiates a request to the data usage right control engine according to the predefined data usage contract; after the engine verifies the authorization, it allows the consumer to perform fusion calculation and analysis on encrypted or de-identified data from multiple authorized data sources in a specified secure computing environment, outputting results or models, and the original data does not leave the provider's control domain.

[0014] In one possible implementation, triggering cross-system collaborative management strategies and responses includes: Based on the fusion analysis results output in step three, the collaborative management strategy engine matches predefined business rules to generate and automatically execute a cross-subsystem collaborative instruction set, thereby achieving intelligent event linkage and business closure.

[0015] One possible implementation involves end-to-end auditing and continuous optimization. The global audit module records the entire operation log from data access, authorization, fusion computing to policy triggering, forming a traceable and tamper-proof audit record, and continuously optimizes the data fusion model and collaboration strategy based on feedback.

[0016] In one possible implementation, in step three, the secure computing environment includes a secure sandbox, a trusted execution environment, or a federated learning node, supporting multiple integrated computing modes: secure multi-party computation, data association under privacy protection, and federated learning.

[0017] In one possible implementation, in step four, the collaborative management strategy supports graphical low-code orchestration, allowing users to customize "event-condition-action" rules according to actual business scenarios to trigger automated linkage operations across access control, video, broadcast, and work order subsystems.

[0018] In one possible implementation, in step five, the global audit module uses blockchain or distributed ledger technology to store key operation logs as evidence, and uses machine learning methods to iteratively optimize the data fusion algorithm and collaboration strategy based on audit data and business feedback.

[0019] A smart property multi-source data fusion and collaborative management system, wherein the system applies the method described herein, and the system comprises: The spatial infrastructure establishment module is used to build and initialize a trusted data spatial infrastructure. The data access and standardization module is used for trusted access and standardized description of multi-source data. The security fusion and analysis module is used for security fusion and analysis based on data usage rights. The instruction generation module is used to trigger cross-system collaborative management strategies and responses. The audit and optimization module is used for end-to-end auditing and continuous optimization.

[0020] Compared with the prior art, the beneficial effects of the present invention are: (1) Data sovereignty and security controllability: Based on the trusted data space architecture, the separation of data "ownership" and "right of use" is realized. Each subsystem retains data sovereignty and opens up data value only under strict authorization and security environment, which fundamentally reduces the risk of privacy leakage and abuse.

[0021] (2) Efficiently break down data silos: Through standardized connectors and unified data models, low-cost and rapid access and semantic interoperability of heterogeneous multi-source data are achieved, laying the foundation for deep data fusion.

[0022] (3) Achieve intelligent collaborative management: Through secure data fusion and analysis, drive intelligent linkage and proactive services across subsystems, upgrade property management from "single point response" to "global intelligent collaboration", and significantly improve event handling efficiency and user experience.

[0023] (4) Building a trustworthy collaborative ecosystem: It provides a safe and trustworthy data value exchange platform for property companies, owners, merchants and third-party service providers, which helps to generate new value-added services (such as energy-saving suggestions based on anonymous group behavior, and precise convenience services in cooperation with retailers). Attached Figure Description

[0024] Figure 1 This is the overall architecture and flowchart of the method of the present invention.

[0025] Figure 2 This is a schematic diagram illustrating the integration of data usage rights control and security within the trusted data space in this invention.

[0026] Figure 3 This is a flowchart of a specific embodiment of the present invention based on multi-service collaboration triggered by fusion events (taking emergency fire linkage as an example). Detailed Implementation

[0027] Various exemplary embodiments, features, and aspects of this disclosure will now be described in detail with reference to the accompanying drawings. The same reference numerals in the drawings denote elements that have the same or similar functions. Although various aspects of the embodiments are shown in the drawings, they are not necessarily drawn to scale unless specifically indicated otherwise.

[0028] The term “exemplary” as used herein means “serving as an example, embodiment, or illustration.” Any embodiment illustrated herein as “exemplary” is not necessarily to be construed as superior to or better than other embodiments.

[0029] Furthermore, to better illustrate this disclosure, numerous specific details are set forth in the following detailed description. Those skilled in the art will understand that this disclosure can be practiced without certain specific details. In some instances, methods, means, components, and circuits well known to those skilled in the art have not been described in detail in order to highlight the main points of this disclosure.

[0030] A method for multi-source data fusion and collaborative management of smart properties includes the following steps: Step S1: Construct a trusted data space infrastructure for smart property management.

