Infringement clue tracking data processing system and method based on edge calculation

Abstract

The invention discloses an infringement clue tracking data processing system and method based on edge calculation, and belongs to the technical field of electric digital data processing. The system comprises a data acquisition module, a distributed data processing module, a data transmission module, a central server and a user terminal module. According to the invention, the collected original data is preprocessed and preliminarily analyzed by using the edge computing node, the preprocessed data is transmitted from the distributed data processing module to the central server by using the data transmission module, and the data is comprehensively analyzed by using the deep analysis model through the central server. Therefore, the accuracy and the reliability of data analysis are improved, the processing burden of the central server is reduced, the real-time performance and the response speed of the system are further improved, and the problem of low data processing efficiency in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of electrical digital data processing, and in particular to a data processing system and method for tracking infringement clues based on edge computing. Background Art

[0002] Copyright is the legal ownership of the right to reproduce computer programs, literary works, musical works, photos, games, movies, etc. Copyright can be used to express the rights enjoyed by the creator due to his literary and artistic works. Generally speaking, copyright belongs to the creative author, and stealing copyright constitutes an infringement. With the development of Internet of Things and big data technologies, tracking infringement clues has become increasingly important. Edge computing refers to an open platform that integrates network, computing, storage, and application core capabilities on the side close to the object or data source to provide the nearest-end services nearby.

[0003] The existing infringement clue tracking systems transmit data to a central server through data collection devices for unified processing and analysis, and then monitor personnel view video and audio data in real time to manually analyze and record infringement acts.

[0004] For example, the invention patent with the publication number: CN107506503B discloses an intellectual property appearance infringement analysis and management system, including: a product information entry module for allowing users to enter product information of suspected infringing products, where the product information includes at least the product name and six views; a patent data acquisition module configured with a cloud database, which docks with the patent database of the State Intellectual Property Office through an API interface to obtain corresponding appearance patent data and store it; a patent retrieval module for searching for relevant appearance patents from the cloud database based on the product name of the suspected infringing product entered by the image acquisition module to form primary retrieval data; a patent matching module for matching the six views of the suspected infringing product entered by the image acquisition module with all the patents in the primary retrieval data based on image recognition technology and generating corresponding matching results.

[0005] For example, the invention patent with the publication number: CN109829265B discloses an infringement evidence collection method and system for audio works, including: respectively sampling a comparison object and a to-be-determined object of an audio work, extracting sampling signals, generating a sampling curve graph, analyzing the sampling curve graphs of the comparison object and the to-be-determined object, and respectively generating envelope lines, segmenting the envelope lines by time averaging, respectively calculating the tangent slopes of the intersection points of each time segment line and the envelope line, and using the slope analysis of the comparison object and the to-be-determined object to determine the similarity between the comparison object and the to-be-determined object.

[0006] However, in the process of implementing the technical solutions of the present invention in the embodiments of the present application, it is found that the above technologies have at least the following technical problems:

[0007] In the prior art, all data acquisition devices transmit data to a central server, relying on monitoring personnel for unified processing and analysis. The data acquisition devices regularly collect and upload data, resulting in the problem of low data processing efficiency. Summary of the Invention

[0008] By providing a data processing system and method for tracking infringement clues based on edge computing, the embodiments of the present application solve the problem of low data processing efficiency in the prior art and improve the real-time performance and response speed of the system.

[0009] The embodiments of the present application provide a data processing system for tracking infringement clues based on edge computing, including: a data acquisition module, a distributed data processing module, a data transmission module, a central server, and a user terminal module. Among them, the data acquisition module is used to collect various forms of raw data at the infringement scene; the distributed data processing module is used to preprocess and preliminarily analyze the collected raw data using edge computing nodes; the data transmission module is used to transmit the preprocessed data from the edge computing nodes to the central server; the central server is used to receive and process data from each edge computing node and perform in-depth analysis; the user terminal module is used for users to query and view infringement clue tracking reports.

[0010] Further, the data acquisition module includes a video acquisition unit, an audio acquisition unit, and an image acquisition unit. The video acquisition unit is used to collect real-time video data at the scene in real time through the installation of high-resolution cameras, network cameras, and infrared cameras, and perform real-time video stream transmission; the audio acquisition unit is used to arrange omnidirectional microphones and directional microphones according to the environment, and by enabling noise suppression technology, collect audio data in a noisy environment, perform audio compression and echo cancellation processing, maintain the audio transmission quality, transmit the audio stream in real time, and perform audio signal digitization processing to collect audio data at the scene; the image acquisition unit is set to have a timed shooting function to collect images at specific time intervals and perform image preprocessing, including image enhancement and denoising processing, to collect static image data at the scene.

