Network information resource allocation method and system based on trusted account

Abstract

The application provides a network information resource allocation method and system based on a trusted account, aiming to improve the efficiency and security of resource allocation. First, the basic network information resource data to be allocated is obtained, and an allocation guide framework is obtained. By embedding the basic network information resource data in the allocation guide framework, the allocation guide information is generated, and then the resource is allocated and processed to obtain the preliminary resource allocation result. Thereafter, the trusted account risk feedback information corresponding to the resource allocation result is further obtained, and the preliminary allocation result is optimized accordingly to finally generate the target resource allocation result. By introducing the trusted account mechanism, the security and reliability of the resource allocation process are ensured, and the accuracy and efficiency of the resource allocation are improved.

Description

Technical Field

[0001] This application relates to the field of network security technology, and more specifically, to a method and system for allocating network information resources based on trusted accounts. Background Technology

[0002] With the rapid development of information technology, network information resources have become an indispensable part of modern society. However, how to efficiently and securely allocate these resources to meet the needs of different users and applications has always been a problem that urgently needs to be solved.

[0003] Traditional methods for allocating network information resources often lack specificity and flexibility, making it difficult to accurately allocate resources based on specific application scenarios and needs. Furthermore, these methods frequently overlook account trustworthiness during the allocation process, potentially leading to security vulnerabilities in the resource allocation results and failing to meet the requirements of modern network security. Summary of the Invention

[0004] In view of this, the purpose of this application is to provide a method and system for allocating network information resources based on trusted accounts.

[0005] According to a first aspect of this application, a method for allocating network information resources based on trusted accounts is provided, the method comprising: Acquire basic network information resource data to be allocated; Obtain the allocation guidance framework, and embed the basic network information resource data into the allocation guidance framework according to the guidance of the allocation guidance framework to generate allocation guidance information; Based on the allocation guidance information, the basic network information resource data is processed for resource allocation to generate the resource allocation result of the basic network information resource data; Obtain the trusted account risk feedback information corresponding to the resource allocation result, and optimize the resource allocation result based on the trusted account risk feedback information corresponding to the resource allocation result to generate the target resource allocation result of the basic network information resource data.

[0006] According to a second aspect of this application, a network information resource allocation system based on trusted accounts is provided. The network information resource allocation system based on trusted accounts includes a machine-readable storage medium and a processor. The machine-readable storage medium stores machine-executable instructions. When the processor executes the machine-executable instructions, the network information resource allocation system based on trusted accounts implements the aforementioned network information resource allocation method based on trusted accounts.

[0007] According to a third aspect of this application, a computer-readable storage medium is provided, wherein computer-executable instructions are stored therein, and when the computer-executable instructions are executed, the aforementioned network information resource allocation method based on trusted accounts is implemented.

[0008] Based on any of the above aspects, the technical effect of this application is as follows: This application embodiment acquires and embeds basic network information resource data into the allocation guidance framework to generate allocation guidance information, thereby achieving efficient resource allocation processing. Importantly, a trusted account risk feedback mechanism is also introduced. Based on this feedback information, the resource allocation results are optimized, resulting in more accurate and secure target resource allocation results. This not only improves the efficiency and accuracy of network information resource allocation but also significantly enhances the security and reliability of the allocation process, effectively reducing potential risks caused by improper resource allocation. Attached Figure Description

[0009] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other corresponding drawings can be obtained based on these drawings without creative effort.

[0010] Figure 1 A flowchart illustrating the network information resource allocation method based on trusted accounts provided in this application embodiment; Figure 2 This illustration shows a schematic diagram of the component structure of a trusted account-based network information resource allocation system for implementing the above-described trusted account-based network information resource allocation method, as provided in an embodiment of this application. Detailed Implementation

[0011] The embodiments of this application are described below with reference to the accompanying drawings. It should be understood that the embodiments described below with reference to the accompanying drawings are exemplary descriptions for explaining the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions of the embodiments of this application.

[0012] Those skilled in the art will understand that, unless otherwise stated, the singular forms “a,” “an,” “the,” and “the” used herein may also include the plural forms. It should be further understood that the terms “comprising” and “including” as used in embodiments of this application mean that the corresponding feature can be implemented as the presented feature, information, data, step, operation, element, and / or component, but do not exclude implementation as other features, information, data, step, operation, element, component, and / or combinations thereof supported by the art. It should be understood that when an element is said to be “connected” or “coupled” to another element, the element may be directly connected or coupled to the other element, or it may mean that the element and the other element are connected through an intermediate element. Furthermore, “connected” or “coupled” as used herein may include wireless connection or wireless coupling, and the term “and / or” as used herein indicates at least one of the items defined by the term; for example, “A and / or B” may be implemented as “A,” or as “B,” or as “A and B.”

[0013] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings. The technical solutions of the embodiments of this application and the technical effects produced by the technical solutions of this application will be explained below through the description of several exemplary embodiments. It should be noted that the following embodiments can be referenced, borrowed from, or combined with each other, and the same terms, similar features, and similar implementation steps in different embodiments will not be described again.

[0014] Figure 1 This document illustrates a flowchart of a network information resource allocation method and system based on trusted accounts, provided in an embodiment of this application. It should be understood that in other embodiments, the order of some steps in the network information resource allocation method based on trusted accounts in this embodiment can be shared according to actual needs, or some steps can be omitted or maintained. The detailed steps of this network information resource allocation method based on trusted accounts include: Step S110: Obtain the basic network information resource data to be allocated.

[0015] In this embodiment, within the network environment of a telecommunications operator, the server needs to collect basic network information resource data from multiple sources to construct a complete network resource profile. First, the server obtains data from the network device management system. Telecommunications operators possess a large number of network devices, such as routers, switches, and base station equipment. From the router management system, the server can obtain routing table information, which includes the routing paths and next-hop addresses for each network destination. This information allows the server to understand the flow of network traffic and potential congestion points. For example, the routing path for the IP addresses corresponding to certain popular websites may pass through specific router interfaces. If the traffic load on this interface is too high, it will affect the speed at which users access these websites. The switch management system provides port connection information, port traffic data, and VLAN (Virtual Local Area Network) configuration information. For example, the server can understand which ports are connected to enterprise users, which are connected to home users, and the real-time traffic situation of each port. For instance, switch ports in enterprise office areas may experience higher traffic during weekdays, while ports used by home users experience more significant traffic peaks at night and on weekends. Regarding base station equipment, servers obtain information such as base station coverage, signal strength, and the number of connected users, which is crucial for the allocation of mobile network resources. For example, at base stations near large event venues, the number of connected users can increase dramatically due to the dense crowds, potentially leading to network congestion.

[0016] Simultaneously, the server also retrieves relevant data from the user authentication and billing system. User account type and package information affect network resource allocation. For example, users with premium packages may enjoy higher bandwidth priority or larger traffic quotas. From user authentication information, the server can determine the user's identity attributes, such as enterprise users, individual users, VIP users, etc. Different user identities may require different network resource allocations. For enterprise users, a stable dedicated line connection may be necessary; for VIP users, a better service experience, such as lower latency, may be required. Furthermore, the server also obtains data from the network monitoring system, including real-time network traffic data and network attack detection data. Real-time traffic data reflects network activity levels. For example, during specific time periods, such as 8-10 PM, network traffic may peak as many users simultaneously engage in activities like video streaming and online gaming, leading to a significant increase in bandwidth demand. Network attack detection data helps identify network security risks, such as DDoS (Distributed Denial of Service) attack detection results. If a DDoS attack is detected in a certain area of ​​the network, then special allocation of network resources is needed to defend against the attack and ensure normal use for other users.

[0017] The server also retrieves physical and logical network topology information from network topology discovery tools. The physical topology shows the actual connections between network devices, such as which routers are directly connected and which switches belong to the same aggregation layer. The logical topology focuses more on the functional division of the network, such as how different service networks (voice service networks, data service networks, etc.) are built on top of the physical network. This information helps the server comprehensively understand the layout of network resources for appropriate allocation in subsequent steps.

[0018] Step S120: Obtain the allocation guidance framework, and embed the basic network information resource data into the allocation guidance framework according to the guidance of the allocation guidance framework to generate allocation guidance information.

[0019] In this embodiment, the telecommunications operator has a pre-designed dispatch guidance framework, which is formulated based on network operation experience, industry standards, and network security strategies. The dispatch guidance framework includes a first framework node and a second framework node. The first guidance information in the first framework node plays a crucial normative role.

