Method, device and electronic equipment for analyzing wireless network spectrum

Abstract

The application provides a wireless network spectrum analysis method, device and electronic equipment, and belongs to the wireless network field, to solve the problem that the existing method cannot comprehensively reflect the utilization efficiency, coverage condition, service carrying capacity and future development trend of the spectrum. The method comprises the following steps: obtaining engineering parameters and network management data of a region to be analyzed; performing spectrum coverage analysis according to the engineering parameters to obtain spectrum coverage indexes, wherein the spectrum coverage indexes comprise coverage rates or average inter-station distances of different frequency bands or different modes; determining a first index set and a second index set based on the network management data, wherein the first index set comprises user carrying class indexes, and the second index set comprises unit spectrum carrying efficiency class indexes; obtaining a social benefit index according to the spectrum coverage indexes and the first index set, and obtaining an economic benefit according to the second index set.

Description

Technical Field

[0001] This application relates to the field of wireless networks, and more particularly to a method, apparatus, electronic device, and computer program product for analyzing the spectrum of a wireless network. Background Technology

[0002] Existing wireless network spectrum analysis methods primarily rely on code channel utilization in Code Division Multiple Access (CDMA) systems and physical resource block (PRB) utilization in Long Term Evolution (LTE) / 5G systems. These methods assess frequency resource utilization by calculating the ratio of busy-hour occupancy to the total system resources. However, these methods only focus on the resource proportion during busy hours, resulting in a limited evaluation dimension and failing to comprehensively reflect spectrum utilization efficiency, coverage, service carrying capacity, and future development trends. Summary of the Invention

[0003] This application provides a method, apparatus, electronic device, and computer program product for analyzing wireless network spectrum, which can solve the problem that existing methods cannot fully reflect spectrum utilization efficiency, coverage, service carrying capacity, and future development trends.

[0004] In a first aspect, embodiments of this application provide a method for analyzing the spectrum of a wireless network, the method comprising the following steps: Obtain engineering parameters and network management data for the area to be analyzed; Based on the engineering parameters, a spectrum coverage analysis is performed to obtain spectrum coverage indicators, which include coverage rates or average station spacing for different frequency bands or different standards. Based on the network management data, a first set of indicators and a second set of indicators are determined. The first set of indicators includes user carrying capacity indicators, and the second set of indicators includes unit spectrum carrying efficiency indicators. The social benefit index is obtained based on the spectrum coverage index and the first index set, and the economic benefit index is obtained based on the second index set. The social benefit index and the economic benefit index constitute a comprehensive index of the wireless network spectrum.

[0005] Secondly, embodiments of this application provide a wireless network spectrum analysis apparatus, which includes the following: The data acquisition module is used to acquire engineering parameters and network management data of the area to be analyzed. The engineering parameter module is used to perform spectrum coverage analysis based on the engineering parameters to obtain spectrum coverage indicators, which include coverage rates or average station spacing for different frequency bands or different standards. The network management data module is used to determine a first indicator set and a second indicator set based on the network management data. The first indicator set includes user-bearing indicators, and the second indicator set includes unit spectrum carrying efficiency indicators. The evaluation index module is used to obtain a social benefit index based on the spectrum coverage index and the first index set, and to obtain an economic benefit index based on the second index set. The social benefit index and the economic benefit index constitute a comprehensive index of the wireless network spectrum.

[0006] Thirdly, embodiments of this application provide an electronic device including a processor, a memory, and a program or instructions stored in the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the steps of the wireless network spectrum analysis method as described in the first aspect.

[0007] Fourthly, embodiments of this application provide a computer program product, the computer program product including a computer program stored on a non-transitory computer-readable storage medium, the computer program including program instructions, which, when executed by a computer, implement the steps of the wireless network spectrum analysis method as described in the first aspect.

[0008] This application's embodiments, by integrating spectrum coverage indicators, user carrying capacity indicators, and unit spectrum carrying efficiency indicators, enable a comprehensive evaluation of wireless network spectrum from multiple dimensions, including coverage, service carrying capacity, and spectrum utilization efficiency. By combining spectrum coverage indicators with user carrying capacity indicators to construct a social benefit index, it objectively reflects the actual contributions of different frequency bands or standards in terms of coverage and user services, providing quantifiable technical indicators for assessing the social value of spectrum resources. Based on unit spectrum carrying efficiency indicators, an economic benefit index is derived, used to quantitatively evaluate the input-output efficiency of spectrum resources, providing a data foundation for optimizing operator spectrum resource allocation. Integrating the social benefit index and the economic benefit index into a comprehensive index allows for a rapid understanding of the overall spectrum situation when evaluating the spectrum landscape. Based on engineering parameters and network management data, it is applicable to different communication standards and frequency band combinations, and the indicator composition and dimensionality reduction methods can be adjusted according to actual needs, demonstrating good applicability. Attached Figure Description

[0009] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0010] Figure 1This is a flowchart illustrating a method for analyzing the spectrum of a wireless network provided in an embodiment of this application; Figure 2 This is a flowchart illustrating another method for analyzing the spectrum of a wireless network provided in an embodiment of this application; Figure 3 This is a flowchart illustrating another wireless network spectrum analysis method provided in an embodiment of this application; Figure 4 This is a radar chart illustrating the social benefits of the 2G communication standard provided in this application embodiment; Figure 5 This is a radar chart illustrating the social benefits of the 4G communication standard provided in this application embodiment; Figure 6 This is a radar chart illustrating the economic benefits of the 4G communication standard provided in this application embodiment; Figure 7 This is a radar chart illustrating the economic benefits of the 5G communication standard provided in this application embodiment; Figure 8 This is a radar chart illustrating the economic benefits of the 4G+5G communication standard provided in the embodiments of this application. Figure 9a , 9b 9c is a schematic diagram of the time series prediction effect provided in the embodiments of this application; Figure 10 This is a radar chart based on time series prediction provided in an embodiment of this application; Figure 11 This is a schematic diagram of the structure of a wireless network spectrum analysis device provided in an embodiment of this application; Figure 12 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0011] To enable those skilled in the art to better understand the technical solutions in this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this application.

[0012] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such use of data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0013] Currently, there are few methods for spectrum situation analysis. Similar methods include common frequency utilization assessment methods such as busy-hour resource block (RB) utilization.

[0014] For example, in a CDMA system, the code channel utilization rate is obtained by calculating the ratio of the number of busy-hour code channels to the total number of code channels in the system. The calculation method is as follows:

[0015] in, B is the number of code channels occupied during busy time i, and B is the total number of code channels in the CDMA system.

[0016] For example, in LTE / 5G systems, the PRB utilization rate is obtained by calculating the ratio of the number of busy-hour Physical Resource Blocks (PRBs) to the total number of PRBs in the system. The calculation method is as follows:

[0017] in, It is the number of PRBs occupied during busy time i. It is the total number of PRBs in the LTE system.

[0018] However, these methods can only assess the proportion of frequency resources used during peak business hours, and the assessment dimensions are singular, failing to fully reflect the actual utilization and overall situation of the spectrum.

[0019] It is evident that existing technologies for assessing the frequency resource allocation of wireless networks are primarily used for wireless network construction and optimization, and the assessment methods are singular and incomplete. Therefore, there is an urgent need for a method for analyzing the wireless network spectrum to comprehensively analyze and assess the spectrum situation of wireless networks.

