Smart city network supervision method and system based on cloud server

Abstract

The invention discloses a smart city network supervision method and system based on a cloud server. The smart city network supervision method comprises the following steps of S1, collecting sent short messages through a network short message collection module; s2, establishing a truncation cache region in the cloud server, and transmitting the real-time collected and sent short message to the truncation cache region for caching; s3, analyzing the collected short messages during the cache region truncation period, and constructing a supervision model; s4, identifying the constructed supervision model, and building a model feature association chain in the same-batch truncation cache region; s5, account information of a short message receiving end is obtained, short message supervision intervention strength is adjusted, and then the short messages stored in the cut-off cache region are sent to the user side according to the priority of the supervision intervention strength, and the method has the advantages of being high in practicability and highly intelligent in supervision.

Description

Technical Field

[0001] This invention relates to the field of network information security technology, specifically to a smart city network monitoring method and system based on cloud servers. Background Technology

[0002] With the rapid development of communication network technology and the continuous expansion of its application areas, numerous mobile value-added services have emerged. SMS, as one of the important application service models of mobile value-added services, provides users with convenient, fast, and inexpensive communication services. However, some criminals use SMS communication platforms to spread spam messages, including those containing pornography, malicious defamation, fraud, incitement to unrest, rumors, threats to public safety, and illegal commercial advertisements. These spam messages seriously disrupt people's lives, endanger social security, and cause network congestion. The issue of network regulation of spam SMS has received widespread attention.

[0003] While existing spam SMS interception technologies employ keyword extraction based on SMS content analysis, user blacklists, and machine learning to detect or directly block each SMS message individually and filter spam in real time, they struggle to comprehensively intercept the sophisticated and ever-changing nature of spam messages. Furthermore, these technologies cannot keep pace with the targeted evasion tactics employed by criminals. This is especially true for users with limited access to information who are easily misled by online content, making them highly susceptible to being misled by spam messages and suffering significant financial losses. Therefore, designing a practical and highly intelligent cloud-based smart city network monitoring method and system is essential. Summary of the Invention

[0004] The purpose of this invention is to provide a smart city network monitoring method and system based on cloud servers to solve the problems mentioned in the background art.

[0005] To address the aforementioned technical problems, this invention provides the following technical solution: a smart city network monitoring method based on a cloud server, comprising the following steps: Step S1: Collect the sent SMS messages through the network SMS collection module; Step S2: Establish a truncation cache in the cloud server and transmit the real-time collected SMS messages to the truncation cache for caching; Step S3: Analyze the collected SMS messages during the truncation buffer period to construct the monitoring model; Step S4: Identify the constructed regulatory model and establish a feature association chain for the model within the same batch truncated cache area; Step S5: Obtain the SMS recipient account information, adjust the level of SMS regulatory intervention, and then send the SMS stored in the truncated cache to the user terminal according to the priority of the regulatory intervention level.

[0006] According to the above technical solution, step S2 specifically includes: establishing a truncation buffer, transmitting short messages within the same truncation period to the truncation buffer, so that the sent short messages are suspended from direct communication transmission to the receiving user terminal.

[0007] According to the above technical solution, the method for analyzing collected short messages in step S3 mainly includes: Based on cloud servers, the city network is used to trace the operating environment, operating behavior, transmission channel, and text message content of the source of text messages. Then, the operating environment and operating behavior are monitored, the text message content is identified, the transmission channel is analyzed, and the feasibility of spoofing is analyzed. Furthermore, a planar radar chart is constructed based on four dimensions: operating environment, operating behavior, SMS content identification, and transmission channel identification. Then, the data content of the monitored SMS messages is analyzed in terms of operating environment, operating behavior, SMS content identification, and transmission channel identification, and the corresponding mapping values ​​under different dimensions are output.

[0008] According to the above technical solution, step S3 further includes: Based on the analysis of the mapping values, the four dimensions of the constructed planar radar chart are modified in a diffusion-type manner, thereby enabling the multi-dimensional data of SMS monitoring to be normalized.

[0009] According to the above technical solution, step S3 further includes: Based on the feasibility of embedding camouflage in the middle of a planar radar image, a vertical bar parameter map is constructed, and the vertical bar parameter map is connected to the four corners of the planar radar image to form a three-dimensional monitoring model.

