Informationized interconnection method and system of water purification terminal

Abstract

The application discloses a kind of informatization interconnection method and system of water purification terminal, specifically relates to information interconnection technical field, including: step one, through mobile terminal AR, user is guided to collect fault evidence, and after evaluating data quality, pre-diagnosis evidence package is generated;Step two, engineer on-site calls equipment digital twin, based on reinforcement learning dynamically generates personalized AR operation guide, and supports remote collaboration with experts;Step three, automatically record the whole process of service and generate digital archives, cloud optimizes diagnosis model and knowledge base accordingly.The corresponding system contains four modules.The application solves the problem of service process disconnection and information asymmetry in existing interconnection mode, realizes the whole-process closed loop from user self-service, on-site intelligent guidance to experience precipitation, significantly improves service accuracy, efficiency and system self-evolution ability.

Description

Technical Field

[0001] This invention relates to the field of information interconnection technology, and more specifically, to an information interconnection method and system for a water purification terminal. Background Technology

[0002] With the rapid development of IoT and smart home technologies, water purification terminal devices are gradually evolving from stand-alone electrical appliances into networked and intelligent information nodes. Currently, most water purification products on the market with network capabilities primarily focus on basic status monitoring and remote alarms. Specifically, the terminal devices upload limited data such as filter lifespan, total water production, and leak alarms to a cloud management platform via built-in communication modules (such as Wi-Fi and NB-IoT). Users or maintenance personnel can view the device status through mobile applications or web pages and receive alerts when the filter is depleted or the device malfunctions. This approach has initially achieved "visualized management" of the equipment, replacing the outdated model of purely manual inspection and representing a significant advancement in the industry's technology.

[0003] However, this traditional interconnection model, which is centered on data reporting and status display, has significant limitations when faced with actual offline service needs such as installation, debugging, and maintenance.

[0004] Firstly, during the service initiation phase, when users discover equipment malfunctions (such as reduced water flow or unusual noises), they can only describe the issue via customer service phone or text chat, resulting in vague and inefficient information transmission. Customer service personnel struggle to accurately predict faults, potentially leading to dispatched engineers carrying the wrong tools or spare parts, resulting in multiple on-site visits, a poor service experience, and high costs.

[0005] Secondly, during the service execution phase, engineers rely heavily on personal experience for fault diagnosis and repair, lacking intelligent on-site operational support. For complex faults, engineers often need to contact backend technical support themselves, resulting in low communication efficiency. Furthermore, key operations during the service process (such as disassembling components and replacing parts) lack objective and traceable digital records, hindering quality control and experience accumulation. Finally, during the service optimization phase, massive amounts of on-site service data have not been effectively structured and deeply mined. The system cannot learn and optimize autonomously from historical cases, leading to stagnant pre-diagnosis accuracy and making it difficult for maintenance strategies to evolve from scheduled replacement to on-demand prediction with intelligent capabilities. Summary of the Invention

[0006] To overcome the above-mentioned deficiencies of the prior art, embodiments of the present invention provide an information interconnection method and system for water purification terminals.

[0007] To achieve the above objectives, the present invention provides the following technical solution: An information interconnection method for water purification terminals includes the following steps: Step 1: Augmented Reality Evidence Collection and Structured Submission for User Self-Service Pre-diagnosis: Through the AR guidance engine of the mobile terminal APP, users are guided to collect multi-dimensional evidence of the faulty water purification terminal, and the quality of the collected data is evaluated and fed back in real time, generating a structured pre-diagnosis evidence package and uploading it to the cloud. Step 2: Remote Engineer Collaboration and Operation Guidance Based on Digital Twin and AR Overlay: After arriving at the site, the engineer retrieves and loads the service digital twin of the water purification terminal through an AR device; based on the digital twin and real-time data, AR operation guidance is generated and overlaid for the engineer; and remote expert collaboration mode is supported. Step 3: Digital recording and dynamic knowledge base optimization of the entire service process: During the service process, key operation nodes and results are automatically recorded to generate structured digital service archives; based on the accumulated digital service archives, the cloud dynamically optimizes the pre-diagnosis model, AR guidance script and fault knowledge base.