[0020] This application proposes a comprehensive spectrum situation analysis method based on network management big data and wireless network engineering parameters. It is a multi-dimensional comprehensive analysis method from a frequency perspective, aiming to assess frequency utilization, coverage, service carrying capacity, user development, and the proportional relationships between different frequency standards. This analysis method not only focuses on the current spectrum status but also predicts future development trends, providing decision-makers with a comprehensive spectrum situation view.

[0021] The challenge of spectrum situation analysis lies in its broad analytical dimensions and relatively divergent objectives. However, its advantage lies in its high analytical value. Since both wireless communication technologies and user services rely on frequency, spectrum situation analysis can reveal the essence of communication and provide important analysis and visualizations. These analytical indicators not only reflect the requirements of communication systems but also involve the statistical indicator needs of relevant organizations. The overall analysis process is a continuous dimensionality reduction process, employing a method of screening and extracting important and key indicators from multidimensional variables (i.e., the original data sequence) to construct low-dimensional evaluation indicators. In this way, a more comprehensive assessment of the spectrum situation can be achieved.

[0022] Spectrum situation analysis not only assesses spectrum usage, utilization rate, and service development, but also reflects network health from another perspective. The resulting comprehensive health indicators provide a complete understanding of the spectrum situation, offering strong support for the sustainable development of wireless communications.

[0023] The following is in conjunction with the appendix Figures 1 to 12 This application provides a detailed description of a wireless network spectrum analysis method, apparatus, electronic device, and computer program product through specific embodiments and application scenarios.

[0024] Figure 1 This application illustrates an embodiment of a method for analyzing the spectrum of a wireless network. This method can be executed by an electronic device, which may include a server and / or terminal devices. In other words, the method can be executed by software or hardware installed on the server and / or terminal devices, and includes the following steps: Step 110: Obtain the engineering parameters and network management data of the area to be analyzed.

[0025] The engineering parameters include basic data recorded during the construction of the wireless network, which typically include the latitude and longitude coordinates of the cell, antenna height, azimuth angle, downtilt angle, transmit power, and frequency configuration information, to reflect the physical deployment structure and coverage capability of the network.

[0026] The network management data includes operational data collected from the network management system, which typically includes user connection count, service traffic, data transmission rate, resource block utilization, and interference level, to reflect the real-time operating status and service load of the network.

[0027] In this step, engineering parameters are primarily used for subsequent coverage analysis, while network management data is used to assess the network's service carrying capacity and spectrum utilization efficiency. These two types of data come from different sources but together constitute the basic data input for spectrum situational analysis. Engineering parameters are relatively stable, reflecting the static deployment of the network, while network management data has time-varying characteristics, reflecting the dynamic operating status of the network.

[0028] Step 120: Perform spectrum coverage analysis based on the engineering parameters to obtain spectrum coverage indicators, which include coverage rates or average station spacing for different frequency bands or different standards.

[0029] The spectrum coverage analysis evaluates the coverage range of wireless networks under different frequency bands or standards based on engineering parameters. Coverage rate refers to the proportion of the coverage area of ​​a certain frequency band or standard to the total coverage area of ​​the area under analysis. Average inter-cell spacing refers to the average distance between cells in the area, which is usually estimated by the coverage area and the number of cells.

[0030] In this step, spectrum coverage analysis is performed based on the acquired engineering parameters to obtain spectrum coverage indicators. These indicators specifically include coverage rates for different frequency bands or standards, and average inter-cell spacing. Coverage rate calculation needs to consider the coverage radius of cells and the overlap between cells, using a rasterization method to statistically determine the proportion of covered area. Average inter-cell spacing can be estimated from the coverage area and the number of cells. These indicators reflect the spatial distribution of spectrum resources from a coverage perspective, providing a data foundation for subsequent steps.

[0031] Step 130: Determine a first set of indicators and a second set of indicators based on the network management data. The first set of indicators includes user carrying capacity indicators, and the second set of indicators includes unit spectrum carrying capacity efficiency indicators.

[0032] The first set of indicators includes a group of metrics used to assess social benefits, primarily including user carrying capacity metrics. User carrying capacity metrics reflect the scale and activity level of network service users, and may specifically include the number of radio resource control connections, the number of active users during busy hours, the number of IoT users, user data traffic, and user data transmission rates.

[0033] The second set of indicators includes a group of metrics used to evaluate economic efficiency, mainly including metrics related to the efficiency of carrying capacity per unit of spectrum. These metrics reflect the amount of service that can be carried per megahertz of spectrum resources, and specifically can include the number of users carried per unit of spectrum, the data traffic carried per unit of spectrum, the data rate carried per unit of spectrum, spectrum utilization, and communication efficiency.

[0034] In this step, a first set of indicators and a second set of indicators are determined based on network management data. The first set of indicators focuses on evaluating the social service value of the spectrum from the user's perspective, and can cover aspects such as user scale and service volume. The second set of indicators focuses on evaluating the economic output efficiency of the spectrum from the resource utilization perspective, reflecting the input-output level of unit spectrum resources. These two sets of indicators are used in subsequent steps to obtain the social benefit index and the economic benefit index, respectively.

[0035] Step 140: Obtain the social benefit index based on the spectrum coverage index and the first index set, and obtain the economic benefit index based on the second index set. Combine the social benefit index and the economic benefit index to form a comprehensive index for the wireless network spectrum.

[0036] The social benefit index includes quantitative indicators that comprehensively reflect the contribution of spectrum resources to social services. It can be calculated by integrating spectrum coverage indicators and multiple user-bearing indicators from the first indicator set to reflect the comprehensive performance of spectrum in terms of coverage and user services.

[0037] The economic benefit index includes quantitative indicators that comprehensively reflect the efficiency level of spectrum resources in terms of economic output. It can be obtained by merging multiple unit spectrum carrying efficiency indicators in the second indicator set to reflect the economic value of unit spectrum resources.

[0038] The comprehensive indicators include social benefit index and economic benefit index, which are used to comprehensively assess the overall situation of wireless network spectrum.

[0039] In this step, the social benefit index is calculated based on the spectrum coverage index and the first set of indicators. Specifically, each indicator in the spectrum coverage index and the first set of indicators is normalized to eliminate dimensional differences caused by different units. Then, weights are assigned according to the importance of each indicator, and the normalized values ​​are summed using a weighted average. Simultaneously, the economic benefit index is calculated based on the second set of indicators. The indicators in the second set are then normalized and summed using a weighted average. Finally, the social benefit index and the economic benefit index together constitute a comprehensive index for the wireless network spectrum.

[0040] In this embodiment, by integrating spectrum coverage indicators, user carrying capacity indicators, and unit spectrum carrying efficiency indicators, a comprehensive evaluation of wireless network spectrum can be achieved from multiple dimensions, including coverage, service carrying capacity, and spectrum utilization efficiency. By combining spectrum coverage indicators with user carrying capacity indicators to construct a social benefit index, the actual contribution of different frequency bands or standards to coverage and user services can be objectively reflected, providing quantifiable technical indicators for assessing the social value of spectrum resources. Based on unit spectrum carrying efficiency indicators, an economic benefit index is obtained, used to quantitatively evaluate the input-output efficiency of spectrum resources, providing a data foundation for optimizing operator spectrum resource allocation. Integrating the social benefit index and the economic benefit index into a comprehensive index allows for a rapid understanding of the overall spectrum situation. Based on engineering parameters and network management data, this approach is applicable to different communication standards and frequency band combinations, and the indicator composition and dimensionality reduction methods can be adjusted according to actual needs, demonstrating good applicability.