[0011] Further, the distributed data processing module includes a data cleaning unit, a format conversion unit, and a feature extraction unit. The data cleaning unit is used to clean the raw data on the edge computing nodes to remove noise and invalid data; the format conversion unit is used to perform data preprocessing on the edge computing nodes to convert the cleaned data into a unified format; the feature extraction unit is used to extract feature information from the converted data on the edge computing nodes through a feature extraction formula.

[0012] Further, the feature extraction formula is:

[0013]

[0014] In the formula, F e represents the feature extraction result, which is the feature value extracted from the data. K represents the total number of features, k represents the feature number, where k = 1, 2,..., K, and γ k represents the weight coefficient of the k-th feature, D represents the feature extraction data, and t k represents the k-th time point. represents the derivative of the feature extraction data D with respect to time t, representing the change rate of the k-th time feature. λ represents the regularization parameter, L represents the number of feature dimensions, and δ l represents the weight coefficient of the first feature dimension, where 1 represents the weight coefficient number, and l = 1, 2,..., L, D max represents the maximum value of the feature extraction data, D min represents the minimum value of the feature extraction data.

[0015] Furthermore, the specific process of the data transmission module is as follows: The preprocessed data is encapsulated in a packet format through an edge computing node to obtain a complete data packet; the complete data packet is encrypted using a symmetric encryption algorithm; the encrypted data packet selects a transmission path according to the current network condition using a dynamic routing protocol; the complete data packet is fragmented; the data fragments are transmitted from the edge computing node to the central server according to the selected transmission path.

[0016] Furthermore, the specific steps for receiving and processing data from each edge computing node and performing in-depth analysis are as follows: When the central server receives the data fragments, it reorganizes the data fragments to restore the complete data packet according to the fragment sequence number; decrypts the restored data packet to recover the original preprocessed data; the central server verifies the decrypted data and validates the integrity and correctness of the data through the check code; after the verification passes, the central server sends a confirmation message to the edge computing node to confirm that the data has been successfully received and decrypted. If the data verification fails, the central server sends an error message to the edge computing node to identify the data fragments that need to be retransmitted; the edge computing node re-encapsulates, encrypts, and transmits the corresponding data fragments according to the received error message until the central server confirms that the data has been received; the central server stores the successfully received and verified data; establishes an in-depth analysis model; the central server uses the in-depth analysis model to comprehensively analyze the data.

[0017] Further, the steps for establishing the in-depth analysis model are as follows: obtaining the data features of the feature extraction module; assigning weights to each feature to represent its importance in infringement behavior analysis; collecting external factor data and assigning weights; separately analyzing each feature to obtain its analysis result; separately analyzing each external factor to obtain its analysis result; performing weighted summation on the analysis results of all features according to their weights; performing weighted summation on the analysis results of all external factors according to their weights; adding the weighted summation results of all features and the weighted summation results of all external factors to obtain the in-depth analysis model.

[0018] Further, the in-depth analysis formula is as follows:

[0019]

[0020] In the formula, A d represents the in-depth analysis result for feature analysis, n represents the total number of data features, i represents the number of the data feature, i = 1, 2,..., n, θ i represents the weight coefficient of the i-th data feature, A i represents the analysis result of the i-th data feature, m represents the total number of external factors, j represents the number of the external factor, j = 1, 2,..., m, k j represents the weight coefficient of the j-th external factor, G j represents the influence of the j-th external factor.

[0021] Further, the user terminal module includes a user identity authentication unit, a user access interface unit, a report generation unit, a data visualization unit, a notification and reminder unit, a historical data query and management unit, and a security and privacy protection unit: The user identity authentication unit is used to perform user identity authentication; the user access interface unit is used for the user to query and view the infringement clue tracking report; the report generation unit is used to generate the infringement clue tracking report according to the user's needs and query conditions; the data visualization unit is used to visually display the analysis results and data trends; the notification and reminder unit is used to automatically send notifications when new infringement clues or reports are generated; the historical data query and management unit is used for the user to query and manage historical data and reports and perform annotation, marking, and archiving management on historical reports; the security and privacy protection unit is used to perform security audits and vulnerability scans to protect user data and privacy.