[0010] According to the above technical solution, the method for analyzing the feasibility of spoofing is as follows: monitor the operating environment and operating behavior in the cloud server, identify the content of the short message, parse the transmission channel, simulate the spoofing process of the spoofed information, determine the percentage of simulated spoofing operations based on the complexity of the operating behavior and the variability of the operating environment, identify the difficulty of cracking encryption on the transmission channel, and identify the passive interference of the SMS content, and then calculate and output the spoofing feasibility index by weighting the above parameters.

[0011] According to the above technical solution, step S4 specifically includes: Identify the length and angle values ​​of the connecting lines at the four corners of the vertical parameter map and the planar radar map respectively. Then, set the length error value m and the angle error value n for the association chain matching. Repeat the above steps until the length and angle values ​​of all connecting lines are identified. Then, perform association matching according to the preset error values. When the length error between the connecting lines at the four corners of all corresponding vertical parameter maps and planar radar maps in each pair of regulatory models is less than m and the angle error is less than n, the association matching of the two regulatory models is successful. When the association matching between multiple regulatory models is successful, a model feature association chain can be built between all the successfully matched regulatory models.

[0012] According to the above technical solution, the method for obtaining the SMS receiver account information in step S5 is as follows: After establishing the model feature association chain for SMS messages within the same cutoff period, the system retrieves SMS recipient account information from the cloud server and performs a self-assessment of the SMS recipient account's security. The assessment method primarily includes: acquiring the recipient account's age, education level, and third-party settings data; then dividing these data into three tiers, each corresponding to a score of 100, 80, and 60 from highest to lowest; and then setting the corresponding tiers for age, education level, and third-party settings data, with preset values ​​adjustable. The third-party settings data represent the user's self-assessment or self-protection requirements during account registration, also corresponding to a score of 100, 80, and 60, set by the user. Finally, the scores from the analysis of age, education level, and third-party settings data are summed, and the result of the self-assessment of the SMS recipient account's security is output.

[0013] A cloud server-based smart city network monitoring system, comprising: The network SMS collection module is used to collect sent SMS messages; The cache area truncation module is used to store the real-time collected and sent SMS messages; The regulatory model building module is used to analyze collected SMS messages and construct a regulatory model during the truncation buffer period; The correlation feature recognition module is used to identify correlation features between the constructed regulatory models; The regulatory authority adjustment module is used to adjust the level of intervention in SMS regulation.

[0014] Compared with existing technologies, the beneficial effects achieved by this invention are as follows: This invention first stores network SMS messages in a truncated buffer, then analyzes the SMS messages and constructs a monitoring model. This achieves indicator normalization processing of multi-dimensional data for SMS monitoring. The constructed radar chart can analyze and compare the analytical mapping values ​​of SMS sending sources. Simultaneously, the constructed model can achieve rapid correlation matching. Finally, by performing autonomous security judgment on the SMS receiving account, SMS messages in the truncated buffer are prioritized for sending to users with strong autonomous security. Then, by utilizing feedback reports from users with strong autonomy, combined with the established correlation chain, SMS messages with similar characteristics under the multi-dimensional judgment in both directions are intercepted. This effectively reduces the number of malicious actors using spam SMS messages to exploit information asymmetry and deceive vulnerable users, greatly improving the strength and accuracy of spam SMS monitoring. Attached Figure Description

[0015] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings: Figure 1 A flowchart illustrating the steps of a smart city network monitoring method based on a cloud server, as provided in Embodiment 1 of the present invention; Figure 2 This is a schematic diagram of the module composition of the smart city network monitoring system based on a cloud server provided in Embodiment 2 of the present invention. Detailed Implementation

[0016] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0017] Example 1, Figure 1 This is a flowchart illustrating the steps of a cloud server-based smart city network monitoring method according to Embodiment 1 of the present invention. This embodiment is applicable to the monitoring of spam SMS messages. The method can be executed by a cloud server-based smart city network monitoring system provided in this embodiment of the present invention. Figure 1 As shown, the method specifically includes the following steps: S1. Collect the sent SMS messages through the network SMS collection module; S2. Establish a truncation cache in the cloud server and transmit the real-time collected and sent SMS messages to the truncation cache for caching. For example, in this embodiment of the invention, a truncation buffer is established, and short messages within the same truncation period are transmitted to the truncation buffer, so that the sent short messages are suspended from direct communication and transmission to the receiving user terminal. By entering the buffer, comprehensive monitoring and analysis of network short messages can be achieved, laying a programmatic foundation for subsequent intelligent monitoring and interception of short messages.

