Multi-terminal position monitoring system based on artificial intelligence and NFC chip and application

Abstract

The invention relates to the technical field of position monitoring, in particular to a multi-terminal position monitoring system and application based on artificial intelligence and an NFC chip, and the system comprises a biological terminal module, a data aggregation module, an analysis module, a simulation deduction module, a cooperation module, an interaction module, a block chain evidence storage module and an operation and maintenance module. The biological terminal module is used for body area energy, biological characteristic acquisition and near-field identity identification; and the data aggregation module is used for heterogeneous data access and spatio-temporal data alignment. According to the method, a complete closed loop from individual identification, real-time monitoring, intelligent prediction to group cooperation is constructed, an accurate search network can be started instantly when a pet is lost, passive waiting is converted into active early warning and intelligent guidance, the search pertinence and efficiency are greatly improved, and the search efficiency is improved. At the same time, the self-organized community cooperation mode converts an accidental sight event into an inevitable systematic response, and unprecedented secure guarantee is provided for the pet owner.

Description

Technical Field

[0001] This invention relates to the field of location monitoring technology, specifically to a multi-terminal location monitoring system and application based on artificial intelligence and NFC chips. Background Technology

[0002] Currently, with improved living conditions, more and more families are choosing to keep pets. This trend stems from people's growing demand for emotional companionship and spiritual comfort. Pets have gradually become an indispensable emotional bond in many families. The establishment of this close relationship makes the health and safety of pets one of the most important concerns for pet owners.

[0003] However, with the continuous growth of the number of pets, the number of pets going missing is also increasing, and finding lost pets has become extremely difficult. This is because pets will move around constantly due to fright in unfamiliar environments. Urban environments are complex and full of uncertainties, and traditional search methods are like looking for a needle in a haystack, which is inefficient and has a low success rate, causing huge emotional distress and time and economic costs to owners.

[0004] Traditional methods of finding pets mainly rely on posting paper lost pet notices, visiting nearby pet shelters, and posting requests for help on social media. These methods not only consume a lot of manpower and time, but also have a limited reach and are highly dependent on accidental eyewitness clues. There is a serious lag in information transmission. Once the pet leaves the initial area where it went missing, these methods become ineffective and often miss the best opportunity to find it.

[0005] In summary, a multi-terminal location monitoring system and application based on artificial intelligence and NFC chips are needed to solve the above problems. Summary of the Invention

[0006] The purpose of this invention is to provide a multi-terminal location monitoring system and application based on artificial intelligence and NFC chips to solve the problems mentioned in the background art.

[0007] To achieve the above objectives, the present invention provides the following technical solution:

[0008] This invention proposes a multi-terminal location monitoring system based on artificial intelligence and NFC chips, including a biometric terminal module, a data aggregation module, an analysis module, a simulation and deduction module, a collaboration module, an interaction module, a blockchain evidence storage module, and an operation and maintenance module;

[0009] The biological terminal module is used for body energy, biometric data acquisition, and near-field identification; the data aggregation module is used for heterogeneous data access and spatiotemporal data alignment; the analysis module is used for learning behavioral patterns and identifying abnormal situations; the simulation and inference module is used for geographic field simulation and behavioral prediction; the collaboration module is used to provide direct communication between edge computing nodes and terminals; the interaction module is used for near-field triggered interaction and augmented reality search; the blockchain notarization module is used for distributing group perception tasks, tracing sources, and incentive settlement; and the operation and maintenance module is used for feedback reinforcement learning and dynamic resource scheduling.

[0010] Preferably, the biological terminal module further includes a body energy harvesting unit, a biometric sensing unit, and a near-field identification unit;

[0011] The body energy harvesting unit harvests micro-energy by using a thermoelectric thin film attached to biological tissue and the continuous difference between the pet's core body temperature and the ambient temperature, thereby enabling the terminal device to have permanent battery life.

[0012] The biometric sensing unit integrates miniature biosensors to continuously monitor the pet's core physiological parameters, such as heart rate and skin temperature, to achieve raw data collection of pet characteristics.

