Holographic traffic signal light system and method

Abstract

The present application relates to the technical field of traffic management infrastructure, and specifically discloses a holographic traffic light system and method, which utilizes a vibration detector to collect vibration wave data in real time, and remotely sends the collected vibration wave data to a third-party platform, then extracts the vibration wave archive data marked as abnormal from the three-party data source as a data set for comparison and analysis, and introduces a deep learning algorithm to extract waveform features of the vibration wave data and each abnormal vibration wave archive data, and conducts dynamic query response analysis based on fluctuation features on the vibration wave data and each abnormal vibration wave archive data to dig out the potential correlation between the real-time vibration wave data and the abnormal vibration wave archive data, thereby realizing intelligent earthquake early warning release. In this way, the problem of false triggering caused by transient interference factors can be effectively overcome, the accuracy and reliability of earthquake early warning can be improved, and the situation of false alarms and missed alarms can be reduced.

Description

Technical Field

[0001] The present application relates to the technical field of traffic management infrastructure, and more particularly, to a holographic traffic signal light system and method. Background Art

[0002] With the acceleration of urbanization and the development of science and technology, the concept of smart cities has gradually become an important direction of modern urban management. The construction of smart cities requires not only improving resource utilization efficiency and optimizing urban management, but also the ability to respond quickly when facing emergencies such as natural disasters. As an important part of urban infrastructure, the function of traffic lights has expanded from a single traffic command to a comprehensive system that integrates multiple intelligent detection and analysis technologies. For example, the invention patent with publication number CN113724512A proposes a holographic traffic light system, which not only has traditional traffic command functions, but also integrates road panoramic camera, microwave vehicle inspection, air quality analysis and earthquake monitoring functions, providing a powerful basic traffic measure for the application of smart cities.

[0003] In this holographic traffic light system, earthquake monitoring is implemented through seismic wave analysis. When the seismic wave analysis data reaches a threshold preset by a third-party platform, the system triggers an earthquake early warning mechanism, promptly notifying relevant departments and the public to take necessary protective measures. This helps improve the city's early warning capabilities and emergency response to earthquake disasters. However, in practice, this earthquake early warning mechanism, based on simple threshold judgments, can be disrupted by various factors, such as short bursts of strong winds, the passage of heavy trucks, or nearby construction activities. These factors can cause abnormal fluctuations in seismic wave data and falsely trigger the earthquake early warning mechanism.

[0004] Therefore, an optimized holographic traffic signal light system and method are desired. Summary of the Invention

[0005] In order to solve the above technical problems, the present application is proposed. The embodiment of the present application provides a holographic traffic light system and method, which uses a vibration detector to collect vibration wave data in real time, and remotely sends the collected vibration wave data to a third-party platform. Then, the vibration wave archive data marked as abnormal is extracted from the three-party data source as a data set for comparison and analysis, and a deep learning algorithm is introduced to extract waveform features of the vibration wave data and each abnormal vibration wave archive data. The vibration wave data and each abnormal vibration wave archive data are subjected to dynamic query response analysis based on fluctuation characteristics to dig out the potential correlation between the real-time vibration wave data and the abnormal vibration wave archive data, thereby realizing intelligent earthquake early warning issuance. In this way, the problem of false triggering caused by transient interference factors can be effectively overcome, the accuracy and reliability of earthquake early warning can be improved, and the situation of false alarms and missed alarms can be reduced.

[0006] Accordingly, according to one aspect of the present application, a holographic traffic light system is provided, which includes a traffic light installed at an intersection and a traffic light control box thereof, a vibration detector and a remote communication module, wherein the vibration detector is used to collect vibration wave data in real time, and send the vibration wave data to a third-party platform through the remote communication module, and the third-party platform is used to compare and analyze the vibration wave data with the third-party data source to obtain a vibration wave analysis result, and the vibration wave analysis result is used to indicate whether to issue an earthquake early warning prompt, wherein the comparison and analysis of the vibration wave data with the third-party data source includes extracting fluctuation characteristics of the vibration wave data and the vibration wave archive data marked as abnormal, and performing dynamic query response analysis based on the fluctuation characteristics to obtain the vibration wave analysis result.

[0007] According to another aspect of the present application, a method for controlling a holographic traffic light is provided, comprising:

[0008] Using a vibration detector to collect vibration wave data in real time, and sending the vibration wave data to a third-party platform via a remote communication module;

[0009] On the third-party platform, the shock wave data is compared and analyzed with the third-party data source to obtain a shock wave analysis result, and the shock wave analysis result is used to indicate whether to issue an earthquake early warning prompt. The comparison and analysis of the shock wave data with the third-party data source includes extracting fluctuation characteristics of the shock wave data and the shock wave archive data marked as abnormal, and performing dynamic query response analysis based on the fluctuation characteristics to obtain the shock wave analysis result.