[0018] S3. Analyze the collected SMS messages during the truncation buffer period and construct a monitoring model; For example, in this embodiment of the invention, the method for collecting and analyzing short messages mainly includes: based on a cloud server, using the urban network to trace the operating environment, operating behavior, transmission channel, and short message content of the short message sending source; then monitoring the operating environment and operating behavior, identifying the short message content, parsing the transmission channel, and analyzing the feasibility of spoofing. Further, a planar radar chart is constructed based on four dimensions: operating environment, operating behavior, short message content identification, and transmission channel identification. Then, based on the monitored short messages, the data content of the operating environment, operating behavior, short message content identification, and transmission channel identification are analyzed respectively, outputting corresponding mapping values ​​under different dimensions. Based on the analyzed mapping values, diffusion-type modifications are made to the four dimensions of the constructed planar radar chart, thereby normalizing the multi-dimensional data of short message monitoring. Through the constructed radar chart, the analyzed mapping values ​​of the short message sending source can be analyzed and compared, achieving rapid correlation matching and reducing the problem of low intelligence in monitoring and interception caused by the lack of entry-level analysis standards for complex data.

[0019] For example, in an embodiment of the present invention, a vertical bar parameter map of camouflage feasibility is embedded in the middle of a planar radar image, and the vertical bar parameter map is connected to the four corners of the planar radar image to construct a three-dimensional surveillance model. Through the three-dimensional surveillance model, information can be expressed in two directions and in multiple dimensions, including comprehensive camouflage feasibility analysis of the sending source and mapping value analysis in four dimensions.

[0020] In this embodiment of the invention, the method for analyzing the feasibility of spoofing is as follows: monitoring the operating environment and operating behavior in the cloud server, identifying the content of the short message, parsing the transmission channel, simulating the spoofing process of the spoofed information, judging the percentage of the simulated spoofed information operation based on the complexity of the operating behavior and the variability of the operating environment, identifying the difficulty of cracking encryption on the transmission channel, and identifying the passive interference of the SMS content, and then calculating and outputting the spoofing feasibility index by weighting the above parameters.

[0021] In this embodiment of the invention, the mapping values ​​under different dimensions are the dimensional expansion of the radar image corresponding to the comprehensive digital serial code composed of various elements under the same dimension. The dimensional expansion of the radar image cannot directly determine the danger of the short message, but it can intuitively identify the correlation of short messages within the same truncation period, thus achieving the effect of easy integration and processing.

[0022] S4. Identify the constructed regulatory model and build a model feature association chain within the same batch truncated cache area; For example, in this embodiment of the invention, three-dimensional image recognition is performed on the monitoring models of all short messages within the same cutoff period. Specifically, the length and angle values ​​of the connecting lines at the four corners of the vertical parameter map and the planar radar map are identified respectively. Then, the length error value m and the angle error value n of the association chain matching are set. The above steps are repeated until the length and angle values ​​of all connecting lines are identified. Then, the association matching is performed according to the preset error value. When the length error between the connecting lines at the four corners of all corresponding vertical parameter maps and the planar radar map is less than m and the angle error is less than n in every two sets of monitoring models, the association matching of the two sets of monitoring models is successful. When the association matching between multiple sets of monitoring models is successful, a model feature association chain can be built between all the successfully matched monitoring models.

[0023] S5. Obtain the SMS recipient's account information, adjust the level of SMS regulatory intervention, and then send the SMS stored in the truncated cache to the user terminal according to the priority of the regulatory intervention level.