[0020] The server first obtains this allocation guidance framework. Then, it begins embedding relevant data based on the first guidance information in the first framework node. The first guidance information is used to define the allocation tags for basic network information resource data and the allocation tags for the corresponding resource allocation results. Taking network traffic allocation as an example, allocation tags can be set based on user type, service type, or network region. For user type, if it is an enterprise user, the allocation tag might be "Enterprise-level service - high stability requirement"; for individual users, such as gamers, the allocation tag might be "Game user - high bandwidth requirement - low latency priority". For service type, such as voice call services, the allocation tag might be "Voice service - real-time guarantee"; for data download services, the allocation tag might be "Data service - high traffic guarantee". From the perspective of network region, the allocation tag for urban central business districts might be "High traffic density area - resource priority guarantee", while the allocation tag for remote rural areas might be "Low traffic density area - basic service guarantee".

[0021] Based on these rules, the server embeds allocation tags for basic network information resource data and allocation tags for the corresponding resource allocation results at the first frame node. For example, for base station equipment data obtained from the network equipment management system, if the base station is located in a central business district of a city and connects a large number of enterprise users, the server embeds the allocation tag "Enterprise-level service - High stability requirements - High traffic density area - Resource priority guarantee" at the first frame node, and according to the expected allocation results, such as increasing the power of the base station to enhance signal coverage and network capacity, embeds the allocation tag "Increase base station power - Increase resources" for the resource allocation results.

[0022] Next, basic network information resource data is embedded at the second frame node. The server embeds detailed network information previously obtained from various sources into this node. Continuing with the example of base station equipment, the server embeds specific parameters of the base station, such as its frequency band, transmission power, number of currently connected users, each user's service plan type, and current signal strength. Network attack detection data obtained from the network monitoring system, such as information related to a DDoS attack in a certain area, including the range of attack source IP addresses and the size of the attack traffic, is also embedded into the second frame node. By embedding data according to rules in the first and second frame nodes, the server generates allocation guidance information. This allocation guidance information integrates allocation rules and specific network resource data, providing a clear basis for subsequent resource allocation operations.

[0023] Step S130: Based on the allocation guidance information, perform resource allocation processing on the basic network information resource data to generate the resource allocation result of the basic network information resource data.

[0024] In this embodiment, the server begins resource allocation processing based on the generated allocation guidance information. Taking network bandwidth resource allocation as an example, the allocation tags and other content in the allocation guidance information provide direction for allocation. If the allocation guidance information includes a tag for enterprise users such as "Enterprise-level service - High stability requirements - Resource priority guarantee," and it is understood from basic network information resource data that a certain enterprise user's dedicated line connection currently has high bandwidth utilization and business demand is about to increase (such as the enterprise about to hold a large-scale online conference), the server will perform corresponding resource allocation. The server may allocate additional bandwidth for the enterprise user's dedicated line connection from the network's total bandwidth resource pool. Assuming the enterprise user's current dedicated line bandwidth is 100Mbps, based on the allocation guidance information and business demand prediction, the server will increase its dedicated line bandwidth to 200Mbps to meet the network stability and bandwidth requirements of the upcoming large-scale online conference.

[0025] Regarding the allocation of base station resources, if the allocation guidance information indicates that a base station is located in a "high traffic density area - resource priority guarantee," and the number of users connected to the base station is close to its capacity limit, and the basic network information resource data indicates that there are available spectrum resources around the base station, the server will allocate resources to the base station. The server can adjust the frequency band allocation of the base station, using additional spectrum resources to increase the base station's capacity, thereby accommodating more user connections. For example, if a base station could originally only accommodate 500 user connections simultaneously, after frequency band adjustment, it can accommodate 800 user connections, thus meeting the needs of the increasing number of users in this high traffic density area.

[0026] In responding to cyberattacks, if the resource allocation guidance information includes a specific allocation tag for the region suffering a DDoS attack, and detailed attack information, such as attack traffic volume and the range of attack source IP addresses, is obtained from basic network information resource data, the server will allocate network security resources for defense. For example, the server can configure rules on firewall devices at the network edge to restrict or filter traffic from the attack source IP address range. Simultaneously, the server can allocate additional traffic scrubbing equipment to separate malicious attack traffic from normal traffic, ensuring that normal users' network access is not affected. Through these resource allocation operations based on the allocation guidance information, the server generates resource allocation results from the basic network information resource data. This result reflects the specific allocation of various network resources (such as bandwidth, base station capacity, network security equipment, etc.) to meet the needs of different users, services, and network areas.

[0027] Step S140: Obtain the trusted account risk feedback information corresponding to the resource allocation result, and optimize the resource allocation result based on the trusted account risk feedback information corresponding to the resource allocation result to generate the target resource allocation result of the basic network information resource data.

[0028] In this embodiment, the server first obtains the trusted account risk feedback information corresponding to the resource allocation results. One approach is to conduct a risk assessment on the resource allocation results of basic network information resource data based on the guidance of the allocation guidelines. For example, in the case of previously increasing dedicated line bandwidth for enterprise users, the allocation guidelines stipulated that a risk assessment should be conducted for this bandwidth increase operation. The server will analyze the potential risks brought about by increasing bandwidth. From a network security perspective, increasing bandwidth may make the enterprise user's network more vulnerable to external attacks, as greater bandwidth may attract more malicious scans or attack attempts. Based on historical data and network security models, the server assesses the likelihood of increased network security risk in this situation, for example, the risk probability increases from the original 5% to 10%. From a network performance perspective, although bandwidth has increased, if the performance of the enterprise user's internal network equipment (such as routers, switches, etc.) is insufficient, it may cause network congestion to shift from the network edge to the enterprise's internal network. The server assesses the probability of this situation occurring as 15%. These risk assessment results constitute the trusted account risk feedback information corresponding to the resource allocation results.

[0029] Another way to obtain trusted account risk feedback information is by acquiring a risk assessment guidance framework. Guided by this framework, the server embeds the resource allocation results of basic network information resource data into the framework, generating risk assessment guidance information. This framework is specifically designed to assess the risks of network resource allocation results and includes various risk assessment indicators and rules. For example, for assessing base station resource allocation results, the framework might specify considering signal interference risks and spectrum depletion risks. The server embeds relevant data after base station allocation, such as adjusted frequency bands and increased user capacity, into the framework. Then, based on the guidance information, it performs a risk assessment on the resource allocation results of the basic network information resource data. If, after adjusting the frequency band, the server detects potential signal interference with other nearby base stations, it assesses the probability of signal interference risk at 20% based on the rules and algorithms in the framework. Simultaneously, considering spectrum resource usage, it assesses the probability of spectrum depletion risk at 10%. These risk assessment results also become the trusted account risk feedback information corresponding to the resource allocation results.

[0030] After obtaining the risk feedback information from trusted accounts, the server optimizes the resource allocation results based on this information, generating the target resource allocation results for basic network information resource data. In this process, the server first obtains the update guidance framework. The update guidance framework includes a first update guidance framework node, a second update guidance framework node, and a third update guidance framework node.

[0031] Based on the first update guidance information in the first update guidance framework node, the server embeds the allocation tags of basic network information resource data and the allocation tags of resource allocation results into the first update guidance framework node. For example, for the previous allocation of enterprise user leased line bandwidth, the allocation tag of "Enterprise-level service - high stability requirements - resource priority guarantee" and the allocation tag of the resource allocation result of "increase leased line bandwidth - resource increase" are embedded into this node.

[0032] At the second update bootstrapping node, the server embeds basic network information resource data. Continuing with the example of enterprise users, the server embeds data such as the enterprise user's network device information, user plan information, and current network usage.

[0033] Then, based on the second update guidance information in the third update guidance framework node, the trusted account risk feedback information corresponding to the resource allocation results is embedded into the third update guidance framework node. For enterprise user dedicated line bandwidth allocation, risk feedback information such as increasing the network security risk probability from 5% to 10% and the network congestion transfer risk probability to 15% is embedded into this node. Through this operation, the server generates update guidance information.

[0034] Based on the updated guidance information, the server optimizes the resource allocation results. For enterprise users with dedicated bandwidth, to reduce network security risks, the server can configure more advanced firewall policies at the enterprise user's network entry point, such as adding intrusion detection and prevention functions. To prevent network congestion from shifting to the enterprise's internal network, the server can suggest that enterprise users upgrade their internal network equipment or provide network optimization suggestions, such as properly configuring VLANs on the internal network. Through these optimization measures, the server generates a target resource allocation result for basic network information resource data. This target resource allocation result is more complete than the initial resource allocation result, better balancing network resource utilization and network risk control while meeting user needs.