[0008] Specifically, in step one: The AR guidance engine uses device recognition, spatial registration, and guide box rendering to overlay a virtual guide box onto the user's mobile terminal's real-world screen, guiding the user to sequentially capture a panoramic view of the device, designated components, and perform specific actions, thereby collecting multimodal evidence including video, images, and audio.

[0009] Specifically, in step one: When generating the pre-diagnostic evidence package, the data quality assessment engine is activated to quantify and score the jitter stability, component visibility, and lighting adequacy of the evidence. If the overall score is lower than the preset threshold, the user will be provided with targeted guidance to resubmit the score until the score reaches the target or the user confirms that the submission can be skipped.

[0010] Specifically, in step two: The service digital twin is obtained by scanning device identifiers and includes a 3D model of the device, historical service records, current pre-diagnosis evidence package and fault analysis results. It is synchronized in real time with the status of the physical device through a network connection.

[0011] Specifically, in step two: AR operation instructions are generated based on a guided sequence planner; The guided sequence planner dynamically selects the optimal guided action based on the currently inspected component, completed steps, real-time sensor data of the equipment, fault confidence distribution, and engineer skill level to generate a personalized AR service sequence.

[0012] Specifically, in step two: The remote expert collaboration mode synchronizes the engineer's first-person view video stream, environmental data, and AR annotation layer from the AR device to the expert's end. Experts annotate the shared screen in real time, and the annotations are overlaid back into the engineers' AR view, creating a two-way immersive collaboration.

[0013] Specifically, in step three: Automatic recording of key operation nodes includes: verifying and recording the completion of operation actions through the local connection between the AR device and the water purification terminal, checking the serial number of the replaced parts, and collecting the equipment operating parameters after the service is repaired.

[0014] An information interconnection system for a water purification terminal includes the following modules: User self-service pre-diagnosis and evidence collection module: It is used to guide users to collect multimodal evidence of faulty water purification terminals through the AR guidance engine of mobile terminal APP, evaluate the data quality, generate a pre-diagnosis evidence package and upload it to the cloud. Equipment Digital Twin and Data Management Module: Used to build, store and manage digital twins corresponding to physical water purification terminals, and to achieve real-time synchronization between the digital twins and the physical equipment status; Augmented Reality Intelligent Guidance and Remote Collaboration Module: Used to generate personalized AR operation guidance for engineers and overlay it onto real devices, as well as to establish a remote expert collaboration channel to achieve two-way immersive collaboration; Service Knowledge Base and Intelligent Optimization Module: Used to analyze digital archives generated during the service process and optimize pre-diagnosis models, AR guidance scripts, and fault knowledge bases.

[0015] The technical effects and advantages of this invention are as follows: This significantly improves the efficiency, accuracy, and user experience of water purification terminal services. Through user-side AR-guided self-service evidence collection and quality control, the integrity and reliability of fault information are ensured from the source, greatly enhancing the accuracy of cloud-based pre-diagnosis. This enables precise parts preparation and personnel dispatch, effectively avoiding multiple on-site visits due to misjudgment. In the on-site service phase, engineers, using digital twins synchronized with equipment status in real time and intelligently generated AR operation guides, can quickly locate faults and receive standardized operating instructions. This not only reduces reliance on personal experience but also greatly minimizes operational errors. Simultaneously, an immersive remote expert collaboration channel allows for real-time remote "consultation" to resolve complex and difficult problems, significantly improving the first-time repair rate and shortening service time. A data-driven service optimization closed loop has been constructed, enabling the system to learn and evolve continuously. The system automates and digitally records the entire service process, generating immutable, structured service archives, transforming implicit on-site experience into analyzable data assets. By continuously analyzing this massive amount of archive data, the cloud can automatically optimize the judgment logic of the pre-diagnosis AI model, dynamically adjust the steps and sequence of AR guidance scripts, and uncover fault correlation patterns between components. This results in increasingly accurate fault prediction, superior maintenance strategies, and a more intelligent service knowledge base. This fundamentally upgrades traditional reactive maintenance to a predictable and preventative intelligent service model. Attached Figure Description

[0016] Figure 1 This is a flowchart of the method of the present invention. Detailed Implementation

[0017] 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.