[0041] In yet another exemplary embodiment, based on step 120 of the above embodiment, spectral coverage analysis is performed according to the engineering parameters to obtain spectral coverage indicators. The method of this embodiment may further include the following specific steps: Based on the number of cells and cell coverage radius in the engineering parameters, determine the ratio of the coverage area of ​​different frequency bands or different standards to the total coverage area of ​​the area to be analyzed, and obtain the coverage rate; or, based on the number of cells and coverage area in the engineering parameters, calculate the average station spacing.

[0042] In this embodiment, the spectrum coverage index is based on the coverage rate as a percentage of the coverage area or on the average distance between cells and the coverage area. The calculation of the coverage rate takes into account the overlap of cell coverage, which can truly reflect the coverage breadth of different frequency bands or standards in actual space and avoid misjudgment caused by a large number of cells but serious coverage overlap. The calculation of the average distance between cells can indirectly reflect the network investment density and coverage depth, providing a quantitative basis for network planning and optimization. This expands the spectrum coverage analysis from a single quantitative dimension to area and distance dimensions, providing accurate coverage dimension input for subsequent social benefit assessment.

[0043] In yet another exemplary embodiment, the cell's engineering parameters are used for spectrum coverage analysis. As shown in formula (1).

[0044] (1) in, The number of cells selected within the region, including the total number of cells across multiple standards and frequency bands; Let n be the number of cells of a certain standard and frequency band in cell N within a region.

[0045] Converting formula (1) into an area ratio, the formula for calculating the area coverage ratio R is as follows: (2) S(*) means that the coverage area of ​​the cell is calculated based on the cell coverage radius. It is the area of ​​the grid set. It should be noted that the coverage radius will be different for different frequency bands or communication standards. The meaning is to take the area of ​​the union of the grids covered by n cells, and remove the grids with overlapping coverage; A collection of cells using a certain standard will collectively use a specific frequency band; It is a collection of cells covering all frequency bands and all standards. Therefore, This represents the area that needs to be covered. This represents the coverage area of ​​a specific frequency band / standard.

[0046] pass The value can be used to obtain an approximate average station spacing. .

[0047] The spectrum coverage metric used in this embodiment is the average station spacing. Of course, the area coverage rate R is also applicable to other scenarios.

[0048] In yet another exemplary embodiment, the user bearer class indicators include at least one of the following: number of radio resource control connections, number of active users during busy hours, number of IoT users, user data traffic, and user data transmission rate.

[0049] The number of wireless resource control connections includes the number of users in a connected state on the network, reflecting the current scale of online users. The number of active users during peak hours includes the number of users actually using the service during the busiest network periods, reflecting the network's capacity pressure during peak times. The number of IoT users includes the number of IoT terminal devices connected to the network, reflecting the network's service scale in the IoT field. User data traffic includes the total amount of data transmitted by users within a certain period, reflecting the network's service capacity. User data transmission rate includes the amount of data transmitted by users per unit time, reflecting the network's service transmission efficiency.

[0050] User capacity metrics can reflect the scale of network service users and service carrying capacity from different perspectives. Wireless resource control connections and busy-hour active users focus on user scale, IoT user numbers focus on terminal connection scale, and user data traffic and user data transmission rate focus on service volume and transmission efficiency. By selecting one or more of these metrics, a user capacity metric system can be flexibly constructed according to different analytical needs.

[0051] In yet another exemplary embodiment, the user data traffic includes at least one of uplink MAC layer traffic, downlink MAC layer traffic, uplink physical layer traffic, and downlink physical layer traffic.

[0052] Uplink MAC layer traffic includes data traffic sent from the user terminal to the network, which is statistically analyzed at the Media Access Control (MAC) layer and reflects the amount of data uploaded by the user. Downlink MAC layer traffic includes data traffic sent from the network to the user terminal, which is statistically analyzed at the MAC layer and reflects the amount of data downloaded by the user. Uplink physical layer traffic includes data traffic sent from the user terminal to the network, which is statistically analyzed at the physical layer and includes data content and redundant information added during transmission. Downlink physical layer traffic includes data traffic sent from the network to the user terminal, which is statistically analyzed at the physical layer and also includes data content and redundant information. MAC layer traffic reflects the actual amount of data sent and received by the user, while physical layer traffic reflects the total amount of data actually transmitted on the wireless channel.

[0053] The difference between MAC layer traffic and physical layer traffic lies in whether or not redundant information from the transmission process is included. Comparing the two can reflect communication efficiency and wireless channel quality. By selecting one or more traffic metrics, the focus can be on the amount of user content data or the actual amount of data transmitted, providing a reference for network optimization and spectrum efficiency assessment, depending on the analysis requirements.

[0054] In yet another exemplary embodiment, the user data transmission rate includes at least one of the following: uplink MAC layer rate, downlink MAC layer rate, uplink physical layer rate, and downlink physical layer rate.

[0055] The uplink MAC layer rate includes the rate at which the user sends data from the terminal to the network. This rate is statistically analyzed at the Media Access Control (MAC) layer and reflects the transmission speed of uploaded content. The downlink MAC layer rate includes the rate at which the network sends data to the user terminal. This rate is statistically analyzed at the MAC layer and reflects the transmission speed of downloaded content. The uplink physical layer rate includes the rate at which the user sends data from the terminal to the network. This rate is statistically analyzed at the physical layer and reflects the actual transmission speed, including redundancy information. The downlink physical layer rate includes the rate at which the network sends data to the user terminal. This rate is statistically analyzed at the physical layer and reflects the actual transmission speed, including redundancy information. The MAC layer rate reflects the actual transmission speed experienced by the user, while the physical layer rate reflects the actual transmission capacity of the wireless channel.

[0056] The difference between the MAC layer rate and the physical layer rate reflects the proportion of redundancy overhead during transmission. Comparing the two can evaluate the transmission efficiency and channel quality of the wireless channel. By selecting one or more rate indicators, the focus can be on the user experience rate or the actual transmission rate of the channel, providing a quantitative basis for network performance evaluation and spectrum resource allocation, depending on the analysis requirements.

[0057] In yet another exemplary embodiment, the unit spectrum carrying efficiency index includes at least one of the following: number of users carried per unit spectrum, data traffic carried per unit spectrum, data rate carried per unit spectrum, frequency utilization, and communication efficiency.

[0058] The number of users carried per unit of spectrum includes the number of online users per megahertz of spectrum resource, obtained by dividing the number of users by the total system bandwidth, reflecting the utilization efficiency of spectrum resources in terms of user scale. The data traffic carried per unit of spectrum includes the data traffic carried per megahertz of spectrum resource, obtained by dividing the data traffic by the total system bandwidth, reflecting the utilization efficiency of spectrum resources in terms of service carrying capacity. The data rate carried per unit of spectrum includes the data transmission rate carried per megahertz of spectrum resource, obtained by dividing the data rate by the total system bandwidth, reflecting the utilization efficiency of spectrum resources in terms of transmission efficiency. Spectrum utilization rate includes the degree of spectrum resource occupancy in the time or frequency dimension, reflecting the intensity of spectrum resource usage. Communication efficiency refers to the ratio of effective data to total transmitted data, reflecting the transmission quality and efficiency of the wireless channel.