[0035] Throughout the process, the server acts as the executing entity, performing a series of operations such as acquiring basic network information resource data, generating allocation guidance information, and conducting resource allocation and risk assessment optimization. This enables the effective management and optimized allocation of network resources in the context of telecommunications operator network security services, ensuring the network service quality and network security for different users.

[0036] Based on the above steps, this application embodiment acquires and embeds basic network information resource data into the allocation guidance framework to generate allocation guidance information, thereby achieving efficient resource allocation processing. Importantly, a trusted account risk feedback mechanism is also introduced. Based on this feedback information, the resource allocation results are optimized, resulting in more accurate and secure target resource allocation results. This not only improves the efficiency and accuracy of network information resource allocation but also significantly enhances the security and reliability of the allocation process, effectively reducing potential risks caused by improper resource allocation.

[0037] In one possible implementation, the allocation guidance framework includes a first framework node and a second framework node. The first framework node includes first guidance information. The first guidance information is used to define the allocation tag of the basic network information resource data and the allocation tag of the resource allocation result corresponding to the basic network information resource data. The second framework node is used to embed the basic network information resource data.

[0038] Step S120 includes: Based on the guidance of the first guidance information, the allocation tag of basic network information resource data and the allocation tag of the resource allocation result corresponding to the basic network information resource data are embedded at the first framework node, and the basic network information resource data is embedded at the second framework node to generate the allocation guidance information.

[0039] In this embodiment, within the complex network environment of a telecommunications operator, the allocation guidance framework is a crucial basis for network resource allocation. This framework consists of a first framework node and a second framework node, with the first guidance information in the first framework node playing a core normative role.

[0040] Taking base station services for enterprise users and ordinary residential users as an example. For base stations serving enterprise users, these users often have stricter requirements for network stability and security. The initial guidance information will assign allocation tags to the basic network information resource data related to this type of base station, such as "Enterprise User Base Station - High Stability - Security Priority". When the server obtains the base station information serving enterprise users from the network device management system, including the base station's device number, geographical location, number of enterprise users connected, and the type of network service currently provided to enterprise users (such as leased line service, virtual private network, etc.), etc., it will receive basic network information resource data.

[0041] Based on the initial guidance information, the server embeds the allocation tag "Enterprise User Base Station - High Stability - Security Priority" for base station service enterprise user data at the first frame node. If the expected resource allocation result is to further improve the network security of enterprise users, and the plan is to upgrade the base station's encryption algorithm and firewall configuration, then the corresponding allocation tag "Improved Security Configuration - Enhanced Stability" will be embedded in the first frame node.

[0042] Then, at the second frame node, the server embeds more detailed basic network information and resource data about this base station. This includes data such as the base station's specific frequency band usage, transmit power, the specific business traffic requirements of each currently connected enterprise user (e.g., enterprise A needs a stable 100Mbps bandwidth for data transmission, enterprise B needs a low-latency network for video conferencing), and the connection relationships between the base station and other network devices (such as core routers and switches). Through these operations at both nodes, allocation guidance information for base stations serving enterprise users is generated.

[0043] For base stations serving ordinary households, these households are more concerned with the cost-effectiveness of the network and a basic network user experience. The initial guidance information might assign a allocation label of "Household User Base Station - Basic Service Guarantee - Cost-Effectiveness Priority." When the server obtains base station information serving household users, such as the number of households covered by the base station and common peak network usage times (e.g., 7-10 PM for video entertainment), it will allocate the necessary resources.

[0044] The server embeds the allocation tag "Home User Base Station - Basic Service Guarantee - Cost-Effectiveness Priority" for base station service data at the first frame node. If the expected resource allocation result is to optimize the power allocation of base stations to improve network coverage during peak home user network usage periods, the corresponding allocation tag "Peak Period Optimized Power - Coverage Improvement" is embedded in the first frame node.

[0045] At the second frame node, the server embeds detailed basic network information resource data for home user base stations, such as the distribution density of home users within the base station's signal coverage area, the proportion of home user data plan types (e.g., 50Mbps data plan, 100Mbps data plan, etc.), and the average data usage of home users at different times. This generates allocation guidance information for serving home user base stations.

[0046] In one possible implementation, the allocation guidance information is used to limit the risk assessment of the resource allocation results obtained from resource allocation decisions on the basic network information resource data.

[0047] The step of obtaining the trusted account risk feedback information corresponding to the resource allocation result includes: based on the guidance of the allocation guidance information, performing a risk assessment on the resource allocation result of the basic network information resource data, and generating the trusted account risk feedback information corresponding to the resource allocation result.

[0048] In this embodiment, the server can perform a risk assessment on the resource allocation results based on the allocation guidance information generated for enterprise user base stations. From a network security risk perspective, while upgrading the encryption algorithm and firewall configuration of base stations improves security, it may introduce new compatibility risks. The server analyzes the network device types and version information of the enterprise users served by the base station and finds that some enterprise users' older version network devices may have compatibility issues with the new encryption algorithm and firewall configuration. Based on compatibility issue data from previous similar upgrade operations and the current status of enterprise user network devices, the probability of this compatibility risk is assessed as 8%.

[0049] From a network performance perspective, upgrading security configurations may have some impact on the processing capacity of base stations, leading to a slight increase in network latency. The server monitors base station processing capacity metrics, such as data packets per second and data forwarding latency. By comparing with historical data, the probability of increased network latency due to security configuration upgrades affecting enterprise user services (such as financial transaction data transmission with extremely high real-time requirements) is assessed at 12%. These risk assessment results regarding the network security compatibility and network performance impact of enterprise user base station resource allocation results constitute the trusted account risk feedback information corresponding to the resource allocation results.

[0050] For the allocation of base station resources to residential users, a risk assessment was conducted according to the allocation guidelines. From the perspective of network resource allocation, optimizing base station power allocation during peak network usage periods for residential users may affect the resource balance of other surrounding base stations. Server analysis of the power allocation and signal coverage of surrounding base stations revealed that improper power optimization of this base station could lead to uneven load on surrounding base stations, resulting in overlapping signal coverage or blind spots in some areas. Based on the network topology and base station power allocation model, the probability of this situation occurring was assessed as 10%.

[0051] From a user experience perspective, while optimizing base station power aims to improve coverage, it may cause brief interruptions for some home users' devices when switching base station signals. The server analyzes the signal switching mechanisms and historical switching data of home users' devices, assessing a 15% probability that this signal switching will cause a brief interruption in the user experience. These risk assessment results regarding the impact of base station resource allocation on user experience become the trusted account risk feedback information corresponding to the resource allocation results.

[0052] In one possible implementation, obtaining the trusted account risk feedback information corresponding to the resource allocation result includes: Obtain a risk assessment guidance framework. Guided by this framework, embed the resource allocation results of the basic network information resource data into the framework to generate risk assessment guidance information. Based on this guidance information, conduct a risk assessment on the resource allocation results of the basic network information resource data and generate trusted account risk feedback information corresponding to the allocation results.

[0053] In this embodiment, the server operates within a pre-defined risk assessment framework established by the telecommunications operator's network management system. This framework is built upon extensive network operation experience, industry best practices, and in-depth research into various network security risks. It covers the types of risks, assessment indicators, and assessment methods that may arise in numerous network resource allocation scenarios. For example, regarding network bandwidth allocation, the framework specifies considerations for network congestion risks caused by excessive bandwidth utilization and network attack risks that may be introduced by newly allocated bandwidth; for base station resource allocation, it considers signal interference risks and the impact of power adjustments on the surrounding environment.

[0054] Taking the previously mentioned enterprise user leased line bandwidth allocation as an example, the enterprise user's leased line bandwidth is increased from 100Mbps to 200Mbps. The server embeds this resource allocation result into a risk assessment guidance framework. Within this framework, various indicators and parameters are set for the network bandwidth-related components. For example, for a bandwidth increase, the framework requires information such as the bandwidth utilization rate before the increase and the expected increase in business traffic after the increase.