[0022] The embodiment of the present application provides a data processing method for tracking infringement clues based on edge computing, including: collecting various forms of original data at the infringement scene; using edge computing nodes to preprocess and preliminarily analyze the collected original data; transmitting the preprocessed data from the edge computing nodes to the central server; receiving and processing data from each edge computing node and performing in-depth analysis; and querying and viewing the infringement clue tracking report by the user.

[0023] One or more technical solutions provided in the embodiment of the present application have at least the following technical effects or advantages:

[0024] 1. By using edge computing nodes to preprocess and preliminarily analyze the collected original data, the data transmission volume is reduced, thereby improving the real-time performance and response speed of the system, and effectively solving the problem of low data processing efficiency in the prior art.

[0025] 2. Through the data transmission module, the preprocessed data is transmitted from the distributed data processing module to the central server, thereby reducing the processing burden of the central server and improving the system performance and processing capacity.

[0026] 3. By using the central server to comprehensively analyze the data with the in-depth analysis model, the accuracy and reliability of data analysis are improved, thereby realizing more accurate identification and tracking of complex infringement behaviors. Description of the Drawings

[0027] Figure 1 It is a schematic structural diagram of a data processing system for tracking infringement clues based on edge computing provided by the embodiment of the present application;

[0028] Figure 2 It is a feature extraction result diagram provided by the embodiment of the present application;

[0029] Figure 3 It is a flowchart of a data processing method for tracking infringement clues based on edge computing provided by the embodiment of the present application. Detailed Embodiments

[0030] The embodiment of the present application provides a data processing system and method for tracking infringement clues based on edge computing, solves the problem of low data processing efficiency in the prior art, and realizes the improvement of the real-time performance and response speed of the system by using edge computing nodes and in-depth analysis models to preprocess and analyze the collected original data.

[0031] The technical solution in the embodiment of the present application aims to solve the problem of low data processing efficiency, and the general idea is as follows: collect various forms of raw data at the infringement scene through the data acquisition module; use edge computing nodes in the distributed data processing module to preprocess and preliminarily analyze the collected raw data; through the data transmission module, transmit the preprocessed data from the edge computing nodes to the central server; through the central server, receive and process the data from each edge computing node and conduct in-depth analysis; through the user terminal module, users can query and view the infringement clue tracking report, achieving the effect of improving the real-time performance and response speed of the system.

[0032] To better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings of the specification and specific implementation manners.

[0033] As Figure 1 shown, it is a schematic structural diagram of a data processing system for infringement clue tracking based on edge computing provided by an embodiment of the present application. The data processing system for infringement clue tracking based on edge computing provided by an embodiment of the present application includes: a data acquisition module, a distributed data processing module, a data transmission module, a central server, and a user terminal module. Among them, the data acquisition module is used to collect various forms of raw data at the infringement scene; the distributed data processing module is used to preprocess and preliminarily analyze the collected raw data by using edge computing nodes; the data transmission module is used to transmit the preprocessed data from the edge computing nodes to the central server; the central server is used to receive and process the data from each edge computing node and conduct in-depth analysis; the user terminal module is used for users to query and view the infringement clue tracking report.

[0034] In this embodiment, edge computing refers to an open platform that integrates network, computing, storage, and application core capabilities on the side close to the object or data source to provide the nearest-end service nearby. The edge computing node preprocesses the data, reduces the data transmission volume, and improves the system response speed. The encryption processing during data transmission and storage ensures data security. The in-depth analysis model can identify complex infringement behaviors and improve the detection accuracy. The user terminal module provides the function of accessing data anytime and anywhere, improving the usability and user experience of the system.

[0035] Further, the data acquisition module includes a video acquisition unit, an audio acquisition unit, and an image acquisition unit: The video acquisition unit is used to collect real-time video data on-site in real time by installing high-resolution cameras, network cameras, and infrared cameras, and perform real-time video stream transmission; The audio acquisition unit is used to arrange omnidirectional microphones and directional microphones according to the environment, collect audio data in a noisy environment by enabling noise suppression technology, perform audio compression and echo cancellation processing, maintain the audio transmission quality, transmit the audio stream in real time, and perform audio signal digitization processing to collect the audio data on-site; The image acquisition unit is set with a timing shooting function to collect images at specific time intervals and perform image preprocessing, including image enhancement and denoising processing, to collect the static image data on-site.