[0018] like Figure 1 As shown, the steps of an information interconnection method for a water purification terminal are as follows: Step 1: Augmented Reality (AR) Evidence Collection and Structured Submission for User-Style Self-Service Pre-Diagnosis; Specific Execution Steps: When a user initiates a service request through the service app, they select the problem type (e.g., no water supply, unusual noise). The app immediately accesses the phone's camera and activates the AR guidance engine.

[0019] The AR guidance engine overlays virtual guide boxes and step-by-step prompts onto the real-world image on the phone screen. For example, when the user selects "no water," the guidance process is as follows: a) The guide box automatically frames the water purification terminal host and prompts the user to take a stable panoramic shot of the device for 3 seconds. The APP automatically records a short video and extracts the device model, LED status light color and flashing frequency. b) Next, the guide box locks onto the water inlet valve, prompting you to point your fingertip at the red valve and tap the screen. The APP uses gesture recognition and image analysis to confirm the valve status. c) Finally, the guidance box covers the faucet, prompting you to fill a cup with water for 10 seconds. The APP uses sound analysis to identify the presence and volume of water flow and associates it with a timestamp.

[0020] The app automatically packages the collected multimodal evidence (video clips, image analysis results, audio features, and device identifiers identified by sensors) and associates them with the device's unique ID, user's geographical location, and historical service records to generate a structured pre-diagnosis evidence package.

[0021] The AR guidance engine is developed based on the ARKit (iOS) or ARCore (Android) platform, and uses SLAM (Simultaneous Localization and Mapping) technology to achieve precise device positioning in physical space. The virtual guide box is generated using the following method: Device identification stage: The water purification terminal device in the camera image is identified by a pre-trained MobileNetV2 lightweight convolutional neural network; Spatial registration stage: Use ORB or SIFT feature point detection algorithms to match the key points of the device's 3D model with the real device, and calculate the device's pose (position and orientation) in the camera coordinate system. Guide box rendering stage: Based on the fault type, extract the list of components that need to be checked from the preset fault handling knowledge graph, and render a semi-transparent highlighted frame at the 3D model coordinates of the corresponding component.

[0022] Simultaneously, the embedded data quality assessment engine is activated to perform real-time analysis of the multimodal data stream within the evidence package and calculate a comprehensive data quality score. The process is as follows: The quantitative assessment focuses on three key dimensions that influence the diagnosis: Shake stability: Analyze the video stream to assess the degree of shaking during shooting; Component visibility: Calculate the proportion of the area obscured by key components under inspection (such as valves and indicator lights) using an image segmentation model; Adequate illumination: Analyze the average brightness and contrast of the image to assess whether the ambient light meets the recognition requirements; The overall quality score (DQS) is calculated using the following formula: ; in: Score the data quality. These are the weight coefficients for each dimension, and It is obtained through training on historical data, such as setting it to... ; These are the normalized function values ​​for jitter stability, component visibility, and lighting adequacy, respectively. The original measurements for each dimension are mapped to the [0,1] interval, with 1 representing the optimal value. The specific definitions are as follows:

[0023] JS is a quantization value for shake stability, calculated from the angular velocity variance based on gyroscope data from the mobile device. A larger value indicates more severe shooting shake. The attenuation coefficient; It is an exponential function, ensuring The range of its value is within the interval (0,1]; the greater the jitter, the lower the value. The larger the value, The closer to 0; =1 - (Number of occluded pixels / Total number of pixels in the component); where To quantify component visibility, the following parameters are defined: Occlusion Pixel Count: The number of pixels of the key inspected component (such as a valve or indicator light) identified by the image segmentation model as being occluded; Total Component Pixel Count: The total number of pixels that the key component should occupy in the image under ideal, unoccluded conditions; the less occlusion, the better. The closer to 1; ,in This is a quantitative representation of sufficient light. The average brightness of the current image. This represents the ideal brightness threshold; the closer the brightness is to the ideal value, the better. The closer it is to 1.