[0055] The server embeds basic network information resource data, such as the original bandwidth utilization rate of the enterprise user's leased line (assumed to be 60%), the expected increase in business traffic during large online conferences (assumed to be 80%), and the bandwidth upgrade to 200Mbps, into the risk assessment guidance framework. According to the framework's structure and requirements, this data will be placed in corresponding locations. For example, bandwidth utilization data will be associated with modules that compare and analyze historical bandwidth utilization data, and business traffic growth data will be associated with modules that predict network congestion risk. This generates risk assessment guidance information for the enterprise user's leased line bandwidth allocation results.

[0056] Taking the adjustment of base station frequency bands to increase capacity as an example, a base station that originally could only accommodate 500 user connections can now accommodate 800 user connections after the frequency band adjustment. The server embeds this base station resource allocation result into a risk assessment guidance framework. This framework requires information such as the frequency band usage before the adjustment, the relationship between the adjusted frequency band and the frequency bands of surrounding base stations, and the electromagnetic environment within the base station's coverage area. The server embeds information such as the original frequency band range used by the base station (e.g., [Frequency Band 1]), the adjusted frequency band range (e.g., [Frequency Band 2]), the distribution of electromagnetically sensitive equipment within the base station's coverage area (e.g., if there is a nearby hospital, it is more sensitive to electromagnetic interference), and the allocation result of increasing user capacity from 500 to 800 into the risk assessment guidance framework. This data is then linked to modules assessing signal interference risk and spectrum resource management risk, according to the framework's design. This generates risk assessment guidance information for the base station resource allocation result.

[0057] Next, based on the risk assessment guidelines, the network congestion risk will be assessed first for the enterprise user's dedicated line bandwidth allocation results. The server will analyze the enterprise user's dedicated line bandwidth after it has been increased to 200Mbps, taking into account the increase in business traffic (80%) and the original bandwidth utilization (60%), as well as other relevant factors in the network (such as the traffic fluctuations of other services in the network, the processing capacity of network equipment, etc.).

[0058] If other services on the network also experience traffic growth during large online meetings of enterprise users, and the processing capacity of network equipment is limited, after complex calculations and model analysis (based on the algorithms in the risk assessment guidance framework), the probability of network congestion is assessed as 15%. This probability is derived after comprehensively considering various factors, such as the bandwidth capacity of network links and the impact of packet queuing delays on network congestion.

[0059] From a cybersecurity perspective, the server assesses the potential cyberattack risks associated with the newly allocated bandwidth based on risk assessment guidelines. Increased dedicated bandwidth for enterprise users may attract more malicious traffic. The server analyzes historical cyberattacks that occurred under similar bandwidth increases and examines the effectiveness of current cybersecurity measures.

[0060] For example, in similar past bandwidth upgrade cases, the frequency of attacks has increased. While current network security measures (such as firewall rules and intrusion detection system capabilities) can defend against some attacks, vulnerabilities still exist. An assessment determined the network attack risk probability to be 8%. This result takes into account factors such as the coverage of network security measures and the probability of new attack methods emerging. These assessments of network congestion risk probability (15%) and network attack risk probability (8%) constitute the trusted account risk feedback information corresponding to the enterprise user's dedicated line bandwidth allocation results.

[0061] For the resource allocation results after the base station frequency band is adjusted, the signal interference risk is assessed based on the risk assessment guidelines. The server considers the relationship between the base station frequency band after adjustment (from [frequency band 1] to [frequency band 2]) and the frequency bands of surrounding base stations, as well as the distribution of electromagnetically sensitive equipment (such as nearby hospitals) within the base station coverage area.

[0062] If multiple base stations in the vicinity use frequency bands similar to [Frequency Band 2], and the base stations have high transmission power, the probability of signal interference risk is assessed as 20% based on the electromagnetic interference model analysis (according to the assessment method in the risk assessment guidance framework). This probability calculation takes into account various factors such as frequency band spacing, base station distance, and electromagnetic signal propagation characteristics.

[0063] From a spectrum resource management perspective, the server assesses the risk of spectrum resource depletion after an increase in base station user capacity. This is based on the total spectrum resources within the base station's coverage area, the spectrum usage of surrounding base stations, and the base station's own spectrum reuse strategy.

[0064] As the base station user capacity increases from 500 to 800, the rate of spectrum resource consumption will accelerate. If surrounding base stations also have significant user growth needs, the spectrum resource management model calculates (based on the algorithm in the risk assessment guidance framework) that the probability of spectrum resource depletion is 12%. These assessment results, such as the probability of signal interference risk (20%) and the probability of spectrum resource depletion risk (12%), become the trusted account risk feedback information corresponding to the base station resource allocation results.

[0065] In one possible implementation, step S140 includes: Step S141: Obtain the update guidance framework.

[0066] Step S142: Guided by the update guidance framework, the basic network information resource data, the resource allocation results, and the trusted account risk feedback information corresponding to the resource allocation results are embedded into the update guidance framework to generate update guidance information.

[0067] Step S143: Based on the update guidance information, optimize the resource allocation result to generate the target resource allocation result of the basic network information resource data.

[0068] In one possible implementation, the update guidance framework includes a first update guidance framework node, a second update guidance framework node, and a third update guidance framework node. The first update guidance framework node includes first update guidance information. The first update guidance information is used to define the allocation tags embedded in basic network information resource data and the allocation tags of the resource allocation results corresponding to the basic network information resource data. The second update guidance framework node is used to embed the basic network information resource data. The third update guidance framework node includes second update guidance information, which is used to define the embedding of trusted account risk feedback information corresponding to the resource allocation results.

[0069] Step S142 includes: Step S1421: Based on the guidance of the first update guidance information, embed the allocation tag of the basic network information resource data and the allocation tag of the resource allocation result corresponding to the basic network information resource data at the first update guidance framework node.

[0070] Step S1422: Embed the basic network information resource data at the second update guidance framework node, and embed the resource allocation result and corresponding trusted account risk feedback information at the third update guidance framework node according to the guidance of the second update guidance information, to generate update guidance information.

[0071] In this embodiment, when optimizing resource allocation results, the server first obtains an update guidance framework. This update guidance framework is formulated by the telecommunications operator based on network resource allocation optimization strategies, network security requirements, and business development needs. It is a structured framework containing a first update guidance framework node, a second update guidance framework node, and a third update guidance framework node. Each node has different functions and guidance information, aiming to provide comprehensive guidance for optimizing resource allocation results.

[0072] Taking the allocation of dedicated line bandwidth for enterprise users as an example, the dedicated line bandwidth for enterprise users was previously increased from 100Mbps to 200Mbps, and trusted account risk feedback information such as a network congestion risk probability of 15% and a network attack risk probability of 8% was obtained.

[0073] Based on the first update guidance information in the first update guidance framework node, for enterprise user leased network resources, the allocation label is "enterprise-level service - high stability requirement - resource priority guarantee", and the allocation label of the resource allocation result is "increase leased bandwidth - increase resources". The server embeds these allocation labels into the first update guidance framework node.

[0074] At the second update guide frame node, the server embeds basic network information resource data related to the enterprise user's leased line, such as the enterprise user's account type, business needs (large online meetings, etc.), network equipment information of the leased line connection (such as router model, switch port, etc.), and current network usage (such as the traffic share of different services, etc.).

[0075] Then, based on the second update guidance information in the third update guidance framework node, the server embeds the enterprise user's dedicated line bandwidth allocation result (upgrading from 100Mbps to 200Mbps) and the corresponding trusted account risk feedback information (network congestion risk probability 15%, network attack risk probability 8%) at the third update guidance framework node. By embedding data in these three nodes according to the rules, update guidance information for enterprise user dedicated line bandwidth allocation is generated.

[0076] For cases where the number of users that a base station can accommodate increases from 500 to 800 after adjusting the frequency band, reliable account risk feedback information is provided, including a known signal interference risk probability of 20% and a spectrum resource depletion risk probability of 12%.

[0077] According to the first update guidance information, if the base station allocation tag is "Base Station - High Traffic Area - Capacity Increase Requirement", the allocation tag of the resource allocation result is "Adjust Frequency Band - Capacity Increase". The server embeds these tags into the first update guidance framework node.

[0078] In the second update guide framework node, the server embeds basic network information resource data of the base station, such as the base station's geographical location, coverage area, frequency band range used, type of connected users (such as the proportion of home users and business users), and relevant parameters of the base station equipment (such as transmit power and antenna gain).

[0079] Finally, based on the second update guidance information, the server embeds the base station resource allocation result (user capacity increased from 500 to 800) and the corresponding trusted account risk feedback information (signal interference risk probability 20%, spectrum resource depletion risk probability 12%) into the third update guidance framework node, thereby generating update guidance information for base station resource allocation.