[0013] The near-field identification unit passively provides a globally unique identification code when an external reading or writing device approaches via an embedded NFC chip, enabling tamper-proof identification of the pet.

[0014] Preferably, the data aggregation module further includes a heterogeneous data access unit and a spatiotemporal data alignment unit;

[0015] The heterogeneous data access unit receives sensor data from heterogeneous devices such as smart biological terminals, third-party GPS collars, and smart feeders by defining a unified device access protocol, thereby achieving standardized access to multi-source data.

[0016] The spatiotemporal data alignment unit uses a spatiotemporal indexing algorithm to match and associate location information with different timestamps and different precisions with corresponding physiological and environmental data, in order to construct information fragments with complete context.

[0017] Preferably, the analysis module further includes a behavior pattern learning unit and an abnormal situation insight unit;

[0018] The behavior pattern learning unit analyzes historical spatiotemporal trajectories and physiological data streams, and uses time-series models to learn the daily activity patterns and normal behavioral baselines of pets, thereby realizing the digital modeling of individual behavior patterns.

[0019] The abnormal situation insight unit runs a lightweight anomaly detection algorithm to compare the current sensor data with the established behavioral pattern baseline in real time, in order to instantly identify abnormal behaviors such as prolonged inactivity, sudden surges in activity, or abnormal heart rate.

[0020] Preferably, the simulation and deduction module further includes a geographical enclosure simulation unit and a behavior deduction and prediction unit;

[0021] The geographic enclosure simulation unit integrates high-precision maps with real-time traffic and weather data to construct a computable environment model that includes dynamic obstacles and risk areas, used to simulate the movement possibilities of pets in the real world.

[0022] The behavior prediction unit injects the pet's behavior patterns into the geographic enclosure model, runs Monte Carlo simulations, and predicts its most likely movement path and destination in the future, in order to achieve forward-looking early warning of the risk of getting lost and guidance for search.

[0023] Preferably, the collaboration module further includes an edge computing node unit and a direct communication unit between terminals;

[0024] The edge computing node unit deploys lightweight AI models on devices such as home routers and community cameras, enabling it to process NFC scanning signals and video streams locally in real time. This allows for rapid identification and verification of terminal identities, reducing cloud load.

[0025] The direct communication unit between terminals uses Bluetooth Mesh or Wi-Fi Aware technology to enable pet terminals of different users within range to automatically form a self-organizing network, which is used to transmit alarm information to the nearest online node through multi-hop relay when there is no Internet connection.

[0026] Preferably, the interaction module further includes a near-field triggered interaction unit and an augmented reality search unit;

[0027] The near-field triggering interaction unit uses the NFC read / write function of a smartphone to automatically wake up the App and display the pet's key status information when it is near the pet, enabling zero-operation, one-touch identity verification and information query.

[0028] The augmented reality search unit uses the mobile device's camera and AR engine to overlay AI-generated search heatmaps and historical trajectory lines onto real street scenes, assisting searchers in intuitive on-site orientation and tracking.

[0029] Preferably, the blockchain evidence storage module further includes a task distribution unit and a settlement unit;

[0030] When a pet is marked as lost, the task distribution unit automatically sends an anonymous, micro-reward collaborative perception task to all system user terminals within a specific range around the location of the lost pet via a smart contract. This task incentivizes users to actively activate device scanning, thus forming a dynamic monitoring network.

[0031] The clearing unit uses a blockchain distributed ledger to record and preserve each NFC scanning event and valid clue reporting behavior in an immutable manner, and automatically issues points incentives to nodes that provide valid information according to the rules of smart contracts, in order to build a trustworthy and self-driven crowdsourcing collaboration system.

[0032] Preferably, the operation and maintenance module further includes a resource dynamic scheduling unit and a feedback reinforcement learning unit;

[0033] The feedback reinforcement learning unit collects user feedback on the accuracy of AI warnings (confirmation / false alarms) and the final successful retrieval records. It uses this data as reward signals for reinforcement learning to continuously iterate and optimize the behavioral strategies of the AI ​​prediction model.

[0034] The resource dynamic scheduling unit monitors the computing, storage, and network resource consumption of each module to maximize the efficiency of system resource utilization.

