A data center intelligent identity recognition inspection method and system

Abstract

This application relates to the technical field of fixed-point inspection, and more particularly to an inspection method and system for intelligent identity recognition in data centers. The method includes real-time monitoring of signal quality parameters of the identity recognition device in the inspection area; when the signal quality parameters are lower than a preset threshold, an automatic activation of a backup recognition mode is performed, wherein the backup recognition mode acquires the operator's biometric features through a visual acquisition device; based on the biometric features, a pre-stored identity database is matched to generate an identity verification result; if the identity verification is successful, missed registration events caused by signal quality issues are dynamically compensated, and a complete inspection log containing timestamps, operator identity, and device location information is generated. This application solves the problem of missed registrations caused by signal interference in densely populated equipment areas through real-time signal monitoring and automatic switching of the backup mode, improving the completeness of audit logs and eliminating compliance risks caused by missed registrations.

Description

Technical Field

[0001] This application relates to the technical field of fixed-point inspection, and in particular to an inspection method and system for intelligent identity recognition in data centers. Background Technology

[0002] Data center operation and maintenance management relies on efficient inspection mechanisms to ensure the safe operation of equipment, with personnel identity verification and inspection process registration being core control links. With the upgrading of intelligent systems, automated inspection systems based on identity recognition have become an important development direction. These systems achieve dual monitoring of equipment status and operational behavior by registering the identity, time, and operation trajectory of inspection personnel in real time. Such systems must meet the requirements of high-precision identity authentication and automated process recording to comply with the stringent standards of modern data centers for security auditing and operational traceability.

[0003] However, in situations involving dense clusters of equipment or collaborative operations by multiple personnel, signal interference can easily lead to missed registrations or misidentification (e.g., personnel A is operating the equipment, but personnel B's card is misread), and real-time tracking of personnel movement paths is impossible. This results in inaccurate binding of inspection time records with operator identities, making it difficult for the system to generate reliable and complete audit logs, thus hindering the compliance of intelligent data center management and control. Summary of the Invention

[0004] To address at least one of the aforementioned technical problems, this application provides a data center intelligent identity recognition inspection method and inspection system.

[0005] Firstly, this application provides a data center intelligent identity recognition inspection method, which adopts the following technical solution, including:

[0006] Real-time monitoring of signal quality parameters of the identification device in the inspection area;

[0007] When the signal quality parameter is lower than a preset threshold, the backup identification mode is automatically activated, wherein the backup identification mode acquires the operator's biometric features through a visual acquisition device;

[0008] Based on the biometric features matched against a pre-stored identity database, an identity verification result is generated.

[0009] If authentication is successful, the system will dynamically compensate for any missed registration events caused by signal quality issues and generate a complete inspection log containing timestamps, operator identity, and device location information.

[0010] By adopting the above technical solution, when primary identification methods such as RFID fail, the system immediately activates visual recognition to capture the operator's facial / fingerprint features, ensuring uninterrupted identity verification. After successful verification, the dynamic compensation module automatically reconstructs missed registration events, binding the operator's identity, timestamp, and device location to generate logs. Through real-time signal monitoring and automatic switching to backup mode, the system solves the problem of missed registrations caused by signal interference in densely populated equipment areas, improving the integrity of audit logs, eliminating compliance risks caused by missed registrations, and requiring no manual intervention throughout the entire process.

[0011] In one possible implementation, the step of automatically activating a backup recognition mode when the signal quality parameter is below a preset threshold, wherein the backup recognition mode, prior to the step of acquiring the operator's biometric features through a visual acquisition device, further includes:

[0012] Based on the equipment layout heat map, high-risk areas for signal interference are predicted, and the visual acquisition equipment is preloaded to standby mode in the inspection path planning.

[0013] By adopting the above technical solution, the traditional system suffers from missed key operations due to the time required for camera wake-up. This solution uses a heat map of equipment layout to predict signal blind spots (such as high-density cabinet clusters), completes equipment preheating before the operator reaches the high-risk area, and adjusts the vision equipment to standby mode in advance, which greatly shortens the response time of the standby mode. This solves the problem of equipment start-up delay in dynamic inspection, ensures that no biometric features are missed, improves system robustness, and avoids the defect of not being able to track paths in real time.