[0036] In this embodiment, data acquisition: Install and configure data acquisition devices to ensure that the areas where infringement may occur can be covered. Regularly maintain and calibrate the devices to ensure the accuracy and reliability of data acquisition. Data preprocessing: Implement data cleaning algorithms on the edge computing node to remove noise and invalid data. Perform format conversion to convert the data into a unified format for convenient subsequent processing. Data transmission: Select an appropriate network transmission protocol to ensure the stability and security of data transmission. Implement encryption algorithms to encrypt the data to prevent data leakage. In-depth analysis: Use machine learning models to train and analyze the preprocessed data to extract valuable information. Real-time update and optimize the model to improve the accuracy and efficiency of analysis. User interaction: Design a user-friendly interface to facilitate users to query and view the analysis results. Provide various data display forms (such as charts, reports) to help users more intuitively understand the data. The edge computing node preprocesses the data, reduces the data transmission volume, and improves the system response speed. The encryption processing during data transmission and storage ensures data security; The in-depth analysis model can identify complex infringement behaviors and improve the detection accuracy; The user terminal module provides the function of accessing data anytime and anywhere, improving the usability of the system and the user experience.

[0037] Further, the distributed data processing module includes a data cleaning unit, a format conversion unit, and a feature extraction unit: The data cleaning unit is used to clean the raw data on the edge computing node to remove noise and invalid data; The format conversion unit is used to perform data preprocessing on the edge computing node to convert the cleaned data into a unified format; The feature extraction unit is used to extract feature information from the converted data on the edge computing node through a feature extraction formula.

[0038] In this embodiment, the main task of the data cleaning unit is to process the raw data obtained from the data acquisition module to remove noise, invalid data, and outliers, ensuring the quality and consistency of the data. Data cleaning includes steps such as missing value handling, noise filtering, duplicate data deletion, and anomaly detection. Detect missing values in the data and fill them using methods such as mean, median, and interpolation to ensure the integrity of each data record. Technical implementation: Various data cleaning techniques can be used, such as using the mean filling method to handle missing values, low-pass filters to remove noise, hash algorithms to detect and delete duplicate data, and box plots to identify and handle outliers. Application scenario: The data cleaning unit is applicable to any scenario that requires ensuring data quality, especially important in cases where the data volume is large and the data sources are diverse. The format conversion unit is responsible for converting the cleaned data into a unified format. Various data conversion tools and libraries can be used, such as the pandas library in Python, which can facilitate data type and structure conversion. Regular expressions are used for unit conversion of text data. The format conversion unit is applicable to situations where data sources are diverse and formats are inconsistent. The feature extraction unit extracts valuable feature information from the uniformly formatted data through pre-defined feature extraction algorithms and formulas. These feature information can be statistics (such as mean, variance), time series features (such as trends, periodicity), or complex patterns (such as spectral features). Through the combination of the data cleaning unit, format conversion unit, and feature extraction unit, the edge computing node module can efficiently and accurately process raw data, providing high-quality data support for subsequent in-depth analysis and decision-making. This not only improves the real-time performance and response speed of the system but also significantly enhances the reliability and intelligence level of the system.

[0039] Further, the feature extraction formula is:

[0040]

[0041] In the formula, F e represents the feature extraction result, represents the feature value extracted from the data, K represents the total number of features, k represents the feature number, k = 1, 2,..., K, γ k represents the weight coefficient of the k-th feature, D represents the feature extraction data, t k represents the k-th time point, represents the derivative of the feature extraction data D with respect to time t, representing the change rate of the k-th time feature, λ represents the regularization parameter, L represents the number of feature dimensions, δ l represents the weight coefficient of the l-th feature dimension, l represents the weight coefficient number, l = 1, 2,..., L, D max represents the maximum value of the feature extraction data, D min represents the minimum value of the feature extraction data.