[0035] This invention also proposes an application of a multi-terminal location monitoring system based on artificial intelligence and NFC chips in pet location monitoring.

[0036] Compared with existing technologies, the beneficial effects of this invention are as follows: By constructing a complete closed loop from individual identification, real-time monitoring, intelligent prediction to group collaboration, this invention can immediately launch a precise search network the moment a pet goes missing, transforming passive waiting into proactive early warning and intelligent guidance, greatly improving the targeting and efficiency of the search. At the same time, its self-organized community collaboration model transforms accidental sightings into inevitable systematic responses, providing pet owners with unprecedented peace of mind. Attached Figure Description

[0037] Figure 1 The topology diagram of the multi-terminal location monitoring system based on artificial intelligence and NFC chip of the present invention is shown;

[0038] Figure 2 A flowchart of the multi-terminal location monitoring method based on artificial intelligence and NFC chip of the present invention is shown. Detailed Implementation

[0039] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0040] Example 1, please refer to Figure 1 This invention proposes a multi-terminal location monitoring system based on artificial intelligence and NFC chips, including a biological terminal module, a data aggregation module, an analysis module, a simulation and deduction module, a collaboration module, an interaction module, a blockchain evidence storage module, and an operation and maintenance module;

[0041] Furthermore, the biological terminal module is used for body energy, biometric data acquisition, and near-field identification; the data aggregation module is used for heterogeneous data access and spatiotemporal data alignment; the analysis module is used for learning behavioral patterns and identifying abnormal situations; the simulation and inference module is used for geographic field simulation and behavioral prediction; the collaboration module is used to provide direct communication between edge computing nodes and terminals; the interaction module is used for near-field triggered interaction and augmented reality search; the blockchain notarization module is used for distributing group perception tasks, tracing sources, and incentive settlement; and the operation and maintenance module is used for feedback reinforcement learning and dynamic resource scheduling.

[0042] It should also be noted that the bio-terminal module also includes a body energy harvesting unit, a biometric sensing unit, and a near-field identification unit.

[0043] Furthermore, the body energy harvesting unit uses a thermoelectric thin film attached to biological tissue to harvest micro-energy by utilizing the continuous difference between the pet's core body temperature and the ambient temperature, in order to achieve permanent battery life for the terminal device.

[0044] Furthermore, the biometric sensing unit integrates miniature biosensors to continuously monitor the pet's core physiological parameters, such as heart rate and skin temperature, to achieve raw data collection of the pet's characteristics.

[0045] Furthermore, the near-field identification unit passively provides a globally unique identification code when an external reading or writing device approaches via an embedded NFC chip, enabling tamper-proof identification of the pet.

[0046] It should also be noted that the data aggregation module includes a heterogeneous data access unit and a spatiotemporal data alignment unit;

[0047] Furthermore, the heterogeneous data access unit receives sensor data from heterogeneous devices such as smart biological terminals, third-party GPS collars, and smart feeders by defining a unified device access protocol, thereby achieving standardized access to multi-source data.

[0048] Furthermore, the spatiotemporal data alignment unit uses a spatiotemporal indexing algorithm to match and associate location information with different timestamps and different precisions with corresponding physiological and environmental data, in order to construct information fragments with complete context.

[0049] It should also be noted that the analysis module includes a behavior pattern learning unit and an abnormal situation insight unit.

[0050] Furthermore, the behavior pattern learning unit analyzes historical spatiotemporal trajectories and physiological data streams, and uses time-series models to learn the daily activity patterns and normal behavioral baselines of pets, thereby achieving digital modeling of individual behavior patterns.

[0051] Furthermore, the abnormal situation insight unit runs a lightweight anomaly detection algorithm to compare the current sensor data with the established behavioral pattern baseline in real time, in order to instantly identify abnormal behaviors such as prolonged inactivity, surges in activity, or abnormal heart rate.

[0052] It should also be noted that the simulation and inference module includes a geographical field simulation unit and a behavior inference and prediction unit.

[0053] Furthermore, the geographic enclosure simulation unit integrates high-precision maps with real-time traffic and weather data to construct a computable environmental model that includes dynamic obstacles and risk areas, used to simulate the movement possibilities of pets in the real world.