[0010] Compared with the prior art, the holographic traffic light system and method provided by the present application utilizes a vibration detector to collect vibration wave data in real time, and remotely transmits the collected vibration wave data to a third-party platform. Subsequently, the vibration wave archive data marked as abnormal is extracted from the third-party data source as a data set for comparison and analysis, and a deep learning algorithm is introduced to extract waveform features of the vibration wave data and each abnormal vibration wave archive data. By performing a dynamic query response analysis based on the fluctuation features on the vibration wave data and each abnormal vibration wave archive data, the potential correlation between the real-time vibration wave data and the abnormal vibration wave archive data is excavated, thereby realizing intelligent earthquake early warning issuance. In this way, the problem of false triggering caused by transient interference factors can be effectively overcome, the accuracy and reliability of earthquake early warnings can be improved, and the situation of false alarms and missed alarms can be reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The above and other purposes, features, and advantages of the present application will become more apparent through a more detailed description of the embodiments of the present application in conjunction with the accompanying drawings. The accompanying drawings are intended to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the drawings, the same reference numerals generally represent the same components or steps.

[0012] Figure 1 is a block diagram of a third-party platform in a holographic traffic signal light system according to an embodiment of the present application;

[0013] Figure 2 Schematic diagram of data flow on a third-party platform in a holographic traffic signal system according to an embodiment of the present application;

[0014] Figure 3 4 is a block diagram of a waveform feature query response encoding module in a holographic traffic signal light system according to an embodiment of the present application;

[0015] Figure 4 Flowchart of a method for controlling a holographic traffic light according to an embodiment of the present application. DETAILED DESCRIPTION

[0016] Below, the embodiments of the present application will be described in more detail with reference to the accompanying drawings, and the above-mentioned and other purposes, features, and advantages of the present application will become more apparent. Obviously, the described embodiments are only some embodiments of the present application, rather than all embodiments of the present application, and it should be understood that the present application is not limited to the example embodiments described herein.

[0017] As mentioned in the background technology above, patent CN113724512A proposes a holographic traffic light system, which includes a traffic light installed at an intersection and its traffic light control box, a vibration detector and a remote communication module. In addition to the traditional traffic command function, it also integrates the earthquake monitoring function, providing a powerful basic traffic measure for the application of smart cities.

[0018] In this holographic traffic light system, earthquake monitoring is implemented through seismic wave analysis. When the seismic wave analysis data reaches a threshold preset by a third-party platform, the system triggers an earthquake early warning mechanism, promptly notifying relevant departments and the public to take necessary protective measures. This helps improve the city's early warning capabilities and emergency response to earthquake disasters. However, in practice, this earthquake early warning mechanism, based on simple threshold judgments, can be disrupted by various factors, such as short bursts of strong winds, the passage of heavy trucks, or nearby construction activities. These factors can cause abnormal fluctuations in seismic wave data and falsely trigger the earthquake early warning mechanism.

[0019] In response to the above technical problems, the present application proposes an optimized holographic traffic light system based on the above scheme, which uses a vibration detector to collect vibration wave data in real time, and remotely sends the collected vibration wave data to a third-party platform. Then, the vibration wave archive data marked as abnormal is extracted from the three-party data source as a data set for comparison and analysis, and a deep learning algorithm is introduced to extract waveform features of the vibration wave data and each abnormal vibration wave archive data. The vibration wave data and each abnormal vibration wave archive data are subjected to dynamic query response analysis based on fluctuation characteristics to explore the potential correlation between the real-time vibration wave data and the abnormal vibration wave archive data, thereby realizing intelligent earthquake early warning issuance. In this way, the problem of false triggering caused by transient interference factors can be effectively overcome, the accuracy and reliability of earthquake early warning can be improved, and the situation of false alarms and missed alarms can be reduced.

[0020] Specifically, in the technical solution of the present application, the vibration detector is used to collect vibration wave data in real time, and send the vibration wave data to a third-party platform through a remote communication module. The third-party platform is used to compare and analyze the vibration wave data with the third-party data source to obtain a vibration wave analysis result. The vibration wave analysis result is used to indicate whether to issue an earthquake early warning prompt. The comparison and analysis of the vibration wave data with the third-party data source includes extracting fluctuation characteristics of the vibration wave data and the vibration wave archived data marked as abnormal, and performing dynamic query response analysis based on the fluctuation characteristics to obtain the vibration wave analysis result.

[0021] In practice, the performance and selection of vibration detectors, as front-end equipment for data acquisition, are crucial. Currently, there are many types of vibration detectors on the market, such as accelerometers and displacement sensors based on the piezoelectric effect. In this system, high-precision, wide-bandwidth accelerometers are selected as vibration detectors. This type of accelerometer can sensitively sense extremely subtle vibration changes on the Earth's surface. Its operating principle is based on the characteristic that piezoelectric materials produce changes in surface charge when deformed by external forces. When the accelerometer is fixed to a monitoring location such as the ground or a building foundation, the acceleration changes caused by ground vibrations will cause the piezoelectric material to produce corresponding changes in charge. This charge change is converted into an electrical signal output proportional to the vibration acceleration through a specific circuit.