[0014] In one possible implementation, the step of dynamically compensating for missed registration events due to signal quality issues and generating a complete inspection log containing timestamps, operator identity, and device location information if authentication is successful specifically includes:

[0015] The location and time of the operator's most recent successful identity verification;

[0016] Extract the operating status change data of the target device;

[0017] Based on the behavioral pattern analysis model, compensation log entries containing operator identity, operation time, and device number are generated.

[0018] By adopting the above technical solution, the operator's last known location / time is first bound, then the target equipment status change data is retrieved (such as a sudden temperature rise indicating someone is operating), and then the details of the missed registration event are deduced by combining the historical behavior model (such as the operator's inspection habits). Finally, accurate compensation is achieved through spatiotemporal correlation and behavior analysis, which solves the problem of the operator's identity and equipment actions being out of sync and improves the accuracy of the compensation log.

[0019] In one possible implementation, the method further includes:

[0020] Real-time tracking of the spatial coordinates of each operator using wearable devices;

[0021] When multiple operators are detected to be within the same device's operating radius, the visual acquisition device is forcibly activated to perform facial recognition.

[0022] By adopting the above technical solution, the wearable device provides real-time feedback of the operator's coordinates. When the system detects that multiple people enter the device's operating range at the same time (e.g., within a 1-meter radius), it forcibly activates facial recognition. Through precise positioning and collaborative triggering mechanisms, it resolves mis-association of identities and eliminates errors such as when person A is operating the device, but person B is recorded. For example, when two people approach the server during maintenance, the system instantly captures the facial features of the actual operator, ensuring the uniqueness of the identity and device binding.

[0023] In one possible implementation, the step of forcibly activating the visual acquisition device to perform face recognition when multiple operators are detected to be within the same device's operating radius further includes, after forcibly activating face recognition:

[0024] Synchronously acquire trigger signals from the target device's operation interface;

[0025] The timestamp of the trigger signal, the interface number, and the identified face identity are triple-bound.

[0026] By adopting the above technical solution, while performing facial recognition, the system records the device interface trigger signals (such as button presses and switch toggles) in real time, establishing a triple association between "facial identity - operation action - device interface". Through multi-source signal fusion, the system achieves operation traceability, overcoming the defect of not being able to distinguish concurrent operations. For example, when two people are repairing different device interfaces at the same time, the system can accurately distinguish their respective operation objects, and the audit log can be traced back to the specific interface unit.

[0027] In one possible implementation, the method further includes:

[0028] When the equipment layout changes, the signal coverage model is recalculated based on the coordinates of the newly added equipment.

[0029] The power of the identity recognition device and the acquisition angle of the visual acquisition device are dynamically adjusted.

[0030] By adopting the above technical solutions, after adding / moving equipment, the system can reconstruct the signal coverage model (such as RFID reading and writing range) in real time, automatically enhance the power of equipment in high interference areas, and adjust the camera angle to cover blind spots. Through adaptive adjustment, the system can maintain recognition stability and solve the problem of poor adaptability of static systems. For example, when adding a cabinet causes the original recognition blind spot, the system can complete parameter optimization within 10 seconds to ensure the recognition rate of the changed area.

[0031] In one possible implementation, the step of dynamically compensating for missed registration events due to signal quality and generating a complete inspection log containing timestamps, operator identity, and device location information if authentication is successful, further includes the following after generating the complete inspection log:

[0032] Logs are stored on blockchain nodes, and each log entry is accompanied by a digital signature of the device and a unique biometric code of the operator.

[0033] By adopting the above technical solutions, blockchain storage ensures that logs are tamper-proof, device digital signatures (such as hardware encrypted IDs) verify the authenticity of devices, and biometric codes (such as fingerprint hash values) bind the operator's identity. In this way, the credibility of audits is improved through tamper-proof evidence storage, and the defects of untrustworthy audit logs are eradicated. For example, during regulatory review, the operator's identity can be verified in reverse through biometric codes, which increases the cost of forgery.

[0034] Secondly, this application provides a data center intelligent identity recognition inspection system, comprising:

[0035] The signal monitoring module is configured to collect the signal strength and signal quality of the identity recognition device in real time;

[0036] The multi-mode switching module is connected to the signal monitoring module. When the signal strength is lower than the first threshold or the signal quality is lower than the second threshold, the visual acquisition device is triggered to start.