[0054] Furthermore, the behavior extrapolation and prediction unit injects the pet's behavior patterns into the geographic enclosure model, runs Monte Carlo simulations, and extrapolates its most likely movement path and destination in the future, in order to achieve forward-looking early warning of the risk of getting lost and guidance for search.

[0055] It should also be noted that the collaboration module includes edge computing node units and direct communication units between terminals;

[0056] Furthermore, edge computing node units deploy lightweight AI models on home routers and community camera devices, enabling them to process NFC scanning signals and video streams locally in real time, thereby achieving rapid identification and verification of terminal identities and reducing cloud load.

[0057] Furthermore, the direct communication units between terminals use Bluetooth Mesh or Wi-Fi Aware technology to enable pet terminals of different users within range to automatically form a self-organizing network, which is used to transmit alarm information to the nearest online node through multi-hop relay when there is no Internet connection.

[0058] It should also be noted that the interaction module includes a near-field triggered interaction unit and an augmented reality search unit;

[0059] Furthermore, the near-field triggering interaction unit uses the NFC read / write function of a smartphone to automatically wake up the App and display the pet's key status information when it is near the pet, enabling zero-operation, one-touch identity verification and information query.

[0060] Furthermore, the augmented reality search unit uses the mobile device's camera and AR engine to overlay AI-generated search heatmaps and historical trajectory lines onto real street view images, assisting searchers in intuitive on-site orientation and tracking.

[0061] It should also be noted that the blockchain evidence storage module includes a task distribution unit and a settlement unit.

[0062] Furthermore, the task distribution unit uses smart contracts to automatically issue an anonymous, micro-reward collaborative perception task to all system user terminals within a specific range around the location where the pet is lost, when the pet is marked as lost. This task incentivizes users to actively activate device scanning, thus forming a dynamic monitoring network.

[0063] Furthermore, the clearing unit uses a blockchain distributed ledger to record and preserve every NFC scanning event and valid clue reporting behavior in an immutable manner, and automatically issues points incentives to nodes that provide valid information according to the rules of smart contracts, in order to build a trustworthy and self-driven crowdsourcing collaboration system.

[0064] It should also be noted that the operation and maintenance module includes a resource dynamic scheduling unit and a feedback reinforcement learning unit.

[0065] Furthermore, the feedback reinforcement learning unit collects user feedback on the accuracy of AI warnings (confirmation / false alarms) and the final successful retrieval records. This data is used as reward signals for reinforcement learning to continuously iterate and optimize the behavioral strategies of the AI ​​prediction model.

[0066] Furthermore, the resource dynamic scheduling unit monitors the computing, storage, and network resource consumption of each module to maximize the efficiency of system resource utilization.

[0067] Example 2, please refer to Figure 2 Based on the above system, in practical applications of pet location monitoring, this invention also proposes a multi-terminal location monitoring method based on artificial intelligence and NFC chips, specifically including the following steps:

[0068] S1: Data Acquisition and Energy Self-Supply

[0069] The implanted terminal continuously collects physiological data such as heart rate and skin temperature of the target pet, as well as its precise location information.

[0070] At the same time, the difference between the target pet's body temperature and the ambient temperature is used to continuously generate micro-electricity, providing energy for data collection and transmission operations.

[0071] The multimodal raw data stream generated in this step is the data foundation for all subsequent steps;

[0072] S2: Multi-source data fusion and context construction:

[0073] It receives heterogeneous data from S1 and other third-party devices such as smart collars and feeders, and processes it using a unified protocol.

[0074] Furthermore, by using a spatiotemporal indexing algorithm, location, physiological, and environmental data from different sources and with varying precision are aligned and correlated to generate unified data records with complete time, space, and event labels.

[0075] The standardized spatiotemporal data packets output in this step provide high-quality input for S3's intelligent analysis;

[0076] S3: Behavioral Modeling and Abnormal Situation Recognition

[0077] Based on the historical data stream output by S2, a time series model is used to learn and establish an individualized daily activity pattern and normal physiological baseline model for the target pet.