[0042] In this embodiment, the feature extraction result can be obtained through actual data calculation; the regularization parameter can be obtained through cross-validation using the preprocessed original data by the k-fold cross-validation method; the weight coefficient can be obtained by substituting the feature extraction data into a regression model such as LASSO regression (Least Absolute Shrinkage and Selection Operator); the feature extraction data can be obtained by referring to expert materials. The feature extraction formula performs a weighted sum of multiple features according to the weight coefficient and the change rate to obtain the comprehensive feature extraction result. By using the maximum and minimum values of the feature extraction data, it is ensured that different features are compared on the same scale, improving the accuracy of feature extraction. The introduction of the regularization parameter helps to control the complexity of the model, prevent overfitting, and improve the generalization ability of the model. As shown in Table 1, the data table of the feature extraction formula:

[0043] Table 1 Data table of the feature extraction formula

[0044]

[0045]

[0046] As Figure 2 shown in the feature extraction result graph, according to Table 1 and Figure 2 analysis, it is concluded that the feature extraction results of different groups vary between 0.675 and 1.797. For example, the values of Group 4 and Group 9 are relatively high, being 1.797 and 1.736 respectively. This indicates that in these groups, the change rate and the feature dimension weight of the features are relatively large, or the difference between the maximum and minimum values of the feature extraction data is relatively large, resulting in relatively high feature extraction results. The feature extraction result F e can comprehensively reflect the change situation and importance of the data features. A higher F e value indicates that the features in this group of data have a higher change rate or importance and make a greater contribution to the overall analysis. By analyzing the change trend and influencing factors of F e , the feature extraction process can be optimized to improve the accuracy and reliability of the analysis results. It can be seen from the image and the data table that the feature extraction result F e increases as the feature weight coefficient, the data change rate, and the feature dimension weight coefficient increase.

[0047] Furthermore, the specific process of the data transmission module is as follows: encapsulate the preprocessed data in a packet format through the edge computing node to obtain a complete data packet; perform data encryption processing on the complete data packet using a symmetric encryption algorithm; select a transmission path for the encrypted data packet according to the current network conditions using a dynamic routing protocol; perform data fragmentation processing on the complete data packet; transmit the data fragments from the edge computing node to the central server according to the selected transmission path.

[0048] In this embodiment, the edge computing node encapsulates the preprocessed data to ensure the integrity and accuracy of the data during transmission. Using a standard data encapsulation protocol (such as TCP / IP), the data is encapsulated into data packets in a predefined format, including the meta-information of the data (such as data length, data type, timestamp, etc.). The encapsulated data packets are encrypted to protect the confidentiality of the data and prevent it from being stolen or tampered with during transmission. The data is encrypted using a pre-shared key. The encryption algorithm is efficient and secure, suitable for real-time data transmission. The optimal transmission path is selected according to the current network conditions to ensure the efficiency and reliability of data transmission. The transmission path is dynamically adjusted according to the real-time state of the network (such as network bandwidth, latency, node load). The data packets are fragmented to meet the requirements of different network transmissions and ensure the smooth transmission of large data packets. According to the requirements of the network transmission protocol (such as the IP protocol), the data packets are divided into multiple small pieces, each containing part of the data and the necessary header information, ensuring that the fragmented data can be correctly reassembled at the receiving end. The fragmented data packets are transmitted from the edge computing node to the central server through the selected transmission path to ensure that the data can reach the destination completely and accurately. Using the transport layer protocol (such as the TCP protocol), it is ensured that the data packets will not be lost during transmission and can arrive in order. The transmission protocol provides a reliable data transmission mechanism, including functions such as data packet acknowledgment, retransmission, and flow control.

[0049] Furthermore, the specific steps for receiving and processing data from each edge computing node and performing in-depth analysis are as follows: When the central server receives the data fragments, it reassembles the data fragments and restores the complete data packet according to the fragment sequence number; decrypts the restored data packet to recover the original preprocessed data; the central server verifies the decrypted data and validates the integrity and correctness of the data through the check code; after the verification passes, the central server sends a confirmation message to the edge computing node to confirm that the data has been successfully received and decrypted. If the data verification fails, the central server sends an error message to the edge computing node to identify the data fragments that need to be retransmitted; the edge computing node re-encapsulates, encrypts, and transmits the corresponding data fragments according to the received error message until the central server confirms that the data has been completely received; the central server stores the successfully received and verified data; establishes an in-depth analysis model; the central server uses the in-depth analysis model to comprehensively analyze the data.