[0024] For example, in this embodiment of the invention, after the model feature association chain of SMS messages within the same truncation period is built, the SMS receiving terminal account information is obtained based on the cloud server, and the SMS receiving terminal account is autonomously judged. The judgment method mainly includes: obtaining the age, education, and third-party setting data of the receiving terminal account, and then dividing the age, education, and third-party setting data into three levels, each level corresponding to three scores of 100, 80, and 60 from high to low. Then, the age, education, and third-party setting data are set to the corresponding levels. For example, the age range of 18-60 years old is the first level, corresponding to 100 points; the age range of under 12 years old and over 80 years old is the third level, corresponding to 60 points; and the remaining age range corresponds to 80 points. The education level is divided in the same way, and the specific preset values ​​can be adjusted. The third-party setting data is the self-assessment or self-protection requirement value during the user's account registration process, which also corresponds to three scores of 100, 80, and 60, and is set by the user. Finally, the scores of the analysis and judgment of the age, education, and third-party setting data are accumulated, and the result of the autonomous security judgment of the SMS receiving terminal account is output.

[0025] The intensity of regulatory intervention on SMS receivers will be adjusted. Specifically, SMS messages analyzed and constructed within the truncation buffer will be sent to users in batches based on the SMS receiver's self-assessment of security. First, SMS messages will be sent to SMS receivers with a security assessment score of 300 or higher. The option to receive spam SMS reports via the cloud server will be enabled. Within one-third of the truncation period, feedback from the first batch of users regarding spam SMS messages will be obtained. When feedback on spam SMS messages is received, the network monitoring system will immediately retrieve the three-dimensional monitoring model of the reported spam SMS messages as the core, obtain all SMS messages corresponding to the three-dimensional monitoring models that have built their own association chains with the reported spam SMS messages, and intercept and process these SMS messages.

[0026] After interception, SMS messages are sent to recipients with scores between 240 and 300. Similarly, within one-third of the truncation period, feedback from a second batch of users regarding spam SMS messages is obtained. When feedback on spam SMS messages is received, the network monitoring system immediately retrieves the three-dimensional monitoring model of the reported spam SMS messages, obtains all SMS messages corresponding to the three-dimensional monitoring models that have built association chains with the reported spam SMS messages, and intercepts and processes these SMS messages.

[0027] Finally, the SMS messages after secondary interception are sent to SMS receivers with a time limit of 240 or less.

[0028] Through the above steps, SMS messages can be first stored in a truncated buffer, then analyzed and a monitoring model can be constructed. This allows for the normalization of multi-dimensional data on SMS monitoring indicators. A constructed radar chart can be used to analyze and compare the analytical mapping values ​​of SMS sending sources. The model can also be used for rapid correlation matching. Finally, by assessing the self-security of SMS recipient accounts, SMS messages in the truncated buffer are prioritized for delivery to users with strong self-security. Feedback reports from these users are then used, combined with a built-in correlation chain to intercept SMS messages exhibiting similar characteristics based on multi-dimensional assessments from both directions. This effectively reduces the risk of malicious actors exploiting information asymmetry to deceive vulnerable users through spam SMS messages, significantly improving the effectiveness and accuracy of spam SMS monitoring.

[0029] Example 2: This invention provides a smart city network monitoring system based on a cloud server. Figure 2 This is a schematic diagram of the module composition of the cloud server-based smart city network monitoring system provided in Embodiment 2 of the present invention, as shown below. Figure 2 As shown, the system includes: The network SMS collection module is used to collect sent SMS messages; The cache area truncation module is used to store the real-time collected and sent SMS messages; The regulatory model building module is used to analyze collected SMS messages and construct a regulatory model during the truncation buffer period; The correlation feature recognition module is used to identify correlation features between the constructed regulatory models; The regulatory authority adjustment module is used to adjust the level of intervention in SMS regulation.

[0030] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0031] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A smart city network monitoring method based on cloud servers, characterized in that: The method includes the following steps: Step S1: Collect the sent SMS messages through the network SMS collection module; Step S2: Establish a truncation cache in the cloud server and transmit the real-time collected SMS messages to the truncation cache for caching; Step S3: Analyze the collected SMS messages during the truncation buffer period to construct the monitoring model; Step S4: Identify the constructed regulatory model and establish a feature association chain for the model within the same batch truncated cache area; Step S5: Obtain the SMS recipient account information, adjust the level of SMS regulatory intervention, and then send the SMS stored in the truncated cache to the user terminal according to the priority of the regulatory intervention level.