[0022] To achieve real-time acquisition of seismic wave data, an efficient data acquisition mechanism must be established. The electrical signal output by the vibration detector is first processed by a signal conditioning circuit. The main function of the signal conditioning circuit is to amplify and filter the raw electrical signal. Because the electrical signal output by the vibration detector is typically weak and may be mixed with various noise interference, the amplification circuit amplifies the signal to an amplitude range suitable for subsequent processing. Simultaneously, the filtering circuit uses a bandpass filter to filter out interfering signals such as high-frequency noise and low-frequency drift based on the frequency characteristics of seismic waves (typically between 0.1Hz and 10Hz), retaining only the significant frequency components related to the seismic waves. The conditioned electrical signal enters the analog-to-digital converter (ADC). The ADC converts the continuous analog electrical signal into a discrete digital signal for processing and storage by the computer system. To meet the requirements of real-time acquisition, a high-speed, high-precision ADC chip is selected. The sampling frequency can be set according to actual needs, generally ranging from several hundred Hz to several thousand Hz, to ensure accurate capture of the dynamic changes of the seismic waves. For example, setting the sampling frequency to 1000 Hz means that 1000 vibration wave data points can be collected per second, which can restore the waveform of the vibration wave more finely.

[0023] After the digital signal is converted by the ADC, it enters the data acquisition controller. Data acquisition controllers are typically implemented based on microcontrollers (MCUs) or digital signal processors (DSPs). In this system, a high-performance DSP is selected as the data acquisition controller. The DSP has powerful digital signal processing capabilities and fast data processing speeds, enabling it to efficiently process and store large amounts of vibration wave data. The data acquisition controller packages and stores the digital signal converted by the ADC according to a preset acquisition strategy and monitors the data acquisition status in real time. To ensure data integrity and accuracy, the data acquisition controller also has data verification and error correction functions. For example, it uses a cyclic redundancy check (CRC) algorithm to verify the collected data. If data errors or loss are detected, timely measures such as retransmission can be taken to correct them.

[0024] After the vibration detector collects vibration wave data in real time, it needs to send the data to a third-party platform via a remote communication module. The selection of a remote communication module needs to consider factors such as communication distance, data transmission rate, and stability. In this system, a 5G wireless communication module is used as the primary method of remote communication. 5G communication technology has a high data transmission rate and can meet the needs of real-time, large-scale transmission of vibration wave data. The 5G wireless communication module establishes a connection with the mobile communication base station via an antenna, encapsulating and transmitting the vibration wave data packaged by the data acquisition controller according to the 5G communication protocol. During the data transmission process, to ensure the security and reliability of the data, encrypted transmission technologies such as the SSL / TLS encryption protocol are used to encrypt the transmitted data to prevent the data from being stolen or tampered with during transmission.

[0025] When integrating with third-party platforms, thorough communication and negotiation with the third-party platform is essential to clarify key information such as data transmission interface specifications, data formats, and communication protocols. Based on the data interface documentation provided by the third-party platform, a dedicated data transmission program should be developed. This data transmission program, running on the data acquisition controller, is responsible for converting and packaging locally collected vibration wave data into the format required by the third-party platform. For example, the third-party platform may require data transmission in JSON format. The data transmission program converts the collected vibration wave data into a JSON-compliant data structure and adds necessary metadata, such as data collection time, location, and device serial number. The data transmission program then transmits the packaged data to the third-party platform via the 5G wireless communication module. During data transmission, the data transmission program monitors the data transmission status in real time, including transmission progress and success. If data transmission fails, the data transmission program retransmits according to a pre-defined retry strategy to ensure that the data reaches the third-party platform accurately.

[0026] To ensure the stability and reliability of the entire data collection and transmission process, a comprehensive monitoring and maintenance mechanism is also necessary. Regarding hardware, regular inspection and maintenance of equipment such as vibration detectors, signal conditioning circuits, ADCs, and 5G wireless communication modules are essential to ensure proper operation. For example, the vibration detectors should be checked for secure installation, looseness, or damage; the electronic components of the signal conditioning circuits should be inspected for signs of aging or damage; and the signal strength of the 5G wireless communication module should be regularly tested to ensure communication quality. Regarding software, the running status of the data collection and transmission programs should be monitored in real time, with logging and other means used to record key events and error messages during program operation. Any program anomalies should be promptly identified and corrected. Furthermore, regular performance testing of the data collection and transmission system should be conducted, focusing on metrics such as data acquisition accuracy, transmission rate, and packet loss rate. System optimization and adjustments should be made based on the test results.