[0037] The biometric storage module stores biometric templates of authorized personnel;

[0038] The log compensation module is configured to retrieve historical operation data and reconstruct missed inspection events based on the recognition results of the visual acquisition device.

[0039] By adopting the above technical solution, the signal monitoring module diagnoses the status of the identification device in real time; the multi-mode switching module activates backup identification; the biometric storage module provides a verification benchmark; and the log compensation module actively retrieves historical data to reconstruct events. Through modular collaboration, closed-loop self-repair is achieved. The four modules work together to address the core deficiency of insufficient registration reliability. For example, when RFID fails, the system can complete the entire process from visual recognition to log compensation in a short time, greatly improving fault recovery speed.

[0040] Thirdly, this application provides an electronic device including a memory and a processor, wherein the memory is used to store computer program code, and the processor is used to execute the computer program code stored in the memory to implement the methods in the first aspect and any one of the first aspects, or in the second aspect and any possible implementation of the second aspect.

[0041] Fourthly, this application provides a computer-readable storage medium storing a computer program or instructions that, when executed, implement the methods described in the first aspect and any one thereof, or the second aspect and any possible implementation thereof. Attached Figure Description

[0042] Figure 1 This is a flowchart illustrating a data center intelligent identity recognition inspection method provided in an embodiment of this application.

[0043] Figure 2 This is a schematic diagram of the structure of a data center intelligent identity recognition inspection system provided in an embodiment of this application.

[0044] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0045] The technical solutions in this application will now be described with reference to all the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them.

[0046] In the description of the embodiments of this application, unless otherwise stated, " / " means "or". For example, A / B can mean A or B. "And / or" in this document is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Furthermore, in the description of the embodiments of this application, "plural" or "multiple" refers to two or more than two.

[0047] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this embodiment, unless otherwise stated, "a plurality of" means two or more.

[0048] The terminology used in the following embodiments is for the purpose of describing particular embodiments only and is not intended to be limiting of this application. As used in the specification and appended claims of this application, the singular expressions “a,” “an,” “the,” “the,” “the,” and “this” are intended to also include expressions such as “one or more,” unless the context clearly indicates otherwise. It should also be understood that in the following embodiments of this application, “at least one” and “one or more” refer to one, two, or more than two.

[0049] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "one embodiment," "some embodiments," "another embodiment," "other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0050] This application provides a data center intelligent identity recognition inspection method, executed by an electronic device. This electronic device can be a standalone physical electronic device, a cluster of multiple physical electronic devices, a distributed system, or a cloud electronic device providing cloud computing services. This application does not impose limitations on this method. Figure 1 As shown, the method includes:

[0051] S1. Real-time monitoring of signal quality parameters of the identity recognition device in the inspection area.

[0052] Specifically, RFID readers supporting the 902-928MHz frequency band are deployed in the computer room corridor. The readers have built-in signal analysis chips that can output the monitored signal quality parameters in real time (including strength value and bit error rate, corresponding to the strength and quality of the signal).

[0053] The monitoring thread polls the reader data every 100ms and transmits the data to the edge computing node. For signal quality assessment, the chip sets dual thresholds (an abnormality is determined when the strength value is <-70dBm or the bit error rate is >10%). The bit error rate is equivalent to the signal quality. Therefore, when judging whether the signal quality parameters are abnormal, it is possible to judge whether the signal strength is lower than the first threshold or whether the signal quality is lower than the second threshold.

[0054] Furthermore, the reader array covers the passageways between server racks. When an operator enters the area carrying an RFID tag, the signal analysis chip continuously calculates the electromagnetic wave propagation loss. Edge nodes construct a signal quality heatmap, marking attenuation areas in real time (such as densely packed metal server rack areas).

[0055] S2. When the signal quality parameter is lower than the preset threshold, the backup recognition mode is automatically activated, whereby the backup recognition mode acquires the operator's biometric features through a visual acquisition device.

[0056] Specifically, the backup identification mode uses a wide-angle camera with infrared illumination, deployed on a bracket at the top of the channel. When an abnormal signal quality parameter is detected, a start command is sent to the designated camera; simultaneously, the device control module shuts down the RFID reader to reduce interference.