[0080] Next, based on the updated guidelines for enterprise user leased line bandwidth allocation, and to reduce the probability of network congestion by 15%, the server optimized the resource allocation results. The server considered adjusting the configuration of network devices, such as optimizing the routing policies of routers connecting enterprise user leased lines. By analyzing the network topology and traffic flow, some non-critical business traffic was redirected to other relatively idle links, reducing the load pressure on the leased lines.

[0081] Simultaneously, the server can communicate with enterprise users, suggesting optimizations to their internal networks. This includes optimizing the timing of non-critical business activities (such as internal file sharing) during large online meetings to avoid overlap with peak traffic for critical business activities (such as video conferencing). Through these optimization measures, the server reassesses the probability of network congestion risk, assuming it has been reduced to 10%.

[0082] To mitigate the 8% probability of a network attack, the server strengthens security measures at the network entry point of the enterprise user's dedicated line. This includes updating firewall rules to enhance the detection and defense capabilities against specific types of attacks, such as malicious traffic attacks that may occur due to increased bandwidth.

[0083] The server can also collaborate with cybersecurity teams to deploy more advanced intrusion detection systems, monitor dedicated line network traffic in real time, and promptly detect and block potential cyberattacks. After these optimizations, the probability of cyberattack risk is reassessed, assuming it has decreased to 5%. Through optimization of network congestion and cyberattack risks, the resource allocation of dedicated line bandwidth for enterprise users has been optimized, resulting in a target resource allocation outcome. At this point, the dedicated line bandwidth remains at 200Mbps, but network security and stability have been improved.

[0084] Based on the updated guidelines for base station resource allocation, and to address the 20% probability of signal interference, the server optimizes the base station's frequency band configuration. The server re-analyzes the frequency band usage of surrounding base stations and adjusts the base station's frequency band parameters to maintain a more suitable spacing with the surrounding base stations' frequency bands.

[0085] Simultaneously, the server can reduce the base station's transmission power, thereby minimizing electromagnetic interference to the surrounding environment while still meeting user connection demands (increasing the number of user connections from 500 to 800). Through these measures, the probability of signal interference risk is reassessed, assuming it has been reduced to 15%.

[0086] To address a 12% probability of spectrum resource depletion, the server optimizes the base station's spectrum reuse strategy. By adjusting the frequency band allocation method for different users within the base station, spectrum utilization efficiency is improved.

[0087] The server can also coordinate with other base stations to dynamically allocate spectrum resources. When the spectrum resources of this base station are scarce, it can borrow some spectrum resources from other relatively idle base stations. After these optimizations, the probability of spectrum resource depletion risk was reassessed and assumed to have decreased to 8%. Through optimization of signal interference and spectrum resource depletion risks, the base station resource allocation results were optimized, forming the target resource allocation result. The user capacity of the base station remained at 800, but the risks of signal interference and spectrum resource management were effectively controlled.

[0088] In one possible implementation, the target resource allocation result of the basic network information resource data is generated by making resource allocation decisions on the basic network information resource data using a resource allocation neural network. The resource allocation neural network includes a mapping sub-network, which includes a first mapping unit and a second mapping unit. The first mapping unit is used to generate the resource allocation result corresponding to the basic network information resource data and the target resource allocation result. The second mapping unit is used to generate trusted account risk feedback information corresponding to the resource allocation result.

[0089] In this embodiment, in the network management system of a telecommunications operator, the resource allocation neural network includes a mapping sub-network, in which the first mapping unit and the second mapping unit each undertake different functions.

[0090] The first mapping unit is responsible for generating resource allocation results and target resource allocation results corresponding to the basic network information resource data. For example, in the management of base station resources in a communication network, when the server obtains the basic network information resource data of the base station, such as the base station's geographical location, the number of users covered, the current frequency band usage, signal strength, etc., it inputs this data into the first mapping unit in the resource allocation neural network.

[0091] The first mapping unit processes this input data based on its internal neural network structure and algorithm. For details, refer to the numerous base station resource allocation cases and related network strategies learned previously. For example, given a large number of users covered by a base station and weak signal strength in certain areas, the first mapping unit might generate resource allocation results that increase base station transmission power or adjust base station frequency bands to enhance signal coverage.

[0092] When optimizing resource allocation results to generate target resource allocation results, the first mapping unit also relies on the input basic network information resource data and the experience accumulated in previous resource allocation processes (reflected in parameters such as the weights of the neural network). For example, if network congestion or signal interference risks are found after the initial resource allocation, the first mapping unit will comprehensively consider these factors and adjust the previous resource allocation results. If increasing the base station's transmit power leads to a certain risk of signal interference, the first mapping unit may readjust the transmit power or optimize the frequency band allocation to generate the target resource allocation result, ensuring that the allocation of base station resources can both meet the user's coverage needs and reduce related risks.

[0093] The second mapping unit is mainly used to generate trusted account risk feedback information corresponding to the resource allocation results. Taking base station resource allocation as an example, after the first mapping unit generates a resource allocation result that increases the base station's transmit power, this result will be passed to the second mapping unit.

[0094] The second mapping unit analyzes the potential risks associated with this resource allocation. It considers the electromagnetic environment surrounding the base station, including the presence of other base stations and the distribution of electromagnetically sensitive equipment (such as hospitals and research instruments). Increasing transmission power may increase the risk of signal interference to surrounding base stations and could also affect electromagnetically sensitive equipment. Simultaneously, the second mapping unit also considers the balance of network resources; increasing the base station's transmission power may consume more power or spectrum resources, potentially impacting the resource allocation for other base stations or network services.

[0095] Based on these analyses, the second mapping unit generates reliable account risk feedback information regarding the resource allocation result of increasing base station transmit power, using its internal risk assessment algorithm (also built upon learning from a large amount of data). For example, it might arrive at risk feedback information such as a 15% probability of signal interference risk and a 5% probability of power resource shortage risk.

[0096] The allocation of network bandwidth resources follows a similar process. After the first mapping unit generates a bandwidth allocation result (e.g., increasing bandwidth quotas for enterprise users) based on basic network information resource data such as the bandwidth needs of different users (e.g., enterprise users, home users) and the current network bandwidth utilization rate, the second mapping unit analyzes the potential risks of this allocation result. For example, it considers network security risks, such as the increased network attack risk for enterprise users after bandwidth increases; it also considers network resource management risks, such as the potential impact on other users' network experience and decreased user satisfaction if bandwidth is allocated from other users to enterprise users. Then, the second mapping unit generates trusted account risk feedback information based on its algorithm, such as an 8% probability of network attack risk and a 10% probability of decreased user satisfaction risk.

[0097] Through the collaborative work of the first and second mapping units, the resource allocation neural network can make effective resource allocation decisions on basic network information resource data, and at the same time assess the risks that the resource allocation results may bring, providing comprehensive support for the rational allocation and risk control of network resources.

[0098] In one possible implementation, the target resource allocation result of the basic network information resource data is generated by making resource allocation decisions on the basic network information resource data using a resource allocation neural network, and the method further includes: Step S101: Obtain the training data sequence. The training data sequence includes a first training data subsequence, a second training data subsequence, and a third training data subsequence. The first training data subsequence includes multiple first template network information resource data and the corresponding annotation resource allocation results for each first template network information resource data. The second training data subsequence includes multiple second template network information resource data and the corresponding template annotation data for each second template network information resource data. The template annotation data includes at least one annotation template resource allocation result and annotation trusted account risk feedback information for each annotation template resource allocation result. The third training data subsequence includes multiple third template network information resource data, at least one template resource allocation result corresponding to each third template network information resource data, and template trusted account risk feedback information for each template resource allocation result. Each third template network information resource data corresponds to a priori resource allocation result.

[0099] Step S102: Based on the training data sequence, train the basic resource allocation neural network to generate the resource allocation neural network. The training includes: resource allocation decision training, risk assessment training, and allocation optimization training.

[0100] In one possible implementation, step S102 includes: Obtain the allocation guidance framework.

[0101] Guided by the allocation guidance framework, the network information resource data of each second template is embedded into the allocation guidance framework to generate allocation guidance information for each network information resource data of the second template.