[0078] The system compares the current data transmitted from S2 with the established baseline model in real time, and uses a lightweight anomaly detection algorithm to identify deviation events such as prolonged stillness, rapid running behavior, or abnormal heart rate.

[0079] The abnormal event signals and characteristic data output in this step will trigger the inference and analysis in S4;

[0080] S4: Environmental Simulation and Behavioral Prediction:

[0081] Integrate high-precision maps and real-time traffic and weather information to construct a dynamic, computable environment model;

[0082] The abnormal event characteristics and historical behavior patterns of the target identified by S3 are injected into the environmental model. Through simulation algorithms, several most likely movement paths and potential destinations of the target in the future are deduced, and a predictive heat map is generated.

[0083] The deduction path and risk heat map output in this step are the core basis for S6 to conduct precise searches and S7 to initiate group tasks.

[0084] S5: Near-field interaction and augmented reality presentation:

[0085] When the user terminal approaches the target pet, it automatically reads its identity and wakes up the application to present the target's identity profile and latest status information.

[0086] In search scenarios, based on the inferred heat map and historical trajectory data output by S4, virtual guidance information is superimposed on the real physical environment through the camera of mobile devices to generate an augmented reality view that integrates virtual guidance and real scene.

[0087] S6: Edge Collaboration and Self-Organizing Network Communication

[0088] Deploy processing modules on home routers and community camera edge devices to perform real-time analysis of locally generated NFC scanning signals and video streams, enabling rapid on-site identification and feedback of identity information.

[0089] When there is no internet connection between devices, the terminals within range automatically form a mesh network and forward the emergency alarm information generated by S3 to the nearest online gateway node through multi-hop relay communication.

[0090] S7: Distributed Task Distribution and Trusted Incentives

[0091] Upon receiving a confirmation of an anomaly signal from S3, an anonymous, incentivized collaborative scanning task is automatically sent to all user terminals within the high-risk area deduced by S4.

[0092] All valid scanning and clue reporting behaviors generated during the task response process are recorded in an immutable manner, and the incentive settlement and distribution operations are automatically completed according to preset rules, forming a reliable crowdsourcing collaboration closed loop.

[0093] S8: System Strategy Iteration and Resource Optimization

[0094] Continuously collect user confirmations, false alarm feedback, and final handling results of the warning signals generated by S3, and use this feedback data as optimization signals to continuously adjust and update the behavior and anomaly recognition model in S3;

[0095] At the same time, the system monitors the consumption of computing, storage, and communication resources throughout the entire system and dynamically allocates resource priorities to ensure the computing power supply for core analysis tasks.

[0096] Through the above steps, this invention constructs a complete closed loop from individual identification, real-time monitoring, intelligent prediction to group collaboration, enabling the immediate activation of a precise search network the moment a pet goes missing. This transforms passive waiting into proactive early warning and intelligent guidance, greatly improving the targeting and efficiency of the search. At the same time, its self-organized community collaboration model transforms accidental sightings into inevitable systematic responses, providing pet owners with unprecedented peace of mind.

[0097] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their likenesses.

Claims

1. A multi-terminal location monitoring system based on artificial intelligence and NFC chips, characterized in that, It includes a biological terminal module, a data aggregation module, an analysis module, a simulation and deduction module, a collaboration module, an interaction module, a blockchain evidence storage module, and an operation and maintenance module; The biological terminal module is used for body energy, biometric data acquisition, and near-field identification; the data aggregation module is used for heterogeneous data access and spatiotemporal data alignment; the analysis module is used for learning behavioral patterns and identifying abnormal situations; the simulation and inference module is used for geographic field simulation and behavioral prediction; the collaboration module is used to provide direct communication between edge computing nodes and terminals; the interaction module is used for near-field triggered interaction and augmented reality search; the blockchain notarization module is used for distributing group perception tasks, tracing sources, and incentive settlement; and the operation and maintenance module is used for feedback reinforcement learning and dynamic resource scheduling.