[0057] Furthermore, when a signal strength value <-70dBm or a bit error rate >10% is received, which corresponds to an alarm indicating that the signal strength is below the first threshold or the signal quality is below the second threshold, the system executes a three-level response: locates the coordinates of the signal attenuation (e.g., 2 meters in front of the K23 cabinet); dispatches the nearest camera to the target area; and initiates the biometric data collection process (e.g., face / fingerprint).

[0058] In some embodiments, to address the device startup delay issue during dynamic inspection and ensure that no biometric data is missed, the following steps are included before S2:

[0059] S201. Based on the equipment layout heat map, predict high-risk areas of signal interference and preload visual acquisition equipment to standby state in the inspection path planning.

[0060] Specifically, laser rangefinders are installed in the computer room to construct a 3D spatial model. The visual acquisition equipment consists of pan-tilt cameras equipped with ±180° horizontal rotation mechanisms. A heatmap engine for the equipment layout analyzes the equipment coordinates and material data (such as metal density / thickness) and sends pre-positioning commands to the cameras via wireless channels.

[0061] Furthermore, the equipment's preloading process extracts the areas to be traversed in the next 30 seconds based on the inspection task path, and marks high-risk areas (such as the G7 area with a metal density of 92%) based on historical signal data, controlling the PTZ camera to turn towards the path entrance in advance.

[0062] In summary, traditional systems suffer from missed captures of critical operations due to camera wake-up time. This solution uses a heat map of equipment layout to predict signal blind spots (such as high-density cabinet clusters), preheating the equipment before the operator reaches the high-risk area and adjusting the vision equipment to standby mode in advance. This significantly shortens the response time of the standby mode, thereby solving the problem of equipment startup delay in dynamic inspections, ensuring no omissions in biometric data collection, improving system robustness, and avoiding the defect of not being able to track paths in real time.

[0063] In this embodiment, the method further includes:

[0064] S3. Generate authentication results by matching pre-stored identity databases with biometric features.

[0065] Specifically, the biometric database is pre-stored on an encrypted SSD. Taking facial recognition as an example, the facial recognition engine receives a video stream, extracts feature vectors, and then calculates the similarity with the biometric database.

[0066] Furthermore, the verification process involves video decoding to obtain facial region images, key point detection to locate predetermined feature points such as pupils / nose tip, and generating feature vectors that are then compared in parallel with 5,000 records in the database.

[0067] S4. If the identity verification is successful, the system will dynamically compensate for any missed registration events caused by signal quality issues and generate a complete inspection log containing timestamps, operator identity, and device location information.

[0068] Specifically, the log server is configured with dual network interface card redundancy. When a sudden change in device status is detected but authentication is successful, the operator's identity and last known location (e.g., 2 minutes ago in rack K22) are retrieved, abnormal data of the target device is analyzed (e.g., a sudden 20% increase in fan power in rack K23), and compensation records are registered in conjunction with the verification information to generate a complete inspection log.

[0069] In summary, when primary identification methods such as RFID fail, the system immediately activates visual recognition to capture the operator's facial / fingerprint features, ensuring uninterrupted identity verification. Upon successful verification, the dynamic compensation module automatically reconstructs any missed registration events, binding the operator's identity, timestamp, and device location to generate logs. Through real-time signal monitoring and automatic switching to backup mode, the system resolves the issue of missed registrations caused by signal interference in densely populated equipment areas, improving audit log integrity by over 90%, eliminating compliance risks due to missed registrations, and requiring no manual intervention throughout the entire process.

[0070] In some embodiments, to address the issue of disconnect between operator identity and device actions and improve the accuracy of compensation logs, the dynamic compensation for missed registration events in S4 specifically includes the following steps:

[0071] S401, Location and time of the most recent successful authentication of the associated operator.

[0072] Specifically, when an abnormality is detected in the equipment (such as a sudden increase of 50% in vibration value) but there is no identity record, the system will obtain the trajectory of all operators within a 3-meter radius of the equipment in the last 2 minutes and filter the last successfully verified record (such as operator A swiping the card at the K22 cabinet at 08:15:32).

[0073] S402. Extract the operating status change data of the target equipment.

[0074] Specifically, extract the status time-series data of abnormal equipment (such as the K22 cabinet) (e.g., the temperature rises from 25°C to 38°C at 08:15:40), and establish the event causal chain, such as the strong correlation between the sudden temperature rise and the sudden increase in vibration.

[0075] S403. Based on the behavior pattern analysis model, generate compensation log entries containing operator identity, operation time, and equipment number.