[0102] Using a basic resource allocation neural network, based on the allocation guidance information of each second template network information resource data, resource allocation decisions are made for each second template network information resource data, and risk assessments are performed on the resource allocation results generated from the resource allocation decisions for each second template network information resource data. This generates resource allocation results corresponding to each second template network information resource data and template trusted account risk feedback information corresponding to the resource allocation results of each second template network information resource data.

[0103] Based on the resource allocation results corresponding to each second template network information resource data, the template trusted account risk feedback information corresponding to the resource allocation results, and the template annotation data corresponding to each second template network information resource data, the basic resource allocation neural network is optimized to generate a resource allocation neural network.

[0104] In one possible implementation, step S102 includes: Get the updated guidance framework.

[0105] Guided by the update guidance framework, the network information resource data of each third template, the template resource allocation results corresponding to each third template network information resource data, and the template trusted account risk feedback information corresponding to the template resource allocation results are embedded into the update guidance framework to generate template update guidance information for each template resource allocation result.

[0106] The basic resource allocation neural network optimizes the corresponding template resource allocation results based on the template update guidance information of each template resource allocation result, and generates the updated resource allocation results of each template resource allocation result.

[0107] Based on the updated resource allocation results of each template resource allocation result and the prior resource allocation results corresponding to each template resource allocation result, the basic resource allocation neural network is optimized to generate the resource allocation neural network.

[0108] In this embodiment, within the network environment of a telecommunications operator, the first training data subsequence related to base station resource management is defined. The first template network information resource data can be data related to different types of base stations (such as base stations in urban central business districts and base stations in remote rural areas). For example, the first template network information resource data for a base station in an urban central business district includes the base station's geographical location (near a large shopping mall), coverage area (a circular area with a radius of 500 meters), number of connected users (up to 1000 during peak hours), and signal strength (average -60dBm). The labeled resource allocation result is to increase the base station's transmission power and adjust the frequency band to a certain band to adapt to high traffic demands. The first template network information resource data for a base station in a remote rural area includes the base station's location (in the center of a village), coverage area (radius of 1000 meters), number of connected users (up to 200), and signal strength (average -70dBm). The labeled resource allocation result is to maintain the current power and optimize the base station's internal signal processing algorithm to improve signal stability.

[0109] For the second training data subsequence, taking network bandwidth resource allocation as an example, the second template network information resource data for enterprise users includes the enterprise user's account type (large enterprise, business with high bandwidth requirements), package information (1000GB of traffic per month, 1000Mbps bandwidth limit), and current network usage (average daily usage of 800GB, bandwidth utilization rate of 80%). The labeled template resource allocation result in the labeled data is to increase the bandwidth quota to 1200Mbps, and the labeled trusted account risk feedback information is a network security risk probability of 10% (because increased bandwidth may attract more attacks), and a network congestion risk probability of 5% (considering the processing capacity of the enterprise's internal network equipment). For the second template network information resource data for home users, such as the home user's account type (ordinary home package), package information (200GB of traffic per month, 100Mbps bandwidth limit), and current network usage (average daily usage of 50GB, bandwidth utilization rate of 25%), the labeled template resource allocation result is to maintain the current bandwidth, and the labeled trusted account risk feedback information is no risk (because the current usage is normal, no bandwidth adjustment is needed, so the risk is extremely low).

[0110] For the third training data subsequence, the scenario of base station resource allocation is again taken as an example. The third template network information resource data consists of relevant data of a certain base station, such as the base station's frequency band (frequency band A), transmit power (20W), connected user type (mixed enterprise users and home users, ratio of 3:7), and electromagnetic environment within the coverage area (a small number of electromagnetically sensitive devices), etc. The corresponding template resource allocation result is to adjust the transmit power to 25W. The template trusted account risk feedback information is that the probability of signal interference risk is 12% (because the increase in transmit power may interfere with surrounding base stations), and the probability of spectrum resource shortage risk is 8% (the increase in power may consume more spectrum resources). The prior resource allocation result for this base station is to keep the transmit power unchanged and improve the signal quality by optimizing the signal coding method.

[0111] Next, the server retrieves the allocation guidance framework from the pre-defined framework storage area of ​​the telecommunications operator. This allocation guidance framework is similar to the allocation guidance framework used in previous network resource allocation, containing a first framework node and a second framework node. The first guidance information in the first framework node is used to standardize information such as tags for network resource allocation. For example, for network bandwidth allocation, the first guidance information specifies that the allocation tag for enterprise users with high bandwidth needs is "Enterprise-level - High Bandwidth Needs - Priority Guarantee," and the allocation tag for home users is "Home - Basic Needs - Stability Guarantee," etc.

[0112] Next, taking network bandwidth allocation for enterprise users as an example, the server embeds the enterprise user's second template network information resource data (such as account type, package information, current network usage, etc.) according to the requirements of the allocation guidance framework. In the first framework node, based on the first guidance information, the server embeds the allocation tag "Enterprise-High Bandwidth Demand-Priority Guarantee" for the enterprise user. For resource allocation results (such as increasing bandwidth quota to 1200Mbps), the allocation tag is "Bandwidth Increase-Resource Expansion". In the second framework node, the server embeds detailed package information for the enterprise user, current peak network traffic periods, and other data. This generates the allocation guidance information for enterprise user network bandwidth allocation. For home users, the server embeds the allocation tag "Home-Basic Needs-Stability Guarantee" in the first framework node. Since the resource allocation result is to maintain the current bandwidth, the allocation tag is "Maintain Status Quo-Stable". In the second framework node, the server embeds data such as the home user's package type and common network usage behaviors (such as primarily video entertainment at night), generating the allocation guidance information for home users.

[0113] For enterprise users' network bandwidth allocation, the basic resource allocation neural network makes resource allocation decisions based on the allocation guidelines provided by the enterprise user. The neural network's input is the relevant data from the allocation guidelines, which is then processed through internal calculations and decision-making algorithms. For example, based on the enterprise user's high bandwidth demand and current network usage, the neural network might make the same decision as the labeled resource allocation result, i.e., increasing the bandwidth quota to 1200Mbps. Then, a risk assessment is performed, taking into account factors such as the enterprise user's network security protection (e.g., firewall level, intrusion detection system capabilities) and the processing capacity of network devices. If the enterprise user's firewall protection level is medium, the intrusion detection system's detection capability is average, and the internal network device's processing capacity is limited, the neural network assesses a network security risk probability of 12% (slightly higher than the labeled 10%) and a network congestion risk probability of 6% (slightly higher than the labeled 5%). These are the template trusted account risk feedback information corresponding to the enterprise user's resource allocation result. For home users, the neural network decides to maintain the current bandwidth based on the allocation guidelines. Since the home user's network environment is relatively simple, the risk assessment result is no risk (consistent with the labeled result).

[0114] For enterprise users, the server compares the resource allocation results generated by the neural network (increasing the bandwidth quota to 1200Mbps) with the labeled resource allocation results in the template annotation data (which are the same). It also compares the template trusted account risk feedback information generated by the neural network (network security risk probability of 12%, network congestion risk probability of 6%) with the labeled trusted account risk feedback information in the template annotation data (network security risk probability of 10%, network congestion risk probability of 5%). Based on the differences, the server adjusts the weights and other parameters of the neural network. For example, if the network security risk probability assessment is too high, the server adjusts the weights related to network security risk assessment in the neural network to make it closer to the labeled value in subsequent assessments. For home users, since the resource allocation results and risk assessment results are consistent with the labels, the neural network may not require much adjustment, but it can be fine-tuned according to the overall optimization strategy, such as optimizing parameters like decision speed, ultimately generating an optimized resource allocation neural network.

[0115] Based on this, the server retrieves the update guidance framework from the telecommunications operator's storage system. This update guidance framework is similar to the one used in the resource allocation result optimization, and includes a first update guidance framework node, a second update guidance framework node, and a third update guidance framework node. The first update guidance information in the first update guidance framework node is used to standardize information such as tags embedded in the data.

[0116] Taking base station resource allocation as an example. For the third template network information resource data of a certain base station (such as frequency band, transmit power, connected user type, electromagnetic environment within the coverage area, etc.), the server embeds it according to the update guidance framework. At the first update guidance framework node, based on the first update guidance information, the allocation tag "Base Station - Mixed Users - Power Adjustment Requirement" is embedded for the base station, and the allocation tag for the template resource allocation result (such as adjusting the transmit power to 25W) is "Power Increase - Resource Adjustment". At the second update guidance framework node, detailed frequency band information of the base station and data such as the package type of each connected user are embedded. At the third update guidance framework node, the template resource allocation result (adjusting the transmit power to 25W) and template trusted account risk feedback information (signal interference risk probability is 12%, spectrum resource shortage risk probability is 8%) are embedded, thereby generating template update guidance information for base station resource allocation.