[0024] Intelligent feedback and decision-making: A quality threshold θ is preset (e.g., θ=0.7); if DQS≥θ: the evidence package is deemed to be of acceptable quality, and the subsequent encrypted upload process is automatically executed; If DQS < θ: the quality is deemed unacceptable, the system immediately interrupts the upload and triggers the APP's interaction layer; at this time, the APP will display precise guidance prompts to the user, for example; If the f(JS) score is low, the message is: the shooting is too shaky. Please lean your elbow against a fixed object and take another 3 seconds to stabilize the shot. If the g(PV) score is low, the message will be: The water inlet valve is blocked. Please adjust the angle so that the red valve can be fully visible in the picture. If the h(IS) score is low, the message is: The ambient light is insufficient. Please turn on the overhead light or use your phone's flashlight to supplement the light. Users will re-collect data as prompted, and the system will re-evaluate the new data until DQS ≥ θ or the user manually skips the process. This DQS score and whether data was re-collected will be added as metadata to the evidence package, providing the cloud-based AI model with a weighted reliability of the data during diagnosis.

[0025] The pre-diagnostic evidence package is encrypted and uploaded to the cloud. The cloud-based pre-diagnostic AI model analyzes the evidence package to generate a preliminary failure probability distribution (e.g., filter blockage: 70%, water pump failure: 25%, inlet valve closure: 5%) and a recommended spare parts list, which are then sent to the designated engineer's mobile terminal along with the work order.

[0026] Step Two: Remote Engineer Collaboration and Work Guidance Based on Digital Twin and AR Overlay; Specific Implementation Steps: Once engineers arrive on-site, they use AR devices to scan the device's QR code or identify its shape to automatically retrieve the terminal's service digital twin. This twin includes a 3D model of the device, historical service records, a pre-diagnostic evidence package, and AI analysis results.

[0027] The AR devices utilize industrial-grade AR glasses such as the Microsoft HoloLens 2 or Vuzix Blade, and are powered by the Qualcomm XR2 platform, supporting SLAM, gesture recognition, and voice interaction. The loading process of the digital twin is as follows: The device's unique ID is obtained by scanning a QR code, which uses the QR Code standard and contains the device model, production batch, and encrypted device identification information. An HTTP RESTful API request is sent to the cloud-based digital twin management module to obtain the device's complete digital twin data. The device's 3D model is loaded using the glTF2.0 format. This model contains a layered structure, such as the device casing, filter assembly, circuit board, water pump, and other sub-components. The device status updates are subscribed to in real time via a WebSocket connection to ensure that the digital twin is synchronized with the physical device.

[0028] AR spatial positioning employs the following hybrid positioning technologies: Visual positioning: The AR device's front-facing RGB-D camera collects environmental point clouds and matches them with a pre-stored device point cloud map; UWB ultra-wideband positioning: A UWB tag is installed on the water purification terminal to communicate with the UWB base station on the AR device; IMU inertial navigation: The AR device's built-in nine-axis IMU (accelerometer, gyroscope, magnetometer) calculates the trajectory and provides continuous positioning when visual positioning fails.

[0029] Based on real-time synchronization of the digital twin, a bootstrap sequence planner based on Markov Decision Process (MDP) is initiated. Taking into account the pre-diagnostic fault probability distribution, equipment historical service records, current real-time sensor data, and the engineer's skill level (extracted from historical service records), the optimal AR service bootstrap sequence is dynamically generated, rather than executing a fixed script. The specific process is as follows: State space definition: State space Each state in It is a multidimensional feature vector, defined as follows: ; in: The system state at time t is a multidimensional feature vector; : Represents the one-hot encoded vector of the component identifier currently being inspected or operated; : Represents a binary vector of completed steps, with each bit corresponding to a standard operation step (such as disassembling the casing or detecting the voltage). : Represents a vector of sensor readings acquired from the device in real time, such as =[pressure p, flow rate q, TDS value d].

[0030] : Represents the current fault confidence distribution vector, given by the pre-diagnosis model and updated based on real-time data, such as =[P(blockage),P(pump),P(valve)]; : Represents the engineer's skill level scalar, which is normalized to the [0,1] interval based on indicators such as average fault resolution time and first-time resolution rate in historical service records.

[0031] Action space definition: Action space Each action in A guided action that an AR device can perform includes: Displays 3D disassembly / assembly animation; Highlight and mark specific detection points; Play step-by-step audio guidance; : Retrieve and hover display of relevant circuit diagrams or component drawings; Displays a comparison between the sensor's real-time readings and the normal range.