2. The smart city network monitoring method based on cloud servers according to claim 1, characterized in that: Step S2 specifically includes: establishing a truncation buffer, transmitting short messages within the same truncation period to the truncation buffer, so that the sent short messages are suspended from direct communication and transmitted to the receiving user terminal.

3. The smart city network monitoring method based on cloud servers according to claim 1, characterized in that: The method for analyzing collected short messages in step S3 mainly includes: Based on cloud servers, the city network is used to trace the operating environment, operating behavior, transmission channel, and text message content of the source of text messages. Then, the operating environment and operating behavior are monitored, the text message content is identified, the transmission channel is analyzed, and the feasibility of spoofing is analyzed. Furthermore, a planar radar chart is constructed based on four dimensions: operating environment, operating behavior, SMS content identification, and transmission channel identification. Then, the data content of the monitored SMS messages is analyzed in terms of operating environment, operating behavior, SMS content identification, and transmission channel identification, and the corresponding mapping values ​​under different dimensions are output.

4. The smart city network monitoring method based on cloud servers according to claim 3, characterized in that: Step S3 further includes: Based on the analysis of the mapping values, the four dimensions of the constructed planar radar chart are modified in a diffusion-type manner, thereby enabling the multi-dimensional data of SMS monitoring to be normalized.

5. The smart city network monitoring method based on cloud servers according to claim 4, characterized in that: Step S3 further includes: Based on the feasibility of embedding camouflage in the middle of a planar radar image, a vertical bar parameter map is constructed, and the vertical bar parameter map is connected to the four corners of the planar radar image to form a three-dimensional monitoring model.

6. The smart city network monitoring method based on cloud servers according to claim 3, characterized in that: The method for analyzing the feasibility of spoofing is as follows: monitor the operating environment and operating behavior in the cloud server, identify the content of the SMS message, analyze the transmission channel, simulate the spoofing process of the spoofed message, determine the percentage of simulated spoofing operations based on the complexity of the operating behavior and the variability of the operating environment, identify the difficulty of cracking encryption on the transmission channel, and identify the passive interference of the SMS content, and then calculate the spoofing feasibility index by weighting the above parameters.

7. The smart city network monitoring method based on cloud servers according to claim 1, characterized in that: Step S4 specifically includes: Identify the length and angle values ​​of the connecting lines at the four corners of the vertical parameter map and the planar radar map respectively. Then, set the length error value m and the angle error value n for the association chain matching. Repeat the above steps until the length and angle values ​​of all connecting lines are identified. Then, perform association matching according to the preset error values. When the length error between the connecting lines at the four corners of all corresponding vertical parameter maps and planar radar maps in each pair of regulatory models is less than m and the angle error is less than n, the association matching of the two regulatory models is successful. When the association matching between multiple regulatory models is successful, a model feature association chain can be built between all the successfully matched regulatory models.

8. The smart city network monitoring method based on cloud servers according to claim 1, characterized in that: The method for obtaining SMS receiver account information in step S5 is as follows: After establishing the model feature association chain for SMS messages within the same cutoff period, the system retrieves SMS recipient account information from the cloud server and performs a self-assessment of the SMS recipient account's security. The assessment method primarily includes: acquiring the recipient account's age, education level, and third-party settings data; then dividing these data into three tiers, each corresponding to a score of 100, 80, and 60 from highest to lowest; and then setting the corresponding tiers for age, education level, and third-party settings data, with preset values ​​adjustable. The third-party settings data represent the user's self-assessment or self-protection requirements during account registration, also corresponding to a score of 100, 80, and 60, set by the user. Finally, the scores from the analysis of age, education level, and third-party settings data are summed, and the result of the self-assessment of the SMS recipient account's security is output.

9. A smart city network monitoring system based on a cloud server, characterized in that: The system includes: The network SMS collection module is used to collect sent SMS messages; The cache area truncation module is used to store the real-time collected and sent SMS messages; The regulatory model building module is used to analyze collected SMS messages and construct a regulatory model during the truncation buffer period; The correlation feature recognition module is used to identify correlation features between the constructed regulatory models; The regulatory authority adjustment module is used to adjust the level of intervention in SMS regulation.

Images