[0050] In this embodiment, during the data transmission process, the data is fragmented. After the central server receives these data fragments, it needs to recombine them into a complete data packet according to the fragment sequence number. Using the fragment sequence number in the data packet header information, the data packet is recombined in order. Ensure that all fragments can be correctly assembled to form a complete original data packet. Decrypt the recombined data packet to restore the original preprocessed data. The data is encrypted during the transmission process, and decryption is to protect the data security. Check the decrypted data to ensure the integrity and correctness of the data. The check can detect data errors and packet loss phenomena during the transmission process. Use a check code (such as CRC check code) to perform data verification. After decryption, calculate the check code of the data packet and compare it with the check code attached during transmission to verify the data integrity. When the data verification passes, the central server sends a confirmation message to the edge computing node, confirming that the data has been successfully received and decrypted. If the data verification fails, the central server sends an error message to the edge computing node, identifying the data fragments that need to be retransmitted. The confirmation and retransmission mechanism is implemented through a network protocol (such as TCP protocol). The receiving party sends an ACK confirmation packet. After the sending party receives the confirmation packet, it stops retransmitting the data packet; if the receiving party does not receive the ACK confirmation packet, the retransmission mechanism is triggered, and the confirmation and retransmission mechanism is implemented through a network protocol (such as TCP protocol). The receiving party sends an ACK confirmation packet. After the sending party receives the confirmation packet, it stops retransmitting the data packet; if the receiving party does not receive the ACK confirmation packet, the retransmission mechanism is triggered.

[0051] Further, the steps to establish a depth analysis model are as follows: obtain the data features of the feature extraction module; assign weights to each feature, indicating the importance of the feature in the infringement behavior analysis; collect external factor data and assign weights; analyze each feature separately to obtain its analysis result; analyze each external factor separately to obtain its analysis result; perform weighted summation on the analysis results of all features according to the weights; perform weighted summation on the analysis results of all external factors according to the weights; add the weighted summation results of all features and the weighted summation results of all external factors to obtain the depth analysis model.

[0052] In this embodiment, collect external factor data that affects the infringement behavior analysis, such as weather, time, geographical location, etc., and assign weights to these external factors. Obtain external factor data through sensors, external data sources, manual input, etc. Use a method similar to the feature weight assignment to assign weights to external factors. Analyze each data feature separately to obtain the analysis result of the feature. These results are used to evaluate the performance of each feature in identifying infringement behaviors. Analyze each external factor separately to evaluate its impact on the infringement behavior. External factors include weather conditions, time periods, geographical locations, etc.

[0053] Further, the depth analysis formula is:

[0054]

[0055] wherein, A d represents the in-depth analysis result for feature analysis, n represents the total number of data features, i represents the number of the data feature, i = 1, 2,..., n, θ i represents the weight coefficient of the i-th data feature, A i represents the analysis result of the i-th data feature, m represents the total number of external factors, j represents the number of the external factor, j = 1, 2,..., m, k j represents the weight coefficient of the j-th external factor, G j represents the influence of the j-th external factor.

[0056] In this embodiment, A d can be obtained through real-time calculation by a big data analysis platform, or can also be obtained by substituting existing data; θ i can be obtained through historical experience; A i can be obtained by consulting expert materials; k j can be set and obtained through domain knowledge and expert evaluation; G j can be obtained through real-time collection by environmental sensors and external data sources.

[0057] Furthermore, the user terminal module includes a user identity authentication unit, a user access interface unit, a report generation unit, a data visualization unit, a notification and reminder unit, a historical data query and management unit, and a security and privacy protection unit: The user identity authentication unit is used to perform user identity authentication; the user access interface unit is used for the user to query and view the infringement clue tracking report; the report generation unit is used to generate the infringement clue tracking report according to the user's needs and query conditions; the data visualization unit is used to visually display the analysis results and data trends; the notification and reminder unit is used to automatically send notifications when new infringement clues or reports are generated; the historical data query and management unit is used for the user to query and manage historical data and reports and perform annotation, marking, and archival management on historical reports; the security and privacy protection unit is used to perform security audits and vulnerability scans to protect user data and privacy.