[0027] Figure 1 4 is a block diagram of a third-party platform in a holographic traffic light system according to an embodiment of the present application. Figure 2 This is a schematic diagram of data flow on a third-party platform in a holographic traffic light system according to an embodiment of the present application. Figure 1 and Figure 2 As shown, the third-party platform 100 includes: an abnormal shock wave archive data extraction module 110, which is used to extract the shock wave archive data marked as abnormal from the third-party data source to obtain a series of shock wave archive data; a waveform feature extraction module 120, which is used to extract waveform features from the shock wave data and each shock wave archive data in the series of shock wave archive data to obtain a series of shock wave detection data waveform feature coding vectors and archived shock wave data waveform feature coding vectors; a waveform feature query response coding module 130, which is used to perform dynamic weight-driven feature search interactive response coding on the series of shock wave detection data waveform feature coding vectors and archived shock wave data waveform feature coding vectors to obtain a shock wave query response coding vector; and an analysis result generation module 140, which is used to determine the shock wave analysis result based on the shock wave query response coding vector.

[0028] In the third-party platform 100 of the above-mentioned holographic traffic light system, the abnormal shock wave archive data extraction module 110 is used to extract the shock wave archive data marked as abnormal from the third-party data source to obtain a series of shock wave archive data. Specifically, the third-party data source is a data repository collected, organized and labeled by a professional organization or system. Based on the principles of seismology, geological structure knowledge and a large amount of past experience in monitoring geological activities such as earthquakes, it labels the shock wave data and marks the shock wave data related to abnormal situations such as earthquakes as abnormal. This application provides an important reference standard for the analysis of current real-time shock wave data by using the shock wave archive data marked as abnormal as a reference, which helps to more accurately identify the shock wave characteristics related to earthquakes.

[0029] Specifically, before establishing a stable and reliable connection with a third-party data source, a comprehensive assessment of the data source is required, including its data quality, data update frequency, data storage format, and the type of data interface provided. For example, some data sources may use relational databases to store data and provide a data interface based on the SQL query language; while others may store data in the form of a file system and access the data through a specific API (application programming interface). Based on the assessment results, select the appropriate technical means to connect with the data source. If the data source provides an SQL interface, you can use the corresponding database connection tool, such as using the SQLAlchemy library in Python, to establish a connection to the data source database by configuring the correct database connection string. The connection string contains key information such as the database type (such as MySQL, PostgreSQL, etc.), server address, port number, database name, user name, and password to ensure accurate access to the data source.

[0030] Because the data extraction process involves multiple steps, including network communication, data source access, and data processing, a comprehensive error handling and logging mechanism is also necessary. Examples include network connection interruptions, data source server failures, and data format mismatches. To address these potential issues, the data extraction program must have robust error handling capabilities. When errors occur, the program must promptly capture exception information and implement appropriate recovery measures based on the error type. For example, if the network connection is interrupted, the program can attempt to reestablish the connection. If the connection remains unreestablished after a certain number of retries, the program will log the error message and terminate the data extraction process. Furthermore, to facilitate subsequent troubleshooting and system optimization, every key operation and event during the data extraction process must be recorded in detail, including both successful operations and any errors. Log records should include detailed information such as operation time, operation content, data involved, and error messages. By analyzing the log files, problems can be quickly identified and targeted improvements and optimizations can be made to the data extraction process.

[0031] In the third-party platform 100 of the holographic traffic light system, the waveform feature extraction module 120 is configured to extract waveform features from the shock wave data and each archived shock wave data in the sequence of archived shock wave data to obtain a sequence of waveform feature encoding vectors for the shock wave detection data and waveform feature encoding vectors for the archived shock wave data. In a specific example of the present application, the waveform feature extraction module is configured to use a CNN-based waveform feature extractor to perform feature extraction on the shock wave data and each archived shock wave data in the sequence of archived shock wave data to obtain a sequence of waveform feature encoding vectors for the shock wave detection data and waveform feature encoding vectors for the archived shock wave data. It should be understood that since shock wave data is typical time series data, it exhibits certain structures and patterns in the temporal dimension. For example, before an earthquake, shock waves exhibit different frequencies, amplitude variations, and waveform characteristics. Therefore, to effectively capture the fluctuation patterns of shock wave data, the present application employs a CNN (convolutional neural network) model to extract the temporal fluctuation features of the shock wave data and each archived shock wave data. Specifically, the CNN model has excellent performance in processing data with time structure. In this application, the CNN model uses a one-dimensional convolution kernel to slide on the time dimension of the shock wave data and each shock wave archive data, and extracts the fluctuation characteristics of the local time segment, so that it can capture the subtle changes and patterns of the shock wave data in the time dimension. In addition, by setting one-dimensional convolution kernels of different lengths, it is possible to extract fluctuation characteristics of different time scales, so as to more comprehensively understand the characteristics of the shock wave data. For example, a smaller convolution kernel can capture the high-frequency detail characteristics of the shock wave, such as instantaneous shock mutations; while a larger convolution kernel can extract the low-frequency overall trend characteristics, such as long-term shock fluctuations. In this way, the dynamic fluctuation pattern of the shock wave data can be fully explored, and a series of shock wave detection data waveform feature coding vectors and archived shock wave data waveform feature coding vectors containing shock wave time series fluctuation information can be obtained as an important basis for identifying seismic signals.