[0059] The aforementioned indicators can reflect the economic output efficiency of spectrum resources from different perspectives. The number of users carried per unit of spectrum, data traffic, and data rate focus on the ratio between spectrum resources and service output; spectrum utilization focuses on resource occupancy intensity; and communication efficiency focuses on transmission quality. By selecting one or more of these indicators, a system of indicators for unit spectrum carrying efficiency can be flexibly constructed according to different analytical needs.

[0060] In yet another exemplary embodiment, the spectrum utilization includes average physical resource block utilization.

[0061] A physical resource block (PRP) is the smallest unit for resource scheduling in LTE and 5G systems. Each PRP consists of a certain number of subcarriers and a time slot. Average PRP utilization includes the average occupancy rate of PRPs within a statistical period, calculated as the ratio of the number of PRPs occupied during busy hours to the total number of PRPs in the system. This metric reflects the actual intensity of spectrum resource usage at the physical layer and measures spectrum utilization.

[0062] The above indicators reflect the actual usage intensity of spectrum resources during peak service periods by statistically analyzing the occupancy of physical resource blocks during busy hours. A higher average physical resource block utilization rate indicates more efficient use of spectrum resources; however, excessively high utilization may also indicate heavy network load, requiring attention to user experience. This indicator can provide a quantitative basis for spectrum resource expansion planning and load balancing.

[0063] In yet another exemplary embodiment, the communication efficiency includes the ratio of media access control layer traffic to physical layer traffic.

[0064] The media access control layer traffic includes the data traffic that users count at the media access control layer, reflecting the amount of content data that users actually receive and send.

[0065] The physical layer traffic includes the data traffic that users count at the physical layer, reflecting the total amount of data actually transmitted on the wireless channel, including the data content and overhead information such as cyclic redundancy check and coding redundancy added during transmission.

[0066] The ratio of media access control layer traffic to physical layer traffic reflects the proportion of valid data in the total transmitted data. When channel quality is good, retransmissions are fewer and redundancy overhead is lower, resulting in a higher ratio. Conversely, when channel quality is poor, retransmissions increase and redundancy overhead rises, causing the ratio to decrease. This indicator indirectly reflects the quality of the wireless channel and the transmission efficiency of the communication system, providing a reference for network optimization and spectrum resource allocation.

[0067] Figure 2 This diagram illustrates a flowchart of another wireless network spectrum analysis method provided by an embodiment of this application. The method can be executed by an electronic device, which may include a server and / or terminal devices. In other words, the method can be executed by software or hardware installed on the server and / or terminal devices, and includes the following steps: Step 210: Obtain the engineering parameters and network management data of the area to be analyzed.

[0068] Step 220: Perform spectrum coverage analysis based on the engineering parameters to obtain spectrum coverage indicators, which include coverage rates or average station spacing for different frequency bands or different standards.

[0069] Step 230: Determine a first set of indicators and a second set of indicators based on the network management data. The first set of indicators includes user carrying capacity indicators, and the second set of indicators includes unit spectrum carrying capacity efficiency indicators.

[0070] Steps 210-230 can be found above. Figure 1 The specific descriptions of steps 110 to 130 in the illustrated embodiment are provided, and the same technical effects can be achieved. To avoid repetition, they will not be repeated here.

[0071] Step 240, based on step 140 of the above embodiment, obtain the social benefit index according to the spectrum coverage index and the first index set, and obtain the economic benefit index according to the second index set. Combine the social benefit index and the economic benefit index to form a comprehensive index for the wireless network spectrum. The method of this embodiment may further include the following specific steps: The spectrum coverage index and multiple indicators in the first index set are normalized to obtain the normalized value of each index; weight coefficients are assigned to each index, and the normalized values ​​of each index are weighted and summed to obtain the social benefit index.

[0072] The normalization process involves converting indicator values ​​with different units and orders of magnitude into values ​​with a unified dimension. Because the spectrum coverage indicator and the various indicators in the first indicator set have different physical units and numerical ranges—for example, average station spacing is measured in meters, the number of users in units, and data traffic in gigabytes—these indicators cannot be directly mathematically calculated. Normalization compares the actual values ​​of each indicator with their corresponding benchmark values, mapping the indicator values ​​to a unified numerical range, eliminating dimensional differences, and making indicators of different natures comparable and additive. The normalized benchmark value can be one of the following: a theoretical target value, an empirical value, a historical best value, or a regional best value, reflecting the expected level of the indicator under ideal conditions.

[0073] The weighting coefficients represent the relative importance of each indicator. Different indicators contribute differently to the social benefit index. For example, in some analytical scenarios, user scale may be more important than coverage distance, while in others, coverage breadth may be more critical. The weighting coefficients are determined based on the analytical objectives and business needs, and the sum of the weighting coefficients for each indicator is usually one. By assigning differentiated weighting coefficients to different indicators, the relative importance of each indicator in the social benefit assessment can be reflected, making the final social benefit index more consistent with actual analytical needs.

[0074] In this step, the spectrum coverage index and multiple indices in the first index set are normalized to obtain normalized values ​​for each index. The normalization process involves comparing the actual values ​​of each index with a pre-determined normalization benchmark value and calculating the ratio of the actual value to the benchmark value. Through normalization, each index is converted into dimensionless numerical values, which reflect the degree to which the actual performance of each index approaches the ideal level.

[0075] The social benefit index is obtained by multiplying the normalized values ​​of each indicator by their corresponding weighting coefficients and summing the products. As a comprehensive quantitative value, the social benefit index integrates multiple indicators from both spectrum coverage and user carrying capacity dimensions, reflecting the overall performance of spectrum resources in terms of social services. A higher social benefit index indicates better overall performance of spectrum resources in terms of coverage and user services; conversely, a lower index indicates areas for improvement. This method reduces the dimensionality of multiple original indicators of different natures and merges them into a single comprehensive evaluation index, enabling decision-makers to quickly grasp the social service status of spectrum resources.

[0076] In yet another exemplary embodiment, based on step 140 of the above embodiment, a social benefit index is obtained according to the spectrum coverage index and the first index set, and an economic benefit index is obtained according to the second index set. The social benefit index and the economic benefit index are then used to construct a comprehensive index for the wireless network spectrum. The method of this embodiment may further include the following specific steps: Normalize the multiple indicators in the second indicator set to obtain the normalized value of each indicator; assign weight coefficients to each indicator, and sum the normalized values ​​of the indicators by weight to obtain the economic benefit index.

[0077] The economic efficiency index is a quantitative indicator that comprehensively reflects the efficiency level of spectrum resources in terms of economic output. It is derived by fusing multiple unit spectrum carrying efficiency indicators from the second indicator set, reflecting the economic value generated by each megahertz of spectrum resources. The indicators in the second indicator set have different units and orders of magnitude. For example, the number of users carried per unit spectrum is measured in units per megahertz, the data traffic carried per unit spectrum is measured in gigabytes per megahertz, spectrum utilization is expressed as a percentage, and communication efficiency is a dimensionless ratio. These indicators reflect the economic output efficiency of spectrum resources from different perspectives and need to be normalized to eliminate dimensional differences before comprehensive evaluation.