[0058] In this embodiment, through the user identity authentication unit, it is ensured that only authorized users can access the system, effectively preventing unauthorized access and protecting the security of sensitive data. The user access interface unit provides a friendly access interface, supports multi-device access, and improves the operation convenience and satisfaction of users. The report generation unit generates a detailed infringement clue tracking report according to user requirements and query conditions, providing accurate analysis results and decision-making support for users. The data visualization unit displays the analysis results and data trends through intuitive charts, helping users better understand and analyze data. The notification and reminder unit ensures that users receive timely notifications when new infringement clues or reports are generated, improving the response speed and processing efficiency of users. The historical data query and management unit provides efficient historical data retrieval and management functions, supports annotation, marking, and archiving management, and helps users make efficient use of historical data. The security and privacy protection unit ensures the security of user data and privacy through measures such as security auditing, vulnerability scanning, and data encryption, enhances user trust, and complies with data protection regulations. In summary, the functions of each unit of the user terminal module cooperate with each other, providing users with comprehensive, convenient, and secure data query and management services, greatly improving the overall performance and user experience of the system.

[0059] Furthermore, collect various forms of raw data at the infringement scene; use edge computing nodes to preprocess and preliminarily analyze the collected raw data; transmit the preprocessed data from the edge computing nodes to the central server; receive and process data from each edge computing node and conduct in-depth analysis; users query and view the infringement clue tracking report.

[0060] In summary, in the embodiment of the present application, by using edge computing nodes to preprocess and preliminarily analyze the collected raw data, the amount of data transmission is reduced, thereby improving the real-time performance and response speed of the system, and effectively solving the problem of low data processing efficiency in the prior art.

[0061] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) containing computer-usable program code.

[0062] The present invention is described with reference to the flowcharts and / or block diagrams of systems, apparatus (systems), and computer program products according to embodiments of the invention. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and combinations of flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general purpose computer, special purpose computer, embedded processor or other programmable data processing device to produce a machine, such that the instructions executed by the processor of the computer or other programmable data processing device generate means for implementing the specified functions in the flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or means for implementing the specified functions in multiple blocks.

[0063] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory produce a manufacture including instruction means that implement the specified functions in the flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or means for implementing the specified functions in multiple blocks.

[0064] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the specified functions in the flow Figure 1 one flow or multiple flows and / or blocks Figure 1 or means for implementing the specified functions in multiple blocks.

[0065] Although the preferred embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications once they learn the basic creative concept. Therefore, the appended claims are intended to be construed to include the preferred embodiments and all changes and modifications falling within the scope of the present invention.

[0066] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these modifications and variations.

Claims

1. An infringement clue tracking data processing system based on edge computing, characterized in that: include: Data acquisition module, distributed data processing module, data transmission module, central server, user terminal module: The data collection module is used to collect various forms of original data from the scene of the infringement; The distributed data processing module is used to pre-process and preliminarily analyze the collected raw data using edge computing nodes; The data transmission module is used to transmit the pre-processed data from the edge computing node to the central server; The central server is used to receive and process data from each edge computing node and perform in-depth analysis; The user terminal module is used for users to query and view infringement clue tracking reports.

2. The infringement clue tracking data processing system based on edge computing as claimed in claim 1, characterized in that: The data acquisition module includes a video acquisition unit, an audio acquisition unit and an image acquisition unit: The video acquisition unit is used to collect real-time video data of the scene in real time by installing a high-resolution camera, a network camera and an infrared camera, and to perform real-time video streaming transmission; The audio acquisition unit is used to arrange omnidirectional microphones and directional microphones according to the environment, collect audio data in a noisy environment and perform audio compression and echo cancellation processing by enabling noise suppression technology, maintain audio transmission quality, transmit audio streams in real time, and perform audio signal digitization processing to collect audio data on site; The image acquisition unit is provided with a timed shooting function to acquire images at specific time intervals and perform image preprocessing, including image enhancement and denoising, to acquire static image data of the scene.

3. The infringement clue tracking data processing system based on edge computing as claimed in claim 1, characterized in that: The distributed data processing module includes a data cleaning unit, a format conversion unit and a feature extraction unit: The data cleaning unit is used to clean the original data on the edge computing node to remove noise and invalid data; The format conversion unit is used to perform data preprocessing on the edge computing node and convert the cleaned data into a unified format; The feature extraction unit is used to extract feature information from the converted data through a feature extraction formula on the edge computing node.