[0032] In the third-party platform 100 of the holographic traffic light system, the waveform feature query response encoding module 130 is configured to perform dynamic weight-driven feature search interactive response encoding on the sequence of the waveform feature encoding vectors of the seismic wave detection data and the waveform feature encoding vectors of the archived seismic wave data to obtain a seismic wave query response encoding vector. Specifically, the module further performs semantic query interactive response analysis on the waveform features of the real-time seismic wave detection data and the waveform features of each archived seismic wave data marked as abnormal, thereby mining the waveform similarities and correlations between the real-time seismic wave data and the archived anomalous seismic wave data, thereby determining whether the waveform variation pattern of the currently detected seismic wave data matches the known waveform variation pattern of seismic waves.

[0033] Figure 3 FIG. 1 is a block diagram of a waveform feature query response encoding module in a holographic traffic signal light system according to an embodiment of the present application. Figure 3 As shown, the waveform feature query response encoding module 130 includes: a deep implicit feature extraction unit 131, which is used to perform deep implicit feature extraction on the vibration wave detection data waveform feature encoding vector and each archived vibration wave data waveform feature encoding vector in the series of the archived vibration wave data waveform feature encoding vectors to obtain a series of vibration wave detection data waveform deep implicit feature encoding vectors and archived vibration wave data waveform deep implicit feature encoding vectors; a semantic response interaction encoding unit 132, which is used to perform semantic response decision anchor encoding on the vibration wave detection data waveform deep implicit feature encoding vector and each archived vibration wave data waveform deep implicit feature encoding vector in the series of the archived vibration wave data waveform deep implicit feature encoding vectors to obtain a series of vibration wave waveform semantic feature query response anchor encoding matrices; a dynamic aggregation encoding unit 133, which is used to perform dynamic aggregation encoding on the series of vibration wave waveform semantic feature query response anchor encoding matrices based on the feature contribution of each vibration wave waveform semantic feature query response anchor encoding matrix in the series of the vibration wave waveform semantic feature query response anchor encoding matrix to obtain the vibration wave query response encoding vector.

[0034] In a specific example of the present application, the deep implicit feature extraction unit 131 is used to use a deep implicit feature extraction module based on a fully connected coding network to process the vibration wave detection data waveform feature coding vector and each archived vibration wave data waveform feature coding vector in the series of the archived vibration wave data waveform feature coding vectors to obtain the vibration wave detection data waveform deep implicit feature coding vector and the series of the archived vibration wave data waveform deep implicit feature coding vector, which can be expressed as follows:

[0035] V2={v 21 ,v 22 ,...,v 2i ,...,v 2n}

[0036]

[0037] Among them, V2 represents the sequence of waveform feature coding vectors of archived shock wave data, v 21 、v 22 、v 2i and v 2nrepresents the first, second, i-th and n-th archived shock wave data waveform feature coding vectors in the sequence of archived shock wave data waveform feature coding vectors, respectively, n is the number of vectors in the sequence of archived shock wave data waveform feature coding vectors, V1 represents the shock wave detection data waveform feature coding vector, W1 represents the shock wave detection data waveform feature weight matrix, W2 represents the archived shock wave data waveform feature weight matrix, b1 represents the shock wave detection data waveform feature bias term, b2 represents the archived shock wave data waveform feature bias term, sigmoid(·) represents the sigmoid activation function, V d1 Represents the waveform depth implicit feature encoding vector of the vibration wave detection data, v d2i Indicates v 2i The corresponding archived shock wave data waveform depth implicit feature encoding vector.

[0038] Here, in order to enhance the feature expression capability of real-time shock wave data and each shock wave archived data marked as abnormal, the present application first uses a fully connected coding network to perform deep implicit feature extraction on the shock wave detection data waveform feature coding vector and each archived shock wave data waveform feature coding vector, respectively, so as to utilize the powerful nonlinear mapping capability of the fully connected coding network to learn the temporal nonlinear correlation of the global waveform features of the shock wave data, and more finely characterize the fluctuation characteristics of the shock wave data, thereby obtaining a series of deep implicit feature coding vectors of the shock wave detection data waveform and deep implicit feature coding vectors of the archived shock wave data waveform.

[0039] In a specific example of the present application, the semantic response interaction encoding unit 132 is expressed as follows:

[0040]

[0041] in,(·) T represents the transpose of a vector, Represents vector multiplication, S is v d2i The characteristic scale value, M 12i Indicates V d1 and v d2i The vibration wave waveform semantic feature query response anchor encoding matrix.