[0078] The second set of indicators is normalized to obtain normalized values ​​for each indicator. The normalization process involves comparing the actual values ​​of each indicator with a pre-determined normalization benchmark. For positive indicators such as the number of users carried per unit spectrum, data traffic, and data rate, the normalized value can be obtained by dividing the actual value by the benchmark; a higher value indicates higher economic output per unit spectrum. For indicators like spectrum utilization, a normalization benchmark needs to be determined based on the actual analysis objectives, such as the theoretical maximum utilization or the regional average utilization. For ratio indicators like communication efficiency, the theoretical optimal ratio or the empirical optimal ratio can be directly used as the normalization benchmark. Through normalization, each indicator is converted into a dimensionless value to reflect the degree of closeness between the actual performance and the ideal level.

[0079] Assign weight coefficients to each indicator. Determining these weight coefficients requires considering the importance of different indicators in the economic benefit assessment. For example, in scenarios with scarce spectrum resources, data traffic per unit spectrum and spectrum utilization may be given higher weights. In multi-standard coordination scenarios, communication efficiency may be given higher weights. Weight coefficients can be set based on expert experience, derived from historical data analysis, or dynamically adjusted according to the goals of different development stages.

[0080] The economic efficiency index is obtained by weighted summation of the normalized values ​​of various indicators. The specific method of weighted summation is to multiply the normalized value of each indicator by its corresponding weight coefficient, and then sum the products. The economic efficiency index is a comprehensive quantitative value that integrates information from multiple unit spectrum carrying efficiency indicators in the second indicator set, reflecting the overall performance of spectrum resources in terms of economic output. A higher economic efficiency index indicates higher economic output efficiency per unit of spectrum resources and a more rational allocation of spectrum resources; conversely, a lower index indicates room for efficiency improvement. In this way, multiple unit spectrum carrying efficiency indicators of different natures are reduced in dimensionality and integrated into a comprehensive evaluation index, providing a quantitative reference for assessing the economic value of spectrum resources.

[0081] In yet another exemplary embodiment, the normalization process includes: comparing the actual value of each indicator with the corresponding normalization benchmark value to obtain the normalized value of each indicator.

[0082] In yet another exemplary embodiment, the normalized benchmark value includes at least one of a theoretical target value, an empirical value, a historical best value, or a regional best value.

[0083] In yet another exemplary embodiment, the method of this embodiment may further include the following specific steps: Based on network management data from multiple time periods, determine the time series data of each indicator in the first and second indicator sets; based on the time series data of each indicator, predict the indicators for future time periods using a time series prediction algorithm; and determine the corresponding social and economic benefit indicators for future time periods based on the prediction results.

[0084] The time-series data includes numerical sequences of the same indicator arranged in chronological order. For wireless network spectrum analysis, all indicators in the first and second indicator sets can be continuously collected on a monthly or weekly basis to form time-series data that reflects the changing patterns of the indicators, thus showing the trends and periodic characteristics of indicators such as user scale, service traffic, and spectrum utilization over time.

[0085] Time series forecasting algorithms include mathematical methods that use historical data patterns to predict future values. In wireless network spectrum analysis, by analyzing historical patterns in indicators such as user numbers, traffic, and speed, the future trends of these indicators can be predicted. Specifically, vector autoregression (VAR) is a commonly used multivariate time series forecasting method that can capture the interrelationships between multiple indicators. Cointegration models are suitable for multiple indicator sequences with long-term stable relationships, ensuring that the prediction results conform to the long-term equilibrium relationship between the indicators.

[0086] The social and economic benefit indicators for the future time period are recalculated based on the predicted indicators. Since the spectrum coverage indicator is based on relatively stable engineering parameters and typically remains unchanged over the future time period, the social benefit index for the future time period is primarily recalculated based on the predicted first set of indicators and the original spectrum coverage indicator. The economic benefit index for the future time period is recalculated based on the predicted second set of indicators.

[0087] In this embodiment, time-series data of each indicator in the first and second indicator sets are determined based on network management data from multiple time periods. This data reflects the growth trend of user scale, the fluctuation pattern of service traffic, and the changing characteristics of spectrum utilization, providing a foundation for subsequent predictive analysis. Based on the time-series data of each indicator, a time-series prediction algorithm is used to predict the indicators for future time periods. The selection of the prediction algorithm needs to consider the characteristics of the data and the prediction requirements. Vector autoregression (VAR) models are suitable for situations where multiple indicators have mutual influence relationships; for example, user growth drives traffic growth, and traffic growth affects spectrum utilization. These indicators can be predicted jointly. Cointegration models are suitable for situations where indicators have long-term stable relationships; for example, there is a relatively stable proportional relationship between physical layer traffic and media access control layer traffic. Cointegration models can ensure that the prediction results conform to this long-term equilibrium relationship. The prediction time length can be determined according to actual needs, typically the next twelve months. Based on the prediction results, the corresponding social benefit indicators and economic benefit indicators for future time periods are determined. For the social benefit index, the predicted indicators from the first indicator set and the original spectrum coverage indicators are recalculated using the normalization and weighted summation methods described in the previous embodiment to obtain the social benefit index for future time periods. The economic benefit index is recalculated based on the second set of indicators obtained from the forecast. This method not only assesses the current spectrum situation but also predicts future development trends, providing a reference for spectrum resource planning and adjustments.

[0088] In yet another exemplary embodiment, the time series prediction algorithm includes a vector autoregressive model or a cointegration model.

[0089] In yet another exemplary embodiment, the social benefit index for the future time period is determined based on the spectrum coverage index and a first set of predicted indicators, and the economic benefit index for the future time period is determined based on a second set of predicted indicators.

[0090] Figure 3This illustration shows a flowchart of another wireless network spectrum analysis method provided by an embodiment of this application, used for wireless network spectrum situation analysis. The data input for this method includes two parts: wireless engineering parameters and network management multi-dimensional data. The wireless engineering parameters are used for coverage analysis and include engineering parameter information such as cell latitude and longitude, frequency configuration, and coverage scenario. The network management multi-dimensional data includes operational indicators such as timestamps, number of active users during busy hours, resource block utilization, data rate, and data quality.

[0091] In the data processing flow, wireless engineering parameters undergo spectrum coverage analysis to obtain spectrum coverage indicators. These indicators, along with network management multi-dimensional data, are refined and input into the social benefit radar chart to generate a social benefit index. Simultaneously, the network management multi-dimensional data undergoes independent indicator refinement and is input into the economic benefit radar chart to generate an economic benefit index. The social benefit index and the economic benefit index together constitute a comprehensive index.

[0092] Among them, the multi-dimensional data management system also conducts time series analysis based on two branches: user business development and frequency usage efficiency. Through the extraction of time series indicators, the trends of user business development and frequency usage efficiency are obtained. These two analysis results are used to support the future prediction of the social benefit index and the economic benefit index, respectively.

[0093] In this embodiment, a complete spectrum situation analysis process is provided, from multi-source data input to multi-dimensional indicator extraction, and then to radar chart display and comprehensive index generation. At the same time, the predictive ability of time series analysis for future development trends is incorporated.