[0031] Deploy core components of the trusted data space on the property cloud platform or edge computing nodes, including: identity and access management module, data connector library, data usage right control engine, and global audit module. Install standardized data connectors for various data source systems within the property (such as security, access control, business intelligence, and energy consumption systems) and external stakeholders (such as owner apps, merchant systems, and government interfaces).

[0032] Step S2: Trusted access and standardized description of multi-source data.

[0033] Through the aforementioned data connector, raw data from each subsystem (video streams, access control records, sensor readings, work order texts, etc.) is connected to the trusted data space in real time or on a scheduled basis. Metadata descriptions based on a unified data model are added to each piece of data or data stream, and the digital identity credentials of the data provider are bound to it.

[0034] Step S3: Secure integration and processing based on data usage rights.

[0035] Within the data space, data fusion rules are defined and executed. Data consumers (such as intelligent analytics applications and collaborative management engines) request data from the data usage rights control engine based on pre-signed data usage contracts. After the engine verifies the contract, it authorizes consumers to perform fusion calculations and analysis on authorized data from multiple providers within a specific computing environment (such as a secure sandbox or federated learning nodes). The original data does not leave the provider's control domain; only the fused results or models are output.

[0036] Step S4: Trigger the multi-service collaborative management strategy.

[0037] Based on the fusion analysis results generated in step S3 (such as abnormal clustering events in public areas, abnormal energy efficiency of equipment operation, and cross-system fault correlation characteristics), the collaborative management strategy engine matches predefined or self-learning strategy rules to generate a collaborative instruction set.

[0038] For example, when the two events of "fire sensor alarm" and "video analysis confirming fire" are merged in the data space and confirmed as a real fire alarm, the strategy engine automatically generates a sequence of instructions: 1) Link the access control system to open all escape routes; 2) Notify the elevator to be forced to land on the first floor; 3) Push alarm information and evacuation routes to the owner's APP and property management center; 4) Generate an emergency plan work order and assign it to the nearest patrol post.

[0039] Step S5: Full-process audit and continuous optimization.

[0040] The global audit module records the entire chain of operations, from data access and usage right application to fusion computing and policy triggering, forming an immutable audit trail for all parties to monitor and measure data value. Based on audit data and feedback on collaborative effects, machine learning is used to optimize the data fusion model and collaborative policy rules.

[0041] Furthermore, in step S1, the data connector supports multiple protocol adaptations and provides encrypted data transmission, format conversion, and lightweight edge preprocessing functions.

[0042] Furthermore, in step S3, the data fusion and processing supports multiple modes, including but not limited to: statistical queries based on secure multi-party computation, global model training based on federated learning, and information association analysis based on privacy protection.

[0043] Furthermore, in step S4, the collaborative management strategy supports graphical low-code orchestration, allowing property managers to flexibly define cross-system "if-then" response processes according to actual business needs.

[0044] like Figure 1 As shown, the overall process of implementing the method of the present invention is as follows: First, the trusted data space infrastructure was deployed and initialized. In a smart park project, the core components of the data space were deployed in the park's cloud computing center, and customized data connectors were installed for the perimeter security system, building automation system, smart parking system, energy management system, and property customer service platform.

[0045] Secondly, trusted access to multi-source data is implemented. The security system accesses structured events (such as "person loitering at the east entrance") derived from real-time video analysis via connectors; the energy system accesses minute-level electricity consumption data from each floor; and the parking system accesses parking space status change streams. All data access is accompanied by metadata such as data source ID, timestamp, and data type.

[0046] Next, security integration and processing are performed within the space. The park's operations center wants to analyze the reasons for "abnormally high energy consumption on floors with low occupancy rates during holidays." Its data analysis application requests the control engine to retrieve energy consumption data, access control card swipe records, and perimeter video alarm data for the target floor within a specific time period. After verifying that the application has contractual authorization, the engine performs correlation analysis on these three types of data within a designated secure container, and finally outputs an analysis report (e.g., "High energy consumption is related to the abnormally frequent opening of the access control in a certain room, without corresponding video confirmation"), while the original detailed data from the three parties does not leave their respective systems.

[0047] Then, the collaborative management strategy is triggered. Based on the aforementioned fusion analysis report, the strategy engine automatically generates a collaborative work order for "equipment inspection and security verification," which is then dispatched to the engineering department and the security department, and linked to relevant access control logs and video clips for reference.

[0048] Finally, a full-process audit was conducted. The complete log of this data application, analysis, and work order triggering was recorded in the blockchain evidence storage module for subsequent use in billing, accountability, or process optimization.