[0042] That is, the waveform depth implicit feature coding vector of the vibration wave detection data and the waveform depth implicit feature coding vector of each archived vibration wave data are further semantically response anchored and encoded respectively, and feature interaction is performed through multiplication operations between vectors to capture the potential correlation pattern of waveform features between real-time vibration wave data and each vibration wave archived data marked as abnormal, thereby generating a series of vibration wave waveform semantic feature query response anchor coding matrices.

[0043] In a specific example of the present application, the dynamic aggregation coding unit 133 includes: a feature contribution measurement subunit, which is used to calculate the decision anchor adaptive splicing factor of each vibration wave waveform semantic feature query response anchor coding matrix based on the feature distribution of each vibration wave waveform semantic feature query response anchor coding matrix in the series of the vibration wave waveform semantic feature query response anchor coding matrix to obtain a series of vibration wave query response decision anchor adaptive splicing factors. More specifically, the sum of the feature variance and the drift coefficient of the vibration wave waveform semantic feature query response anchor coding matrix is used as the numerator, and the square of the difference between the maximum eigenvalue and the feature mean of the vibration wave waveform semantic feature query response anchor coding matrix is calculated and multiplied by the number of its eigenvalues, and the drift coefficient and twice the feature variance are added as the denominator to obtain the vibration wave query response decision anchor adaptive splicing factor, which is expressed as follows:

[0044]

[0045] k=count(M 12i )

[0046] Where count(·) represents the number of elements in the calculation matrix, k represents the difference amplification coefficient, that is, the number of eigenvalues of the anchor coding matrix of the vibration waveform semantic feature query response, σ 2 represents the characteristic variance of the anchor coding matrix of the vibration waveform semantic feature query response, ∈ represents the drift coefficient of the anchor coding matrix of the vibration waveform semantic feature query response, μ represents the characteristic mean of the anchor coding matrix of the vibration waveform semantic feature query response, max(·) is the maximum value function, E 12i Indicates M 12i The corresponding shock wave query response decision anchor adaptive splicing factor.

[0047] Here, in order to more accurately measure the degree of correlation between the waveform features of real-time shock wave data and each shock wave archive data, this application further introduces a dynamic weight-driven feature interaction response aggregation coding method. Based on the feature distribution of each shock wave waveform semantic feature query response anchor coding matrix, its decision anchor adaptive splicing factor is calculated, and a sequence of shock wave query response decision anchor adaptive splicing factors is generated. Here, the shock wave query response decision anchor adaptive splicing factor is used to reflect the semantic similarity in waveform features between each shock wave archive data marked as abnormal and the real-time shock wave data, as well as the dominance of the semantic interaction information between the two in the global context. It serves as the weight basis for subsequent feature interaction response aggregation coding.

[0048] In particular, here, the drift coefficient is used to smooth the feature distribution fluctuation of the vibration waveform semantic feature query response anchor coding matrix. In a preferred example of the present application, the calculation process of the drift coefficient can be expressed as follows:

[0049]

[0050] Wherein, η is the intermediate transition value of the feature distribution equilibrium state of the vibration waveform semantic feature query response anchor coding matrix, m ij is the matrix M 12i The j-th eigenvalue of , where e is a natural constant.

[0051] Preferably, for the drift coefficient ∈ in the adaptive splicing factor of the shock wave query response decision anchor, the eigenvalue set distribution of the shock wave waveform semantic feature query response anchor coding matrix transitions from a state of weak global interpretability of the mean to a state of strong local interpretability of the maximum value. This application enhances the global dominance basis of the shock wave waveform semantic feature query response anchor coding matrix by introducing a weak to strong interpretability generalization of the drift coefficient ∈.

[0052] Specifically, η is used as the intermediate state transition representation from weak interpretability to strong interpretability, and each eigenvalue m of the anchor encoding matrix is queried for the semantic feature of the vibration waveform. ij , and use it as the importance score of the shock wave waveform semantic feature query response anchor encoding matrix for the global smooth state transition to globally control the importance score weight of the intermediate state transition η relative to the global state transition, so as to achieve an interpretable generalized inference of the weight-based adaptive splicing factor of the shock wave query response decision anchor.

[0053] In a specific example of the present application, the dynamic aggregation coding unit 133 further includes: a weighting subunit, which is used to perform weighting processing on the series of the shock wave query response decision anchor adaptive splicing factors based on the Softmax function to obtain a series of shock wave query response decision anchor adaptive splicing weight factors; an aggregation coding subunit, which is used to perform weighted fusion and feature reshaping on the series of the shock wave waveform semantic feature query response anchor coding matrix based on the series of the shock wave query response decision anchor adaptive splicing weight factors to obtain the shock wave query response coding vector, which is expressed as follows:

[0054] a 12i =softmax(E 12i )

[0055]

[0056] Among them, softmax(·) represents the normalized exponential function, a12i Represents the matrix M 12i The adaptive splicing weight factor of the shock wave query response decision anchor, M c represents the vibration waveform semantic feature query response anchor encoding fusion matrix, reshape(·) represents the feature shape reshaping function, v c Represents the shock wave query response encoding vector.