[0094] In yet another exemplary embodiment, network management data is used as an example for specific illustration. This data includes multi-dimensional data that can be sampled in a time-series manner. Spectrum future development analysis primarily focuses on the number of users, traffic volume (including traffic and busy-hour rates), and the impact of these factors on the existing network, such as RB utilization and interference. Analyzing these key indicators helps to understand spectrum and service development. Using historical sequence data to predict future development trends, assessing the future state of spectrum and services, supports investment decisions in the frequency domain and indirectly reflects network quality.

[0095] For example, time-series forecast data for 4G / 5G communication systems covers the development of user numbers (RRC links), user traffic, and data rates, as shown in the table below. This data can be used to deduce future development trends and predict future changes in user numbers, user traffic, and data rates. This data provides a reference for formulating spectrum and business development strategies.

[0096]

[0097] Applying time series correlation algorithms can effectively predict future development trends. Specifically, monthly timescale data spanning 2-5 years can be used to predict trends for the next 12 months. Interrelationships exist between certain data points, and joint prediction yields better results. For example, combining RRC link counts and MAC layer traffic for prediction typically yields more accurate results. Similarly, downlink transmit power, interference levels, and rate indicators also require joint prediction to improve accuracy.

[0098] When analyzing the development of communication services, key indicators such as the number of users, data traffic, and data rate can be selected, and time series forecasting analysis can be used to gain insights into service development. However, when analyzing spectrum utilization efficiency, factors such as the number of users, data rate, and bandwidth need to be considered. By evaluating indicators such as the number of users carried per unit frequency and the data rate per unit spectrum, a comprehensive understanding of spectrum utilization can be obtained, and the efficiency of investment can be judged accordingly.

[0099] To comprehensively demonstrate the multi-faceted and multi-dimensional characteristics of the current spectrum status, it is necessary to analyze the overall spectrum situation from both social and communication economic perspectives. In this process, radar charts are used as a visual display tool to clearly reflect the comparisons and differences between various indicators.

[0100] In terms of social benefits, the state of the communication spectrum has played a positive role in promoting social progress and communication development. The efficient use of spectrum can boost the number of users and traffic, thereby indirectly driving overall social progress. This contribution is reflected in multiple aspects, including improving communication quality and promoting the construction of an information society.

[0101] From an economic perspective, spectrum availability is closely related to an operator's investment and return on investment. Metrics for measuring economic efficiency include the number of users per unit of spectrum, data traffic, and peak-hour speeds. By comparing the return on investment for different communication standards, the economic value of spectrum can be assessed more accurately. Operators can refer to spectrum analysis when making investment decisions to ensure the effectiveness of their investments and the sustainability of their returns.

[0102] As an analytical tool, radar charts consist of two parts: ideal values ​​and actual values. The ideal value represents the theoretically expected optimal state, while the actual value reflects the current performance of the spectrum. By comparing the ideal and actual values, deficiencies in different indicators of the spectrum state can be clearly identified—that is, the gap between the current state and the ideal state. These deficiencies provide directions for improvement and optimization, which can be used to adjust spectrum strategies and enhance the overall effectiveness of the spectrum.

[0103] By comprehensively analyzing social and communication economic benefits, and combining this with the intuitive display of radar charts, we can understand the multi-dimensional characteristics of the current spectrum status. To further analyze the future development of the spectrum situation, time series correlation algorithms are used to predict the changing trends of various indicators and radar charts.

[0104] The social benefit analysis is based on communication standards, including 2G, 4G and 5G, with one radar chart for each standard, including coverage and service indicators.

[0105] See Figure 4 The social benefits analysis of the 2G communication standard can include the following four indicators: Average station spacing reflects investment on the one hand; higher investment results in lower station spacing. On the other hand, it also reflects the frequency coverage distance. User capacity reflects the user scale; The number of active users during peak hours reflects the number of users who can access the network simultaneously. The number of IoT users reflects the number of users of the Internet of Things (IoT).

[0106] See Figure 5 The social benefits analysis of the 4G communication standard can include the following six indicators: Average station spacing reflects investment on the one hand; higher investment results in lower station spacing. On the other hand, it also reflects the frequency coverage distance. User capacity reflects the user scale; Uplink + downlink MAC layer traffic (GB) reflects the amount of content data sent by the user; Uplink + downlink physical layer traffic (GB) reflects the actual amount of data the user has, including redundant data; Uplink + downlink physical layer busy time rate (MBPS) reflects the user's actual transmission rate, including redundant data; The uplink + downlink MAC layer busy time rate (MBPS) reflects the content transmission rate of the sending user.

[0107] Similarly, the social benefit analysis of 5G communication standards can use the same indicators as that of 4G communication standards, and the radar charts are also similar in structure.

[0108] The economic benefit analysis is based on user and service metrics per unit spectrum.

[0109] See Figure 6 The economic benefits analysis of 4G communication can include the following 7 indicators: RRC User Links / MHz: The number of online users carried per unit spectrum; (Uplink + Downlink MAC layer traffic (GB)) / MHz: The amount of user MAC data carried per unit spectrum; (Uplink + Downlink MAC physical layer traffic (GB)) / MHz: The amount of user PHY data carried per unit spectrum; (MAC layer rate of uplink + downlink (MBPS)) / MHz: User MAC rate carried per unit spectrum; (Uplink + Downlink Physical Layer Rate (MBPS)) / MHz: User PHY rate carried per unit spectrum; (Average uplink + downlink RB utilization): Spectrum utilization; 4G communication efficiency: (uplink + downlink MAC layer traffic (GB)) / (uplink + downlink MAC physical layer traffic (GB)): Reflects communication performance and wireless channel conditions. The higher the proportion of MAC layer traffic, the better.

[0110] See Figure 7 The indicators and radar charts for the economic benefit analysis of 5G communication are similar to those for 4G communication.

[0111] See Figure 8 The economic benefit analysis of 4G+5G communication, based on the total bandwidth of 4G and 5G as the denominator, can include the following eight indicators: 1) 4G+5G RRC user connection count / MHz, the number of online users carried per unit spectrum; 2) 4G+5G (uplink + downlink MAC layer traffic (GB)) / MHz, the amount of user MAC data carried per unit spectrum; 3) 4G+5G (uplink + downlink MAC physical layer traffic (GB)) / MHz, user MAC traffic carried per unit spectrum; 4) 4G+5G (uplink + downlink MAC layer rate (MBPS)) / MHz, the user MAC data rate carried per unit spectrum; 5) 4G+5G (uplink + downlink physical layer rate (MBPS)) / MHz, the user PHY data rate carried per unit spectrum; 6) Traffic splitting ratio between 4G and 5G: 4G (uplink + downlink MAC layer traffic (GB)) / 5G (uplink + downlink MAC layer traffic (GB)), reflecting the traffic share of 4G and 5G. 7) Busy hour rate split ratio of 4G+5G: 4G (uplink + downlink MAC layer rate (MBPS)) / 5G (uplink + downlink MAC layer rate (MBPS)), which reflects the speed comparison between 4G and 5G. It should be less than 1 because the speed of 4G is lower than that of 5G. 8) 4G and 5G communication efficiency ratio: 4G communication efficiency / 5G communication efficiency. Comparing the performance of 4G and 5G, it should be less than 1, reflecting that 5G performs better than 4G.