2. The multi-terminal location monitoring system based on artificial intelligence and NFC chip according to claim 1, characterized in that: The bio-terminal module also includes a body energy harvesting unit, a bio-feature sensing unit, and a near-field identification unit; The body energy harvesting unit harvests micro-energy by utilizing the continuous difference between the pet's core body temperature and the ambient temperature through a thermoelectric thin film attached to biological tissue. The biometric sensing unit continuously monitors the pet's core physiological parameters, such as heart rate and skin temperature, by integrating miniature biosensors. The near-field identification unit passively provides a globally unique identification code when it is approached by an external reading or writing device via an embedded NFC chip.

3. The multi-terminal location monitoring system based on artificial intelligence and NFC chip according to claim 2, characterized in that: The data aggregation module also includes a heterogeneous data access unit and a spatiotemporal data alignment unit; The heterogeneous data access unit receives sensor data from heterogeneous devices such as smart biological terminals, third-party GPS collars, and smart feeders by defining a unified device access protocol. The spatiotemporal data alignment unit uses a spatiotemporal indexing algorithm to match and associate location information with different timestamps and different precisions with corresponding physiological and environmental data.

4. The multi-terminal location monitoring system based on artificial intelligence and NFC chip according to claim 3, characterized in that: The analysis module also includes a behavior pattern learning unit and an abnormal situation insight unit; The behavior pattern learning unit learns the pet's daily activity patterns and normal behavior baseline by analyzing historical spatiotemporal trajectories and physiological data streams using a time series model. The abnormal situation insight unit compares the current sensor data with the established behavioral pattern baseline in real time by running a lightweight anomaly detection algorithm.

5. The multi-terminal location monitoring system based on artificial intelligence and NFC chip according to claim 4, characterized in that: The simulation and deduction module also includes a geographical field simulation unit and a behavior deduction and prediction unit; The geographic enclosure simulation unit integrates high-precision maps with real-time traffic and weather data to construct a computable environment model that includes dynamic obstacles and risk areas; The behavior extrapolation and prediction unit injects the pet's behavior patterns into the geographic enclosure model, runs Monte Carlo simulations, and extrapolates its most likely movement path and destination in the future.

6. The multi-terminal location monitoring system based on artificial intelligence and NFC chip according to claim 5, characterized in that: The collaboration module also includes edge computing node units and direct communication units between terminals; The edge computing node unit enables it to process NFC scanning signals and video streams locally in real time by deploying lightweight AI models on home routers and community camera devices. The direct communication unit between terminals enables pet terminals of different users within range to automatically form a self-organizing network through Bluetooth Mesh or Wi-Fi Aware technology.

7. The multi-terminal location monitoring system based on artificial intelligence and NFC chip according to claim 6, characterized in that: The interaction module also includes a near-field triggered interaction unit and an augmented reality search unit; The near-field triggering interaction unit uses the NFC read / write function of a smartphone to automatically wake up the App and display the pet's key status information when it is near the pet. The augmented reality search unit uses the mobile device's camera and AR engine to overlay AI-generated search heatmaps and historical trajectory lines onto real street scene images.

8. The multi-terminal location monitoring system based on artificial intelligence and NFC chip according to claim 7, characterized in that: The blockchain evidence storage module also includes a task distribution unit and a settlement unit; When a pet is marked as lost, the task distribution unit automatically sends an anonymous, micro-rewarded collaborative perception task to all system user terminals within a specific range around the location of the lost pet via a smart contract. The clearing unit uses a blockchain distributed ledger to record and preserve each NFC scanning event and valid clue reporting behavior in an immutable manner, and automatically issues points incentives to nodes that provide valid information according to the rules of the smart contract.

9. The multi-terminal location monitoring system based on artificial intelligence and NFC chip according to claim 8, characterized in that: The operation and maintenance module also includes a resource dynamic scheduling unit and a feedback reinforcement learning unit; The feedback reinforcement learning unit collects user feedback on the accuracy of AI warnings (confirmation / false alarms) and the final successful retrieval records, and uses this data as reward signals for reinforcement learning. The resource dynamic scheduling unit monitors the computing, storage, and network resource consumption of each module.

10. The application of the multi-terminal location monitoring system based on artificial intelligence and NFC chip according to any one of claims 1-9 in pet location monitoring.

Images