[0057] Specifically, the Softmax function is used to normalize the sequence of adaptive splicing factors of the vibration wave query response decision anchors into a probability distribution with a range of values in the interval [0, 1]. This serves as the weight coefficient for the subsequent feature dynamic response aggregation coding, amplifying the significant differences between the individual vibration wave waveform semantic feature query response anchor coding matrices to enhance the distinguishability and expressiveness of the features. Finally, based on the generated weight coefficients, a weighted fusion is performed on the sequence of vibration wave waveform semantic feature query response anchor coding matrices. This adaptively focuses on the waveform features of the vibration wave archive data that are highly correlated with the waveform features of the real-time vibration wave data, thereby generating the most responsive feature representation and obtaining the vibration wave query response coding vector.

[0058] In the third-party platform 100 of the above-mentioned holographic traffic light system, the analysis result generation module 140 is used to determine the shock wave analysis result based on the shock wave query response code vector. In a specific example of the present application, the analysis result generation module 140 is used to: input the shock wave query response code vector into the classifier-based abnormality diagnosis module to obtain the shock wave analysis result. It should be understood that after the above processing, the shock wave query response code vector contains the waveform association response information between the real-time shock wave data and each shock wave archive data marked as abnormal. After receiving the shock wave query response code vector, the classifier determines whether the real-time shock wave data conforms to the known earthquake signal characteristic pattern by learning its characteristic distribution pattern, thereby determining whether to issue an earthquake warning prompt. Once the classifier determines that the current shock wave data is an earthquake signal, it will immediately trigger an alarm and send an earthquake warning prompt to the surrounding area through the holographic traffic light so that evacuation measures can be taken in time to minimize the losses caused by the earthquake disaster.

[0059] In summary, the holographic traffic light system according to the embodiment of the present application is explained, which uses a vibration detector to collect vibration wave data in real time, and remotely sends the collected vibration wave data to a third-party platform. Then, the vibration wave archive data marked as abnormal is extracted from the three-party data source as a data set for comparison and analysis, and a deep learning algorithm is introduced to extract waveform features of the vibration wave data and each abnormal vibration wave archive data. The vibration wave data and each abnormal vibration wave archive data are subjected to dynamic query response analysis based on fluctuation features to explore the potential correlation between the real-time vibration wave data and the abnormal vibration wave archive data, thereby realizing intelligent earthquake early warning issuance. In this way, the problem of false triggering caused by transient interference factors can be effectively overcome, the accuracy and reliability of earthquake early warning can be improved, and the situation of false alarms and missed alarms can be reduced.

[0060] Furthermore, the present application also provides a method for controlling a holographic traffic light.

[0061] Figure 4 FIG. 1 is a flow chart of a method for controlling a holographic traffic light according to an embodiment of the present application. Figure 4 As shown, the control method of the holographic traffic light includes the following steps: S1, using a vibration detector to collect vibration wave data in real time, and sending the vibration wave data to a third-party platform through a remote communication module; S2, on the third-party platform, comparing and analyzing the vibration wave data with three-party data sources to obtain a vibration wave analysis result, and the vibration wave analysis result is used to indicate whether to issue an earthquake early warning prompt, wherein the comparing and analyzing the vibration wave data with the three-party data sources includes extracting fluctuation characteristics of the vibration wave data and the vibration wave archive data marked as abnormal, and performing dynamic query response analysis based on the fluctuation characteristics to obtain the vibration wave analysis result.

[0062] Here, those skilled in the art will appreciate that the specific operations of each step in the above-mentioned method for controlling a holographic traffic light have been described in detail in the above reference. Figures 1 to 3 The holographic traffic light system has been described in detail in the description of the holographic traffic light system, and therefore, its repeated description will be omitted.

[0063] The basic principles of the present invention have been described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, and effects mentioned in the present invention are merely illustrative and not restrictive, and should not be construed as necessarily possessed by each embodiment of the present invention. Furthermore, the specific details of the above embodiments are provided for illustrative purposes and to facilitate understanding, and are not intended to be limiting. These details do not necessarily limit the present invention to being implemented using these specific details.