4. The infringement clue tracking data processing system based on edge computing as claimed in claim 3, characterized in that: The feature extraction formula is: In the formula, F e Represents the feature extraction result, represents the feature value extracted from the data, K represents the total number of features, k represents the feature number, k=1,2,...,K,γ k represents the weight coefficient of the kth feature, D represents the feature extraction data, t k represents the kth time point, represents the derivative of the feature extraction data D with respect to time t, represents the rate of change of the kth time feature, λ represents the regularization parameter, L represents the number of feature dimensions, δ l Indicates the weight coefficient of the first feature dimension, 1 indicates the weight coefficient number, l = 1, 2, ..., L, D max represents the maximum value of feature extraction data, D min Indicates the minimum value of feature extraction data.

5. The infringement clue tracking data processing system based on edge computing as claimed in claim 1, characterized in that: The specific process of the data transmission module is as follows: The pre-processed data is encapsulated in the encapsulation format through the edge computing node to obtain a complete data packet; The complete data packet is encrypted using a symmetric encryption algorithm; The encrypted data packets are transmitted using a dynamic routing protocol according to the current network conditions; Process the complete data packet into data fragments; The data shards are transmitted from the edge computing nodes to the central server according to the selected transmission path.

6. The infringement clue tracking data processing system based on edge computing as claimed in claim 1, characterized in that: The specific steps of receiving and processing data from each edge computing node and performing in-depth analysis are: When the central server receives the data fragments, it reassembles the data fragments and restores the complete data packet according to the fragment sequence number; Decrypt the restored data packet to recover the original pre-processed data; The central server verifies the decrypted data and verifies the integrity and correctness of the data through the verification code; After the verification is passed, the central server sends a confirmation message to the edge computing node to confirm that the data has been successfully received and decrypted. If the data verification fails, the central server sends an error message to the edge computing node to identify the data fragment that needs to be retransmitted; The edge computing node repackages, encrypts and transmits the corresponding data fragments according to the received error information until the central server confirms that the data has been received; The central server stores the successfully received and verified data; Establishing deep analysis models; The central server uses deep analysis models to conduct comprehensive analysis of the data.

7. The infringement clue tracking data processing system based on edge computing as claimed in claim 6, characterized in that: The steps of establishing the depth analysis model are: Obtain data features of feature extraction module; Assign a weight to each feature, indicating the importance of the feature in the infringement analysis; Collect data on external factors and assign weights; Analyze each feature separately and obtain its analysis results; Analyze each external factor separately and obtain its analysis results; The analysis results of all features are weighted and summed according to the weights; The analysis results of all external factors are weighted and summed according to their weights; The weighted sum of all features and the weighted sum of all external factors are added together to obtain the deep analysis model.

8. The infringement clue tracking data processing system based on edge computing as claimed in claim 1, characterized in that: The depth analysis formula is: In the formula, A d Indicates the results of deep analysis, used for feature analysis, n represents the total number of data features, i represents the number of data features, i = 1, 2, ..., n, θ i Represents the weight coefficient of the i-th data feature, A i represents the analysis result of the i-th data feature, m represents the total number of external factors, j represents the number of external factors, j = 1, 2, ..., m, k j represents the weight coefficient of the jth external factor, G j represents the influence of the jth external factor.

9. The infringement clue tracking data processing system based on edge computing as claimed in claim 1, characterized in that: The user terminal module includes a user identity authentication unit, a user access interface unit, a report generation unit, a data visualization unit, a notification and reminder unit, a historical data query and management unit, and a security and privacy protection unit: The user identity authentication unit is used to perform user identity authentication; The user access interface unit is used for users to query and view infringement clue tracking reports; The report generating unit is used to generate an infringement clue tracking report according to user requirements and query conditions; The data visualization unit is used to visualize the analysis results and data trends; The notification and reminder unit is used for the system to automatically send notifications when new infringement clues or reports are generated; The historical data query and management unit is used for users to query and manage historical data and reports and to annotate, mark and archive historical reports; The security and privacy protection unit is used to perform security audits and vulnerability scans to protect user data and privacy.

10. A data processing method for tracking infringement clues based on edge computing, characterized in that: The following steps are involved: Collect various forms of raw data from the scene of infringement; Use edge computing nodes to pre-process and preliminarily analyze the collected raw data; Transmit the preprocessed data from the edge computing node to the central server; Receive and process data from each edge computing node and perform in-depth analysis; Users query and view infringement clue tracking reports.

Images