[0032] Reward function: Learns the optimal policy by maximizing cumulative reward. Instant reward at each step. Determined by the following multi-objective reward function: ; in: The immediate reward obtained after performing the action at time t; Indicates from state Transferred to The resulting improvement in diagnostic accuracy is achieved through fault confidence distribution. Measured by entropy reduction: , This is the Shannon entropy function; a decrease in entropy indicates a more certain judgment of the fault. Indicates from state Transferred to The resulting improvement in operational efficiency is achieved through completed steps. It is measured by the ratio of the increment to the standard working hours: , The standard working hours for this step are... Let L0 be the L0 norm of the vector (the number of non-zero elements). , These are the binary vectors of completed steps at times t and t+1, respectively. Indicates the execution of an action For skill level The cognitive load caused by engineers. It is a predefined function, such as for complex animations. Novice Engineer Cognitive load (low value) The value is relatively high; for simple reading displays Then for all engineers The values ​​are all low; , , These are the balance coefficients for the three reward components, satisfying... This was determined through offline reinforcement learning training; Strategy Learning and Decision Making: Using Deep Q-Networks (DQN) to Approximate the Optimal Action Value Function Network parameters Update by minimizing the timing difference error: ; in The loss function is a function of the online network parameters. The function whose goal is to minimize it; These are the training weight parameters for the online network in a deep Q-network. The weight parameters of the target network in the deep Q-network are periodically copied from the online network; For mathematical expectation operators, This indicates that empirical quadruples are randomly sampled from the empirical playback buffer D. And take an expectation of it, Let D be a single empirical data point randomly sampled from the empirical playback buffer D, where: Current state The action performed. Instant rewards received. : The next state to which it transitions; For the target network in the next state Next, all possible actions The calculated maximum action value, For experience replay buffer, This is the discount factor.

[0033] In actual service, based on the current status Use a greedy strategy to select actions This allows for the generation of dynamic, personalized guide sequences on AR devices.

[0034] The engineer confirmed the start of service. The AR device uses spatial positioning to precisely overlay virtual guidance information from the twin onto the real device. For example: a) on the filter bottle that needs to be disassembled, the rotation direction arrow and torque value are highlighted; b) on the circuit board test point, the normal voltage value range is displayed floatingly; c) high-probability fault points indicated by AI are marked with flashing virtual icons.

[0035] If engineers encounter any unresolved issues, they can activate the remote expert collaboration mode. The AR device will synchronize the engineer's first-person video stream, real-time environmental data (such as temperature and humidity sensor readings), and the currently overlaid AR annotation layer to the cloud-based expert collaboration platform via a low-latency network.

[0036] Remote experts view live feeds on their own screens and can directly annotate the shared video stream or 3D model (e.g., draw a circle, draw a disassembly path, or enter text prompts). This annotation is overlaid in real-time onto the engineer's AR view, guiding their next steps. Voice, gesture annotations, and focus points are shared synchronously between the two parties, creating an immersive remote collaboration experience.

[0037] Step 3: Digital recording and dynamic knowledge base optimization of the entire service process; Specific execution steps: During the service, the AR device connects to the terminal device via Bluetooth / UWB to automatically record key operation points. These include: ① Operation verification: When the engineer successfully unscrews the filter bottle according to the AR instructions, the data change of the torque sensor built into the equipment is linked and recorded with the AR action completion signal; ② Component matching: Scan the unique serial number of the newly replaced filter element, automatically check and bind it with the spare parts list in the work order; ③ Status Confirmation: After the service is completed, the terminal will automatically power on and upload the repaired key operating parameters (water pressure, flow rate, TDS value).

[0038] The Bluetooth / UWB connection establishment process includes: Device discovery: The AR device scans the BLE beacon of the water purifier terminal via Bluetooth 5.0 broadcast. The beacon broadcasts the device ID and service UUID. Secure pairing: The pairing method uses LESecureConnections and the ECDH key exchange algorithm to establish a secure connection. Service discovery: After the connection is established, the AR device discovers the GATT services provided by the water purifier terminal, including device information service, sensor data service, control service, etc.