Claims

1. A holographic traffic light system, comprising a traffic light installed at an intersection and its control box, a vibration detector, and a remote communication module, characterized in that: The vibration detector is used to collect vibration wave data in real time and send the vibration wave data to a third-party platform via the remote communication module. The third-party platform is used to compare and analyze the vibration wave data with the third-party data source to obtain a vibration wave analysis result. The vibration wave analysis result is used to indicate whether to issue an earthquake early warning prompt. The comparison and analysis of the vibration wave data with the third-party data source includes extracting fluctuation characteristics from the vibration wave data and archived vibration wave data marked as abnormal, and performing dynamic query response analysis based on the fluctuation characteristics to obtain the vibration wave analysis result. The third-party platform includes: An abnormal shock wave archive data extraction module is used to extract the shock wave archive data marked as abnormal from the three-party data source to obtain a sequence of shock wave archive data; a waveform feature extraction module for extracting waveform features from the shock wave data and each shock wave archive data in the series of shock wave archive data to obtain a series of shock wave detection data waveform feature coding vectors and archived shock wave data waveform feature coding vectors; The waveform feature query response encoding module includes: a depth implicit feature extraction unit, configured to perform depth implicit feature extraction on each of the waveform feature code vectors of the vibration wave detection data and the archived vibration wave data waveform feature code vector sequence to obtain a depth implicit feature code vector of the vibration wave detection data waveform and a sequence of the depth implicit feature code vector of the archived vibration wave data waveform; a semantic response interaction coding unit, configured to perform semantic response decision anchor coding on each archived shock wave data waveform depth implicit feature coding vector in the sequence of the shock wave detection data waveform depth implicit feature coding vector and the archived shock wave data waveform depth implicit feature coding vector, respectively, to obtain a sequence of shock wave waveform semantic feature query response anchor coding matrices; Dynamically aggregated coding units, including: The feature contribution measurement subunit is used to use the sum of the feature variance and the drift coefficient of the shock wave waveform semantic feature query response anchor coding matrix as the numerator, and calculate the square of the difference between the maximum eigenvalue and the feature mean of the shock wave waveform semantic feature query response anchor coding matrix multiplied by the number of its eigenvalues, and then add the drift coefficient and twice the feature variance as the denominator to obtain the shock wave query response decision anchor adaptive splicing factor, which is expressed as follows: ； in, Indicates the number of elements in the calculation matrix, represents the difference amplification coefficient, i.e., the number of eigenvalues of the anchor coding matrix of the vibration waveform semantic feature query response, represents the feature variance of the anchor coding matrix of the vibration waveform semantic feature query response, represents the drift coefficient of the vibration waveform semantic feature query response anchor coding matrix, represents the feature mean of the anchor coding matrix of the vibration waveform semantic feature query response, To obtain the maximum value function, express The corresponding shock wave query response decision anchor adaptive splicing factor; The calculation process of the drift coefficient is expressed by the formula: ； ； in, is the intermediate transition representation value of the feature distribution equilibrium state of the vibration waveform semantic feature query response anchor coding matrix, is a matrix No. eigenvalues, is a natural constant; A weighting subunit, configured to perform weighting processing on the series of the shock wave query response decision anchor adaptive splicing factors based on a Softmax function to obtain a series of shock wave query response decision anchor adaptive splicing weight factors; An aggregation coding subunit, configured to perform weighted fusion and feature reshaping on the sequence of the shock wave waveform semantic feature query response anchor coding matrix based on the sequence of the shock wave query response decision anchor adaptive splicing weight factors to obtain a shock wave query response coding vector; The analysis result generating module is used to determine the shock wave analysis result based on the shock wave query response code vector.

2. The holographic traffic signal light system according to claim 1, characterized in that: The waveform feature extraction module is used to: A waveform feature extractor based on a CNN model is used to extract features from the shock wave data and each shock wave archive data in the series of shock wave archive data to obtain a series of the shock wave detection data waveform feature coding vectors and the archived shock wave data waveform feature coding vectors.

3. The holographic traffic signal light system according to claim 2, characterized in that: The depth implicit feature extraction unit is used to: A deep implicit feature extraction module based on a fully connected coding network is used to process the vibration wave detection data waveform feature coding vector and each archived vibration wave data waveform feature coding vector in the series of the archived vibration wave data waveform feature coding vectors to obtain the vibration wave detection data waveform deep implicit feature coding vector and the series of the archived vibration wave data waveform deep implicit feature coding vector.

4. The holographic traffic signal light system according to claim 3, characterized in that: The drift coefficient is used to smooth the feature distribution fluctuation of the vibration wave waveform semantic feature query response anchor coding matrix.

5. The holographic traffic signal light system according to claim 4, characterized in that: The analysis result generating module is used to: The shock wave query response encoding vector is input into a classifier-based abnormality diagnosis module to obtain the shock wave analysis result.

6. A method for controlling a holographic traffic light, executed by the system according to any one of claims 1 to 5, characterized in that: include: Using a vibration detector to collect vibration wave data in real time, and sending the vibration wave data to a third-party platform via a remote communication module; On the third-party platform, the shock wave data is compared and analyzed with the third-party data source to obtain a shock wave analysis result, and the shock wave analysis result is used to indicate whether to issue an earthquake early warning prompt. The comparison and analysis of the shock wave data with the third-party data source includes extracting fluctuation characteristics of the shock wave data and the shock wave archive data marked as abnormal, and performing dynamic query response analysis based on the fluctuation characteristics to obtain the shock wave analysis result.

Images