[0076] Specifically, the historical behavior records of operator A are queried. For example, their inspection operations are concentrated on power modules, with an average operation interval of 4 minutes. The matching degree of the current event is calculated. For example, if the current event operation time difference is 8 seconds (less than the average interval), the target device is the PDU power supply (determined to be consistent with operating habits). Then, a compensation log is generated: "Operator A operated the PDU power supply of cabinet K22 at 08:15:40."

[0077] In summary, the system first binds the operator's last known location / time, then retrieves data on changes in the target device's status (such as a sudden temperature rise indicating someone is operating the device), and then combines this with historical behavior models (such as the operator's inspection habits) to deduce details of missed events. Finally, it achieves precise compensation through spatiotemporal correlation and behavioral analysis, solving the problem of disconnect between operator identity and device actions and improving the accuracy of compensation logs.

[0078] In some embodiments, to improve audit credibility and address the shortcomings of unreliable audit logs, the following steps are also included in S4 after generating a complete inspection log:

[0079] S404. Logs are stored based on blockchain nodes, and each log entry is accompanied by a digital signature of the device and a unique biometric code of the operator.

[0080] Specifically, the device embeds a security chip to generate signatures, and the blockchain nodes adopt a distributed architecture.

[0081] Furthermore, during operation, the security chip generates a signature (including device ID + timestamp + operation code), the server extracts facial features to generate a feature vector, and the blockchain binds and stores these three pieces of data.

[0082] In summary, blockchain storage ensures that logs are immutable, device digital signatures (such as hardware encrypted IDs) verify the authenticity of devices, and biometric codes (such as fingerprint hash values) bind the operator's identity. This enhances audit credibility through tamper-proof evidence storage and eradicates the defect of unreliable audit logs. For example, during regulatory reviews, biometric codes can be used to reverse verify the operator's identity, increasing the cost of forgery.

[0083] In some embodiments, to resolve misidentification, the method of this application further includes the following steps:

[0084] S5. Real-time tracking of the spatial coordinates of each operator through wearable devices.

[0085] S6. When multiple operators are detected to be within the same device's operating radius, the visual acquisition device is forcibly activated to perform face recognition.

[0086] Specifically, the operator wears a positioning wristband, and the equipment is equipped with a 0.8m electronic fence.

[0087] Furthermore, when personnel A / B enter the operating radius of device E1, the visual acquisition device is triggered to capture their faces and mark a precise timestamp, binding only the device operation within 1 second with the identification identity.

[0088] In summary, wearable devices provide real-time feedback of the operator's coordinates. When the system detects multiple people entering the device's operating range simultaneously (e.g., within a 1-meter radius), it forcibly activates facial recognition. Through precise positioning and collaborative triggering mechanisms, it resolves misidentification and eliminates errors such as when person A is operating the device while person B is recorded. For example, if two people approach the server during maintenance, the system instantly captures the actual operator's facial features, ensuring the uniqueness of the identity and device binding.

[0089] In some embodiments, to overcome the inability to distinguish concurrent operations, the following steps are also included after forcibly starting face recognition in S6:

[0090] S601, synchronously acquire trigger signals from the target device's operation interface.

[0091] S602, bind the timestamp of the trigger signal, the interface number, and the identified face identity in a triple binding.

[0092] Specifically, the target device operation interface here takes the device button as an example. The device button integrates a 0-5kg range pressure sensor, and the button number is stored in the chip storage space.

[0093] Furthermore, when the camera captures person A pressing button P1, button P1 integrates a pressure sensor that triggers a threshold (e.g., 0.5 kg), thus binding the relationship to {Face ID: A, Interface Number: P1, Time}.

[0094] In summary, while performing facial recognition, the system records device interface trigger signals (such as button presses and switch toggles) in real time, establishing a triple association between "facial identity - operation action - device interface". By fusing multi-source signals, the system achieves operation traceability, overcoming the defect of not being able to distinguish concurrent operations. For example, when two people are simultaneously repairing different device interfaces, the system can accurately distinguish their respective operation objects, and the audit log can be traced back to the specific interface unit.

[0095] In some embodiments, to address the problem of poor adaptability of static systems, the method of this application further includes the following steps:

[0096] S7. When the equipment layout changes, recalculate the signal coverage model based on the coordinates of the newly added equipment.