[0112] The comprehensive indicators include social benefit index and economic benefit index, which can be calculated based on radar chart results. Specifically, the method involves constructing values ​​in the range (0,1) based on deviation. The closer to 1, the better; the closer to 0, the more problematic. The ideal value of the vertex is derived from target requirements or reasonable experience / theoretical values.

[0113] Social benefit index The 2G social benefit index is calculated using the following formula: , =0.25 The 4G social benefit index is calculated using the following formula: , =1 / 6 The 5G social benefit index is calculated using the following formula: , =1 / 6 Economic efficiency index The 4G economic benefit index is calculated using the following formula: , =1 / 7 The 5G economic benefit index is calculated using the following formula: , =1 / 7 The 4G+5G economic benefit index is calculated using the following formula: , =1 / 8 In another exemplary embodiment, taking the network management data using a time series algorithm as an example, it can not only predict the data items of the original data, but also predict the actual values ​​and comprehensive indicators of the radar chart. It can not only clearly show the current spectrum situation, but also reflect the future development of the spectrum situation.

[0114] The prediction model can be a multi-vector hysteresis model, also known as a vector autoregression (VAR) model.

[0115]

[0116] The specific formula is as follows:

[0117] in, These are the coefficients of the VAR equation; It is the error term at time t.

[0118] Considering the 12-month cycle, 12 hysteresis terms are used. Training is first performed using data output from the northbound interface. The coefficients are then used to iterate the equation and output the prediction results, as shown in the following formula, which illustrates the prediction results for 12 months:

[0119]

[0120]

[0121] ...

[0122] Predictive models can also employ cointegration models. When cointegration exists, the Error Correction Model (ECM) can serve as a model to ensure long-term stable relationships between variables. This can be implemented in two steps: First, calculate the fit between variables, and then use the least squares method to obtain the error sequence ECM:

[0123] Establish a fitting equation between the difference variables, and use the error term in 1) as one of the fitting variables:

[0124]

[0125] When fitting, the stationarity characteristic is guaranteed, and the parameter estimates are reliable.

[0126] Both prediction models can be used here. The VAR model has a better fit, while the cointegration model has better stability, more reliable parameter estimates, and better interpretability. Preferably, the cointegration model is used.

[0127] Figure 9a , 9b Figure 9c shows the time series prediction effect, where, Figure 9a The solid line represents historical observations, and the dashed line represents predicted values. Figure 9b The term in the table represents the historical residuals, used to evaluate the accuracy of the predictive model. Figure 9c This indicates a comparison between historical observed values ​​and historical predicted values.

[0128] These predicted values ​​are typically used as the actual values ​​at the apex of the radar chart, forming the predicted portion of the radar chart. See [link to relevant documentation]. Figure 10 Based on the predictive radar chart, various comprehensive indices can be predicted, including the social benefit index and the communication economic benefit index.

[0129] Corresponding to the wireless network spectrum analysis method provided in the above embodiments, based on the same technical concept, this application also provides a wireless network spectrum analysis apparatus. See [link to previous document]. Figure 11 The device 400 includes a data acquisition module 410, a data acquisition module 420, a network management data module 430, and an evaluation index module 440.

[0130] The data acquisition module 410 is used to acquire engineering parameters and network management data of the area to be analyzed; the engineering parameter module 420 is used to perform spectrum coverage analysis based on the engineering parameters to obtain spectrum coverage indicators, which include coverage rates or average station spacing for different frequency bands or different standards; the network management data module 430 is used to determine a first indicator set and a second indicator set based on the network management data, where the first indicator set includes user carrying capacity indicators and the second indicator set includes unit spectrum carrying capacity efficiency indicators; and the evaluation index module 440 is used to obtain a social benefit index based on the spectrum coverage indicators and the first indicator set, and an economic benefit index based on the second indicator set, and to construct a comprehensive index for the wireless network spectrum based on the social benefit index and the economic benefit index.

[0131] It should be noted that the wireless network spectrum analysis device and the wireless network spectrum analysis method provided in this application embodiment are based on the same application concept. Therefore, the specific implementation of this embodiment can refer to the implementation of the aforementioned wireless network spectrum analysis method, and the repeated parts will not be described again.

[0132] The wireless network spectrum analysis method and apparatus provided in this application can be used for overall spectrum situation analysis. This includes transforming wireless network engineering parameters and wireless network management data into indicators for evaluating the spectrum situation. Multiple raw data items are continuously integrated and dimensionality reduced to form a social benefit index and a communication economic benefit index, ultimately constructing a comprehensive index. Furthermore, the data indicators can be stored in a time-series format, meaning time-series algorithms can be used to predict the future. The method and apparatus provided in this application provide richer code channel occupancy and RB occupancy data than existing methods and can dynamically display future development trends.

[0133] Corresponding to the wireless network spectrum analysis method provided in the above embodiments, based on the same technical concept, this application also provides an electronic device for performing the above method. Figure 12 To illustrate the structure of an electronic device according to various embodiments of this application, as shown in the following diagrams... Figure 12As shown. Electronic device 500 can vary considerably due to differences in configuration or performance, and may include one or more processors 510 and memory 520. Memory 520 may store one or more application programs or data. Memory 520 may be temporary or persistent storage. The application programs stored in memory 520 may include one or more modules (not shown), each module may include a series of computer-executable instructions for the electronic device. Furthermore, processor 510 may be configured to communicate with memory 520 and execute the series of computer-executable instructions stored in memory 520 on the electronic device.

[0134] This application also provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium. The computer program includes program instructions, which, when executed by a computer, implement the steps of the wireless network spectrum analysis method described above.

[0135] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, apparatus, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0136] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems, devices), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0137] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0138] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0139] In a typical configuration, an electronic device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0140] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0141] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0142] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0143] Those skilled in the art will understand that embodiments of this application can be provided as methods, apparatus, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0144] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

[0145] It should be understood that the training and prediction processes of the artificial intelligence (AI) models involved in the various embodiments of this specification all adhere to multiple legal and compliant principles, including legal data sources, compliant data content, compliant data governance, compliant training objectives and schemes, compliant training processes, compliant training environments and tools, and compliant ethical verification of training results, and comply with the requirements of Article 5 of the Patent Law. Among them: Data source legitimacy: All datasets used for AI model training were obtained through legal means, covering three categories: publicly authorized data, data authorized by partners, and self-collected compliant data. Publicly authorized data comes from compliant data sources following open-source licenses such as Apache 2.0, with complete copyright attribution and authorization scope clearly marked, and no unauthorized open-source code or data reuse. Data authorized by partners has been subject to formal data usage agreements, clearly defining the scope, duration, and confidentiality obligations, and possessing a complete authorization chain. For self-collected data involving personal information, strict informed consent procedures have been followed, and anonymization processes (including but not limited to field masking, feature anonymization, and differential privacy technology applications) have been implemented to remove personally identifiable information, fully complying with the requirements of relevant laws and regulations such as the "Interim Measures for the Administration of Generative Artificial Intelligence Services" and the "Personal Information Protection Law."