[0039] Specific implementation of operation verification: Torque sensor data acquisition: The water purification terminal has a built-in strain gauge torque sensor with a sampling rate of 100Hz and an accuracy of ±0.5%FS; Action completion detection: When the torque value is detected to drop from the peak value to more than the threshold (e.g., from 20N·m to below 5N·m) and the duration exceeds 200ms, the disassembly action is determined to be completed; Data association: The AR device receives sensor data via Bluetooth and aligns it with the completion event timestamp of the AR guidance steps, with an error window of ±500ms.

[0040] Generation of structured service reports: Data aggregation: After the service is completed, the AR device packages all locally recorded operation logs, sensor data, and annotation records; Digital signature: The report is signed with SHA256 with RSA using the engineer's digital certificate; Blockchain notarization: The report hash value is written to a consortium blockchain (such as Hyperledger Fabric) to ensure immutability; Related storage: The full text of the report is encrypted and stored in cloud object storage (such as AWS S3), and the index information is stored in a relational database.

[0041] A structured service report is generated, automatically integrating the following information: pre-diagnostic evidence package, initial AI judgment, all AR-guided steps actually performed by the engineer and their completion time, remote expert collaboration session records (if any), replacement component serial numbers, post-repair terminal self-test data, supplementary voice / text notes by the engineer, and user electronic signature confirmation form. This information is encrypted and packaged into an immutable digital service file, linked to the terminal's digital twin.

[0042] Dynamically optimize the knowledge base and decision-making model. Regularly analyze digital archives in the cloud. By comparing AI pre-diagnostics with engineers' final conclusions, we can identify cases of AI misjudgment and use them to optimize the pre-diagnostic model. Analyze the optimal solution path and average time for different faults, and optimize the steps and sequence of the AR service bootstrapping script; The system analyzes the failure rate and associated operating conditions of each component model to provide data support for product improvement and precise inventory management. The optimized model and scripts will be automatically updated to the service systems of all terminals.

[0043] An information interconnection system for a water purification terminal includes the following modules: The user-initiated pre-diagnosis and evidence collection module, hosted on a user's mobile app, integrates an augmented reality (AR) guidance engine and a data quality assessment engine. It guides users through a standardized process to collect multi-dimensional evidence (including video, images, and audio) from faulty water purifiers. The module also provides real-time quantitative assessment and immediate feedback on key quality dimensions of the collected data, such as jitter, occlusion, and lighting conditions. This ensures that the pre-diagnosis evidence package uploaded to the cloud has a high-quality and reliable data foundation, providing a guarantee for subsequent intelligent diagnosis. The equipment digital twin and data management module, deployed in the cloud, is responsible for building, storing, and maintaining a dynamic digital twin that corresponds one-to-one with each physical water purification terminal. It integrates and manages the equipment's static 3D model, dynamic real-time operating data, full lifecycle historical service records, and current work order information. Through real-time data synchronization, this module ensures that the digital twin accurately maps the physical equipment's status, providing a unified and accurate data source for front-end AR services, remote collaboration, and back-end analysis. Augmented Reality Intelligent Guidance and Remote Collaboration Module. Relying on front-end AR devices (such as AR glasses) and a cloud-based collaborative platform, it serves as the core support for engineers' on-site services. Based on a reinforcement learning model, it dynamically generates personalized AR operation guidance (such as disassembly animations and highlighting of detection points) according to real-time status, supplemented by monitoring of operational standards. The second function is to establish a low-latency remote expert collaboration channel, supporting two-way synchronization of audio and video streams, first-person perspective images, and real-time annotation information, enabling experts to remotely "see through" the site and guide engineers in solving complex problems. The service knowledge base and intelligent optimization module deeply mine and learn from the service archives generated by the end-to-end digitalization; by analyzing massive service data (such as operation steps, time consumption, and fault conclusion comparison), it automatically optimizes the accuracy and efficiency of the pre-diagnosis AI model and AR guidance script; and through graph neural network and other models, it discovers fault correlations between components, builds and continuously evolves the equipment fault handling knowledge graph, thereby realizing the system's self-evolution and improving preventive maintenance capabilities.

[0044] The above formulas are all dimensionless calculations. Dimensionless calculations can be performed using various methods such as standardization, which will not be elaborated here. The formulas are derived from software simulations based on a large amount of collected data, and the preset parameters in the formulas can be set by those skilled in the art according to the actual situation.