[0097] S8. Dynamically adjust the power of the identity recognition device and the acquisition angle of the visual acquisition device.

[0098] Specifically, the device layout here takes the scenario of adding a new device as an example. The new device is pre-installed with Bluetooth 5.1 beacons, and the RFID reader supports power adjustment from 0-30dBm. The main chip's spatial engine receives the beacon coordinates.

[0099] Furthermore, the three-dimensional coordinates of the new cabinet beacon broadcast are added, the engine calculates the signal obstruction effect, automatically increases the power of the reader in the obstructed area to 28dBm, and then adjusts the camera tilt angle to cover the blind spot.

[0100] In summary, after adding or moving equipment, the system reconstructs the signal coverage model (such as RFID reading and writing range) in real time, automatically enhances the power of equipment in high interference areas, and adjusts the camera angle to cover blind spots. It maintains recognition stability through adaptive adjustment, solving the problem of poor adaptability of static systems. For example, when adding a cabinet causes the original recognition blind spot, the system completes parameter optimization within 10 seconds to ensure the recognition rate of the changed area.

[0101] The following describes the data center intelligent identity recognition inspection system provided in the embodiments of this application. The data center intelligent identity recognition inspection system described below can be referred to in correspondence with the data center intelligent identity recognition inspection method described above.

[0102] refer to Figure 2 The data center intelligent identity recognition inspection system includes:

[0103] Signal monitoring module 1 is configured to collect the signal strength and signal quality of the identity recognition device in real time.

[0104] Specifically, the module is equipped with a dual-frequency RFID reader / writer, supporting both 902-928MHz and 2.4GHz frequency bands, and features a built-in spectrum analysis chip. It also includes a signal quality sensor with integrated RSSI (Received Signal Strength Indicator) and BER (Bit Error Rate) detection circuits, corresponding to signal strength and signal quality, with measurement ranges of RSSI: -100~0dBm and BER: 0-20%. Finally, it features an anti-interference antenna array employing a 4×4 MIMO directional antenna.

[0105] Furthermore, the monitoring process polls the reader register every 100ms and transmits data to the edge gateway. The dynamic thresholds are: a first strength threshold: <-75dBm (dense metal area) / <-65dBm (open area); and a second bit error rate threshold: >8% (high interference area) / >5% (normal area). Here, the second threshold is converted to signal quality, as in the previous embodiment, and will not be elaborated further.

[0106] Multi-mode switching module 2 is connected to signal monitoring module 1. When the signal strength is lower than the first threshold or the signal quality is lower than the second threshold, the visual acquisition device is triggered to start.

[0107] Specifically, the module is configured with an intelligent relay group and a vision device controller, wherein the vision device controller uses a pan-tilt camera (horizontal / vertical rotation speed 60° / s).

[0108] Furthermore, it monitors for abnormal signal events (such as BER > 10% for 200ms). At this point, it sends a linkage command to the camera to locate the coordinates based on the signal attenuation point. The preset parameter is that the focus automatically aligns to a human body height of 1.5-2m.

[0109] Biometric storage module 3 stores biometric templates of authorized personnel.

[0110] Specifically, the biometric storage module adopts a sharded storage architecture, in which the basic templates are stored on the central server (5,000 faces / fingerprints each), and the edge nodes retain the 100 most recent high-frequency records in the dynamic cache.

[0111] Furthermore, the verification process involves starting face detection in the video stream, extracting features, and comparing feature similarity.

[0112] Log compensation module 4 is configured to retrieve historical operation data and reconstruct missed inspection events based on the recognition results of the visual acquisition device.

[0113] In summary, the signal monitoring module diagnoses the status of the identification device in real time; the multi-mode switching module activates backup identification; the biometric storage module provides a verification benchmark; and the log compensation module actively retrieves historical data to reconstruct events. Through modular collaboration, a closed-loop self-healing mechanism is achieved. The four modules work together to address the core deficiency of insufficient registration reliability. For example, in the event of RFID failure, the system can complete the entire process from visual recognition to log compensation in a short time, significantly improving fault recovery speed.

[0114] This application provides an electronic device, such as... Figure 3 As shown, Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 3 The illustrated electronic device 300 includes a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, for example, via a bus 302. Optionally, the electronic device 300 may also include a transceiver 304. It should be noted that in practical applications, the transceiver 304 is not limited to one type, and the structure of this electronic device 300 does not constitute a limitation on the embodiments of this application.