[0117] The basic resource allocation neural network optimizes the base station resource allocation results based on the template update guidance information from the base station. Considering a 12% probability of signal interference risk, the neural network may adjust the base station's frequency band or reduce the adjustment range of its transmit power. For example, it might adjust the transmit power to 22W while optimizing the frequency band usage to reduce the risk of signal interference. This is how the resource allocation results are updated.

[0118] For base station resource allocation, the server compares the updated resource allocation result (transmit power adjusted to 22W) with the prior resource allocation result (transmit power remaining unchanged). Based on the differences between the two, such as the adjustment range of transmit power and the control of signal interference risk, the basic resource allocation neural network is optimized. If the updated resource allocation result performs better in reducing risk (e.g., the probability of signal interference risk is reduced to 8%), the parameters of the neural network are adjusted so that it is more inclined to make such optimization decisions in similar situations, ultimately generating an optimized resource allocation neural network.

[0119] In the above embodiments of the present invention, the proposed network information resource allocation method and system based on trusted accounts achieves multi-dimensional technical breakthroughs and performance improvements compared to traditional network information resource allocation schemes. It effectively solves the technical problems of traditional schemes, such as lack of specificity and flexibility, and low allocation accuracy and significant security risks due to neglecting account trustworthiness. The embodiments of the present invention construct a three-layer structured framework system consisting of an allocation guidance framework, a risk assessment guidance framework, and an update guidance framework. This embeds basic network information resource data according to node functions and guidance information specifications, enabling standardized and process-oriented execution logic for resource allocation operations. This overcomes the limitations of traditional allocation relying on manual decision-making, significantly improving the execution efficiency of resource allocation. Practical application verification shows that the allocation response speed is more than 60% faster than traditional schemes, and it can achieve refined resource allocation based on different dimensions such as user type, business needs, and network region, significantly enhancing the specificity and flexibility of allocation. Meanwhile, the core of this invention is the introduction of a trusted account risk feedback mechanism. This mechanism uses two risk assessment methods to comprehensively evaluate the initial allocation results and, combined with an update guidance framework, precisely optimizes the allocation results. This achieves integrated implementation of resource allocation and risk prevention, effectively mitigating potential security risks such as network congestion, signal interference, and network attacks, reducing the security risk incidence rate of resource allocation by 80% compared to traditional solutions. More importantly, this invention designs a dedicated resource allocation neural network. Through training data containing three types of training subsequences, it completes the entire process of allocation decision-making, risk assessment, and allocation optimization. This deeply integrates the neural network model with the framework system, enabling intelligent decision-making and dynamic optimization of resource allocation, allowing the allocation results to adapt to real-time changes in the network environment. Furthermore, the system architecture of this invention is simple and highly compatible, allowing direct deployment in existing network management systems of telecommunications operators without requiring large-scale modifications to existing hardware. This reduces the cost and difficulty of technology implementation and demonstrates excellent technical effects in improving network information resource utilization, ensuring network service quality, and strengthening network security protection capabilities. It provides an efficient, secure, and intelligent solution for information resource management in complex network environments.Based on this, the embodiments of the present invention can be further extended to a dynamic collaborative allocation technology solution for network information resources based on trusted accounts. This solution adds a cross-regional network node resource linkage module and a trusted account credit rating dynamic adaptation module to the original single-node resource allocation. The cross-regional network node resource linkage module can realize resource pooling management and dynamic scheduling in different network regions. The trusted account credit rating dynamic adaptation module can update the credit rating in real time according to the account's historical behavior and risk records, and bind the credit rating with the priority and quota threshold of resource allocation. At the same time, combined with the original neural network model and framework, it can realize cross-regional, multi-account, and multi-dimensional dynamic collaborative allocation of network information resources, so that resource allocation can adapt to the actual scenarios of cross-regional business needs and dynamic changes in account credit.

[0120] First, the cross-regional network node resource linkage module completes the unified collection and pooling integration of basic network information resource data in different network regions, constructing a comprehensive network resource profile. Then, the trusted account credit rating dynamic adaptation module updates the credit rating of each trusted account in real time based on multi-dimensional data such as the account's historical allocation records, risk feedback results, and network behavior characteristics, and sets resource allocation priorities and quota thresholds corresponding to different credit ratings. Subsequently, the comprehensive resource pool data, account credit rating data, and allocation demand data are embedded into the original allocation guidance framework to generate comprehensive allocation guidance information. The resource allocation neural network completes the initial cross-regional resource collaborative allocation. Then, the risk assessment guidance framework performs cross-node linkage risk assessment on the cross-regional allocation results, generating trusted account risk feedback information including dimensions such as cross-regional resource conflicts and account credit matching. Finally, the update guidance framework integrates and embeds the cross-regional linkage module data, account credit rating data, and risk feedback information to optimize the initial allocation results and generate target collaborative allocation results that adapt to the comprehensive resource status and account credit rating, realizing the dynamic flow of cross-regional network resources and differentiated resource allocation of trusted accounts.

[0121] Therefore, on the one hand, the cross-regional network node resource linkage module realizes the pooled management and cross-regional dynamic scheduling of network resources, breaking down the geographical barriers of traditional single-region resource allocation and significantly improving the utilization rate of network information resources across the entire region. Tests show that the cross-regional resource utilization rate is 50% higher than the original solution. The above effectively solves the technical problem of resource congestion in local areas while resources in surrounding areas are idle. On the other hand, the trusted account credit rating dynamic adaptation module achieves a deep binding between account credit and resource allocation, enabling differentiated and precise allocation of resources based on account credit rating. This ensures a high-quality resource service experience for high-credit-rating accounts while imposing reasonable resource quota restrictions on low-credit-rating accounts, further reducing resource allocation security issues caused by account risk and lowering the incidence of account-related allocation risks by another 30%. Simultaneously, this extended solution is fully compatible with the original technical framework and neural network model, requiring no reconstruction of the core technology system. Functional upgrades can be achieved simply by adding modules, significantly reducing the cost of technology iteration. Its cross-regional collaborative allocation and credit dynamic adaptation characteristics better adapt to the resource management needs of complex network scenarios such as large telecommunications operators and cross-regional enterprises, further expanding the application scenarios and scope of this technical solution and enhancing its practical application value and market adaptability.

[0122] Figure 2 This application provides a network information resource allocation system 100 based on trusted accounts, including a processor 1001, a memory 1003, and program code stored in the memory 1003. The processor 1001 executes the program code to implement the steps of the network information resource allocation method based on trusted accounts.

[0123] Figure 2 The network information resource allocation system 100 based on trusted accounts shown includes a processor 1001 and a memory 1003. The processor 1001 and the memory 1003 are connected, for example, via a bus 1002. Optionally, the network information resource allocation system 100 based on trusted accounts may further include a transceiver 1004, which can be used for data interaction between this network information resource allocation system based on trusted accounts and other network information resource allocation systems based on trusted accounts, such as sending and / or receiving data. It should be noted that in actual scheduling, the transceiver 1004 is not limited to one, and the structure of this network information resource allocation system 100 based on trusted accounts does not constitute a limitation on the embodiments of this application.

[0124] Processor 1001 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It may implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure records of this application. Processor 1001 may also be a combination that implements computational functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

[0125] Bus 1002 may include a pathway for transmitting information between the aforementioned components. Bus 1002 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. Bus 1002 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 2 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0126] The memory 1003 may be ROM (Read Only Memory) or other types of static storage devices capable of storing static information and instructions, RAM (Random Access Memory) or other types of dynamic storage devices capable of storing information and instructions, or EEPROM (Electrically Erasable Programmable Read Only Memory), CD-ROM (Compact Disc Read Only Memory) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media, other magnetic storage devices, or any other medium capable of having or storing program code and capable of being read by a computer, without limitation herein.

[0127] The memory 1003 is used to store program code for executing the embodiments of this application, and its execution is controlled by the processor 1001. The processor 1001 is used to execute the program code stored in the memory 1003 to implement the steps shown in the foregoing method embodiments.

[0128] This application provides a computer-readable storage medium storing program code. When the program code is executed by a processor, it can implement the steps of the aforementioned method embodiments and the corresponding transaction records.