[0049] like Figure 3 As shown, a more specific example of fire emergency coordination is illustrated below: When the fire sensor triggers a "smoke alarm" data event (Event_F) and accesses the data space, simultaneously, the video analytics system triggers a "visible smoke in the 10th-floor corridor of Building 7" event (Event_V) and accesses the data space. The collaborative strategy engine predefines the rule: IF Event_F AND Event_V FROM same area within 10s THEN Confirm fire alarm.

[0050] Upon triggering the rule, the engine immediately executes a sequence of coordinated instructions: 1) It calls the access control system API via the connector to unlock all safety exits in Building 7; 2) It calls the elevator control system API to put all elevators into fire emergency landing mode; 3) It calls the information publishing system API to push fire alarm notifications and evacuation maps to the apps of all registered users in Building 7; 4) It displays the on-site video and emergency plan with the highest priority on the large screen in the property management command center. The entire process is completed automatically within seconds, without the need for manual judgment or individual system operation.

[0051] The various embodiments of this disclosure have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principles, practical application, or technical improvements to the embodiments in the market, or to enable others skilled in the art to understand the embodiments disclosed herein.

Claims

1. A method for multi-source data fusion and collaborative management of a smart property, characterized in that, The method includes: Step 1: Build and initialize the trusted data space infrastructure; Step 2: Trusted access and standardized description of multi-source data; Step 3: Secure integration and analysis processing based on data usage rights; Step 4: Trigger cross-system collaborative management strategies and responses; Step 5: Full-process audit and continuous optimization. 2.The method according to claim 1, characterized in that, Build and initialize the trusted data space infrastructure, including: Deploy core components of a trusted data space, including identity and access management, a data usage rights control engine, and a global audit module, on the property cloud platform or edge nodes, and configure standardized data connectors for various data source systems within the property and external stakeholders. The data connector supports multiple network and data protocols and has functions such as encrypted data transmission, format conversion, and edge preprocessing. 3.The method of claim 2, wherein, Trusted access and standardized description of multi-source data: Through the data connector, heterogeneous data from security, access control, equipment maintenance, energy metering, and customer service work order subsystems are connected to the trusted data space in real time or on a timed basis, and metadata descriptions and data source identity identifiers based on a unified model are added to the connected data.

4. The method according to claim 2, characterized in that, Secure fusion and analysis processing based on data usage rights, including: The data consumer initiates a request to the data usage right control engine according to the predefined data usage contract; after the engine verifies the authorization, it allows the consumer to perform fusion calculation and analysis on encrypted or de-identified data from multiple authorized data sources in a specified secure computing environment, outputting results or models, and the original data does not leave the provider's control domain.

5. The method according to claim 2, wherein, Triggering cross-system collaborative management strategies and responses, including: Based on the fusion analysis results output in step three, the collaborative management strategy engine matches predefined business rules to generate and automatically execute a cross-subsystem collaborative instruction set, thereby achieving intelligent event linkage and business closure.

6. The method according to claim 2, wherein, End-to-end auditing and continuous optimization: The global audit module records the entire operation log from data access, authorization, fusion computing to policy triggering, forming a traceable and tamper-proof audit record, and continuously optimizes the data fusion model and collaboration strategy based on feedback.

7. The method for multi-source data fusion and collaborative management of smart property management according to claim 4, characterized in that, In step three, the secure computing environment includes a secure sandbox, a trusted execution environment, or a federated learning node, supporting multiple integrated computing modes: secure multi-party computation, data association and federated learning under privacy protection.

8. The method for multi-source data fusion and collaborative management of smart property management according to claim 5, characterized in that, In step four, the collaborative management strategy supports graphical low-code orchestration, allowing users to customize "event-condition-action" rules according to actual business scenarios to trigger automated linkage operations across access control, video, broadcast, and work order subsystems.

9. A method for multi-source data fusion and collaborative management of smart property management according to claim 2, characterized in that, In step five, the global audit module uses blockchain or distributed ledger technology to store key operation logs as evidence, and uses machine learning methods to iteratively optimize the data fusion algorithm and collaboration strategy based on audit data and business feedback.

10. A smart property multi-source data fusion and collaborative management system, characterized in that, The system employs the method according to any one of claims 1-9, the system comprising: The spatial infrastructure establishment module is used to build and initialize a trusted data spatial infrastructure. The data access and standardization module is used for trusted access and standardized description of multi-source data. The security fusion and analysis module is used for security fusion and analysis based on data usage rights. The instruction generation module is used to trigger cross-system collaborative management strategies and responses. The audit and optimization module is used for end-to-end auditing and continuous optimization.

Images