[0115] Processor 301 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in connection with the embodiments of this application. Processor 301 may also be a combination that implements computing functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

[0116] Bus 302 may include a pathway for transmitting information between the aforementioned components. Bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. Bus 302 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 3 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0117] The memory 303 may be a ROM (Read-Only Memory) or other type of static storage device capable of storing static information and instructions, RAM (Random Access Memory) or other type of dynamic storage device capable of storing information and instructions, or it may be an EEPROM (Electrically Erasable Programmable Read-Only Memory), a CD-ROM (Compact Disc Read-Only Memory) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto.

[0118] The memory 303 is used to store application code that executes the scheme of the embodiments of this application, and its execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the content shown in the foregoing method embodiments.

[0119] Among them, electronic devices include, but are not limited to: mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), and in-vehicle terminals (such as in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Figure 3 The electronic device shown is merely an example and should not be construed as limiting the functionality or scope of the embodiments described in this application.

[0120] This application provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements the steps of the data center intelligent identity recognition inspection method described above.

[0121] Since the embodiments of the computer-readable storage medium portion correspond to the embodiments of the method portion, please refer to the description of the embodiments of the method portion for the embodiments of the computer-readable storage medium portion.

[0122] It should be understood that although the steps in the flowcharts of the accompanying figures are shown sequentially as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the accompanying figures may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0123] The above are only some embodiments of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A data center intelligent identity recognition inspection method, characterized in that, include: The signal quality parameters of the identity recognition device in the inspection area are monitored in real time. The signal quality parameters include strength value and bit error rate, which correspond to the strength and quality of the signal. When judging whether the signal quality parameters are abnormal, it can be achieved by judging whether the strength value is lower than the first threshold or whether the bit error rate is higher than the second threshold. When the intensity value is lower than the first threshold or the bit error rate is higher than the second threshold, an alarm is triggered, and the backup identification mode is automatically activated. The backup identification mode acquires the operator's biometric features through a visual acquisition device. The automatic activation of the backup identification mode includes locating the signal attenuation coordinates, dispatching the nearest visual acquisition device to the target area, and initiating the biometric feature acquisition process, i.e., a three-level response. Based on the biometric features matched against a pre-stored identity database, an identity verification result is generated. If authentication is successful, the system dynamically compensates for missed registration events caused by signal quality, generating a complete inspection log containing timestamps, operator identity, and device location information. Specifically, the dynamic compensation for missed registration events includes associating the location and time of the operator's most recent successful authentication, extracting the target device's operating status change data, and generating compensation log entries containing operator identity, operation time, and device number based on a behavioral pattern analysis model. Before automatically activating the backup identification mode when the intensity value is lower than the first threshold or the bit error rate is higher than the second threshold, the high-risk area of ​​signal interference is predicted based on the equipment layout heat map, and the visual acquisition device is preloaded to standby state in the inspection path planning. The wearable device tracks the spatial coordinates of each operator in real time. When multiple operators are detected to be within the same operating radius of the device, the visual acquisition device is forcibly activated to perform face recognition and simultaneously collects the trigger signal of the target device's operating interface. The timestamp of the trigger signal, the interface number, and the identified face identity are triple-bound.

2. The method according to claim 1, characterized in that, The method further includes: When the equipment layout changes, the signal coverage model is recalculated based on the coordinates of the newly added equipment. The power of the identity recognition device and the acquisition angle of the visual acquisition device are dynamically adjusted.

3. The method according to claim 1, characterized in that, If authentication is successful, the step of dynamically compensating for missed registration events due to signal quality and generating a complete inspection log containing timestamps, operator identity, and device location information further includes the following after generating the complete inspection log: Logs are stored on blockchain nodes, and each log entry is accompanied by a digital signature of the device and a unique biometric code of the operator.

4. An electronic device, characterized in that, include: One or more processors; One or more memory units; And one or more computer programs, wherein the one or more computer programs are stored in the one or more memories, the one or more computer programs including instructions that, when executed by the one or more processors, cause the electronic device to perform the method as described in any one of claims 1 to 3.

5. A computer-readable storage medium, characterized in that, The storage medium stores a program or instructions that, when executed, implement the method as described in any one of claims 1 to 3.

Images