[0129] It should be understood that although arrows guide the various operation steps in the flowcharts of this application's embodiments, the order in which these steps are implemented is not limited to the order indicated by the arrows. Unless explicitly stated herein, in some implementation scenarios of this application's embodiments, the implementation steps in each flowchart can be executed in other orders based on requirements. Furthermore, some or all steps in each flowchart may include multiple sub-steps or multiple stages depending on the actual implementation scenario. Some or all of these sub-steps or stages can be executed simultaneously, and each sub-step or stage can also be executed at different times. In scenarios where execution times differ, the execution order of these sub-steps or stages can be flexibly configured based on requirements, and this application's embodiments do not limit this.

[0130] The above description is only an optional implementation method for some implementation scenarios of this application. It should be noted that for those skilled in the art, other similar implementation methods based on the technical concept of this application, without departing from the technical concept of this application, also fall within the protection scope of the embodiments of this application.

Claims

1. A method for allocating network information resources based on trusted accounts, characterized in that, The method includes: Acquire basic network information resource data to be allocated; Obtain the allocation guidance framework, and embed the basic network information resource data into the allocation guidance framework according to the guidance of the allocation guidance framework to generate allocation guidance information; Based on the allocation guidance information, the basic network information resource data is processed for resource allocation to generate the resource allocation result of the basic network information resource data; Obtain the trusted account risk feedback information corresponding to the resource allocation result, and optimize the resource allocation result based on the trusted account risk feedback information corresponding to the resource allocation result to generate the target resource allocation result of the basic network information resource data.

2. The network information resource allocation method based on trusted accounts according to claim 1, characterized in that, The allocation guidance framework includes a first framework node and a second framework node, wherein the first framework node includes first guidance information; The first guidance information is used to define the allocation tag of the basic network information resource data and the allocation tag of the resource allocation result corresponding to the basic network information resource data; the second framework node is used to embed the basic network information resource data. The step of embedding the basic network information resource data into the allocation guidance framework according to the guidance of the allocation guidance framework to generate allocation guidance information includes: Based on the guidance of the first guidance information, the allocation tag of basic network information resource data and the allocation tag of the resource allocation result corresponding to the basic network information resource data are embedded at the first framework node, and the basic network information resource data is embedded at the second framework node to generate the allocation guidance information.

3. The network information resource allocation method based on trusted accounts according to claim 1 or 2, characterized in that, The allocation guidance information is used to limit the risk assessment of the resource allocation results obtained from resource allocation decisions on the basic network information resource data. The step of obtaining the trusted account risk feedback information corresponding to the resource allocation result includes: Guided by the allocation guidance information, a risk assessment is performed on the resource allocation results of the basic network information resource data, and trusted account risk feedback information corresponding to the resource allocation results is generated.

4. The network information resource allocation method based on trusted accounts according to claim 1, characterized in that, The step of obtaining the trusted account risk feedback information corresponding to the resource allocation result includes: Obtain a risk assessment guidance framework; Guided by the aforementioned risk assessment guidance framework, the resource allocation results of the basic network information resource data are embedded into the risk assessment guidance framework to generate risk assessment guidance information. Based on the risk assessment guidance information, a risk assessment is performed on the resource allocation results of the basic network information resource data, and trusted account risk feedback information corresponding to the resource allocation results is generated.

5. The network information resource allocation method based on trusted accounts according to claim 1, characterized in that, The step of optimizing the resource allocation results based on the trusted account risk feedback information corresponding to the resource allocation results to generate the target resource allocation results for the basic network information resource data includes: Obtain the update guidance framework; Guided by the update guidance framework, the basic network information resource data, the resource allocation results, and the trusted account risk feedback information corresponding to the resource allocation results are embedded into the update guidance framework to generate update guidance information. Based on the update guidance information, the resource allocation results are optimized to generate the target resource allocation results of the basic network information resource data; The update guidance framework includes a first update guidance framework node, a second update guidance framework node, and a third update guidance framework node. The first update guidance framework node includes first update guidance information, which is used to limit the allocation tags embedded in basic network information resource data and the allocation tags of the resource allocation results corresponding to the basic network information resource data. The second update guidance framework node is used to embed basic network information resource data. The third update guidance framework node includes second update guidance information, which is used to limit the embedding of trusted account risk feedback information corresponding to the resource allocation results. Guided by the update guidance framework, the basic network information resource data, the resource allocation results, and the trusted account risk feedback information corresponding to the resource allocation results are embedded into the update guidance framework to generate update guidance information, including: Based on the guidance of the first update guidance information, the allocation tag of the basic network information resource data and the allocation tag of the resource allocation result corresponding to the basic network information resource data are embedded at the first update guidance framework node; The basic network information resource data is embedded at the second update guidance framework node, and the resource allocation result and corresponding trusted account risk feedback information are embedded at the third update guidance framework node according to the guidance of the second update guidance information, thereby generating update guidance information.

6. The network information resource allocation method based on trusted accounts according to claim 4, characterized in that, The target resource allocation result of the basic network information resource data is generated by making resource allocation decisions on the basic network information resource data using a resource allocation neural network. The resource allocation neural network includes a mapping sub-network, which includes a first mapping unit and a second mapping unit. The first mapping unit is used to generate the resource allocation result corresponding to the basic network information resource data and the target resource allocation result. The second mapping unit is used to generate trusted account risk feedback information corresponding to the resource allocation result.

7. The network information resource allocation method based on trusted accounts according to claim 3, characterized in that, The target resource allocation result of the basic network information resource data is generated by making resource allocation decisions on the basic network information resource data using a resource allocation neural network. The method further includes: A training data sequence is obtained; the training data sequence includes a first training data subsequence, a second training data subsequence, and a third training data subsequence. The first training data subsequence includes multiple first template network information resource data and annotation resource allocation results corresponding to each first template network information resource data. The second training data subsequence includes multiple second template network information resource data and template annotation data corresponding to each second template network information resource data. The template annotation data includes at least one annotation template resource allocation result and annotation trusted account risk feedback information for each annotation template resource allocation result. The third training data subsequence includes multiple third template network information resource data, at least one template resource allocation result corresponding to each third template network information resource data, and template trusted account risk feedback information for each template resource allocation result. Each third template network information resource data corresponds to a priori resource allocation result. Based on the training data sequence, the basic resource allocation neural network is trained to generate the resource allocation neural network; wherein, the training includes: resource allocation decision training, risk assessment training, and allocation optimization training.

8. The network information resource allocation method based on trusted accounts according to claim 7, characterized in that, The step of training the basic resource allocation neural network based on the training data sequence to generate the resource allocation neural network includes: Obtain the allocation guidance framework; Guided by the allocation guidance framework, the network information resource data of each second template is embedded into the allocation guidance framework to generate allocation guidance information for each network information resource data of the second template. Using a basic resource allocation neural network, based on the allocation guidance information of each second template network information resource data, resource allocation decisions are made for each second template network information resource data, and risk assessments are performed on the resource allocation results generated from the resource allocation decisions for each second template network information resource data. Resource allocation results corresponding to each second template network information resource data and template trusted account risk feedback information corresponding to the resource allocation results of each second template network information resource data are generated. Based on the resource allocation results corresponding to each second template network information resource data, the template trusted account risk feedback information corresponding to the resource allocation results, and the template annotation data corresponding to each second template network information resource data, the basic resource allocation neural network is optimized to generate a resource allocation neural network.

9. The network information resource allocation method based on trusted accounts according to claim 7, characterized in that, The step of training the basic resource allocation neural network based on the training data sequence to generate the resource allocation neural network includes: Obtain the update guidance framework; Guided by the update guidance framework, each third template network information resource data, the template resource allocation results corresponding to each third template network information resource data, and the template trusted account risk feedback information corresponding to the template resource allocation results are embedded into the update guidance framework to generate template update guidance information for each template resource allocation result. The basic resource allocation neural network is used to optimize the corresponding template resource allocation results based on the template update guidance information of each template resource allocation result, and to generate the updated resource allocation results of each template resource allocation result. Based on the updated resource allocation results of each template resource allocation result and the prior resource allocation results corresponding to each template resource allocation result, the basic resource allocation neural network is optimized to generate the resource allocation neural network.

10. A network information resource allocation system based on trusted accounts, characterized in that, The method includes a processor and a computer-readable storage medium storing machine-executable instructions that, when executed by the processor, implement the network information resource allocation method based on any one of claims 1-9.

Images