[0146] Data content compliance: The AI ​​model's dataset undergoes multiple screenings and cleaning processes to remove all content that may violate social morality or harm public interests. It contains no obscene, pornographic, violent, discriminatory, or information that endangers national or public safety, nor does it involve the illegal acquisition or use of genetic resources. For data in sensitive fields (such as healthcare and finance), an additional privacy-preserving computation module (including federated learning and secure multi-party computation technologies) ensures that the data is "usable but not visible," avoiding compliance risks during the original data transmission process and ensuring that the data application scenarios and uses comply with public order and good morals and industry regulatory requirements.

[0147] Data governance norms: A complete data traceability system is established during the AI ​​model training process to automatically record the source, collection time, annotation process, cleaning rules, and permission allocation of training data, generating traceable compliance reports to ensure that the data is verifiable throughout its entire lifecycle. The dataset annotation process for AI models is completed by a professional human R&D team, clearly defining the proportion of human creative contributions and avoiding reliance on AI-generated data that has not undergone substantial human modification, thus meeting the examination requirements for "human main contributions" in AI patent applications.

[0148] Training objectives and plans are compliant: The training objective of the AI ​​model focuses on [specific technical scenarios that can be supplemented, such as intelligent driving decision optimization, multimodal information interaction, etc., and replaced based on specific content]. The training scheme and the final output results do not violate any mandatory provisions of laws and administrative regulations, do not harm the public interest or the legitimate rights and interests of others, and do not pose any potential risks of being used for illegal activities, infringing on privacy, or disrupting public safety. The model strictly adheres to the ethical principle of "intelligent for good".

[0149] Training process compliance: A closed-loop training framework is adopted to ensure compliance and controllability of the training process. The specific process is as follows: First, training samples are obtained through compliant data sources. After the aforementioned data cleaning and desensitization, they are input into the neural network model to generate preliminary training results. Second, an expert system is introduced to verify the preliminary results. Based on preset rules and human expert experience, the feasibility of the results is evaluated, and outputs that may pose ethical risks or compliance hazards are corrected (such as removing decision-making logic that violates public order and good morals, and adjusting model parameters that do not comply with safety regulations). Finally, the loss function weights are dynamically optimized based on expert system feedback to strengthen the model's learning of compliant results, avoid overfitting errors or non-compliant labels, and form a closed-loop control of "data input - model training - expert verification - parameter optimization - result feedback" to ensure that the entire training process complies with A5 ethical review requirements.

[0150] Training environment and tool compliance: AI model training is implemented using nationally licensed chips and a compliant training platform. All open-source frameworks and components used in the training process have obtained their corresponding licenses, and copyright statements and patent citation information are fully retained, with no instances of infringement or reuse. The training environment is built using virtual devices (containers / virtual machines) with fixed random seeds and initial parameter configurations to ensure the reproducibility of the training process. Furthermore, through access control and operation log recording, risks such as data leakage and parameter tampering during training are prevented, ensuring the security and compliance of the training process.

[0151] Training results ethical verification compliance: After the model is trained, it undergoes additional third-party ethical compliance assessment and algorithm filing review to verify that the model output does not violate social morality or harm public interests. For potentially sensitive scenarios (such as public services and intelligent decision-making), a special result verification mechanism is established to ensure that the model always complies with Article 5 of the Patent Law and relevant laws and regulations in practical applications.

[0152] In summary, the data and training process used in the AI ​​model of this specification strictly comply with the relevant provisions of Article 5 of the Patent Law and the Patent Examination Guidelines (2023 Edition), and there are no violations of laws, social ethics, public interests, or illegal use of genetic resources. It fully meets the compliance requirements for patent authorization.

Claims

1. A method for analyzing the spectrum of a wireless network, characterized in that, The method includes the following steps: Obtain engineering parameters and network management data for the area to be analyzed; Based on the engineering parameters, a spectrum coverage analysis is performed to obtain spectrum coverage indicators, which include coverage rates or average station spacing for different frequency bands or different standards. Based on the network management data, a first set of indicators and a second set of indicators are determined. The first set of indicators includes user carrying capacity indicators, and the second set of indicators includes unit spectrum carrying efficiency indicators. The social benefit index is obtained based on the spectrum coverage index and the first index set, and the economic benefit index is obtained based on the second index set. The social benefit index and the economic benefit index constitute a comprehensive index of the wireless network spectrum.

2. The method according to claim 1, characterized in that, The step of performing spectrum coverage analysis based on the engineering parameters to obtain spectrum coverage indicators includes the following steps: Based on the number of cells and cell coverage radius in the engineering parameters, determine the ratio of the coverage area of ​​different frequency bands or different standards to the total coverage area of ​​the area to be analyzed, and obtain the coverage rate; or, The average station spacing is calculated based on the number of cells and coverage area in the engineering parameters.

3. The method according to claim 1, characterized in that, The user-carrying category metrics include at least one of the following: Wireless resource control connection count, number of active users during busy hours, number of IoT users, user data traffic, and user data transmission rate.

4. The method according to claim 1, characterized in that, The unit spectrum carrying efficiency index includes at least one of the following: Number of users carried per unit spectrum, data traffic carried per unit spectrum, data rate carried per unit spectrum, frequency utilization, and communication efficiency.

5. The method according to claim 1, characterized in that, The process of obtaining the social benefit index based on the spectrum coverage index and the first index set includes the following steps: The spectrum coverage index and multiple indices in the first index set are normalized to obtain the normalized values ​​of each index. Weight coefficients are assigned to each indicator, and the normalized values ​​of each indicator are summed in weight to obtain the social benefit index.

6. The method according to claim 1, characterized in that, The step of obtaining the economic benefit index based on the second indicator set includes the following steps: Normalize the multiple indicators in the second indicator set to obtain the normalized values ​​of each indicator. Weight coefficients are assigned to each indicator, and the normalized values ​​of each indicator are weighted and summed to obtain the economic benefit index.

7. The method according to claim 1, characterized in that, It also includes the following steps: The time series data of each indicator in the first and second indicator sets are determined based on network management data from multiple time periods. Based on the time series data of each indicator, the indicators for future time periods are predicted using a time series prediction algorithm. Based on the forecast results, determine the corresponding social and economic benefit indicators for the future time period.

8. A device for analyzing the spectrum of a wireless network, characterized in that, The device includes the following: The data acquisition module is used to acquire engineering parameters and network management data of the area to be analyzed. The engineering parameter module is used to perform spectrum coverage analysis based on the engineering parameters to obtain spectrum coverage indicators, which include coverage rates or average station spacing for different frequency bands or different standards. The network management data module is used to determine a first set of indicators and a second set of indicators based on the network management data. The first set of indicators includes user carrying capacity indicators, and the second set of indicators includes unit spectrum carrying efficiency indicators. as well as, The evaluation index module is used to obtain a social benefit index based on the spectrum coverage index and the first index set, and to obtain an economic benefit index based on the second index set. The social benefit index and the economic benefit index constitute a comprehensive index of the wireless network spectrum.

9. An electronic device, characterized in that, It includes a processor, a memory, a program or instructions stored in the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the steps of the method as described in any one of claims 1 to 7.

10. A computer program product, characterized in that, The computer program product includes a computer program stored on a non-transitory computer-readable storage medium, the computer program including program instructions that, when executed by a computer, implement the steps of the method as described in any one of claims 1 to 7.

Images