[0045] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, ATA hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. The semiconductor medium can be a solid-state ATA hard disk.

[0046] It should be understood that in the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0047] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0048] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0049] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0050] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0051] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable ATA hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0052] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for information interconnection of water purification terminals, characterized in that, Includes the following steps: Step 1: Augmented Reality Evidence Collection and Structured Submission for User Self-Service Pre-diagnosis: Through the AR guidance engine of the mobile terminal APP, users are guided to collect multi-dimensional evidence of the faulty water purification terminal, and the quality of the collected data is evaluated and fed back in real time, generating a structured pre-diagnosis evidence package and uploading it to the cloud. Step 2: Remote Engineer Collaboration and Operation Guidance Based on Digital Twin and AR Overlay: After arriving at the site, the engineer retrieves and loads the service digital twin of the water purification terminal through an AR device; based on the digital twin and real-time data, AR operation guidance is generated and overlaid for the engineer; and remote expert collaboration mode is supported. Step 3: Digital recording and dynamic knowledge base optimization of the entire service process: During the service process, key operation nodes and results are automatically recorded to generate structured digital service archives; based on the accumulated digital service archives, the cloud dynamically optimizes the pre-diagnosis model, AR guidance script and fault knowledge base.

2. The information interconnection method for a water purification terminal according to claim 1, characterized in that, In step one: The AR guidance engine uses device recognition, spatial registration, and guide box rendering to overlay a virtual guide box onto the user's mobile terminal's real-world screen, guiding the user to sequentially capture a panoramic view of the device, designated components, and perform specific actions, thereby collecting multimodal evidence including video, images, and audio.

3. The information interconnection method for a water purification terminal according to claim 2, characterized in that, In step one: When generating the pre-diagnostic evidence package, the data quality assessment engine is activated to quantify and score the jitter stability, component visibility, and lighting adequacy of the evidence. If the overall score is lower than the preset threshold, the user will be provided with targeted guidance to resubmit the score until the score reaches the target or the user confirms that the submission can be skipped.

4. The information interconnection method for a water purification terminal according to claim 1, characterized in that, In step two: The service digital twin is obtained by scanning device identifiers and includes a 3D model of the device, historical service records, current pre-diagnosis evidence package and fault analysis results. It is synchronized in real time with the status of the physical device through a network connection.

5. The information interconnection method for a water purification terminal according to claim 4, characterized in that, In step two: AR operation instructions are generated based on a guided sequence planner; The guided sequence planner dynamically selects the optimal guided action based on the currently inspected component, completed steps, real-time sensor data of the equipment, fault confidence distribution, and engineer skill level to generate a personalized AR service sequence.

6. The information interconnection method for a water purification terminal according to claim 5, characterized in that, In step two: The remote expert collaboration mode synchronizes the engineer's first-person view video stream, environmental data, and AR annotation layer from the AR device to the expert's end. Experts annotate the shared screen in real time, and the annotations are overlaid back into the engineers' AR view, creating a two-way immersive collaboration.

7. The information interconnection method for a water purification terminal according to claim 1, characterized in that, In step three: Automatic recording of key operation nodes includes: verifying and recording the completion of operation actions through the local connection between the AR device and the water purification terminal, checking the serial number of the replaced parts, and collecting the equipment operating parameters after the service is repaired.

8. A system applied to the information interconnection method for a water purification terminal according to any one of claims 1-7, characterized in that, Includes the following modules: User self-service pre-diagnosis and evidence collection module: It is used to guide users to collect multimodal evidence of faulty water purification terminals through the AR guidance engine of mobile terminal APP, evaluate the data quality, generate a pre-diagnosis evidence package and upload it to the cloud. Equipment Digital Twin and Data Management Module: Used to build, store and manage digital twins corresponding to physical water purification terminals, and to achieve real-time synchronization between the digital twins and the physical equipment status; Augmented Reality Intelligent Guidance and Remote Collaboration Module: Used to generate personalized AR operation guidance for engineers and overlay it onto real devices, as well as to establish a remote expert collaboration channel to achieve two-way immersive collaboration; Service Knowledge Base and Intelligent Optimization Module: Used to analyze digital archives generated during the service process and optimize pre-diagnosis models, AR guidance scripts, and fault knowledge bases.

Images